NeurIPS 2025 Wednesday 12/3

Timezone: America/Los_Angeles

Full Schedule Sun 11/30 Mon 12/1 Tue 12/2 Wed 12/3 Thu 12/4 Fri 12/5 Sat 12/6 Sun 12/7

Registration Desk

7:30 AM - 6:00 PM

Invited Talk

The Oak Architecture: A Vision of SuperIntelligence from Experience

Rich Sutton

8:30 AM - 9:30 AM

As AI has become a huge industry, to an extent it has lost its way. What is needed to get us back on track to true intelligence? We need agents that learn continually. We need world models and planning. We need knowledge that is high-level and learnable. We need to meta-learn how to generalize. The Oak architecture is one answer to all these needs. It is a model-based RL architecture with three special features: 1) all of its components learn continually, 2) each learned weight has a dedicated step-size parameter that is meta-learned using online cross-validation, and 3) abstractions in state and time are continually created in a five-step progression: Feature Construction, posing a SubTask based on the feature, learning an Option to solve the subtask, learning a Model of the option, and Planning using the option’s model (the FC-STOMP progression). The Oak architecture is rather meaty; in this talk we give an outline and point to the many works, prior and contemporaneous, that are contributing to its overall vision of how superintelligence can arise from an agent’s experience.

... more

Speaker Bio

Research Scientist, Keen Technologies; Professor, University of Alberta; Chief Scientific Advisor, Amii; Chief Scientific Officer, ExperienceFlow.ai. Sutton co-developed temporal difference learning and policy gradient methods in reinforcement learning. He received the 2024 Turing Award with Andrew Barto for foundational contributions to reinforcement learning. He is co-author of the textbook "Reinforcement Learning: An Introduction" and is a Fellow of the Royal Society and the Royal Society of Canada. His research focuses on computational principles underlying learning and decision-making.

... more

Talk

Exhibitor Spot Talks - Session 2

9:30 AM - 4:45 PM

24 Events in this session

Arm AI Acceleration in Action: ExecuTorch + ONNX on Mobile and Edge

Michael Hall

The Importance and Fragility of CoT Monitorability

Bowen Baker

Financial Markets: The Ultimate Testbed for Intelligence (Susquehanna)

Ali Nazari

Scaling AI Workloads with Decentralized GPU Networks: A Systems Perspective

Tyler Mattikow

Dolphin: A Large-Scale ASR Model for Eastern Languages

Xiaofeng Xin

AI for Creativity

Building Enterprise AI to Transform Productivity: Lessons from Atlassian

Guihong Cao

Bridging Research & Reality - Applied AI, Lessons from CommBank on Applied AI

Anna Leontjeva

Exhibitor Talk - Yokogawa Digital Corporation

Scaling Data Quality in the Era of LLMs: A Quality Framework

Olga Megorskaya

Exploring Diffusion Transformer Designs via Grafting

Juan Carlos Niebles

Exhibitor Talk - Uber AI Solutions

Behind SWE-rebench: infrastructure to build massive datasets of SWE tasks

Pearl: A Foundation Model Advancing Small Molecule Drug Discovery

Ken Leidal

Agentic Full-Stack Benchmarking for Knowledge Work

The Quiet Enabler: AI-Amplified Discovery

Joseph Tracy

Towards A Blueprint for Open Science of Foundation Models

Zhengzhong Liu · Jiannan Xiang

T1: A Tool-Oriented Conversational Dataset for Multi-Turn Agentic Planning

Shixiong Zhang · Genta Winata

Gen AI Firsts - Qualcomm

Fatih Porikli

Personalized Dental Care: 3D generative models for biomimetic dental restorations

Dylan DeSantis

Building close-loop simulation with realtime generative modeling

Patrick Cho

Charting the Course for Human+AI Collaboration at Upwork

Zhao Chen

Open Source Models in Trading: Free Like a Puppy, Not Like a Beer

Wachi Bandara

Accelerating AI for the Real World: Strategies for safe deployment and rapid scaling

Karan Kapoor · Alfiya Timorshina

Go to Event Page

Oral

Oral 1B Generation/Simulation 1

10:00 AM - 11:00 AM

3 Events in this session

Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

Ge Wu · Shen Zhang · Ruijing Shi · Shanghua Gao · Zhenyuan Chen · Lei Wang · Zhaowei Chen · Hongcheng Gao · Yao Tang · jian Yang · Ming-Ming Cheng · Xiang Li

On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity

Quentin Bertrand · Anne Gagneux · Mathurin Massias · Rémi Emonet

Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training

Tony Bonnaire · Raphaël Urfin · Giulio Biroli · Marc Mezard

Go to Event Page

Oral

Oral 1A Language Model 1

10:00 AM - 11:00 AM

3 Events in this session

Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

Jiayi Yuan · Hao Li · Xinheng Ding · Wenya Xie · Yu-Jhe Li · Wentian Zhao · Kun Wan · Jing Shi · Xia Hu · Zirui Liu

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

Liwei Jiang · Yuanjun Chai · Margaret Li · Mickel Liu · Raymond Fok · Nouha Dziri · Yulia Tsvetkov · Maarten Sap · Yejin Choi

SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing

Mingfei Chen · Zijun Cui · Xiulong Liu · Jinlin Xiang · Yang Zheng · Jingyuan Li · Eli Shlizerman

Go to Event Page

Oral

Oral 1E Algorithm 1

10:00 AM - 11:00 AM

3 Events in this session

Adjoint Schrödinger Bridge Sampler

Guan-Horng Liu · Jaemoo Choi · Yongxin Chen · Benjamin K Miller · Ricky T. Q. Chen

Rethinking Joint Maximum Mean Discrepancy for Visual Domain Adaptation

Wei Wang · Haifeng Xia · Chao Huang · Zhengming Ding · Cong Wang · Haojie Li · Xiaochun Cao

Class-wise Balancing Data Replay for Federated Class-Incremental Learning

Zhuang Qi · Ying-Peng Tang · Lei Meng · Han Yu · Xiaoxiao Li · Xiangxu Meng

Go to Event Page

Oral

Oral 1D Multimodal 1

10:00 AM - 11:00 AM

3 Events in this session

Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation

Zihan Wang · Seungjun Lee · Gim Hee Lee

Perception Encoder: The best visual embeddings are not at the output of the network

Daniel Bolya · Po-Yao Huang · Peize Sun · Jang Hyun Cho · Andrea Madotto · Chen Wei · Tengyu Ma · Jiale Zhi · Jathushan Rajasegaran · Hanoona Bangalath · Junke Wang · Marco Monteiro · Hu Xu · Shiyu Dong · Nikhila Ravi · Shang-Wen Li · Piotr Dollar · Christoph Feichtenhofer

Interactive Cross-modal Learning for Text-3D Scene Retrieval

Yanglin Feng · Yongxiang Li · Yuan Sun · Yang Qin · Dezhong Peng · Peng Hu

Go to Event Page

Oral

Oral 1C Theory 1

10:00 AM - 11:00 AM

3 Events in this session

Optimal Mistake Bounds for Transductive Online Learning

Zachary Chase · Steve Hanneke · Shay Moran · Jonathan Shafer

High-Dimensional Calibration from Swap Regret

Maxwell Fishelson · Noah Golowich · Mehryar Mohri · Jon Schneider

Does Stochastic Gradient really succeed for bandits?

Dorian Baudry · Emmeran Johnson · Simon Vary · Ciara Pike-Burke · Patrick Rebeschini

Go to Event Page

Poster

San Diego Poster Session 1

11:00 AM - 2:00 PM

938 Events in this session

Group-Level Data Selection for Efficient Pretraining

Zichun Yu · Fei Peng · Jie Lei · Arnold Overwijk · Scott Yih · Chenyan Xiong

Learning Provably Improves the Convergence of Gradient Descent

Qingyu Song · Wei Lin · Hong Xu

LittleBit: Ultra Low-Bit Quantization via Latent Factorization

Banseok Lee · Dongkyu Kim · Youngcheon You · Youngmin Kim

Cost-Efficient LLM Training with Lifetime-Aware Tensor Offloading via GPUDirect Storage

Ziqi Yuan · Haoyang Zhang · Yirui Zhou · Apoorve Mohan · I-Hsin Chung · Seetharami Seelam · Jian Huang

Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness

Rongzhe Wei · Peizhi Niu · Hans Hao-Hsun Hsu · Ruihan Wu · Haoteng Yin · Mohsen Ghassemi · Yifan Li · Vamsi Potluru · Eli Chien · Kamalika Chaudhuri · Olgica Milenkovic · Pan Li

LLM Strategic Reasoning: Agentic Study through Behavioral Game Theory

Jingru Jia · Zehua Yuan · Junhao Pan · Paul McNamara · Deming Chen

Modeling the Economic Impacts of AI Openness Regulation

Tori Qiu · Benjamin Laufer · Jon Kleinberg · Hoda Heidari

Social World Model-Augmented Mechanism Design Policy Learning

Xiaoyuan Zhang · Yizhe Huang · Chengdong Ma · Zhixun Chen · Long Ma · Yali Du · Song-Chun Zhu · Yaodong Yang · Xue Feng

Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training

Mengru Wang · Xingyu Chen · Yue Wang · Zhiwei He · Jiahao Xu · Tian Liang · Qiuzhi Liu · Yunzhi Yao · Wenxuan Wang · Ruotian Ma · Haitao Mi · Ningyu Zhang · Zhaopeng Tu · Xiaolong Li · Dong Yu

Concept Incongruence: An Exploration of Time and Death in Role Playing

Xiaoyan Bai · Ike Peng · Aditya Singh · Chenhao Tan

For Better or for Worse, Transformers Seek Patterns for Memorization

Madhur Panwar · Gail Weiss · Navin Goyal · Antoine Bosselut

Taming Hyperparameter Sensitivity in Data Attribution: Practical Selection Without Costly Retraining

Weiyi Wang · Junwei Deng · Yuzheng Hu · Shiyuan Zhang · Xirui Jiang · Runting Zhang · Han Zhao · Jiaqi Ma

LeapFactual: Reliable Visual Counterfactual Explanation Using Conditional Flow Matching

Zhuo Cao · Xuan Zhao · Lena Krieger · Hanno Scharr · Ira Assent

Deferring Concept Bottleneck Models: Learning to Defer Interventions to Inaccurate Experts

Andrea Pugnana · Riccardo Massidda · Francesco Giannini · Pietro Barbiero · Mateo Espinosa Zarlenga · Roberto Pellungrini · Gabriele Dominici · Fosca Giannotti · Davide Bacciu

Head Pursuit: Probing Attention Specialization in Multimodal Transformers

Lorenzo Basile · Valentino Maiorca · Diego Doimo · Francesco Locatello · Alberto Cazzaniga

The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?

Denis Sutter · Julian Minder · Thomas Hofmann · Tiago Pimentel

Capturing Polysemanticity with PRISM: A Multi-Concept Feature Description Framework

Laura Kopf · Nils Feldhus · Kirill Bykov · Philine L Bommer · Anna Hedström · Marina Höhne · Oliver Eberle

On the creation of narrow AI: hierarchy and nonlocality of neural network skills

Eric Michaud · Asher Parker-Sartori · Max Tegmark

Evaluating LLM-contaminated Crowdsourcing Data Without Ground Truth

Yichi Zhang · Jinlong Pang · Zhaowei Zhu · Yang Liu

Neural Networks for Learnable and Scalable Influence Estimation of Instruction Fine-Tuning Data

Ishika Agarwal · Dilek Hakkani-Tur

Bootstrapping Hierarchical Autoregressive Formal Reasoner with Chain-of-Proxy-Autoformalization

Qi Liu · Xinhao Zheng · Renqiu Xia · Qinxiang Cao · Junchi Yan

Sculpting Features from Noise: Reward-Guided Hierarchical Diffusion for Task-Optimal Feature Transformation

Nanxu Gong · Zijun Li · Sixun Dong · Haoyue Bai · Wangyang Ying · Xinyuan Wang · Yanjie Fu

CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays

Hyungyung Lee · Geon Choi · Jung-Oh Lee · Hangyul Yoon · Hyuk Hong · Edward Choi

Revisiting Reinforcement Learning for LLM Reasoning from A Cross-Domain Perspective

Jorge (Zhoujun) Cheng · Shibo Hao · Tianyang Liu · Fan Zhou · Yutao Xie · Feng Yao · Yuexin Bian · Nilabjo Dey · Yonghao Zhuang · Yuheng Zha · Yi Gu · Kun Zhou · Yuqi Wang · Yuan Li · Richard Fan · Jianshu She · Chengqian Gao · Abulhair Saparov · Taylor W. Killian · Haonan Li · Mikhail Yurochkin · Eric Xing · Zhengzhong Liu · Zhiting Hu

Enhancing Multilingual LLM Pretraining with Model-Based Data Selection

Bettina Messmer · Vinko Sabolčec · Martin Jaggi

STARC-9: A Large-scale Dataset for Multi-Class Tissue Classification for CRC Histopathology

Barathi Subramanian · Rathinaraja Jeyaraj · Mitchell Peterson · Terry Guo · Nigam Shah · Curtis Langlotz · Andrew Ng · Jeanne Shen

ChemPile: A 250 GB Diverse and Curated Dataset for Chemical Foundation Models

Adrian Mirza · Nawaf Alampara · Martiño Ríos-García · Mohamed Abdelalim · Jack Butler · Bethany Connolly · Tunca Dogan · Marianna Nezhurina · Bünyamin Şen · Santosh Tirunagari · Mark Worrall · Adamo Young · Philippe Schwaller · Michael Pieler · Kevin Maik Jablonka

Fair Continuous Resource Allocation with Equality of Impact

Blossom Metevier · Dennis Wei · Karthikeyan Natesan Ramamurthy · Philip Thomas

The Boundaries of Fair AI in Medical Image Prognosis: A Causal Perspective

Thai-Hoang Pham · Jiayuan Chen · Seungyeon Lee · Yuanlong Wang · Sayoko Moroi · Xueru Zhang · Ping Zhang

DEGauss: Defending Against Malicious 3D Editing for Gaussian Splatting

Lingzhuang Meng · Mingwen Shao · Yuanjian Qiao · Xiang Lv

Taught Well Learned Ill: Towards Distillation-conditional Backdoor Attack

Yukun Chen · Boheng Li · Yu Yuan · Leyi Qi · Yiming Li · Tianwei Zhang · Zhan Qin · Kui Ren

Adjacent Words, Divergent Intents: Jailbreaking Large Language Models via Task Concurrency

Yukun Jiang · Mingjie Li · Michael Backes · Yang Zhang

GUARDIAN: Safeguarding LLM Multi-Agent Collaborations with Temporal Graph Modeling

Jialong Zhou · Lichao Wang · Xiao Yang

Efficient Fairness-Performance Pareto Front Computation

Mark Kozdoba · Binyamin Perets · Shie Mannor

Epistemic Uncertainty for Generated Image Detection

Jun Nie · Yonggang Zhang · Tongliang Liu · Yiu-ming Cheung · Bo Han · Xinmei Tian

Semantic Surgery: Zero-Shot Concept Erasure in Diffusion Models

Lexiang Xiong · Liu Chengyu · Jingwen Ye · YAN LIU · Yuecong Xu

Information Retrieval Induced Safety Degradation in AI Agents

Cheng Yu · Benedikt Stroebl · Diyi Yang · Orestis Papakyriakopoulos

Improving Deep Learning for Accelerated MRI With Data Filtering

Kang Lin · Anselm Krainovic · Kun Wang · Reinhard Heckel

Redefining Experts: Interpretable Decomposition of Language Models for Toxicity Mitigation

Zuhair Hasan Shaik · Abdullah Mazhar · Aseem Srivastava · Md Shad Akhtar

DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios

Yao Huang · Yitong Sun · Yichi Zhang · Ruochen Zhang · Yinpeng Dong · Xingxing Wei

NeuroRenderedFake: A Challenging Benchmark to Detect Fake Images Generated by Advanced Neural Rendering Methods

Chengdong Dong · B. V. K. Vijaya Kumar · Zhenyu Zhou · Ajay Kumar

Comprehensive Assessment and Analysis for NSFW Content Erasure in Text-to-Image Diffusion models

Die Chen · Zhiwen Li · Cen Chen · Yuexiang Xie · Xiaodan Li · Jinyan Ye · Yingda Chen · Yaliang Li

CARES: Comprehensive Evaluation of Safety and Adversarial Robustness in Medical LLMs

Sijia Chen · Xiaomin Li · mengxue zhang · Eric Hanchen Jiang · Qingcheng Zeng · Chen-Hsiang Yu

Interpretable and Parameter Efficient Graph Neural Additive Models with Random Fourier Features

Thummaluru Siddartha Reddy · Vempalli Naga Sai Saketh · Mahesh Chandran

COCONut-PanCap: Joint Panoptic Segmentation and Grounded Captions for Fine-Grained Understanding and Generation

Xueqing Deng · Linjie Yang · Qihang Yu · Ali Athar · Chenglin Yang · Xiaojie Jin · Xiaohui Shen · Liang-Chieh Chen

SWE-smith: Scaling Data for Software Engineering Agents

John Yang · Kilian Lieret · Carlos Jimenez · Alexander Wettig · Kabir Khandpur · Yanzhe Zhang · Binyuan Hui · Ofir Press · Ludwig Schmidt · Diyi Yang

UtilGen: Utility-Centric Generative Data Augmentation with Dual-Level Task Adaptation

Jiyu Guo · Shuo Yang · Yiming Huang · Yancheng Long · Xiaobo Xia · Xiu Su · Bo Zhao · Zeke Xie · Liqiang Nie

Limited Preference Data? Learning Better Reward Model with Latent Space Synthesis

Leitian Tao · Xuefeng Du · Sharon Li

Prismatic Synthesis: Gradient-based Data Diversification Boosts Generalization in LLM Reasoning

Jaehun Jung · Seungju Han · Ximing Lu · Skyler Hallinan · David Acuna · Shrimai Prabhumoye · Mostofa Patwary · Mohammad Shoeybi · Bryan Catanzaro · Yejin Choi

More of the Same: Persistent Representational Harms Under Increased Representation

Jennifer Mickel · Maria De-Arteaga · Liu Leqi · Kevin Tian

RiOSWorld: Benchmarking the Risk of Multimodal Computer-Use Agents

Jingyi Yang · Shuai Shao · Dongrui Liu · Jing Shao

Fairness-aware Bayes Optimal Functional Classification

Xiaoyu Hu · Gengyu Xue · Zhenhua Lin · Yi Yu

Individual Fairness In Strategic Classification

Zhiqun Zuo · Mohammad Mahdi Khalili

Panacea: Mitigating Harmful Fine-tuning for Large Language Models via Post-fine-tuning Perturbation

Yibo Wang · Tiansheng Huang · Li Shen · Huanjin Yao · Haotian Luo · Rui Liu · Naiqiang Tan · Jiaxing Huang · Dacheng Tao

Size-adaptive Hypothesis Testing for Fairness

Antonio Ferrara · Francesco Cozzi · Alan Perotti · André Panisson · Francesco Bonchi

Semantic Representation Attack against Aligned Large Language Models

Jiawei Lian · Jianhong Pan · Lefan Wang · Yi Wang · Shaohui Mei · Lap-Pui Chau

Privacy Reasoning in Ambiguous Contexts

Ren Yi · Octavian Suciu · Adrian Gascon · Sarah Meiklejohn · Eugene Bagdasarian · Marco Gruteser

Query-Efficient Locally Private Hypothesis Selection via the Scheffe Graph

Gautam Kamath · Alireza F. Pour · Matthew Regehr · David Woodruff

DictPFL: Efficient and Private Federated Learning on Encrypted Gradients

Jiaqi Xue · Mayank Kumar · Yuzhang Shang · Shangqian Gao · Rui Ning · Mengxin Zheng · Xiaoqian Jiang · Qian Lou

CryptoMoE: Privacy-Preserving and Scalable Mixture of Experts Inference via Balanced Expert Routing

Yifan Zhou · Tianshi Xu · Jue Hong · Ye Wu · Meng Li

Secure and Confidential Certificates of Online Fairness

Olive Franzese · Ali Shahin Shamsabadi · Carter Luck · Hamed Haddadi

Sum Estimation under Personalized Local Differential Privacy

Dajun Sun · Wei Dong · Yuan Qiu · Ke Yi · Graham Cormode

A Private Approximation of the 2nd-Moment Matrix of Any Subsamplable Input

Bar Mahpud · Or Sheffet

What Really is a Member? Discrediting Membership Inference via Poisoning

Neal Mangaokar · Ashish Hooda · Zhuohang Li · Bradley Malin · Kassem Fawaz · Somesh Jha · Atul Prakash · Amrita Roy Chowdhury

Instance-Optimality for Private KL Distribution Estimation

Jiayuan Ye · Vitaly Feldman · Kunal Talwar

Generative Model Inversion Through the Lens of the Manifold Hypothesis

Xiong Peng · Bo Han · Fengfei Yu · Tongliang Liu · Feng Liu · Mingyuan Zhou

ConfTuner: Training Large Language Models to Express Their Confidence Verbally

Yibo Li · Miao Xiong · Jiaying Wu · Bryan Hooi

WMCopier: Forging Invisible Watermarks on Arbitrary Images

Ziping Dong · Chao Shuai · Zhongjie Ba · Peng Cheng · Zhan Qin · Qinglong Wang · Kui Ren

A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation

Yiwen Tu · Pingbang Hu · Jiaqi Ma

Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models

Xinran Wang · Jin Du · Azal Khan · qi le · Enmao Diao · Jiawei Zhou · Jie Ding · Ali Anwar

LORE: Lagrangian-Optimized Robust Embeddings for Visual Encoders

Borna Khodabandeh · Amirabbas Afzali · Amirhossein Afsharrad · Shahab Mousavi · Sanjay Lall · Sajjad Amini · Seyed-Mohsen Moosavi-Dezfooli

Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families

Felipe Maia Polo · Seamus Somerstep · Leshem Choshen · Yuekai Sun · Mikhail Yurochkin

LoSplit: Loss-Guided Dynamic Split for Training-Time Defense Against Graph Backdoor Attacks

Di Jin · Yuxiang Zhang · Bingdao Feng · Xiaobao Wang · Dongxiao He · Zhen Wang

Provable Gradient Editing of Deep Neural Networks

Zhe Tao · Aditya V Thakur

Absence Bench: Language Models Can’t See What’s Missing

Harvey Yiyun Fu · Aryan Shrivastava · Jared Moore · Peter West · Chenhao Tan · Ari Holtzman

Private Evolution Converges

Tomás González Lara · Giulia Fanti · Aaditya Ramdas

Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization

Xiaoling Zhou · Mingjie Zhang · Zhemg Lee · YUNCHENG HUA · chengli xing · Wei Ye · Flora Salim · Shikun Zhang

ObCLIP: Oblivious CLoud-Device Hybrid Image Generation with Privacy Preservation

Haoqi Wu · Wei Dai · Ming Xu · Wang Li · Qiang Yan

Private Set Union with Multiple Contributions

Travis Dick · Haim Kaplan · Alex Kulesza · Uri Stemmer · Ziteng Sun · Ananda Theertha Suresh

From Dormant to Deleted: Tamper-Resistant Unlearning Through Weight-Space Regularization

Shoaib Ahmed Siddiqui · Adrian Weller · David Krueger · Gintare Karolina Dziugaite · Michael Mozer · Eleni Triantafillou

AC-LoRA: (Almost) Training-Free Access Control Aware Multi-Modal LLMs

Lara Magdalena Lazier · Aritra Dhar · Vasilije Stambolic · Lukas Cavigelli

One Token Embedding Is Enough to Deadlock Your Large Reasoning Model

Mohan Zhang · Yihua Zhang · Jinghan Jia · Zhangyang "Atlas" Wang · Sijia Liu · Tianlong Chen

Inference-Time Reward Hacking in Large Language Models

Hadi Khalaf · Claudio Mayrink Verdun · Alex Oesterling · Himabindu Lakkaraju · Flavio Calmon

Long-tailed Recognition with Model Rebalancing

JIAAN LUO · Feng Hong · Qiang Hu · Xiaofeng Cao · Feng Liu · Jiangchao Yao

Neural Rule Lists: Learning Discretizations, Rules, and Order in One Go

Sascha Xu · Nils Philipp Walter · Jilles Vreeken

Backdoor Cleaning without External Guidance in MLLM Fine-tuning

Xuankun Rong · Wenke Huang · Jian Liang · Jinhe Bi · Xun Xiao · Yiming Li · Bo Du · Mang Ye

Probabilistic Stability Guarantees for Feature Attributions

Helen Jin · Anton Xue · Weiqiu You · Surbhi Goel · Eric Wong

Empowering Decision Trees via Shape Function Branching

Nakul Upadhya · Eldan Cohen

Finding and Reactivating Post-Trained LLMs' Hidden Safety Mechanisms

Mingjie Li · Wai Man Si · Michael Backes · Yang Zhang · Yisen Wang

Understanding and Improving Adversarial Robustness of Neural Probabilistic Circuits

Weixin Chen · Han Zhao

Fair Representation Learning with Controllable High Confidence Guarantees via Adversarial Inference

Yuhong Luo · Austin Hoag · Xintong Wang · Philip Thomas · Przemyslaw Grabowicz

Backdoor Mitigation via Invertible Pruning Masks

Kealan Dunnett · Reza Arablouei · Volkan Dedeoglu · Dimity Miller · Raja Jurdak

Bridging Symmetry and Robustness: On the Role of Equivariance in Enhancing Adversarial Robustness

Longwei Wang · Ifrat Ikhtear Uddin · Prof. KC Santosh (PhD) · Chaowei Zhang · Xiao Qin · Yang Zhou

Evaluating the Inductive Abilities of Large Language Models: Why Chain-of-Thought Reasoning Sometimes Hurts More Than Helps

Haibo Jin · Peiyan Zhang · Man Luo · Haohan Wang

JADE: Joint Alignment and Deep Embedding for Multi-Slice Spatial Transcriptomics

Yuanchuan Guo · Jun Liu · Huimin Cheng · Ying Ma

The Omni-Expert: A Computationally Efficient Approach to Achieve a Mixture of Experts in a Single Expert Model

Sohini Saha · Mezisashe Ojuba · Leslie Collins · Boyla Mainsah

VeriLoC: Line-of-Code Level Prediction of Hardware Design Quality from Verilog Code

Raghu Vamshi Hemadri · Jitendra Bhandari · Andre Nakkab · Johann Knechtel · Badri Gopalan · Ramesh Narayanaswamy · Ramesh Karri · Siddharth Garg

LLM-PySC2: Starcraft II learning environment for Large Language Models

Zongyuan Li · Yanan Ni · Runnan Qi · Chang Lu · Lumin Jiang · Xu Xiaojie · Xiangbei Liu · Pengfei Li · Yunzheng Guo · Zhe Ma · Huanyu Li · wu hui · Xian Guo · Kuihua Huang · Xuebo Zhang

SymRTLO: Enhancing RTL Code Optimization with LLMs and Neuron-Inspired Symbolic Reasoning

Yiting Wang · Wanghao Ye · Ping Guo · Yexiao He · Ziyao Wang · Bowei Tian · Shwai He · Guoheng Sun · Zheyu Shen · Sihan Chen · Ankur Srivastava · Qingfu Zhang · Gang Qu · Ang Li

MaintainCoder: Maintainable Code Generation Under Dynamic Requirements

Zhengren Wang · Rui ling · Chufan Wang · Yongan Yu · Sizhe Wang · Zhiyu li · Feiyu Xiong · Wentao Zhang

Learning Interestingness in Automated Mathematical Theory Formation

George Tsoukalas · Rahul Saha · Amitayush Thakur · Sabrina Reguyal · Swarat Chaudhuri

Fine-grained List-wise Alignment for Generative Medication Recommendation

Chenxiao Fan · Chongming Gao · Wentao Shi · Yaxin Gong · Zhao Zihao · Fuli Feng

Reason-RFT: Reinforcement Fine-Tuning for Visual Reasoning of Vision Language Models

Huajie Tan · Yuheng Ji · Xiaoshuai Hao · Xiansheng Chen · Pengwei Wang · Zhongyuan Wang · Shanghang Zhang

SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens

Yinhan He · Wendy Zheng · Yaochen Zhu · Zaiyi Zheng · Lin Su · Sriram Vasudevan · Qi Guo · Liangjie Hong · Jundong Li

STEER-ME: Assessing the Microeconomic Reasoning of Large Language Models

Narun Raman · Taylor Lundy · Thiago Amin · Kevin Leyton-Brown · Jesse Perla

GTPBD: A Fine-Grained Global Terraced Parcel and Boundary Dataset

Zhiwei Zhang · Zi Ye · Yibin Wen · Shuai Yuan · Haohuan Fu · Huang Jianxi · Juepeng Zheng

CPRet: A Dataset, Benchmark, and Model for Retrieval in Competitive Programming

Han Deng · Yuan Meng · SHIXIANG TANG · Wanli Ouyang · Xinzhu Ma

Open-Insect: Benchmarking Open-Set Recognition of Novel Species in Biodiversity Monitoring

Yuyan Chen · Nico Lang · B. Schmidt · Aditya Jain · Yves Basset · Sara Beery · Maxim Larrivee · David Rolnick

Does Representation Guarantee Welfare?

Jakob de Raaij · Ariel Procaccia · Alexandros Psomas

Validating LLM-as-a-Judge Systems under Rating Indeterminacy

Luke Guerdan · Solon Barocas · Kenneth Holstein · Hanna Wallach · Steven Wu · Alex Chouldechova

Precise Information Control in Long-Form Text Generation

Jacqueline He · Howard Yen · Margaret Li · Stella Li · Zhiyuan Zeng · Weijia Shi · Yulia Tsvetkov · Danqi Chen · Pang Wei Koh · Luke Zettlemoyer

Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models

Tomas Soucek · Sylvestre-Alvise Rebuffi · Pierre Fernandez · Nikola Jovanović · Hady Elsahar · Valeriu Lacatusu · Tuan Tran · Alexandre Mourachko

AgentNet: Decentralized Evolutionary Coordination for LLM-based Multi-Agent Systems

Yingxuan Yang · Huacan Chai · Shuai Shao · Yuanyi Song · Siyuan Qi · Renting Rui · Weinan Zhang

IGD: Token Decisiveness Modeling via Information Gain in LLMs for Personalized Recommendation

Zijie Lin · Yang Zhang · Xiaoyan Zhao · Fengbin ZHU · Fuli Feng · Tat-Seng Chua

CPSea: Large-scale cyclic peptide-protein complex dataset for machine learning in cyclic peptide design

Ziyi Yang · Hanyuan Xie · Yinjun Jia · Xiangzhe Kong · Jiqing Zheng · Ziting Zhang · Yang Liu · Lei Liu · Yanyan Lan

FGBench: A Dataset and Benchmark for Molecular Property Reasoning at Functional Group-Level in Large Language Models

Xuan Liu · Siru Ouyang · Xianrui Zhong · Jiawei Han · Huimin Zhao

KnowMol: Advancing Molecular Large Language Models with Multi-Level Chemical Knowledge

Zaifei Yang · Hong Chang · RuiBing Hou · Shiguang Shan · Xilin Chen

NeuralPLexer3: Accurate Biomolecular Complex Structure Prediction with Flow Models

Jarren Zhuoran Qiao · Feizhi Ding · Thomas Dresselhaus · Mia Rosenfeld · Xiaotian Han · Owen Howell · Aniketh Iyengar · Stephen Opalenski · Anders Christensen · Sai Krishna Sirumalla · Fred Manby · Thomas Miller · Matthew Welborn

Mol-LLaMA: Towards General Understanding of Molecules in Large Molecular Language Model

Dongki Kim · Wonbin Lee · Sung Ju Hwang

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search

Zonglin Yang · Wanhao Liu · Ben Gao · Yujie Liu · Wei Li · Tong Xie · Lidong Bing · Wanli Ouyang · Erik Cambria · Dongzhan Zhou

AANet: Virtual Screening under Structural Uncertainty via Alignment and Aggregation

Wenyu Zhu · Jianhui Wang · Bowen Gao · Yinjun Jia · Haichuan Tan · Ya-Qin Zhang · Wei-Ying Ma · Yanyan Lan

CellCLIP - Learning Perturbation Effects in Cell Painting via Text-Guided Contrastive Learning

MingYu Lu · Ethan Weinberger · Chanwoo Kim · Su-In Lee

Template-Guided 3D Molecular Pose Generation via Flow Matching and Differentiable Optimization

Noémie Bergues · Arthur Carré · Paul Join-Lambert · Brice Hoffmann · Arnaud Blondel · Hamza Tajmouati

FIGRDock: Fast Interaction-Guided Regression for Flexible Docking

Shikun Feng · Bicheng Lin · Yuanhuan Mo · Yuyan Ni · Wenyu Zhu · Bowen Gao · Wei-Ying Ma · haitao li · Yanyan Lan

Symmetry-Preserving Conformer Ensemble Networks for Molecular Representation Learning

Yanqiao Zhu · Yidan Shi · Yuanzhou Chen · Fang Sun · Yizhou Sun · Wei Wang

Dynamic and Chemical Constraints to Enhance the Molecular Masked Graph Autoencoders

Jiahui Zhang · Wenjie Du · Yang Wang

Learning Repetition-Invariant Representations for Polymer Informatics

Yihan Zhu · Gang Liu · Eric Inae · Tengfei Luo · Meng Jiang

TreeFinder: A US-Scale Benchmark Dataset for Individual Tree Mortality Monitoring Using High-Resolution Aerial Imagery

Zhihao Wang · Cooper Li · Ruichen Wang · Lei Ma · George Hurtt · Xiaowei Jia · Gengchen Mai · Zhili Li · Yiqun Xie

SentinelKilnDB: A Large-Scale Dataset and Benchmark for OBB Brick Kiln Detection in South Asia Using Satellite Imagery

Rishabh Mondal · Jeet Parab · Heer Kubadia · Shataxi Dubey · Shardul Junagade · Zeel Bharatkumar Patel · Nipun Batra

scGeneScope: A Treatment-Matched Single Cell Imaging and Transcriptomics Dataset and Benchmark for Treatment Response Modeling

Joel Dapello · Marcel Nassar · Ridvan Eksi · Ban Wang · Jules Gagnon-Marchand · Kenneth Gao · akram Baharlouei · Kyra Thrush · Nina Riehs · Amy Peterson · Aniket Tolpadi · Abhejit Rajagopal · Henry Miller · Ashley Conard · David Alvarez-Melis · Rory Stark · Simone Bianco · Morgan Levine · Ava Amini · Alex X Lu · Nicolo Fusi · Ravi Pandya · Valentina Pedoia · Hana El-Samad

An Investigation of Memorization Risk in Healthcare Foundation Models

Sana Tonekaboni · Lena Stempfle · Adibvafa Fallahpour · Walter Gerych · Marzyeh Ghassemi

Towards Doctor-Like Reasoning: Medical RAG Fusing Knowledge with Patient Analogy through Textual Gradients

Yuxing Lu · Gecheng Fu · Wei Wu · Xukai Zhao · Sin Yee Goi · Jinzhuo Wang

DoseSurv: Predicting Personalized Survival Outcomes under Continuous-Valued Treatments

Moritz Gögl · Yu Liu · Christopher Yau · Peter Watkinson · Tingting Zhu

MedMax: Mixed-Modal Instruction Tuning for Training Biomedical Assistants

Hritik Bansal · Daniel Israel · Siyan Zhao · Shufan Li · Tung Nguyen · Aditya Grover

FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion Recognition

Pragya Singh · Ankush Gupta · Somay Jalan · Mohan Kumar · Pushpendra Singh

MedicalNarratives: Connecting Medical Vision and Language with Localized Narratives

Wisdom Ikezogwo · Kevin M. Zhang · Saygin Seyfioglu

PatientSim: A Persona-Driven Simulator for Realistic Doctor-Patient Interactions

Daeun Kyung · Hyunseung Chung · Seongsu Bae · Jiho Kim · Jae Ho Sohn · Taerim Kim · Soo Kyung Kim · Edward Choi

PRSformer: Disease Prediction from Million-Scale Individual Genotypes

Payam Dibaeinia · Chris German · Suyash Shringarpure · Adam Auton · Aly A. Khan

ShapeEmbed: a self-supervised learning framework for 2D contour quantification

Anna Foix-Romero · Craig Russell · Alexander Krull · Virginie Uhlmann

Bidirectional Representations Augmented Autoregressive Biological Sequence Generation: Application in De Novo Peptide Sequencing

Xiang Zhang · Jiaqi Wei · Zijie Qiu · Sheng Xu · Zhi Jin · ZhiQiang Gao · Nanqing Dong · Siqi Sun

Understanding protein function with a multimodal retrieval-augmented foundation model

Timothy Truong Jr · Tristan Bepler

Joint Velocity-Growth Flow Matching for Single-Cell Dynamics Modeling

Dongyi Wang · Yuanwei Jiang · Zhenyi Zhang · Xiang Gu · Peijie Zhou · Jian Sun

Tabula: A Tabular Self-Supervised Foundation Model for Single-Cell Transcriptomics

Jiayuan Ding · Jianhui Lin · Shiyu Jiang · Yixin Wang · Ziyang Miao · Zhaoyu Fang · Jiliang Tang · Min Li · Xiaojie Qiu

KINDLE: Knowledge-Guided Distillation for Prior-Free Gene Regulatory Network Inference

Rui Peng · Yuchen Lu · Qichen Sun · Yuxing Lu · Chi Zhang · Ziru Liu · Jinzhuo Wang

Zero-shot protein stability prediction by inverse folding models: a free energy interpretation

Jes Frellsen · Maher Kassem · Tone Bengtsen · Lars Olsen · Kresten Lindorff-Larsen · Jesper Ferkinghoff-Borg · Wouter Boomsma

Gene Regulatory Network Inference in the Presence of Selection Bias and Latent Confounders

Gongxu Luo · Haoyue Dai · Longkang Li · Chengqian Gao · Boyang Sun · Kun Zhang

OCTDiff: Bridged Diffusion Model for Portable OCT Super-Resolution and Enhancement

Ye Tian · Angela McCarthy · Gabriel Gomide · Nancy Liddle · Jedrzej Golebka · Royce Chen · Jeff Liebmann · Kaveri Thakoor

PhysioWave: A Multi-Scale Wavelet-Transformer for Physiological Signal Representation

Yanlong Chen · Mattia Orlandi · Pierangelo Rapa · Simone Benatti · Luca Benini · Yawei Li

D-VST: Diffusion Transformer for Pathology-Correct Tone-Controllable Cross-Dye Virtual Staining of Whole Slide Images

shurong yang · Dong Wei · Yihuang Hu · Qiong Peng · Hong Liu · Yawen Huang · Xian Wu · Yefeng Zheng · Liansheng Wang

Sequential Attention-based Sampling for Histopathological Analysis

Tarun Gogisetty · Naman Malpani · Gugan Chandrashekhar Mallika Thoppe · Sridharan Devarajan

EmergentTTS-Eval: Evaluating TTS Models on Complex Prosodic, Expressiveness, and Linguistic Challenges Using Model-as-a-Judge

Ruskin Raj Manku · Yuzhi Tang · Xingjian Shi · Mu Li · Alexander Smola

WritingBench: A Comprehensive Benchmark for Generative Writing

Yuning Wu · Jiahao Mei · Ming Yan · Chenliang Li · Shaopeng Lai · Yuran Ren · Zijia Wang · Ji Zhang · Mengyue Wu · Qin Jin · Fei Huang

TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios

Shaohang Wei · Wei Li · Feifan Song · Wen Luo · Tianyi Zhuang · Haochen Tan · Zhijiang Guo · Houfeng Wang

FocalCodec: Low-Bitrate Speech Coding via Focal Modulation Networks

Luca Della Libera · Francesco Paissan · Cem Subakan · Mirco Ravanelli

Unbiased Sliced Wasserstein Kernels for High-Quality Audio Captioning

Tien Manh Luong · Khai Nguyen · Dinh Phung · Reza Haffari · Lizhen Qu

Benford’s Curse: Tracing Digit Bias to Numerical Hallucination in LLMs

Jiandong Shao · Yao Lu · Jianfei Yang

SALMONN-omni: A Standalone Speech LLM without Codec Injection for Full-duplex Conversation

Wenyi Yu · Siyin Wang · Xiaoyu Yang · Xianzhao Chen · Xiaohai Tian · Jun Zhang · Guangzhi Sun · Lu Lu · Yuxuan Wang · Chao Zhang

Probabilistic Reasoning with LLMs for Privacy Risk Estimation

Jonathan Zheng · Alan Ritter · Sauvik Das · Wei "Coco" Xu

ZeroSep: Separate Anything in Audio with Zero Training

Chao Huang · Yuesheng Ma · Junxuan Huang · Susan Liang · Yunlong Tang · Jing Bi · Wenqiang Liu · Nima Mesgarani · Chenliang Xu

Learning to Instruct for Visual Instruction Tuning

Zhihan Zhou · Feng Hong · JIAAN LUO · Yushi Ye · Jiangchao Yao · Dongsheng Li · Bo Han · Ya Zhang · Yanfeng Wang

The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning

Shivam Agarwal · Zimin Zhang · Lifan Yuan · Jiawei Han · Hao Peng

Geo-Sign: Hyperbolic Contrastive Regularisation for Geometrically Aware Sign Language Translation

Edward Fish · Richard Bowden

STEP: A Unified Spiking Transformer Evaluation Platform for Fair and Reproducible Benchmarking

Sicheng Shen · Dongcheng Zhao · Linghao Feng · Zeyang Yue · Jindong Li · Tenglong Li · Guobin Shen · Yi Zeng

Execution Guided Line-by-Line Code Generation

Boaz Lavon · Shahar Katz · Lior Wolf

TaDiCodec: Text-aware Diffusion Speech Tokenizer for Speech Language Modeling

Yuancheng Wang · Dekun Chen · Xueyao Zhang · Junan Zhang · Jiaqi Li · Zhizheng Wu

DETree: DEtecting Human-AI Collaborative Texts via Tree-Structured Hierarchical Representation Learning

Yongxin He · Shan Zhang · Yixuan Cao · Lei Ma · Ping Luo

QiMeng-SALV: Signal-Aware Learning for Verilog Code Generation

Yang Zhang · Rui Zhang · Jiaming Guo · Huang Lei · Di Huang · Yunpu Zhao · Shuyao Cheng · Pengwei Jin · Chongxiao Li · Zidong Du · Xing Hu · Qi Guo · Yunji Chen

SimulMEGA: MoE Routers are Advanced Policy Makers for Simultaneous Speech Translation

Chenyang Le · Bing Han · Jinshun Li · Songyong Chen · Yanmin Qian

Hogwild! Inference: Parallel LLM Generation via Concurrent Attention

Gleb Rodionov · Roman Garipov · Alina Shutova · George Yakushev · Erik Schultheis · Vage Egiazarian · Anton Sinitsin · Denis Kuznedelev · Dan Alistarh

Atom of Thoughts for Markov LLM Test-Time Scaling

Fengwei Teng · Quan Shi · Zhaoyang Yu · Jiayi Zhang · Yuyu Luo · Chenglin Wu · Zhijiang Guo

Exploring Polyglot Harmony: On Multilingual Data Allocation for Large Language Models Pretraining

Ping Guo · Yubing Ren · BINBINLIU · Fengze Liu · Haobin Lin · Yifan Zhang · Bingni Zhang · Taifeng Wang · Yin Zheng

Reverse Engineering Human Preferences with Reinforcement Learning

Lisa Alazraki · Yi-Chern Tan · Jon Ander Campos · Maximilian Mozes · Marek Rei · Max Bartolo

The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning

Xinyu Zhu · Mengzhou Xia · Zhepei Wei · Wei-Lin Chen · Danqi Chen · Yu Meng

Preference Distillation via Value based Reinforcement Learning

Minchan Kwon · Junwon Ko · Kangil kim · Junmo Kim

VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model

Zuwei Long · Yunhang Shen · Chaoyou Fu · Heting Gao · Lijiang Li · Peixian Chen · Mengdan Zhang · Hang Shao · Jian Li · Jinlong Peng · Haoyu Cao · Ke Li · Rongrong Ji · Xing Sun

BlockDecoder: Boosting ASR Decoders with Context and Merger Modules

Darshan Prabhu · Preethi Jyothi

The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity

Parshin Shojaee · Iman Mirzadeh · Keivan Alizadeh vahid · Maxwell Horton · Samy Bengio · Mehrdad Farajtabar

SkyLadder: Better and Faster Pretraining via Context Window Scheduling

Tongyao Zhu · Qian Liu · Haonan Wang · Shiqi Chen · Xiangming Gu · Tianyu Pang · Min-Yen Kan

Who Reasons in the Large Language Models?

Jie Shao · Jianxin Wu

Bohdi: Heterogeneous LLM Fusion with Automatic Data Exploration

俊琪高 · Zhichang Guo · Dazhi Zhang · Dong Li · Runze Liu · Pengfei Li · Kai Tian · Biqing Qi

Generalizable, real-time neural decoding with hybrid state-space models

Avery Hee-Woon Ryoo · Nanda H Krishna · Ximeng Mao · Mehdi Azabou · Eva L Dyer · Matthew G Perich · Guillaume Lajoie

Bridging Scales: Spectral Theory Reveals How Local Connectivity Rules Sculpt Global Neural Dynamics in Spatially Extended Networks

Yuhan Huang · Keren Gao · Dongping Yang · Sen Song · Guozhang Chen

Finding separatrices of dynamical flows with Deep Koopman Eigenfunctions

Kabir Dabholkar · Omri Barak

SplashNet: Split‑and‑Share Encoders for Accurate and Efficient Typing with Surface Electromyography

Nima Hadidi · Jason Chan · Ebrahim Feghhi · Jonathan Kao

Learning to cluster neuronal function

Nina Nellen · Polina Turishcheva · Michaela Vystrčilová · Shashwat Sridhar · Tim Gollisch · Andreas Tolias · Alexander Ecker

CRRL: Learning Channel-invariant Neural Representations for High-performance Cross-day Decoding

Xianhan Tan · Binli Luo · Yu Qi · Yueming Wang

Error Broadcast and Decorrelation as a Potential Artificial and Natural Learning Mechanism

Mete Erdogan · Cengiz Pehlevan · Alper Erdogan

Riemannian Flow Matching for Brain Connectivity Matrices via Pullback Geometry

Antoine Collas · Ce Ju · Nicolas Salvy · Bertrand Thirion

OMiSO: Adaptive optimization of state-dependent brain stimulation to shape neural population states

Yuki Minai · Joana Soldado-Magraner · Byron M Yu · Matthew Smith

Jacobian-Based Interpretation of Nonlinear Neural Encoding Model

Xiaohui Gao · Haoran Yang · cheng yue · Mengfei Zuo · Yiheng Liu · Peiyang Li · Xiaohui Gao

ORBIT - Open Recommendation Benchmark for Reproducible Research with Hidden Tests

Jingyuan He · Jiongnan Liu · Vishan Oberoi · Bolin Wu · Mahima Jagadeesh Patel · Kangrui Mao · Chuning Shi · I-Ta Lee · Arnold Overwijk · Chenyan Xiong

Generating Computational Cognitive models using Large Language Models

Milena Rmus · Akshay Kumar Jagadish · Marvin Mathony · Tobias Ludwig · Eric Schulz

Brain-Like Processing Pathways Form in Models With Heterogeneous Experts

Jack Cook · Danyal Akarca · Rui Costa · Jascha Achterberg

Volume Transmission Implements Context Factorization to Target Online Credit Assignment and Enable Compositional Generalization

Matthew Bull · Po-Chen Kuo · Andrew Smith · Michael Buice

Self-Calibrating BCIs: Ranking and Recovery of Mental Targets Without Labels

Jonathan Grizou · Carlos De la Torre-Ortiz · Tuukka Ruotsalo

Explicitly Modeling Subcortical Vision with a Neuro-Inspired Front-End Improves CNN Robustness

Lucas Piper · Arlindo L Oliveira · Tiago Marques

HetSyn: Versatile Timescale Integration in Spiking Neural Networks via Heterogeneous Synapses

Zhichao Deng · Zhikun Liu · Junxue Wang · Shengqian Chen · Xiang Wei · Qiang Yu

PANORAMA: A Dataset and Benchmarks Capturing Decision Trails and Rationales in Patent Examination

Hyunseung Lim · Sooyohn Nam · Sungmin Na · Ji Yong Cho · June Yong Yang · Hyungyu Shin · Yoonjoo Lee · Juho Kim · Moontae Lee · Hwajung Hong

BRACE: A Benchmark for Robust Audio Caption Quality Evaluation

Tianyu Guo · Hongyu Chen · Hao Liang · Meiyi Qiang · Bohan Zeng · Linzhuang Sun · Bin CUI · Wentao Zhang

IRRISIGHT: A Large-Scale Multimodal Dataset and Scalable Pipeline to Address Irrigation and Water Management in Agriculture

Nibir Chandra Mandal · Oishee Bintey Hoque · Mandy Wilson · Samarth Swarup · Sayjro Nouwakpo · Abhijin Adiga · Madhav Marathe

Words That Unite The World: A Unified Framework for Deciphering Central Bank Communications

Agam Shah · Siddhant Sukhani · Huzaifa Pardawala · Saketh Budideti · Riya Bhadani · Rudra Gopal · Siddhartha Somani · Rutwik Routu · Michael Galarnyk · Soungmin Lee · Arnav Hiray · Akshar Ravichandran · Eric Kim · Pranav Aluru · Joshua Zhang · Sebastian Jaskowski · Veer Guda · Meghaj Tarte · Liqin Ye · Spencer Gosden · Rachel Yuh · Sloka Chava · Sahasra Chava · Dylan Patrick Kelly · Aiden Chiang · Harsit Mittal · Sudheer Chava

On Efficiency-Effectiveness Trade-off of Diffusion-based Recommenders

Wenyu Mao · Jiancan Wu · Guoqing Hu · Zhengyi Yang · Wei Ji · Xiang Wang

How Benchmark Prediction from Fewer Data Misses the Mark

Guanhua Zhang · Florian E. Dorner · Moritz Hardt

Fast Inference for Augmented Large Language Models

Rana Shahout · Cong Liang · Shiji Xin · Qianru Lao · Yong Cui · Minlan Yu · Michael Mitzenmacher

Risk-Averse Total-Reward Reinforcement Learning

Xihong Su · Jia Lin Hau · Gersi Doko · Kishan Panaganti · Marek Petrik

Value-Guided Decision Transformer: A Unified Reinforcement Learning Framework for Online and Offline Settings

Hongling Zheng · Li Shen · Yong Luo · Deheng Ye · Shuhan Xu · Bo Du · Jialie Shen · Dacheng Tao

Boundary-Value PDEs Meet Higher-Order Differential Topology-aware GNNs

Yunfeng Liao · Yangxin Wu · Xiucheng Li

FP64 is All You Need: Rethinking Failure Modes in Physics-Informed Neural Networks

Chenhui Xu · Dancheng Liu · Amir Nassereldine · Jinjun Xiong

Understanding Generalization in Physics Informed Models through Affine Variety Dimensions

Takeshi Koshizuka · Issei Sato

AutoHood3D: A Multi‑Modal Benchmark for Automotive Hood Design and Fluid–Structure Interaction

Vansh Sharma · Harish Ganesh · Maryam Akram · Wanjiao Liu · Venkat Raman

ML4CFD Competition: Results and Retrospective Analysis

Mouadh Yagoubi · David Danan · Milad LEYLI ABADI · Jocelyn Mazari · Jean-Patrick Brunet · Abbas Kabalan · Fabien Casenave · Yuxin Ma · Giovanni Catalani · Jean Fesquet · Jacob Helwig · Xuan Zhang · Haiyang Yu · Xavier BERTRAND · Frédéric TOST · Michaël Bauerheim · Joseph Morlier · Shuiwang Ji

DrivAerStar: An Industrial-Grade CFD Dataset for Vehicle Aerodynamic Optimization

Jiyan Qiu · Lyulin Kuang · Guan Wang · Yichen Xu · Leiyao Cui · Shaotong Fu · Yixin Zhu · Rita Zhang

Scaling Physical Reasoning with the PHYSICS Dataset

Shenghe Zheng · Qianjia Cheng · Junchi Yao · Mengsong Wu · haonan he · Ning Ding · Yu Cheng · Shuyue Hu · LEI BAI · Dongzhan Zhou · Ganqu Cui · Peng Ye

Dendritic Resonate-and-Fire Neuron for Effective and Efficient Long Sequence Modeling

Dehao Zhang · Malu Zhang · Shuai Wang · Jingya Wang · Wenjie Wei · Zeyu Ma · Guoqing Wang · Yang Yang · Haizhou Li

Let Brain Rhythm Shape Machine Intelligence for Connecting Dots on Graphs

Jiaqi Ding · Tingting Dan · Zhixuan Zhou · Guorong Wu

Extracting task-relevant preserved dynamics from contrastive aligned neural recordings

Yiqi Jiang · Kaiwen Sheng · Yujia Gao · Estefany Kelly Buchanan · Yu Shikano · Seung Je Woo · Yixiu Zhao · Tony Hyun Kim · Fatih Dinc · Scott Linderman · Mark Schnitzer

Incremental Sequence Classification with Temporal Consistency

Lucas Maystre · Gabriel Barello · Tudor Berariu · Cambray · Rares Dolga · Alvaro Ortega Gonzalez · Andrei Nica · David Barber

Unveiling the Spatial-temporal Effective Receptive Fields of Spiking Neural Networks

Jieyuan (Eric) Zhang · Xiaolong Zhou · Shuai Wang · Wenjie Wei · Hanwen Liu · Qian Sun · Malu Zhang · Yang Yang · Haizhou Li

Spectral Analysis of Representational Similarity with Limited Neurons

Hyunmo Kang · Abdulkadir Canatar · SueYeon Chung

Caption This, Reason That: VLMs Caught in the Middle

Zihan Weng · Lucas Gomez · Taylor Webb · Pouya Bashivan

Estimating cognitive biases with attention-aware inverse planning

Sounak Banerjee · Daphne Cornelisse · Deepak Gopinath · Emily Sumner · Jonathan DeCastro · Guy Rosman · Eugene Vinitsky · Mark Ho

Local-Global Coupling Spiking Graph Transformer for Brain Disorders Diagnosis from Two Perspectives

Geng Zhang · Jiangrong Shen · Kaizhong Zheng · Liangjun Chen · Badong Chen

Cross-Modal Representational Knowledge Distillation for Enhanced Spike-informed LFP Modeling

Eray Erturk · Saba Hashemi · Maryam Shanechi

Model Selection for Off-policy Evaluation: New Algorithms and Experimental Protocol

Pai Liu · Lingfeng Zhao · Shivangi Agarwal · Jinghan Liu · Audrey Huang · Philip Amortila · Nan Jiang

Scaling Offline RL via Efficient and Expressive Shortcut Models

Nicolas Espinosa-Dice · Yiyi Zhang · Yiding Chen · Bradley Guo · Owen Oertell · Gokul Swamy · Kianté Brantley · Wen Sun

RLtools: A Fast, Portable Deep Reinforcement Learning Library for Continuous Control

Jonas Eschmann · Dario Albani · Giuseppe Loianno

MyoChallenge 2024: A New Benchmark for Physiological Dexterity and Agility in Bionic Humans

Huiyi Wang · Chun Kwang Tan · Balint Hodossy · Shirui Lyu · Pierre Schumacher · James Heald · Kai Biegun · Samo Hromadka · Maneesh Sahani · Gunwoo Park · Beomsoo Shin · JongHyeon Park · Seungbum Koo · Chenhui Zuo · Chengtian Ma · Yanan Sui · Nick Hansen · Stone Tao · Yuan Gao · Hao Su · Seungmoon Song · Letizia Gionfrida · Massimo Sartori · Guillaume Durandau · Vikash Kumar · Vittorio Caggiano

Uncertainty-Sensitive Privileged Learning

Fan-Ming Luo · Lei Yuan · Yang Yu

PALQO: Physics-informed model for Accelerating Large-scale Quantum Optimization

Yiming Huang · Yajie Hao · Yuxuan Du · Jing Zhou · Xiao Yuan · Xiaoting Wang

Efficient Parametric SVD of Koopman Operator for Stochastic Dynamical Systems

Minchan Jeong · Jongha (Jon) Ryu · Se-Young Yun · Gregory Wornell

STNet: Spectral Transformation Network for Solving Operator Eigenvalue Problem

Hong Wang · Yixuan Jiang · Jie Wang · Xinyi Li · Jian Luo · huanshuo dong

AiDE-Q: Synthetic Labeled Datasets Can Enhance Learning Models for Quantum Property Estimation

Xinbiao Wang · Yuxuan Du · Zihan Lou · Yang Qian · Kaining Zhang · Yong Luo · Bo Du · Dacheng Tao

PINN Balls: Scaling Second-Order Methods for PINNs with Domain Decomposition and Adaptive Sampling

Andrea Bonfanti · Ismael Medina · Roman List · Björn Staeves · Roberto Santana · Marco Ellero

Revisiting End-to-End Learning with Slide-level Supervision in Computational Pathology

Wenhao Tang · Rong Qin · Heng Fang · Fengtao Zhou · Hao CHEN · Xiang Li · Ming-Ming Cheng

PAC Bench: Do Foundation Models Understand Prerequisites for Executing Manipulation Policies?

Atharva Gundawar · Som Sagar · Ransalu Senanayake

Embodied Cognition Augmented End2End Autonomous Driving

Ling Niu · Xiaoji Zheng · han wang · Ziyuan Yang · Chen Zheng · Bokui Chen · Jiangtao Gong

AutoVLA: A Vision-Language-Action Model for End-to-End Autonomous Driving with Adaptive Reasoning and Reinforcement Fine-Tuning

Zewei Zhou · Tianhui Cai · Seth Zhao · Yun Zhang · Zhiyu Huang · Bolei Zhou · Jiaqi Ma

Accelerating Visual-Policy Learning through Parallel Differentiable Simulation

Haoxiang You · Yilang Liu · Ian Abraham

What Do Latent Action Models Actually Learn?

Chuheng Zhang · Tim Pearce · Pushi Zhang · Kaixin Wang · Xiaoyu Chen · Wei Shen · Li Zhao · Jiang Bian

Active Test-time Vision-Language Navigation

Heeju Ko · Sung June Kim · Gyeongrok Oh · Jeongyoon YOON · Honglak Lee · Sujin Jang · Seungryong Kim · Sangpil Kim

FreqPolicy: Frequency Autoregressive Visuomotor Policy with Continuous Tokens

Yiming Zhong · Yumeng Liu · Chuyang Xiao · Zemin Yang · Youzhuo Wang · Yufei Zhu · Ye Shi · Yujing Sun · Xinge ZHU · Yuexin Ma

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

Wenyao Zhang · Hongsi Liu · Zekun Qi · Yunnan Wang · XinQiang Yu · Jiazhao Zhang · Runpei Dong · Jiawei He · He Wang · Zhizheng Zhang · Li Yi · Wenjun Zeng · Xin Jin

VLA-Cache: Efficient Vision-Language-Action Manipulation via Adaptive Token Caching

Siyu Xu · Yunke Wang · Chenghao Xia · Dihao Zhu · Tao Huang · Chang Xu

EfficientVLA: Training-Free Acceleration and Compression for Vision-Language-Action Models

Yantai Yang · Yuhao Wang · Zichen Wen · Luo Zhongwei · Chang Zou · Zhipeng Zhang · Chuan Wen · Linfeng Zhang

Rotary Masked Autoencoders are Versatile Learners

Uros Zivanovic · Serafina Di Gioia · Andre Scaffidi · Martín de los Rios · Gabriella Contardo · Roberto Trotta

Self-Perturbed Anomaly-Aware Graph Dynamics for Multivariate Time-Series Anomaly Detection

Jinyu Cai · Yuan Xie · Glynnis Lim · Yifang Yin · Roger Zimmermann · See-Kiong Ng

Channel Simulation and Distributed Compression with Ensemble Rejection Sampling

Truong Buu Phan · Ashish Khisti

ScatterAD: Temporal-Topological Scattering Mechanism for Time Series Anomaly Detection

Tao Yin · Shaochen Fu · Zhibin Zhang · Li Huang · Xiaohong Zhang · Yiyuan Yang · Kaixiang Yang · Meng Yan

Single-Step Operator Learning for Conditioned Time-Series Diffusion Models

Hui Chen · Vikas Singh

xLSTM-Mixer: Multivariate Time Series Forecasting by Mixing via Scalar Memories

Maurice Kraus · Felix Divo · Devendra Singh Dhami · Kristian Kersting

TARFVAE: Efficient One-Step Generative Time Series Forecasting via TARFLOW based VAE

Jiawen Wei · jiang lan · Pengbo Wei · Ziwen Ye · Teng Song · Chen Chen · Guangrui Ma

COOPERA: Continual Open-Ended Human-Robot Assistance

Chenyang Ma · Kai Lu · Ruta Desai · Xavier Puig · Andrew Markham · Niki Trigoni

Aux-Think: Exploring Reasoning Strategies for Data-Efficient Vision-Language Navigation

Shuo Wang · Yongcai Wang · Wanting Li · Xudong Cai · Yucheng Wang · Maiyue Chen · kaihui.wang · Zhizhong Su · Deying Li · Zhaoxin Fan

BEAST: Efficient Tokenization of B-Splines Encoded Action Sequences for Imitation Learning

Hongyi Zhou · Weiran Liao · Xi Huang · Yucheng Tang · Fabian Otto · Xiaogang Jia · Xinkai Jiang · Simon Hilber · Ge Li · Qian Wang · Ömer Yağmurlu · Nils Blank · Moritz Reuss · Rudolf Lioutikov

DynaRend: Learning 3D Dynamics via Masked Future Rendering for Robotic Manipulation

Jingyi Tian · Le Wang · Sanping Zhou · Sen Wang · lijiayi · Gang Hua

AC-DiT: Adaptive Coordination Diffusion Transformer for Mobile Manipulation

Sixiang Chen · Jiaming Liu · Siyuan Qian · Han Jiang · Zhuoyang Liu · Chenyang Gu · Xiaoqi Li · Chengkai Hou · Pengwei Wang · Zhongyuan Wang · Renrui Zhang · Shanghang Zhang

EfficientNav: Towards On-Device Object-Goal Navigation with Navigation Map Caching and Retrieval

Zebin Yang · Sunjian Zheng · Tong Xie · Tianshi Xu · Bo Yu · Fan Wang · Jie Tang · Shaoshan Liu · Meng Li

Contact Map Transfer with Conditional Diffusion Model for Generalizable Dexterous Grasp Generation

Yiyao Ma · Kai Chen · Kexin ZHENG · DOU QI

Compliant Residual DAgger: Improving Real-World Contact-Rich Manipulation with Human Corrections

Xiaomeng Xu · Yifan Hou · Zeyi Liu · Shuran Song

Learning 3D Persistent Embodied World Models

Siyuan Zhou · Yilun Du · Yuncong Yang · Lei Han · Peihao Chen · Dit-Yan Yeung · Chuang Gan

Real-Time Execution of Action Chunking Flow Policies

Kevin Black · Manuel Galliker · Sergey Levine

Enhancing Tactile-based Reinforcement Learning for Robotic Control

Elle Miller · Trevor McInroe · David Abel · Oisin Mac Aodha · Sethu Vijayakumar

VideoCAD: A Dataset and Model for Learning Long‑Horizon 3D CAD UI Interactions from Video

King Yiu Brandon Man · Ghadi Nehme · Md Ferdous Alam · Faez Ahmed

Demystifying Network Foundation Models

Roman Beltiukov · Satyandra Guthula · Wenbo Guo · Walter Willinger · Arpit Gupta

RADAR: Benchmarking Language Models on Imperfect Tabular Data

Ken Gu · Zhihan Zhang · Kate Lin · Yuwei Zhang · Akshay Paruchuri · Hong Yu · Mehran Kazemi · Kumar Ayush · A. Ali Heydari · Max Xu · Yun Liu · Ming-Zher Poh · Yuzhe Yang · Mark Malhotra · Shwetak Patel · Hamid Palangi · Xuhai "Orson" Xu · Daniel McDuff · Tim Althoff · Xin Liu

AstroVisBench: A Code Benchmark for Scientific Computing and Visualization in Astronomy

Sebastian Joseph · Syed M. Husain · Stella Offner · Stéphanie Juneau · Paul Torrey · Adam Bolton · Juan Farias · Niall Gaffney · Greg Durrett · Junyi Jessy Li

Quantifying Generalisation in Imitation Learning

Nathan Gavenski · Odinaldo Rodrigues

ArchPower: Dataset for Architecture-Level Power Modeling of Modern CPU Design

Qijun Zhang · Yao Lu · Mengming Li · Shang Liu · Zhiyao Xie

Towards A Translative Model of Sperm Whale Vocalization

Orr Paradise · Liangyuan Chen · Pranav Muralikrishnan · Hugo Flores · Bryan Pardo · Roee Diamant · David Gruber · Shane Gero · Shafi Goldwasser

SMARTraj$^2$: A Stable Multi-City Adaptive Method for Multi-View Spatio-Temporal Trajectory Representation Learning

Tangwen Qian · Junhe Li · Yile Chen · Gao Cong · Zezhi Shao · Jun Zhang · Tao Sun · Fei Wang · Yongjun Xu

Synthesizing Performance Constraints for Evaluating and Improving Code Efficiency

Jun Yang · Cheng-Chi Wang · Bogdan Stoica · Kexin Pei

DualMPNN: Harnessing Structural Alignments for High-Recovery Inverse Protein Folding

Xuhui Liao · qiyu wang · Zhiqiang Liang · Liwei Xiao · Junjie Chen

Personalized Decision Modeling: Utility Optimization or Textualized-Symbolic Reasoning

Yibo Zhao · Yang Zhao · Hongru Du · Hao Frank Yang

RobustMerge: Parameter-Efficient Model Merging for MLLMs with Direction Robustness

Fanhu Zeng · Haiyang Guo · Fei Zhu · Li Shen · Hao Tang

R$^2$ec: Towards Large Recommender Models with Reasoning

Runyang You · Yongqi Li · Xinyu Lin · Xin Zhang · Wenjie Wang · Wenjie Li · Liqiang Nie

Predicting Empirical AI Research Outcomes with Language Models

Jiaxin Wen · Chenglei Si · Yueh-Han Chen · He He · Shi Feng

Seeing What Matters: Generalizable AI-generated Video Detection with Forensic-Oriented Augmentation

Riccardo Corvi · Davide Cozzolino · Ekta Prashnani · Shalini De Mello · Koki Nagano · Luisa Verdoliva

IneqSearch: Hybrid Reasoning for Olympiad Inequality Proofs

Zhaoqun Li · Beishui Liao · Qiwei Ye

SmartCache: Context-aware Semantic Cache for Efficient Multi-turn LLM Inference

Chengye Yu · Tianyu Wang · Zili Shao · Song Jiang

DoDo-Code: an Efficient Levenshtein Distance Embedding-based Code for 4-ary IDS Channel

Alan J.X. Guo · Sihan Sun · Xiang Wei · Mengyi Wei · Xin Chen

Data Fusion for Partial Identification of Causal Effects

Quinn Lanners · Cynthia Rudin · Alexander Volfovsky · Harsh Parikh

Causal Explanation-Guided Learning for Organ Allocation

Alessandro Marchese · Jeroen Berrevoets · Sam Verboven

Practical do-Shapley Explanations with Estimand-Agnostic Causal Inference

Álvaro Parafita · Tomas Garriga · Axel Brando · Francisco Cazorla

Efficient Randomized Experiments Using Foundation Models

Piersilvio De Bartolomeis · Javier Abad · Guanbo Wang · Konstantin Donhauser · Raymond Duch · Fanny Yang · Issa Dahabreh

ProDAG: Projected Variational Inference for Directed Acyclic Graphs

Ryan Thompson · Edwin Bonilla · Robert Kohn

Counterfactual Implicit Feedback Modeling

Chuan Zhou · Lina Yao · Haoxuan Li · Mingming Gong

Handling Missing Responses under Cluster Dependence with Applications to Language Model Evaluation

Zhenghao Zeng · David Arbour · Avi Feller · Ishita Dasgupta · Atanu Sinha · Edward Kennedy

Do-PFN: In-Context Learning for Causal Effect Estimation

Jake Robertson · Arik Reuter · Siyuan Guo · Noah Hollmann · Frank Hutter · Bernhard Schölkopf

It’s Hard to Be Normal: The Impact of Noise on Structure-agnostic Estimation

Jikai Jin · Lester Mackey · Vasilis Syrgkanis

Estimating Interventional Distributions with Uncertain Causal Graphs through Meta-Learning

Anish Dhir · Cristiana Diaconu · Valentinian Lungu · James Requeima · Richard Turner · Mark van der Wilk

Beyond the Average: Distributional Causal Inference under Imperfect Compliance

Undral Byambadalai · Tomu Hirata · Tatsushi Oka · Shota Yasui

Confounding Robust Deep Reinforcement Learning: A Causal Approach

Mingxuan Li · Junzhe Zhang · Elias Bareinboim

Root Cause Analysis of Outliers with Missing Structural Knowledge

William Roy Orchard · Nastaran Okati · Sergio Garrido Mejia · Patrick Blöbaum · Dominik Janzing

Structural Causal Bandits under Markov Equivalence

Min Woo Park · Andy Arditi · Elias Bareinboim · Sanghack Lee

Conformal Prediction for Causal Effects of Continuous Treatments

Maresa Schröder · Dennis Frauen · Jonas Schweisthal · Konstantin Hess · Valentyn Melnychuk · Stefan Feuerriegel

Multivariate Dynamic Mediation Analysis under a Reinforcement Learning Framework

Lan Luo · Chengchun Shi · Jitao Wang · Zhenke Wu · Lexin Li

FuncGenFoil: Airfoil Generation and Editing Model in Function Space

Jinouwen Zhang · Junjie Ren · Ma Qianhong · Jianyu Wu · Aobo Yang · Yan Lu · Lu Chen · Hairun Xie · Jing Wang · Miao Zhang · Wanli Ouyang · SHIXIANG TANG

Look Before You Leap: A GUI-Critic-R1 Model for Pre-Operative Error Diagnosis in GUI Automation

Yuyang Wanyan · Xi Zhang · Haiyang Xu · Haowei Liu · Junyang Wang · Jiabo Ye · Yutong Kou · Ming Yan · Fei Huang · Xiaoshan Yang · Weiming Dong · Changsheng Xu

Demystifying Spectral Feature Learning for Instrumental Variable Regression

Dimitri Meunier · Antoine Moulin · Jakub Wornbard · Vladimir Kostic · Arthur Gretton

Curious Causality-Seeking Agents Learn Meta Causal World

Zhiyu Zhao · Haoxuan Li · Haifeng Zhang · Jun Wang · Francesco Faccio · Jürgen Schmidhuber · Mengyue Yang

Decomposing Interventional Causality into Synergistic, Redundant, and Unique Components

Abel Jansma

Learning CAD Modeling Sequences via Projection and Part Awareness

Yang Liu · Daxuan Ren · Yijie Ding · Jianmin Zheng · Fang Deng

Connecting Jensen–Shannon and Kullback–Leibler Divergences: A New Bound for Representation Learning

Reuben Dorent · Polina Golland · William (Sandy) Wells

Copresheaf Topological Neural Networks: A Generalized Deep Learning Framework

Mustafa Hajij · Lennart Bastian · Sarah Osentoski · Hardik Kabaria · John Davenport · Dawood · Balaji Cherukuri · Joseph Kocheemoolayil · Nastaran Shahmansouri · Adrian Lew · Theodore Papamarkou · Tolga Birdal

VESSA: Video-based objEct-centric Self-Supervised Adaptation for Visual Foundation Models

Jesimon Barreto · Carlos Caetano · Andre Araujo · William Schwartz

Graph Your Own Prompt

Xi Ding · Lei Wang · Piotr Koniusz · Yongsheng Gao

TREND: Unsupervised 3D Representation Learning via Temporal Forecasting for LiDAR Perception

Runjian Chen · Hyoungseob Park · Bo Zhang · Wenqi Shao · Ping Luo · Alex Wong

Ultrametric Cluster Hierarchies: I Want ‘em All!

Andrew Draganov · Pascal Weber · Rasmus Jørgensen · Anna Beer · Claudia Plant · Ira Assent

Structure-Aware Fusion with Progressive Injection for Multimodal Molecular Representation Learning

Zihao Jing · Yan Sun · Yan Yi Li · Sugitha Janarthanan · Alana Deng · Pingzhao Hu

HELM: Hyperbolic Large Language Models via Mixture-of-Curvature Experts

Neil He · Rishabh Anand · Hiren Madhu · Ali Maatouk · Smita Krishnaswamy · Leandros Tassiulas · Menglin Yang · Rex Ying

Randomized-MLP Regularization Improves Domain Adaptation and Interpretability in DINOv2

Joel Valdivia Ortega · Lorenz Lamm · Franziska Eckardt · Benedikt Schworm · Marion Jasnin · Tingying Peng

Joint‑Embedding vs Reconstruction: Provable Benefits of Latent Space Prediction for Self‑Supervised Learning

Hugues Van Assel · Mark Ibrahim · Tommaso Biancalani · Aviv Regev · Randall Balestriero

Emergence of Linear Truth Encodings in Language Models

Shauli Ravfogel · Gilad Yehudai · Tal Linzen · Joan Bruna · Alberto Bietti

Contrastive Representations for Temporal Reasoning

Alicja Ziarko · Michał Bortkiewicz · Michał Zawalski · Benjamin Eysenbach · Piotr Miłoś

SparseMVC: Probing Cross-view Sparsity Variations for Multi-view Clustering

Ruimeng Liu · Xin Zou · Chang Tang · Xiao Zheng · Xingchen Hu · Kun Sun · Xinwang Liu

Adaptive Cannistraci-Hebb Network Automata Modelling of Complex Networks for Path-based Link Prediction

Jialin Zhao · Alessandro Muscoloni · Umberto Michieli · Yingtao Zhang · Carlo Vittorio Cannistraci

Aeolus: A Multi-structural Flight Delay Dataset

Lin Xu · Xinyun Yuan · Yuxuan Liang · Suwan Yin · Yuankai Wu

Test-Time Adaptation by Causal Trimming

Yingnan Liu · Rui Qiao · Mong-Li Lee · Wynne Hsu

Continual Model Merging without Data: Dual Projections for Balancing Stability and Plasticity

Enneng Yang · Anke Tang · Li Shen · Guibing Guo · Xingwei Wang · Xiaochun Cao · Jie Zhang

Merging on the Fly Without Retraining: A Sequential Approach to Scalable Continual Model Merging

Anke Tang · Enneng Yang · Li Shen · Yong Luo · Han Hu · Lefei Zhang · Bo Du · Dacheng Tao

Enhancing Visual Prompting through Expanded Transformation Space and Overfitting Mitigation

Shohei Enomoto

Memory-Integrated Reconfigurable Adapters: A Unified Framework for Settings with Multiple Tasks

Susmit Agrawal · Krishn Vishwas Kher · Saksham Mittal · Swarnim Maheshwari · Vineeth N Balasubramanian

Wasserstein Transfer Learning

Kaicheng Zhang · Sinian Zhang · Doudou Zhou · Yidong Zhou

Rethinking Out-of-Distribution Detection and Generalization with Collective Behavior Dynamics

Zhenbin Wang · Lei Zhang · Wei Huang · Zhao Zhang · Zizhou Wang

Fantastic Features and Where to Find Them: A Probing Method to combine Features from Multiple Foundation Models

Benjamin Ramtoula · Pierre-Yves Lajoie · Paul Newman · Daniele De Martini

PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation

Kunyu Wang · Xueyang Fu · Yuanfei Bao · Chengjie Ge · Chengzhi Cao · Wei Zhai · Zheng-Jun Zha

Searching Latent Program Spaces

Matthew Macfarlane · Clem Bonnet

Few-Shot Knowledge Distillation of LLMs With Counterfactual Explanations

Faisal Hamman · Pasan Dissanayake · Yanjun Fu · Sanghamitra Dutta

Plug-and-play Feature Causality Decomposition for Multimodal Representation Learning

Ye Liu · Zihan Ji · Hongmin Cai

In-Context Compositional Learning vis Sparse Coding Transformer

Wei Chen · Jingxi Yu · Zichen Miao · Qiang Qiu

ProteinConformers: Benchmark Dataset for Simulating Protein Conformational Landscape Diversity and Plausibility

Yihang Zhou · Chen Wei · Minghao Sun · Jin Song · Yang Li · Lin Wang · Yang Zhang

Lorentz Local Canonicalization: How to make any Network Lorentz-Equivariant

Jonas Spinner · Luigi Favaro · Peter Lippmann · Sebastian Pitz · Gerrit Gerhartz · Tilman Plehn · Fred Hamprecht

Benchmarking Large Language Models with Integer Sequence Generation Tasks

Daniel O'Malley · Manish Bhattarai · Nishath Ranasinghe · Erick Draayer · Javier E. Santos

SpecMAS: A Multi-Agent System for Self-Verifying System Generation via Formal Model Checking

Rishabh Agrawal · Kaushik Ranade · Aja Khanal · Kalyan Basu · Apurva Narayan

AF-UMC: An Alignment-Free Fusion Framework for Unaligned Multi-View Clustering

Bohang Sun · Yuena Lin · Tao Yang · Zhen Zhu · Zhen Yang · Gengyu Lyu

SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration

Elif Arslan · Jacobus van der Linden · Serge Hoogendoorn · Marco Rinaldi · Emir Demirović

Confidence-Aware With Prototype Alignment for Partial Multi-label Learning

Weijun Lv · Yu Chen · Xiaozhao Fang · Xuhuan Zhu · Jie Wen · Guoxu Zhou · Sixian Chan

QuanDA: Quantile-Based Discriminant Analysis for High-Dimensional Imbalanced Classification

Qian Tang · Yuwen Gu · Boxiang Wang

Near-Exponential Savings for Population Mean Estimation with Active Learning

Julian Morimoto · JACOB GOLDIN · Daniel Ho

Breaking the Gradient Barrier: Unveiling Large Language Models for Strategic Classification

Xinpeng Lv · Yunxin Mao · Haoxuan Li · KE LIANG · Jinxuan Yang · Wanrong Huang · Haoang Chi · Huan Chen · Long Lan · Cyuanlong · Wenjing Yang · Haotian Wang

Reliably detecting model failures in deployment without labels

Viet Nguyen · Changjian Shui · Vijay Giri · Siddharth Arya · Amol Verma · Fahad Razak · Rahul Krishnan

Imbalances in Neurosymbolic Learning: Characterization and Mitigating Strategies

Efthymia Tsamoura · Kaifu Wang · Dan Roth

Incomplete Multi-view Deep Clustering with Data Imputation and Alignment

Jiyuan Liu · Xinwang Liu · Xinhang Wan · KE LIANG · Weixuan Liang · sihang zhou · Huijun Wu · Kehua Guo

Scalable and adaptive prediction bands with kernel sum-of-squares

Louis Allain · Sébastien Da Veiga · Brian Staber

Evolutionary Multi-View Classification via Eliminating Individual Fitness Bias

Xinyan Liang · Shuai Li · Qian Guo · Yuhua Qian · Bingbing Jiang · Tingjin Luo · Liang Du

Distributionally Robust Learning for Multi-source Unsupervised Domain Adaptation

Zhenyu Wang · Peter Bühlmann · Zijian Guo

DUET: Dual-Perspective Pseudo Labeling and Uncertainty-aware Exploration & Exploitation Training for Source-Free Domain Adaptation

JaeYun Lee · Jae Hyeon Park · Gyoomin Lee · Bogyeong Kim · Min Hee Cha · Hyeok Nam · Joo Jeon · Hyunse Lee · Sung In Cho

Purest Quantum State Identification

Yingqi Yu · Honglin Chen · Jun Wu · Wei Xie · Xiangyang Li

The Power of Iterative Filtering for Supervised Learning with (Heavy) Contamination

Adam Klivans · Konstantinos Stavropoulos · Kevin Tian · Arsen Vasilyan

On Minimax Estimation of Parameters in Softmax-Contaminated Mixture of Experts

Fanqi Yan · Huy Nguyen · Le Dung · Pedram Akbarian · Nhat Ho · Alessandro Rinaldo

Formal Models of Active Learning from Contrastive Examples

Farnam Mansouri · Hans Simon · Adish Singla · Yuxin Chen · Sandra Zilles

Efficient PAC Learning for Realizable-Statistic Models via Convex Surrogates

Shivani Agarwal

Thompson Sampling for Multi-Objective Linear Contextual Bandit

Somangchan Park · Heesang Ann · Min-hwan Oh

IMPROVED LEARNING THEORY FOR KERNEL DISTRIBUTION REGRESSION WITH TWO-STAGE SAMPLING

Alberto González-Sanz · François Bachoc · Jean-Michel Loubes · Louis Béthune

Online Bilateral Trade With Minimal Feedback: Don’t Waste Seller’s Time

Francesco Bacchiocchi · Matteo Castiglioni · Roberto Colomboni · Alberto Marchesi

Evolutionary Prediction Games

Eden Saig · Nir Rosenfeld

Robust Equilibria in Continuous Games: From Strategic to Dynamic Robustness

Kyriakos Lotidis · Panayotis Mertikopoulos · Nicholas Bambos · Jose Blanchet

Combinatorial Ski Rental Problem: Robust and Learning-Augmented Algorithms

Ziwei Li · Bo Sun · Zhiqiu Zhang · Mohammad Hajiesmaili · Binghan Wu · Lin Yang · Yang Gao

Learning-Augmented Facility Location Mechanisms for the Envy Ratio Objective

Haris Aziz · Yuhang Guo · Alexander Lam · Houyu Zhou

Assignments for Congestion-Averse Agents: Seeking Competitive and Envy-Free Solutions

Jiehua Chen · Jiong Guo · Yinghui Wen

The Complexity of Symmetric Equilibria in Min-Max Optimization and Team Zero-Sum Games

Ioannis Anagnostides · Ioannis Panageas · Tuomas Sandholm · Jingming Yan

On the Existence and Complexity of Core-Stable Data Exchanges

Jiaxin Song · Pooja Kulkarni · Parnian Shahkar · Bhaskar Ray Chaudhury

Rethinking Joint Maximum Mean Discrepancy for Visual Domain Adaptation

Wei Wang · Haifeng Xia · Chao Huang · Zhengming Ding · Cong Wang · Haojie Li · Xiaochun Cao

Continuous Domain Generalization

Zekun CAI · Yiheng YAO · Guangji Bai · Renhe Jiang · Xuan Song · Ryosuke Shibasaki · Liang Zhao

MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning

Sizhe Tang · Jiayu Chen · Tian Lan

Temperature is All You Need for Generalization in Langevin Dynamics and other Markov Processes

Itamar Harel · Yonathan Wolanowsky · Gal Vardi · Nati Srebro · Daniel Soudry

Optimal Mistake Bounds for Transductive Online Learning

Zachary Chase · Steve Hanneke · Shay Moran · Jonathan Shafer

On Traceability in $\ell_p$ Stochastic Convex Optimization

Sasha Voitovych · Mahdi Haghifam · Idan Attias · Gintare Karolina Dziugaite · Roi Livni · Dan Roy

Johnson-Lindenstrauss Lemma Beyond Euclidean Geometry

Chengyuan Deng · Jie Gao · Kevin Lu · Feng Luo · Cheng Xin

From Information to Generative Exponent: Learning Rate Induces Phase Transitions in SGD

Konstantinos Tsiolis · Alireza Mousavi-Hosseini · Murat Erdogdu

Improved Balanced Classification with Theoretically Grounded Loss Functions

Corinna Cortes · Mehryar Mohri · Yutao Zhong

High-Dimensional Calibration from Swap Regret

Maxwell Fishelson · Noah Golowich · Mehryar Mohri · Jon Schneider

Unveiling the Power of Multiple Gossip Steps: A Stability-Based Generalization Analysis in Decentralized Training

Qinglun Li · Yingqi Liu · Miao Zhang · Xiaochun Cao · Quanjun Yin · Li Shen

Absorb and Converge: Provable Convergence Guarantee for Absorbing Discrete Diffusion Models

Yuchen Liang · Renxiang Huang · Lifeng LAI · Ness Shroff · Yingbin Liang

Greedy Algorithms for Structured Bandits: A Sharp Characterization of Asymptotic Success / Failure

Aleksandrs Slivkins · Yunzong Xu · Shiliang Zuo

Multi-Agent Imitation by Learning and Sampling from Factorized Soft Q-Function

Yi-Chen Li · Zhongxiang Ling · Tao Jiang · Fuxiang Zhang · Pengyuan Wang · Lei Yuan · Zongzhang Zhang · Yang Yu

Self-Verification Provably Prevents Model Collapse in Recursive Synthetic Training

Shi Fu · Yingjie Wang · Yuzhu Chen · Li Shen · Dacheng Tao

Optimality and NP-Hardness of Transformers in Learning Markovian Dynamical Functions

Yanna Ding · Songtao Lu · Yingdong Lu · Tomasz Nowicki · Jianxi Gao

Towards Understanding Transformers in Learning Random Walks

Wei Shi · Yuan Cao

Conservative classifiers do consistently well with improving agents: characterizing statistical and online learning

Dravyansh Sharma · Alec Sun

Provable Sample-Efficient Transfer Learning Conditional Diffusion Models via Representation Learning

Ziheng Cheng · Tianyu Xie · Shiyue Zhang · Cheng Zhang

Computable universal online learning

Dariusz Kalociński · Tomasz Steifer

Marginal-Nonuniform PAC Learnability

Steve Hanneke · Shay Moran · Maximilian Thiessen

Eliciting Reasoning in Language Models with Cognitive Tools

Brown Wilfried Ebouky Doualla Dina · Andrea Bartezzaghi · Mattia Rigotti

Wonder Wins Ways: Curiosity-Driven Exploration through Multi-Agent Contextual Calibration

Yiyuan Pan · Zhe Liu · Hesheng Wang

Bootstrap Off-policy with World Model

Guojian Zhan · Likun Wang · Xiangteng Zhang · Jiaxin Gao · Masayoshi TOMIZUKA · Shengbo Li

Act Only When It Pays: Efficient Reinforcement Learning for LLM Reasoning via Selective Rollouts

Haizhong Zheng · Yang Zhou · Brian Bartoldson · Bhavya Kailkhura · Fan Lai · Jiawei Zhao · Beidi Chen

Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving

Xinji Mai · Haotian Xu · Xing W · Weinong Wang · Yingying Zhang · Wenqiang Zhang

Robust and Scalable Autonomous Reinforcement Learning in Irreversible Environments

Sang-Hyun Lee

Reinforcing the Diffusion Chain of Lateral Thought with Diffusion Language Models

Zemin Huang · Zhiyang Chen · Zijun Wang · Tiancheng Li · Guo-Jun Qi

DyMoDreamer: World Modeling with Dynamic Modulation

Boxuan Zhang · Runqing Wang · Wei Xiao · Weipu Zhang · Jian Sun · Gao Huang · Jie Chen · Gang Wang

Continual Knowledge Adaptation for Reinforcement Learning

Jinwu Hu · ZiHao Lian · Zhiquan Wen · Chenghao Li · Guohao Chen · Xutao Wen · Bin Xiao · Mingkui Tan

Active Seriation: Efficient Ordering Recovery with Statistical Guarantees

James Cheshire · Yann Issartel

Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel

Yilan Chen · Zhichao Wang · Wei Huang · Andi Han · Taiji Suzuki · Arya Mazumdar

Can Diffusion Models Disentangle? A Theoretical Perspective

Liming Wang · Muhammad Jehanzeb Mirza · Yishu Gong · Yuan Gong · Jiaqi Zhang · Brian Tracey · Katerina Placek · Marco Vilela · Jim Glass

Efficiently Maintaining the Multilingual Capacity of MCLIP in Downstream Cross-Modal Retrieval Tasks

Fengmao Lyu · Jitong Lei · Guosheng Lin · Desheng ZHENG · Jianyang Zhang · Tianrui Li

Pareto Optimal Risk-Agnostic Distributional Bandits with Heavy-Tail Rewards

Kyungjae Lee · Dohyeong Kim · Taehyun Cho · Chaeyeon Kim · Yunkyung Ko · Seungyub Han · Seokhun Ju · Dohyeok Lee · Sungbin Lim

Generalization Bounds for Rank-sparse Neural Networks

Antoine Ledent · Rodrigo Alves · Yunwen Lei

Consistency of the $k_n$-nearest neighbor rule under adaptive sampling

Robi Bhattacharjee · Geelon So · Sanjoy Dasgupta

Exploration via Feature Perturbation in Contextual Bandits

Seouh-won Yi · Min-hwan Oh

Discrete Diffusion Models: Novel Analysis and New Sampler Guarantees

Yuchen Liang · Yingbin Liang · Lifeng LAI · Ness Shroff

From Kolmogorov to Cauchy: Shallow XNet Surpasses KANs

Xin Li · Xiaotao Zheng · Zhihong Xia

Split conformal classification with unsupervised calibration

Santiago Mazuelas

Hybrid Latent Reasoning via Reinforcement Learning

Zhenrui Yue · Bowen Jin · Huimin Zeng · Honglei Zhuang · Zhen Qin · Jinsung Yoon · Lanyu Shang · Jiawei Han · Dong Wang

Off-policy Reinforcement Learning with Model-based Exploration Augmentation

Likun Wang · Xiangteng Zhang · Yinuo Wang · Guojian Zhan · Wenxuan Wang · Haoyu Gao · Jingliang Duan · Shengbo Li

CORE: Collaborative Optimization with Reinforcement Learning and Evolutionary Algorithm for Floorplanning

Pengyi Li · Shixiong Kai · Jianye Hao · Ruizhe Zhong · Hongyao Tang · Zhentao Tang · Mingxuan Yuan · Junchi Yan

Turning Sand to Gold: Recycling Data to Bridge On-Policy and Off-Policy Learning via Causal Bound

Tal Fiskus · Uri Shaham

DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Qiying Yu · Zheng Zhang · Ruofei Zhu · Yufeng Yuan · Xiaochen Zuo · Yu Yue · Weinan Dai · Tiantian Fan · Gaohong Liu · juncai liu · LingJun Liu · Xin Liu · Haibin Lin · Zhiqi Lin · Bole Ma · Guangming Sheng · Yuxuan Tong · Chi Zhang · Mofan Zhang · Ru Zhang · Wang Zhang · Hang Zhu · Jinhua Zhu · Jiaze Chen · Jiangjie Chen · Chengyi Wang · Hongli Yu · Yuxuan Song · Xiangpeng Wei · Hao Zhou · Jingjing Liu · Wei-Ying Ma · Ya-Qin Zhang · Lin Yan · Yonghui Wu · Mingxuan Wang

Distribution Learning Meets Graph Structure Sampling

Arnab Bhattacharyya · Sutanu Gayen · Philips George John · Sayantan Sen · N. V. Vinodchandran

REINFORCEMENT LEARNING FOR INDIVIDUAL OPTIMAL POLICY FROM HETEROGENEOUS DATA

Rui Miao · Babak Shahbaba · Annie Qu

ADG: Ambient Diffusion-Guided Dataset Recovery for Corruption-Robust Offline Reinforcement Learning

Zeyuan Liu · Zhihe Yang · Jiawei Xu · Rui Yang · Jiafei Lyu · Baoxiang Wang · Yunjian Xu · Xiu Li

Exploration from a Primal-Dual Lens: Value-Incentivized Actor-Critic Methods for Sample-Efficient Online RL

Tong Yang · Bo Dai · Lin Xiao · Yuejie Chi

Finite-Sample Analysis of Policy Evaluation for Robust Average Reward Reinforcement Learning

Yang Xu · Washim Mondal · Vaneet Aggarwal

Efficient and Near-Optimal Algorithm for Contextual Dueling Bandits with Offline Regression Oracles

Aadirupa Saha · Robert Schapire

Learning Personalized Ad Impact via Contextual Reinforcement Learning under Delayed Rewards

Yuwei Cheng · Zifeng Zhao · Haifeng Xu

Zero-Shot Trajectory Planning for Signal Temporal Logic Tasks

Ruijia Liu · Ancheng Hou · Xiao Yu · Xiang Yin

True Impact of Cascade Length in Contextual Cascading Bandits

Hyun-jun Choi · Joongkyu Lee · Min-hwan Oh

ActiveVOO: Value of Observation Guided Active Knowledge Acquisition for Open-World Embodied Lifted Regression Planning

Xiaotian Liu · Ali Pesaranghader · Jaehong Kim · Tanmana Sadhu · Hyejeong Jeon · Scott Sanner

NaDRO: Leveraging Dual-Reward Strategies for LLMs Training on Noisy Data

Haolong Qian · Xianliang Yang · Ling Zhang · Lei Song · Jiang Bian · Chun Yuan

Reinforcement Learning Finetunes Small Subnetworks in Large Language Models

Sagnik Mukherjee · Lifan Yuan · Dilek Hakkani-Tur · Hao Peng

Tight Bounds for Maximum Weight Matroid Independent Set and Matching in the Zero Communication Model

Ilan Doron-Arad

Revisiting Glorot Initialization for Long-Range Linear Recurrences

Noga Bar · Mariia Seleznova · ‪Yotam Alexander‬‏ · Gitta Kutyniok · Raja Giryes

Learning-Augmented Online Bipartite Fractional Matching

XianJun, Davin Choo · Billy Jin · Yongho Shin

Learning-Augmented Algorithms for $k$-median via Online Learning

Anish Hebbar · Rong Ge · Amit Kumar · Debmalya Panigrahi

Unbalanced Optimal Total Variation Transport: A Theoretical Approach to Spatial Resource Allocation Problems

Nhan-Phu Chung · Jinhui Han · Bohan Li · Zehao Li

Reasoning by Superposition: A Theoretical Perspective on Chain of Continuous Thought

Hanlin Zhu · Shibo Hao · Zhiting Hu · Jiantao Jiao · Stuart J Russell · Yuandong Tian

Robust Estimation Under Heterogeneous Corruption Rates

Syomantak Chaudhuri · Jerry Li · Thomas Courtade

STAR-Bets: Sequential TArget-Recalculating Bets for Tighter Confidence Intervals

Vaclav Voracek · Francesco Orabona

Nearly-Linear Time and Massively Parallel Algorithms for $k$-anonymity

Kevin Aydin · Honghao Lin · David Woodruff · Peilin Zhong

Optimal Minimum Width for the Universal Approximation of Continuously Differentiable Functions by Deep Narrow MLPs

Geonho Hwang

One Filters All: A Generalist Filter For State Estimation

Shiqi Liu · Wenhan Cao · Chang Liu · Zeyu He · Tianyi Zhang · Yinuo Wang · Shengbo Li

Pragmatic Heterogeneous Collaborative Perception via Generative Communication Mechanism

Junfei Zhou · Penglin Dai · Quanmin Wei · Bingyi Liu · Xiao Wu · Jianping Wang

Taming Adversarial Constraints in CMDPs

Francesco Emanuele Stradi · Anna Lunghi · Matteo Castiglioni · Alberto Marchesi · Nicola Gatti

Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs

Shulun Chen · Runlong Zhou · Zihan Zhang · Maryam Fazel · Simon Du

Efficient Spectral Control of Partially Observed Linear Dynamical Systems

Anand Brahmbhatt · Gon Buzaglo · Sofiia Druchyna · Elad Hazan

From Contextual Combinatorial Semi-Bandits to Bandit List Classification: Improved Sample Complexity with Sparse Rewards

Liad Erez · Tomer Koren

Does Stochastic Gradient really succeed for bandits?

Dorian Baudry · Emmeran Johnson · Simon Vary · Ciara Pike-Burke · Patrick Rebeschini

SOMBRL: Scalable and Optimistic Model-Based RL

Bhavya · Lenart Treven · Carmelo Sferrazza · Florian Dorfler · Pieter Abbeel · Andreas Krause

Stackelberg Self-Annotation: A Robust Approach to Data-Efficient LLM Alignment

Chu Xu · Zhixin Zhang · Tianyu Jia · Yujie Jin

UMoE: Unifying Attention and FFN with Shared Experts

Yuanhang Yang · Chaozheng Wang · Jing Li

Learn2Mix: Training Neural Networks Using Adaptive Data Integration

Shyam Venkatasubramanian · Vahid Tarokh

Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning

Yiqun Chen · Lingyong Yan · Weiwei Sun · Xinyu Ma · Yi Zhang · Shuaiqiang Wang · Dawei Yin · Yiming Yang · Jiaxin Mao

From Pretraining to Pathology: How Noise Leads to Catastrophic Inheritance in Medical Models

HAO SUN · Zhongyi Han · Hao Chen · Jindong Wang · Xin Gao · Yilong Yin

MODEL SHAPLEY: Find Your Ideal Parameter Player via One Gradient Backpropagation

Chu Xu · Xinke Jiang · Rihong Qiu · Jiaran Gao · Junfeng Zhao

DenoiseRotator: Enhance Pruning Robustness for LLMs via Importance Concentration

Tianteng Gu · Bei Liu · Bo Xiao · Ke Zeng · Jiacheng Liu · Yanmin Qian

Reducing the Probability of Undesirable Outputs in Language Models Using Probabilistic Inference

Stephen Zhao · Aidan Li · Rob Brekelmans · Roger Grosse

Efficient Representativeness-Aware Coreset Selection

Zihao Cheng · Binrui Wu · Zhiwei Li · Yuesen Liao · Su Zhao · Shuai Chen · Yuan Gao · Weizhong Zhang

Efficient Data Selection at Scale via Influence Distillation

Mahdi Nikdan · Vincent Cohen-Addad · Dan Alistarh · Vahab Mirrokni

StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs

Qijun Luo · Mengqi Li · Lei Zhao · Xiao Li

Model Merging in Pre-training of Large Language Models

Yunshui Li · Yiyuan Ma · Shen Yan · Chaoyi Zhang · Jing Liu · Jianqiao Lu · Ziwen Xu · Mengzhao Chen · Minrui Wang · Shiyi Zhan · Jin Ma · Xunhao Lai · Yao Luo · Xingyan Bin · Hongbin Ren · Mingji Han · Wenhao Hao · Bairen Yi · LingJun Liu · Bole Ma · Xiaoying Jia · zhou Xun · liang xiang · Yonghui Wu

Semantic-guided Diverse Decoding for Large Language Model

Weijie Shi · Yue Cui · Yaguang Wu · Jingzhi Fang · Shibo Zhang · Mengze Li · Sirui Han · Jia Zhu · Jiajie Xu · Xiaofang Zhou

Distribution-Aligned Decoding for Efficient LLM Task Adaptation

Senkang Hu · Xudong Han · Jinqi Jiang · Yihang Tao · Zihan Fang · Yong Dai · Sam Kwong · Yuguang Fang

MoleBridge: Synthetic Space Projecting with Discrete Markov Bridges

Rongchao Zhang · Yu Huang · Yongzhi Cao · Hanpin Wang

Self-Adapting Language Models

Adam Zweiger · Jyo Pari · Han Guo · Yoon Kim · Pulkit Agrawal

Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs

ChangHao Li · Yuchen Zhuang · Rushi Qiang · Haotian Sun · Hanjun Dai · Chao Zhang · Bo Dai

Neural Fractional Attention Differential Equations

Qiyu Kang · Wenjun Cui · Xuhao Li · Yuxin Ma · Xueyang Fu · Wee Peng Tay · Yidong Li · Zheng-Jun Zha

EasySpec: Layer-Parallel Speculative Decoding for Efficient Multi-GPU Utilization

Yize Wu · KE GAO · Ling Li · Yanjun Wu

On the Sample Complexity Bounds of Bilevel Reinforcement Learning

Mudit Gaur · Utsav Singh · Amrit Singh Bedi · Raghu Pasupathy · Vaneet Aggarwal

Activated LoRA: Fine-tuned LLMs for Intrinsics

Kristjan Greenewald · Luis Lastras · Thomas Parnell · Vraj Shah · Lucian Popa · Giulio Zizzo · Chulaka Gunasekara · Ambrish Rawat · David Cox

Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers

Kazuki Irie · Morris Yau · Samuel J Gershman

Tensor Product Attention Is All You Need

Yifan Zhang · Yifeng Liu · Huizhuo Yuan · Zhen Qin · Yang Yuan · Quanquan Gu · Andrew Yao

Linear Attention for Efficient Bidirectional Sequence Modeling

Arshia Afzal · Elias Abad Rocamora · Leyla Candogan · Pol Puigdemont · Francesco Tonin · Yongtao Wu · Mahsa Shoaran · Volkan Cevher

From Sequence to Structure: Uncovering Substructure Reasoning in Transformers

Xinnan Dai · Kai Yang · Jay Revolinsky · Kai Guo · Aoran Wang · Bohang Zhang · Jiliang Tang

Learning Cocoercive Conservative Denoisers via Helmholtz Decomposition for Poisson Imaging Inverse Problems

Deliang Wei · Peng Chen · Haobo Xu · Jiale Yao · Fang Li · Tieyong Zeng

Implicit Reward as the Bridge: A Unified View of SFT and DPO Connections

Bo Wang · Qinyuan Cheng · Runyu Peng · Rong Bao · Peiji Li · Qipeng Guo · Linyang Li · Zhiyuan Zeng · Yunhua Zhou · Xipeng Qiu

DataRater: Meta-Learned Dataset Curation

Dan Andrei Calian · Greg Farquhar · Iurii Kemaev · Luisa Zintgraf · Matteo Hessel · Jeremy Shar · Junhyuk Oh · András György · Tom Schaul · Jeff Dean · Hado van Hasselt · David Silver

Decoder-Hybrid-Decoder Architecture for Efficient Reasoning with Long Generation

Liliang Ren · Congcong Chen · Haoran Xu · Young Jin Kim · Adam Atkinson · Zheng Zhan · Jiankai Sun · Baolin Peng · Liyuan Liu · Shuohang Wang · Hao Cheng · Jianfeng Gao · Weizhu Chen · yelong shen

Point4Bit: Post Training 4-bit Quantization for Point Cloud 3D Detection

Jianyu Wang · Yu Wang · Shengjie Zhao · Sifan Zhou

G-Net: A Provably Easy Construction of High-Accuracy Random Binary Neural Networks

Alireza Aghasi · Nicholas F. Marshall · Saeid Pourmand · Wyatt Whiting

Integration Matters for Learning PDEs with Backwards SDEs

Sungje Park · Stephen Tu

Adaptive Inference-Time Scaling via Cyclic Diffusion Search

Gyubin Lee · Bao Truong · Jaesik Yoon · Dongwoo Lee · Minsu Kim · Yoshua Bengio · Sungjin Ahn

Unlocker: Disentangle the Deadlock of Learning between Label-noisy and Long-tailed Data

shu chen · HongJun Xu · Ruichi Zhang · Mengke Li · Yonggang Zhang · Yang Lu · Bo Han · Yiu-ming Cheung · Hanzi Wang

Effective Neural Approximations for Geometric Optimization Problems

Samantha Chen · Oren Ciolli · Anastasios Sidiropoulos · Yusu Wang

Jet-Nemotron: Efficient Language Model with Post Neural Architecture Search

Yuxian Gu · Qinghao Hu · Haocheng Xi · Junyu Chen · Shang Yang · Song Han · Han Cai

Computational Budget Should Be Considered in Data Selection

Weilin Wan · Weizhong Zhang · Cheng Jin

$\texttt{BetaConform}$: Efficient MAP Estimation of LLM Ensemble Judgment Performance with Prior Transfer

Huaizhi Qu · Inyoung Choi · Zhen Tan · Song Wang · Sukwon Yun · Qi Long · Faizan Siddiqui · Kwonjoon Lee · Tianlong Chen

LookWhere? Efficient Visual Recognition by Learning Where to Look and What to See from Self-Supervision

Anthony Fuller · Yousef Yassin · Junfeng Wen · Tarek Ibrahim · Daniel Kyrollos · James Green · Evan Shelhamer

DuSA: Fast and Accurate Dual-Stage Sparse Attention Mechanism Accelerating Both Training and Inference

Chong Wu · Jiawang Cao · Renjie Xu · Zhuoheng Ran · Maolin Che · Wenbo Zhu · Hong Yan

EngiBench: A Framework for Data-Driven Engineering Design Research

Florian Felten · Gabriel Apaza · Gerhard Bräunlich · Cashen Diniz · Xuliang Dong · Arthur Drake · Milad Habibi · Nathaniel Hoffman · Matthew Keeler · Soheyl Massoudi · Francis VanGessel · Mark Fuge

Evaluating Generalization Capabilities of LLM-Based Agents in Mixed-Motive Scenarios Using Concordia

Chandler Smith · Marwa Abdulhai · Manfred Díaz · Marko Tesic · Rakshit Trivedi · Sasha Vezhnevets · Lewis Hammond · Jesse Clifton · Minsuk Chang · Edgar Duenez-Guzman · John Agapiou · Jayd Matyas · Danny Karmon · Beining Zhang · Jim Dilkes · Akash Kundu · Hieu Minh Nguyen · Emanuel Tewolde · Jebish Purbey · Ram Mohan Rao Kadiyala · Siddhant Gupta · Aliaksei Korshuk · Buyantuev Alexander · Ilya Makarov · Gang Zhao · Rolando Fernandez · Zhihan Wang · Caroline Wang · Jiaxun Cui · Lingyun Xiao · Di Shi · Yoonchang Sung · Muhammad Arrasy Rahman · Peter Stone · Yipeng Kang · Hyeonggeun Yun · Ananya Ananya · Taehun Cha · Zhiqiang Wu · Elizaveta Tennant · Olivia Macmillan-Scott · Marta Segura · Diana Riazi · Fuyang Cui · Sriram Ganapathi · Toryn Klassen · Nico Schiavone · Mogtaba Alim · Sheila McIlraith · Manuel Rios · Oswaldo Peña · Carlos Rojas · Manuela Chacon-Chamorro · Rubén Manrique · Luis Felipe Giraldo · Nicanor Quijano · Yiding Wang · Yuxuan Chen · Fangwei Zhong · Mengmeng Wang · Wenming Tu · Zhaowei Zhang · Ziang Chen · Zixia Jia · Xue Feng · Zilong Zheng · Chichen Lin · Weijian Fan · Chenao Liu · Sneheel Sarangi · Ziyan Wang · shuqing shi · Yali Du · Avinaash Anand Kulandaivel · Yang Liu · Wu Ruiyang · Chetan Talele · Sunjia Lu · Gema Parreno · Shamika Dhuri · Bain McHale · Tim Baarslag · Dylan Hadfield-Menell · Natasha Jaques · José Hernández-Orallo · Joel Leibo

Streaming Audio Generation from Discrete Tokens via Streaming Flow Matching

Ha-Yeong Choi · Sang-Hoon Lee

PANTHER: Generative Pretraining Beyond Language for Sequential User Behavior Modeling

Guilin Li · Yun Zhang · Xiuyuan Chen · Chengqi Li · Bo Wang · Linghe Kong · Wenjia Wang · Weiran Huang · Matthias Tan

EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test

Yuhui Li · Fangyun Wei · Chao Zhang · Hongyang Zhang

CCS: Controllable and Constrained Sampling with Diffusion Models via Initial Noise Perturbation

Bowen Song · Zecheng Zhang · Zhaoxu Luo · Jason Hu · Wei Yuan · Jing Jia · Zhengxu Tang · Guanyang Wang · Liyue Shen

Probabilistic Token Alignment for Large Language Model Fusion

Runjia Zeng · James Liang · Cheng Han · Zhiwen Cao · Jiahao Liu · Xiaojun Quan · Yingjie Victor Chen · Lifu Huangg · Tong Geng · Qifan Wang · Dongfang Liu

Transition Matching: Scalable and Flexible Generative Modeling

Neta Shaul · Uriel Singer · Itai Gat · Yaron Lipman

Why Diffusion Models Don’t Memorize: The Role of Implicit Dynamical Regularization in Training

Tony Bonnaire · Raphaël Urfin · Giulio Biroli · Marc Mezard

Video Diffusion Models Excel at Tracking Similar-Looking Objects Without Supervision

Chenshuang Zhang · Kang Zhang · Joon Son Chung · In So Kweon · Junmo Kim · Chengzhi Mao

Schrödinger Bridge Matching for Tree-Structured Costs and Entropic Wasserstein Barycentres

Samuel Howard · Peter Potaptchik · George Deligiannidis

Seeds of Structure: Patch PCA Reveals Universal Compositional Cues in Diffusion Models

Qingsong Wang · Zhengchao Wan · Misha Belkin · Yusu Wang

P-Law: Predicting Quantitative Scaling Law with Entropy Guidance in Large Recommendation Models

Tingjia Shen · Hao Wang · Chuhan Wu · Jin Yao Chin · Wei Guo · Yong Liu · Huifeng Guo · Defu Lian · Ruiming Tang · Enhong Chen

Constrained Discrete Diffusion

Michael Cardei · Jacob K Christopher · Bhavya Kailkhura · Tom Hartvigsen · Ferdinando Fioretto

Fractional Diffusion Bridge Models

Gabriel Nobis · Maximilian Springenberg · Arina Belova · Rembert Daems · Christoph Knochenhauer · Manfred Opper · Tolga Birdal · Wojciech Samek

Generative Modeling of Full-Atom Protein Conformations using Latent Diffusion on Graph Embeddings

Aditya Sengar · Ali Hariri · Daniel Probst · PATRICK BARTH · Pierre Vandergheynst

GRIFFIN: Effective Token Alignment for Faster Speculative Decoding

Shijing Hu · Jingyang Li · Xingyu Xie · Zhihui Lu · Kim-chuan Toh · Pan Zhou

Flow Density Control: Generative Optimization Beyond Entropy-Regularized Fine-Tuning

Riccardo De Santi · Marin Vlastelica · Ya-Ping Hsieh · Zebang Shen · Niao He · Andreas Krause

Point Cloud Synthesis Using Inner Product Transforms

Ernst Röell · Bastian Rieck

On the Closed-Form of Flow Matching: Generalization Does Not Arise from Target Stochasticity

Quentin Bertrand · Anne Gagneux · Mathurin Massias · Rémi Emonet

TRIM: Scalable 3D Gaussian Diffusion Inference with Temporal and Spatial Trimming

Zeyuan Yin · Xiaoming Liu

Why Knowledge Distillation Works in Generative Models: A Minimal Working Explanation

Sungmin Cha · Kyunghyun Cho

Sequence Modeling with Spectral Mean Flows

Jinwoo Kim · Max Beier · Petar Bevanda · Nayun Kim · Seunghoon Hong

Omni-Mol: Multitask Molecular Model for Any-to-any Modalities

Chengxin Hu · Hao Li · Yihe Yuan · Zezheng Song · Chenyang Zhao · Haixin Wang

Physics-Constrained Flow Matching: Sampling Generative Models with Hard Constraints

Utkarsh Utkarsh · Pengfei Cai · Alan Edelman · Rafael Gomez-Bombarelli · Christopher Rackauckas

Diffusion Adaptive Text Embedding for Text-to-Image Diffusion Models

Byeonghu Na · Minsang Park · Gyuwon Sim · Donghyeok Shin · HeeSun Bae · Mina Kang · Se Jung Kwon · Wanmo Kang · Il-chul Moon

Cross-fluctuation phase transitions reveal sampling dynamics in diffusion models

Sai Niranjan Ramachandran · Manish Krishan Lal · Suvrit Sra

Constrained Entropic Unlearning: A Primal-Dual Framework for Large Language Models

Taha Entesari · Arman Hatami · Rinat Khaziev · Anil Ramakrishna · Mahyar Fazlyab

Dense Associative Memory with Epanechnikov Energy

Benjamin Hoover · Zhaoyang Shi · Krishnakumar Balasubramanian · Dmitry Krotov · Parikshit Ram

Direct3D-S2: Gigascale 3D Generation Made Easy with Spatial Sparse Attention

Shuang Wu · Youtian Lin · Feihu Zhang · Yifei Zeng · Yikang Yang · yajie bao · Jiachen Qian · Siyu Zhu · Xun Cao · Philip Torr · Yao Yao

Two-Steps Diffusion Policy for Robotic Manipulation via Genetic Denoising

Mateo Clémente · Leo Brunswic · Yang · Xuan Zhao · Yasser Khalil · Haoyu Lei · Amir Rasouli · Yinchuan Li

Energy Matching: Unifying Flow Matching and Energy-Based Models for Generative Modeling

Michal Balcerak · Tamaz Amiranashvili · Antonio Terpin · Suprosanna Shit · Lea Bogensperger · Sebastian Kaltenbach · Petros Koumoutsakos · Bjoern Menze

Multi-Token Prediction Needs Registers

Anastasios Gerontopoulos · Spyridon Gidaris · Nikos Komodakis

Learned Prefix Caching for Efficient LLM Inference

Dongsheng Yang · Austin Li · Kai Li · Wyatt Lloyd

Normalized Attention Guidance: Universal Negative Guidance for Diffusion Models

Dar-Yen Chen · Hmrishav Bandyopadhyay · Kai Zou · Yi-Zhe Song

Understanding and Mitigating Numerical Sources of Nondeterminism in LLM Inference

Jiayi Yuan · Hao Li · Xinheng Ding · Wenya Xie · Yu-Jhe Li · Wentian Zhao · Kun Wan · Jing Shi · Xia Hu · Zirui Liu

Fast Solvers for Discrete Diffusion Models: Theory and Applications of High-Order Algorithms

Yinuo Ren · Haoxuan Chen · Yuchen Zhu · Wei Guo · Yongxin Chen · Grant Rotskoff · Molei Tao · Lexing Ying

A Token is Worth over 1,000 Tokens: Efficient Knowledge Distillation through Low-Rank Clone

Jitai Hao · Qiang Huang · Hao Liu · Xinyan Xiao · Zhaochun Ren · Jun Yu

Efficient Part-level 3D Object Generation via Dual Volume Packing

Jiaxiang Tang · Ruijie Lu · Max Li · Zekun Hao · Xuan Li · Fangyin Wei · Shuran Song · Gang Zeng · Ming-Yu Liu · Tsung-Yi Lin

Inference-Time Scaling for Flow Models via Stochastic Generation and Rollover Budget Forcing

Jaihoon Kim · Taehoon Yoon · Jisung Hwang · Minhyuk Sung

SpecEM: Training-Free LLM Ensembling via Iterative Drafting, Verification, and Online Feedback

Bo Lv · Nayu Liu · Chen Tang · Xin Liu · Yue Yu · Ping Luo

AlignVLM: Bridging Vision and Language Latent Spaces for Multimodal Document Understanding

Ahmed Masry · Juan Rodriguez · Tianyu Zhang · Suyuchen Wang · Chao Wang · Aarash Feizi · Akshay Kalkunte Suresh · Abhay Puri · Xiangru Jian · Pierre-André Noël · Sathwik Tejaswi Madhusudhan · Marco Pedersoli · Bang Liu · Nicolas Chapados · Yoshua Bengio · Enamul Hoque · Chris Pal · Issam Hadj Laradji · David Vazquez · Perouz Taslakian · Spandana Gella · Sai Rajeswar Mudumba

Active Target Discovery under Uninformative Priors: The Power of Permanent and Transient Memory

Anindya Sarkar · Binglin Ji · Yevgeniy Vorobeychik

MDNS: Masked Diffusion Neural Sampler via Stochastic Optimal Control

Yuchen Zhu · Wei Guo · Jaemoo Choi · Guan-Horng Liu · Yongxin Chen · Molei Tao

Spot the Fake: Large Multimodal Model-Based Synthetic Image Detection with Artifact Explanation

Siwei Wen · junyan ye · Peilin Feng · Hengrui Kang · Zichen Wen · Yize Chen · Jiang Wu · wenjun wu · Conghui He · Weijia Li

Shortcutting Pre-trained Flow Matching Diffusion Models is Almost Free Lunch

Xu Cai · Yang Wu · Qianli Chen · Haoran Wu · Lichuan Xiang · Hongkai Wen

PDPO: Parametric Density Path Optimization

Sebastian Gutierrez Hernandez · Peng Chen · Hao-Min Zhou

Scalable In-context Ranking with Generative Models

Nilesh Gupta · Chong You · Srinadh Bhojanapalli · Sanjiv Kumar · Inderjit Dhillon · Felix Yu

The Temporal Graph of Bitcoin Transactions

Vahid Jalili

Cross-Domain Graph Data Scaling: A Showcase with Diffusion Models

Wenzhuo Tang · Haitao Mao · Danial Dervovic · Ivan Brugere · Saumitra Mishra · Yuying Xie · Jiliang Tang

OPTFM: A Scalable Multi-View Graph Transformer for Hierarchical Pre-Training in Combinatorial Optimization

Hao Yuan · Wenli Ouyang · Changwen Zhang · Congrui Li · Yong Sun

Restricted Global-Aware Graph Filters Bridging GNNs and Transformer for Node Classification

Jingyuan Zhang · Xin Wang · Lei Yu · Zhirong Huang · Li Yang · Fengjun Zhang

Understanding and Enhancing Message Passing on Heterophilic Graphs via Compatibility Matrix

Zhuonan Zheng · Yuanchen Bei · Zhiyao Zhou · Sheng Zhou · Yao Ma · Ming Gu · HONGJIA XU · Jiawei Chen · Jiajun Bu

The Underappreciated Power of Vision Models for Graph Structural Understanding

Xinjian Zhao · Wei Pang · Zhongkai Xue · Xiangru Jian · Lei Zhang · Yaoyao Xu · Xiaozhuang Song · Shu Wu · Tianshu Yu

HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations

Shuaicheng Zhang · Haohui Wang · Junhong Lin · Xiaojie Guo · Yada Zhu · Si Zhang · Dongqi Fu · Dawei Zhou

SONAR: Long-Range Graph Propagation Through Information Waves

Alessandro Trenta · Alessio Gravina · Davide Bacciu

Making Classic GNNs Strong Baselines Across Varying Homophily: A Smoothness–Generalization Perspective

Ming Gu · Zhuonan Zheng · Sheng Zhou · Meihan Liu · Jiawei Chen · Qiaoyu Tan · Liangcheng Li · Jiajun Bu

Towards Multiscale Graph-based Protein Learning with Geometric Secondary Structural Motifs

Shih-Hsin Wang · Yuhao Huang · Taos Transue · Justin Baker · Jonathan Forstater · Thomas Strohmer · Bao Wang

Pool Me Wisely: On the Effect of Pooling in Transformer-Based Models

Sofiane Ennadir · Levente Zólyomi · Oleg Smirnov · Tianze Wang · John Pertoft · Filip Cornell · Lele Cao

A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers

Will Merrill · Ashish Sabharwal

Visual Instruction Bottleneck Tuning

Changdae Oh · Jiatong Li · Shawn Im · Sharon Li

Auditing Meta-Cognitive Hallucinations in Reasoning Large Language Models

Haolang Lu · Yilian Liu · Jingxin Xu · Guoshun Nan · Yuanlong Yu · Zhican Chen · Kun Wang

Learning with Calibration: Exploring Test-Time Computing of Spatio-Temporal Forecasting

Wei Chen · Yuxuan Liang

CIDD: Collaborative Intelligence for Structure-Based Drug Design Empowered by LLMs

Bowen Gao · Yanwen Huang · Yiqiao Liu · Wenxuan Xie · Bowei He · Haichuan Tan · Wei-Ying Ma · Ya-Qin Zhang · Yanyan Lan

Double Descent Meets Out-of-Distribution Detection: Theoretical Insights and Empirical Analysis on the Role of Model Complexity

Mouïn Ben Ammar · David Brellmann · Arturo Mendoza · Antoine Manzanera · Gianni Franchi

Adversary Aware Optimization for Robust Defense

Daniel Wesego · Pedram Rooshenas

Clip-and-Verify: Linear Constraint-Driven Domain Clipping for Accelerating Neural Network Verification

Duo Zhou · Jorge Chavez · Hesun Chen · Grani A. Hanasusanto · Huan Zhang

Asymmetric Duos: Sidekicks Improve Uncertainty

Tim G. Zhou · Evan Shelhamer · Geoff Pleiss

Adjusting Initial Noise to Mitigate Memorization in Text-to-Image Diffusion Models

Hyeonggeun Han · Sehwan Kim · Hyungjun Joo · Sangwoo Hong · Jungwoo Lee

Path-Enhanced Contrastive Learning for Recommendation

Haoran Sun · Fei Xiong · Yuanzhe Hu · Liang Wang

SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs

Ruyue Liu · Rong Yin · Xiangzhen Bo · Xiaoshuai Hao · Yong Liu · Jinwen Zhong · Can Ma · Weiping Wang

DyG-Mamba: Continuous State Space Modeling on Dynamic Graphs

Dongyuan Li · Shiyin Tan · Ying Zhang · Ming Jin · Shirui Pan · Manabu Okumura · Renhe Jiang

SALoM: Structure Aware Temporal Graph Networks with Long-Short Memory Updater

Hanwen Liu · Longjiao Zhang · Rui Wang · Tongya Zheng · Sai Wu · Chang Yao · Mingli Song

Probing Equivariance and Symmetry Breaking in Convolutional Networks

Sharvaree Vadgama · Mohammad Islam · Domas Buracas · Christian A Shewmake · Artem Moskalev · Erik Bekkers

Taxonomy of reduction matrices for Graph Coarsening

Antonin Joly · Nicolas Keriven · Aline Roumy

Geometry-Aware Edge Pooling for Graph Neural Networks

Katharina Limbeck · Lydia Mezrag · Guy Wolf · Bastian Rieck

Training Robust Graph Neural Networks by Modeling Noise Dependencies

Yeonjun In · Kanghoon Yoon · Sukwon Yun · Kibum Kim · Sungchul Kim · Chanyoung Park

Permutation Equivariant Neural Controlled Differential Equations for Dynamic Graph Representation Learning

Torben Berndt · Benjamin Walker · Tiexin Qin · Jan Stühmer · Andrey Kormilitzin

LOPT: Learning Optimal Pigovian Tax in Sequential Social Dilemmas

Yun Hua · Shang Gao · Wenhao Li · Haosheng Chen · Bo Jin · Xiangfeng Wang · Jun Luo · Hongyuan Zha

When Do Transformers Outperform Feedforward and Recurrent Networks? A Statistical Perspective

Alireza Mousavi-Hosseini · Clayton Sanford · Denny Wu · Murat Erdogdu

How Classifier Features Transfer to Downstream: An Asymptotic Analysis in a Two-Layer Model

HEE BIN YOO · Sungyoon Lee · Cheongjae Jang · Dong-Sig Han · Jaein Kim · Seunghyeon Lim · Byoung-Tak Zhang

Test Time Scaling for Neural Processes

Hyungi Lee · Moonseok Choi · Hyunsu Kim · Kyunghyun Cho · Rajesh Ranganath · Juho Lee

Token Embeddings Violate the Manifold Hypothesis

Michael Robinson · Sourya Dey · Tony Chiang

Physics of Language Models: Part 4.1, Architecture Design and the Magic of Canon Layers

Zeyuan Allen-Zhu

A Statistical Theory of Contrastive Learning via Approximate Sufficient Statistics

Licong Lin · Song Mei

Large Stepsizes Accelerate Gradient Descent for Regularized Logistic Regression

Jingfeng Wu · Pierre Marion · Peter Bartlett

Escaping Collapse: The Strength of Weak Data for Large Language Model Training

Kareem Amin · Sara Babakniya · Alex Bie · Weiwei Kong · Umar Syed · Sergei Vassilvitskii

SWE-bench Goes Live!

Linghao Zhang · Shilin He · Chaoyun Zhang · Yu Kang · Bowen Li · Chengxing Xie · Junhao Wang · Maoquan Wang · Yufan Huang · Shengyu Fu · Elsie Nallipogu · Qingwei Lin · Yingnong Dang · Saravan Rajmohan · Dongmei Zhang

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling

Hao Chen · Guanxi Lu · Yasuyuki Okoshi · Zhiwen Mo · Masato Motomura · Hongxiang Fan

Results of the Big ANN: NeurIPS’23 competition

Harsha Vardhan simhadri · Martin Aumüller · Matthijs Douze · Dmitry Baranchuk · Amir Ingber · Edo Liberty · George Williams · Ben Landrum · Magdalen Manohar · Mazin Karjikar · Laxman Dhulipala · Meng Chen · Yue Chen · Rui Ma · Kai Zhang · Yuzheng Cai · Jiayang Shi · Weiguo Zheng · Yizhuo Chen · Jie Yin · Ben Huang

The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models

Ke Ji · Jiahao Xu · Tian Liang · Qiuzhi Liu · Zhiwei He · Xiaoyuan Liu · Xingyu Chen · Junying Chen · Benyou Wang · Zhaopeng Tu · Haitao Mi · Dong Yu

Block-Biased Mamba for Long-Range Sequence Processing

Annan Yu · N. Benjamin Erichson

Federated Continual Learning via Orchestrating Multi-Scale Expertise

Xiaoyang Yi · Yang Liu · Binhan Yang · Jian Zhang

QFFT, Question-Free Fine-Tuning for Adaptive Reasoning

Wanlong Liu · Junxiao Xu · Fei Yu · Yukang Lin · Ke Ji · Wenyu Chen · Lifeng Shang · Yasheng Wang · Yan Xu · Benyou Wang

Can LLMs Reason Over Non-Text Modalities in a Training-Free Manner? A Case Study with In-Context Representation Learning

Tianle Zhang · Wanlong Fang · Jonathan Woo · Paridhi Latawa · Deepak Subramanian · Alvin Chan

Permissioned LLMs: Enforcing Access Control in Large Language Models

Bargav Jayaraman · Virendra Marathe · Hamid Mozaffari · William Shen · Krishnaram Kenthapadi

RL Tango: Reinforcing Generator and Verifier Together for Language Reasoning

Kaiwen Zha · Zhengqi Gao · Maohao Shen · Zhang-Wei Hong · Duane Boning · Dina Katabi

Geometry of Decision Making in Language Models

Abhinav Joshi · Divyanshu Bhatt · Ashutosh Modi

Multi-Agent Collaboration via Evolving Orchestration

Yufan Dang · Chen Qian · Xueheng Luo · Jingru Fan · Zihao Xie · Ruijie Shi · Weize Chen · Cheng Yang · Xiaoyin Che · Ye Tian · Xuantang Xiong · Lei Han · Zhiyuan Liu · Maosong Sun

Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems

Hao Liang · shuqing shi · Yudi Zhang · Biwei Huang · Yali Du

Meta-World+: An Improved, Standardized, RL Benchmark

Reginald McLean · Evangelos Chatzaroulas · Luc McCutcheon · Frank Röder · Tianhe Yu · Zhanpeng He · K.R. Zentner · Ryan Julian · J Terry · Isaac Woungang · Nariman Farsad · Pablo Samuel Castro

NS-Gym: A Comprehensive and Open-Source Simulation Framework for Non-Stationary Markov Decision Processes

Nathaniel S. Keplinger · Baiting Luo · Yunuo Zhang · Kyle H Wray · Aron Laszka · Abhishek Dubey · Ayan Mukhopadhyay

Reasoning as an Adaptive Defense for Safety

Taeyoun Kim · Fahim Tajwar · Aditi Raghunathan · Aviral Kumar

Efficient Policy Optimization in Robust Constrained MDPs with Iteration Complexity Guarantees

Sourav Ganguly · Kishan Panaganti · Arnob Ghosh · Adam Wierman

Training Language Models to Generate Quality Code with Program Analysis Feedback

Feng Yao · Zilong Wang · Liyuan Liu · Junxia Cui · Li Zhong · Xiaohan Fu · Haohui Mai · Viswanathan Krishnan · Jianfeng Gao · Jingbo Shang

Strategyproof Reinforcement Learning from Human Feedback

Thomas Kleine Buening · Jiarui Gan · Debmalya Mandal · Marta Kwiatkowska

DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization

Jiacai Liu · Chaojie Wang · Chris Liu · Liang Zeng · Rui Yan · Yiwen Sun · Yang Liu

What Makes a Reward Model a Good Teacher? An Optimization Perspective

Noam Razin · Zixuan Wang · Hubert Strauss · Stanley Wei · Jason Lee · Sanjeev Arora

In-Context Learning of Stochastic Differential Equations with Foundation Inference Models

Patrick Seifner · Kostadin Cvejoski · David Berghaus · César Ali Ojeda Marin · Ramsés J. Sánchez

Vision Transformers Don't Need Trained Registers

Nicholas Jiang · Amil Dravid · Alexei Efros · Yossi Gandelsman

Balanced Active Inference

Boyu Chen · Zhixiang Zhou · Liuhua Peng · Zhonglei Wang

Remarkable Robustness of LLMs: Stages of Inference?

Vedang Lad · Jin Hwa Lee · Wes Gurnee · Max Tegmark

The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training

Weize Chen · Jiarui yuan · Jin Tailin · Ning Ding · Huimin Chen · Zhiyuan Liu · Maosong Sun

Reward Reasoning Models

Jiaxin Guo · Zewen Chi · Li Dong · Qingxiu Dong · Xun Wu · Shaohan Huang · Furu Wei

Exploiting Vocabulary Frequency Imbalance in Language Model Pre-training

Woojin Chung · Jeonghoon Kim

SATURN: SAT-based Reinforcement Learning to Unleash LLMs Reasoning

Huanyu Liu · Jia Li · Hao Zhu · Kechi Zhang · Yihong Dong · Ge Li

Monotone and Separable Set Functions: Characterizations and Neural Models

Soutrik Sarangi · Yonatan Sverdlov · Nadav Dym · Abir De

How to Train Your LLM Web Agent: A Statistical Diagnosis

Dheeraj Vattikonda · Santhoshi Ravichandran · Emiliano Penaloza · Hadi Nekoei · Thibault de Chezelles · Megh Thakkar · Nicolas Gontier · Miguel Muñoz-Mármol · Sahar Omidi Shayegan · Stefania Raimondo · Steve (Xue) Liu · Alexandre Drouin · Alexandre Piche · Alexandre Lacoste · Massimo Caccia

Constructing an Optimal Behavior Basis for the Option Keyboard

Lucas N. Alegre · Ana Bazzan · Andre Barreto · Bruno Silva

Communication-Efficient Diffusion Denoising Parallelization via Reuse-then-Predict Mechanism

Kunyun Wang · Bohan Li · Kai Yu · Minyi Guo · Jieru Zhao

HybridNorm: Towards Stable and Efficient Transformer Training via Hybrid Normalization

Zhijian Zhuo · Yutao Zeng · Ya Wang · Sijun Zhang · Xiaoqing Li · Jian Yang · zhou Xun · Jinwen Ma

Contextual Thompson Sampling via Generation of Missing Data

Kelly W Zhang · Tianhui Cai · Hongseok Namkoong · Daniel Russo

Imitation Learning with Temporal Logic Constraints

Zining Fan · He Zhu

Learning from Demonstrations via Capability-Aware Goal Sampling

Yuanlin Duan · Yuning Wang · Wenjie Qiu · He Zhu

SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes

Xuyuan Xiong · Pedro Chumpitaz-Flores · Kaixun Hua · Cheng Hua

Conformal Prediction Beyond the Horizon: Distribution-Free Inference for Policy Evaluation

Feichen Gan · Lu Youcun · Yingying Zhang · Yukun Liu

Silencer: From Discovery to Mitigation of Self-Bias in LLM-as-Benchmark-Generator

Peiwen Yuan · Yiwei Li · Shaoxiong Feng · Xinglin Wang · Yueqi Zhang · Jiayi Shi · Chuyi Tan · Boyuan Pan · Yao Hu · Prof. Kan

STaRFormer: Semi-Supervised Task-Informed Representation Learning via Dynamic Attention-Based Regional Masking for Sequential Data

Maximilian Forstenhäusler · Daniel Külzer · Christos Anagnostopoulos · Shameem Puthiya Parambath · Natascha Weber

msf-CNN: Patch-based Multi-Stage Fusion with Convolutional Neural Networks for TinyML

Zhaolan Huang · Emmanuel Baccelli

Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models

Sohyun An · Ruochen Wang · Tianyi Zhou · Cho-Jui Hsieh

HiFC: High-efficiency Flash-based KV Cache Swapping for Scaling LLM Inference

Inho Jeong · Sunghyeon Woo · Sol Namkung · Dongsuk Jeon

Transforming Generic Coder LLMs to Effective Binary Code Embedding Models for Similarity Detection

Litao Li · Leo Song · Steven Ding · Benjamin C. M. Fung · Philippe Charland

What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers

Pulkit Gopalani · Wei Hu

Set-LLM: A Permutation-Invariant LLM

Beni Egressy · Jan Stühmer

Shapley-Coop: Credit Assignment for Emergent Cooperation in Self-Interested LLM Agents

Yun Hua · Haosheng Chen · Shiqin Wang · Wenhao Li · Xiangfeng Wang · Jun Luo

A Pre-training Framework for Relational Data with Information-theoretic Principles

Quang Truong · Zhikai Chen · Mingxuan Ju · Tong Zhao · Neil Shah · Jiliang Tang

Revisiting Bi-Linear State Transitions in Recurrent Neural Networks

Reza Ebrahimi · Roland Memisevic

DNA-DetectLLM: Unveiling AI-Generated Text via a DNA-Inspired Mutation-Repair Paradigm

Xiaowei Zhu · Yubing Ren · Fang Fang · Qingfeng Tan · Shi Wang · Yanan Cao

Increasing the Utility of Synthetic Images through Chamfer Guidance

Nicola Dall'Asen · Xiaofeng Zhang · Reyhane Askari Hemmat · Melissa Hall · Jakob Verbeek · Adriana Romero-Soriano · Michal Drozdzal

ScaleDiff: Higher-Resolution Image Synthesis via Efficient and Model-Agnostic Diffusion

Sungho Koh · SeungJu Cha · Hyunwoo Oh · Kwanyoung Lee · Dong-Jin Kim

GeoRemover: Removing Objects and Their Causal Visual Artifacts

Zixin Zhu · Haoxiang Li · Xuelu Feng · He Wu · Chunming Qiao · Junsong Yuan

Vision Foundation Models as Effective Visual Tokenizers for Autoregressive Generation

Zheng Anlin · Xin Wen · Xuanyang Zhang · Chuofan Ma · Tiancai Wang · Gang Yu · Xiangyu Zhang · Xiaojuan Qi

AccuQuant: Simulating Multiple Denoising Steps for Quantizing Diffusion Models

Seunghoon Lee · Jeongwoo Choi · Byunggwan Son · JaeHyeon Moon · Jeimin Jeon · Bumsub Ham

Rectified CFG++ for Flow Based Models

Shreshth Saini · Shashank Gupta · Alan Bovik

Blockwise Flow Matching: Improving Flow Matching Models For Efficient High-Quality Generation

Dogyun Park · Taehoon Lee · Minseok Joo · Hyunwoo J. Kim

MindJourney: Test-Time Scaling with World Models for Spatial Reasoning

Yuncong Yang · Jiageng Liu · Zheyuan Zhang · Siyuan Zhou · Reuben Tan · Jianwei Yang · Yilun Du · Chuang Gan

MagCache: Fast Video Generation with Magnitude-Aware Cache

Zehong Ma · Longhui Wei · Feng Wang · Shiliang Zhang · Qi Tian

FerretNet: Efficient Synthetic Image Detection via Local Pixel Dependencies

Shuqiao Liang · Jian Liu · Chen Renzhang · Quanlong Guan

Pro3D-Editor: A Progressive Framework for Consistent and Precise 3D Editing

Yang Zheng · Mengqi Huang · Nan Chen · Zhendong Mao

SCoT: Unifying Consistency Models and Rectified Flows via Straight-Consistent Trajectories

zhangkai wu · Xuhui Fan · Hongyu Wu · Longbing Cao

Enhancing Consistency of Flow-Based Image Editing through Kalman Control

Haozhe Chi · Zhicheng Sun · Yang Jin · Yi Ma · Jing Wang · Yadong Mu

RelationAdapter: Learning and Transferring Visual Relation with Diffusion Transformers

Yan Gong · Yiren Song · Yicheng Li · Chenglin Li · Yin Zhang

GPSToken: Gaussian Parameterized Spatially-adaptive Tokenization for Image Representation and Generation

Zhengqiang ZHANG · Rongyuan Wu · Lingchen Sun · Lei Zhang

PhysCtrl: Generative Physics for Controllable and Physics-Grounded Video Generation

Chen Wang · Chuhao Chen · Yiming Huang · Zhiyang Dou · Yuan Liu · Jiatao Gu · Lingjie Liu

PocketSR: The Super-Resolution Expert in Your Pocket Mobiles

Haoze Sun · Linfeng Jiang · Fan Li · Renjing Pei · Zhixin Wang · Yong Guo · Jiaqi Xu · Haoyu Chen · Jin Han · Fenglong Song · Yujiu Yang · Wenbo Li

ALTER: All-in-One Layer Pruning and Temporal Expert Routing for Efficient Diffusion Generation

Xiaomeng Yang · LEI LU · Qihui Fan · Changdi Yang · Juyi Lin · Yanzhi Wang · Xuan Zhang · Shangqian Gao

UVE: Are MLLMs Unified Evaluators for AI-Generated Videos?

Yuanxin Liu · Rui Zhu · Shuhuai Ren · Jiacong Wang · Haoyuan Guo · Xu Sun · Lu Jiang

Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models

Chenrui Cao · Liangcheng Song · Zenan Li · Xinyi Le · Xian Zhang · HUI XUE · Fan Yang

Hierarchical Koopman Diffusion: Fast Generation with Interpretable Diffusion Trajectory

Hanru Bai · Weiyang Ding · Difan Zou

Whole-Body Conditioned Egocentric Video Prediction

Yutong Bai · Danny Tran · Amir Bar · Yann LeCun · Trevor Darrell · Jitendra Malik

DenseDPO: Fine-Grained Temporal Preference Optimization for Video Diffusion Models

Ziyi Wu · Anil Kag · Ivan Skorokhodov · Willi Menapace · Ashkan Mirzaei · Igor Gilitschenski · Sergey Tulyakov · Aliaksandr Siarohin

Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens

Bohan Wang · Mingze Zhou · Zhongqi Yue · wang lin · Kaihang Pan · Liyu Jia · Wentao Hu · Wei Zhao · Hanwang Zhang

WorldMem: Long-term Consistent World Simulation with Memory

Zeqi Xiao · Yushi LAN · Yifan Zhou · Wenqi Ouyang · Shuai Yang · Yanhong Zeng · Xingang Pan

ComfyMind: Toward General-Purpose Generation via Tree-Based Planning and Reactive Feedback

Litao Guo · Xinli Xu · Luozhou Wang · Jiantao Lin · Jinsong Zhou · Zixin Zhang · Bolan Su · Yingcong Chen

Preventing Shortcuts in Adapter Training via Providing the Shortcuts

Anujraaj Goyal · Guocheng Qian · Huseyin Coskun · Aarush Gupta · Himmy Tam · Daniil Ostashev · Ju Hu · Dhritiman Sagar · Sergey Tulyakov · Kfir Aberman · Kuan-Chieh Wang

PhysDiff-VTON: Cross-Domain Physics Modeling and Trajectory Optimization for Virtual Try-On

Shibin Mei · Bingbing Ni

RODS: Robust Optimization Inspired Diffusion Sampling for Detecting and Reducing Hallucination in Generative Models

Yiqi Tian · Pengfei Jin · Mingze Yuan · Na Li · Bo Zeng · Quanzheng Li

Cameras as Relative Positional Encoding

Ruilong Li · Brent Yi · Junchen Liu · Hang Gao · Yi Ma · Angjoo Kanazawa

Virtual Fitting Room: Generating Arbitrarily Long Videos of Virtual Try-On from a Single Image

Junkun Chen · Aayush Bansal · Minh Vo · Yu-Xiong Wang

ShoeFit: A New Dataset and Dual-image-stream DiT Framework for Virtual Footwear Try-On

Yuhan Li · Zhiyu Jin · Yifan Tong · Wenxiang Shang · Benlei Cui · Xuanhong Chen · Ran Lin · Bingbing Ni

FSI-Edit: Frequency and Stochasticity Injection for Flexible Diffusion-Based Image Editing

Kaixiang Yang · Xin Li · Yuxi Li · Qiang Li · Zhiwei Wang

VideoREPA: Learning Physics for Video Generation through Relational Alignment with Foundation Models

Xiangdong Zhang · Jiaqi Liao · Shaofeng Zhang · Fanqing Meng · Xiangpeng Wan · Junchi Yan · Yu Cheng

Improved Training Technique for Shortcut Models

Anh Nguyen · Viet Nguyen · Duc Vu · Trung Dao · Chi Tran · Toan Tran · Anh Tran

PolyVivid: Vivid Multi-Subject Video Generation with Cross-Modal Interaction and Enhancement

Teng Hu · Zhentao Yu · Zhengguang Zhou · Jiangning Zhang · Yuan Zhou · Qinglin Lu · Ran Yi

Foresight: Adaptive Layer Reuse for Accelerated and High-Quality Text-to-Video Generation

Muhammad Adnan · Nithesh Kurella · Akhil Arunkumar · Prashant Nair

TTS-VAR: A Test-Time Scaling Framework for Visual Auto-Regressive Generation

Zhekai Chen · Ruihang Chu · Yukang Chen · Shiwei Zhang · Yujie Wei · Yingya Zhang · Xihui Liu

Self-Supervised Selective-Guided Diffusion Model for Old-Photo Face Restoration

Wenjie Li · Xiangyi Wang · Heng Guo · Guangwei Gao · Zhanyu Ma

Latent Harmony: Synergistic Unified UHD Image Restoration via Latent Space Regularization and Controllable Refinement

Yidi Liu · Xueyang Fu · Jie Huang · Jie Xiao · Dong Li · Wenlong Zhang · LEI BAI · Zheng-Jun Zha

Puppeteer: Rig and Animate Your 3D Models

Chaoyue Song · Xiu Li · Fan Yang · Zhongcong XU · Jiacheng Wei · Fayao Liu · Jiashi Feng · Guosheng Lin · Jianfeng Zhang

HoliGS: Holistic Gaussian Splatting for Embodied View Synthesis

Xiaoyuan Wang · Yizhou Zhao · Botao Ye · Shan Xiaojun · Weijie Lyu · Lu Qi · Kelvin Chan · Yinxiao Li · Ming-Hsuan Yang

MPMAvatar: Learning 3D Gaussian Avatars with Accurate and Robust Physics-Based Dynamics

Changmin Lee · Jihyun Lee · Tae-Kyun Kim

APML: Adaptive Probabilistic Matching Loss for Robust 3D Point Cloud Reconstruction

Sasan Sharifipour · Constantino Álvarez Casado · Mohammad Sabokrou · Miguel Bordallo Lopez

CLiFT: Compressive Light-Field Tokens for Compute Efficient and Adaptive Neural Rendering

Zhengqing Wang · Yuefan Wu · Jiacheng Chen · Fuyang Zhang · Yasutaka Furukawa

EAG3R: Event-Augmented 3D Geometry Estimation for Dynamic and Extreme-Lighting Scenes

Xiaoshan Wu · Yifei Yu · Xiaoyang Lyu · Yihua Huang · Bo Wang · Baoheng Zhang · Zhongrui Wang · Xiaojuan Qi

Are Pixel-Wise Metrics Reliable for Computerized Tomography Reconstruction?

Tianyu Lin · Xinran Li · Chuntung Zhuang · Qi Chen · Yuanhao Cai · Kai Ding · Alan Yuille · Zongwei Zhou

ML4CO-Bench-101: Benchmark Machine Learning for Classic Combinatorial Problems on Graphs

Jiale Ma · Wenzheng Pan · Yang Li · Junchi Yan

BevSplat: Resolving Height Ambiguity via Feature-Based Gaussian Primitives for Weakly-Supervised Cross-View Localization

Qiwei Wang · Shaoxun Wu · Yujiao Shi

GeoSVR: Taming Sparse Voxels for Geometrically Accurate Surface Reconstruction

Jiahe Li · Jiawei Zhang · Youmin Zhang · Xiao Bai · Jin Zheng · Xiaohan Yu · Lin Gu

InstaInpaint: Instant 3D-Scene Inpainting with Masked Large Reconstruction Model

Junqi You · Chieh Lin · Weijie Lyu · Zhengbo Zhang · Ming-Hsuan Yang

MIND: Material Interface Generation from UDFs for Non-Manifold Surface Reconstruction

Xuhui Chen · Fei Hou · Wencheng Wang · Hong Qin · Ying He

Anti-Aliased 2D Gaussian Splatting

Mae Younes · Adnane Boukhayma

Rooms from Motion: Un-posed Indoor 3D Object Detection as Localization and Mapping

Justin Lazarow · Kai Kang · Afshin Dehghan

E-MoFlow: Learning Egomotion and Optical Flow from Event Data via Implicit Regularization

Wenpu Li · Bangyan Liao · Yi Zhou · QiXu · Pian Wan · Peidong Liu

Seeing in the Dark: Benchmarking Egocentric 3D Vision with the Oxford Day-and-Night Dataset

Zirui Wang · Wenjing Bian · Xinghui Li · Yifu Tao · Jianeng Wang · Maurice Fallon · Victor Prisacariu

EPA: Boosting Event-based Video Frame Interpolation with Perceptually Aligned Learning

Yuhan Liu · LingHui Fu · Zhen Yang · Hao Chen · Youfu Li · Yongjian Deng

SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation

Zhenyuan Qin · Xincheng Shuai · Henghui Ding

VFRTok: Variable Frame Rates Video Tokenizer with Duration-Proportional Information Assumption

Tianxiong Zhong · Xingye Tian · Boyuan Jiang · Xuebo Wang · Xin Tao · Pengfei Wan · Zhiwei Zhang

RoboScape: Physics-informed Embodied World Model

Yu Shang · Xin Zhang · Yinzhou Tang · Lei Jin · Chen Gao · Wei Wu · Yong Li

DGS-LRM: Real-Time Deformable 3D Gaussian Reconstruction From Monocular Videos

Chieh Lin · Zhaoyang Lv · Songyin Wu · Zhen Xu · Thu Nguyen-Phuoc · Hung-Yu Tseng · Julian Straub · Numair Khan · Lei Xiao · Ming-Hsuan Yang · Yuheng Ren · Richard Newcombe · Zhao Dong · Zhengqin Li

VA-GS: Enhancing the Geometric Representation of Gaussian Splatting via View Alignment

Qing Li · Huifang Feng · Xun Gong · Yu-Shen Liu

MS-GS: Multi-Appearance Sparse-View 3D Gaussian Splatting in the Wild

Deming Li · Kaiwen Jiang · Yutao Tang · Ravi Ramamoorthi · Rama Chellappa · Cheng Peng

PhysX-3D: Physical-Grounded 3D Asset Generation

Ziang Cao · Zhaoxi Chen · Liang Pan · Ziwei Liu

VASA-3D: Lifelike Audio-Driven Gaussian Head Avatars from a Single Image

Sicheng Xu · Guojun Chen · Jiaolong Yang · Yizhong Zhang · Yu Deng · Stephen Lin · Baining Guo

Robust Neural Rendering in the Wild with Asymmetric Dual 3D Gaussian Splatting

CHENGQI LI · Zhihao Shi · Yangdi Lu · Wenbo He · Xiangyu Xu

CLIPGaussian: Universal and Multimodal Style Transfer Based on Gaussian Splatting

Kornel Howil · Joanna Waczynska · Piotr Borycki · Tadeusz Dziarmaga · Marcin Mazur · Przemysław Spurek

Neural Atlas Graphs for Dynamic Scene Decomposition and Editing

Jan Philipp Schneider · Pratik S. Bisht · Ilya Chugunov · Andreas Kolb · Michael Moeller · Felix Heide

D$^2$GS: Dense Depth Regularization for LiDAR-free Urban Scene Reconstruction

Kejing Xia · Jidong Jia · Ke Jin · Yucai Bai · Li Sun · Dacheng Tao · Youjian Zhang

4DGT: Learning a 4D Gaussian Transformer Using Real-World Monocular Videos

Zhen Xu · Zhengqin Li · Zhao Dong · Xiaowei Zhou · Richard Newcombe · Zhaoyang Lv

MM-OPERA: Benchmarking Open-ended Association Reasoning for Large Vision-Language Models

Zimeng Huang · Jinxin Ke · Xiaoxuan Fan · Yufeng Yang · Yang Liu · Liu Zhonghan · Zedi Wang · Junteng Dai · Haoyi Jiang · Yuyu Zhou · Keze Wang · Ziliang Chen

SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models

Xianda Guo · Ruijun Zhang · Yiqun Duan · Yuhang He · Dujun Nie · Wenke Huang · Chenming Zhang · Shuai Liu · Hao Zhao · Long Chen

Collaborating Vision, Depth, and Thermal Signals for Multi-Modal Tracking: Dataset and Algorithm

Xue-Feng Zhu · Tianyang Xu · Yifan Pan · Jinjie Gu · Xi Li · Jiwen Lu · Xiaojun Wu · Josef Kittler

MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations

Vardhan Dongre · Chi Gui · Shubham Garg · Hooshang Nayyeri · Gokhan Tur · Dilek Hakkani-Tur · Vikram Adve

MimeQA: Towards Socially-Intelligent Nonverbal Foundation Models

Hengzhi Li · Megan Tjandrasuwita · Yi R. (May) Fung · Armando Solar-Lezama · Paul Liang

CineTechBench: A Benchmark for Cinematographic Technique Understanding and Generation

Xinran Wang · Songyu Xu · Shan Xiangxuan · Yuxuan Zhang · Muxi Diao · Xueyan Duan · Yanhua huang · Kongming Liang · Zhanyu Ma

STSBench: A Spatio-temporal Scenario Benchmark for Multi-modal Large Language Models in Autonomous Driving

Christian Fruhwirth-Reisinger · Dušan Malić · Wei Lin · David Schinagl · Samuel Schulter · Horst Possegger

Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents

Vijay Veerabadran · Fanyi Xiao · Nitin Kamra · Pedro Matias · Joy Chen · Caley Drooff · Brett Roads · Riley J Williams · Ethan Henderson · Xuanyi Zhao · Kevin Carlberg · Joseph Tighe · Karl Ridgeway

PASS: Path-selective State Space Model for Event-based Recognition

Jiazhou Zhou · Kanghao Chen · Lei Zhang · Lin Wang

Vgent: Graph-based Retrieval-Reasoning-Augmented Generation For Long Video Understanding

Xiaoqian Shen · Wenxuan Zhang · Jun Chen · Mohamed Elhoseiny

LiveStar: Live Streaming Assistant for Real-World Online Video Understanding

Zhenyu Yang · Kairui Zhang · Yuhang Hu · Bing Wang · Shengsheng Qian · Bin Wen · Fan Yang · Tingting Gao · Weiming Dong · Changsheng Xu

CroPe: Cross-Modal Semantic Compensation Adaptation for All Adverse Scene Understanding

Qin Xu · Qihang Wu · Lu Hongtao · Xiaoxia Cheng · Bo Jiang

Enhancing Text-to-Image Diffusion Transformer via Split-Text Conditioning

Yu Zhang · Jialei Zhou · Xinchen Li · Qi Zhang · Zhongwei Wan · Duoqian Miao · Changwei Wang · Longbing Cao

Improve Temporal Reasoning in Multimodal Large Language Models via Video Contrastive Decoding

Daiqing Qi · Dongliang Guo · Hanzhang Yuan · Handong Zhao · Mengxuan Hu · Lehan Yang · Sheng Li

ShotBench: Expert-Level Cinematic Understanding in Vision-Language Models

Hongbo Liu · Jingwen He · Yi Jin · Dian Zheng · Yuhao Dong · Fan Zhang · Ziqi Huang · Yinan He · Weichao Chen · Yu Qiao · Wanli Ouyang · Shengjie Zhao · Ziwei Liu

FlexSelect: Flexible Token Selection for Efficient Long Video Understanding

yunzhu zhang · Yu Lu · Tianyi Wang · Fengyun Rao · Yi Yang · Linchao Zhu

CAPability: A Comprehensive Visual Caption Benchmark for Evaluating Both Correctness and Thoroughness

Zhihang Liu · Chen-Wei Xie · Bin Wen · Feiwu Yu · JixuanChen · Pandeng Li · Boqiang Zhang · Nianzu Yang · YingluLi · Zuan Gao · Yun Zheng · Hongtao Xie

ChartMuseum: Testing Visual Reasoning Capabilities of Large Vision-Language Models

Liyan Tang · Grace Kim · Xinyu Zhao · Thom Lake · Wenxuan Ding · Fangcong Yin · Prasann Singhal · Manya Wadhwa · Zeyu Liu · Zayne Sprague · Ramya Namuduri · Bodun Hu · Juan Rodriguez · Puyuan Peng · Greg Durrett

Paper2Poster: Towards Multimodal Poster Automation from Scientific Papers

Wei Pang · Kevin Qinghong Lin · Xiangru Jian · Xi He · Philip Torr

MMMG: A Massive, Multidisciplinary, Multi-Tier Generation Benchmark for Text-to-Image Reasoning

Yuxuan Luo · Ryan Yuan · Junwen Chen · Haonan Cai · Ziyi Yue · Yuwei Yang · Fatima Zohra Daha · Ji Li · Zhouhui Lian

ExAct: A Video-Language Benchmark for Expert Action Analysis

Han Yi · Yulu Pan · Feihong He · Xinyu Liu · Benjamin Zhang · Oluwatumininu Oguntola · Gedas Bertasius

What’s in Common? Multimodal Models Hallucinate When Reasoning Across Scenes

Candace Ross · Florian Bordes · Adina Williams · Polina Kirichenko · Mark Ibrahim

TaiwanVQA: Benchmarking and Enhancing Cultural Understanding in Vision-Language Models

Hsin Yi Hsieh · Shang-Wei Liu · Chang-Chih Meng · Chien-Hua Chen · Shuo-Yueh Lin · Hung-Ju Lin · Hen-Hsen Huang · I-Chen Wu

WorldModelBench: Judging Video Generation Models As World Models

Dacheng Li · Yunhao Fang · Yukang Chen · Shuo Yang · Shiyi Cao · Justin Wong · Michael Luo · Xiaolong Wang · Hongxu Yin · Joseph Gonzalez · Ion Stoica · Song Han · Yao Lu

In the Eye of MLLM: Benchmarking Egocentric Video Intent Understanding with Gaze-Guided Prompting

Taiying Peng · Jiacheng Hua · Miao Liu · Feng Lu

LISAt: Language-Instructed Segmentation Assistant for Satellite Imagery

Jerome Quenum · Wen-Han Hsieh · Tsung-Han (Patrick) Wu · Ritwik Gupta · Trevor Darrell · David Chan

Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering

Kuicai Dong · CHANG YUJING · Shijie Huang · Yasheng Wang · Ruiming Tang · Yong Liu

MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness

Yunlong Tang · Pinxin Liu · Mingqian Feng · Zhangyun Tan · Rui Mao · Chao Huang · Jing Bi · Yunzhong Xiao · Susan Liang · Hang Hua · Ali Vosoughi · Luchuan Song · Zeliang Zhang · Chenliang Xu

Rebalancing Contrastive Alignment with Bottlenecked Semantic Increments in Text-Video Retrieval

Jian Xiao · Zijie Song · Jialong Hu · Hao Cheng · Jia Li · Zhenzhen Hu · Richang Hong

Temporal Chain of Thought: Long-Video Understanding by Thinking in Frames

Anurag Arnab · Ahmet Iscen · Mathilde Caron · Alireza Fathi · Cordelia Schmid

Video Perception Models for 3D Scene Synthesis

Rui Huang · Guangyao Zhai · Zuria Bauer · Marc Pollefeys · Federico Tombari · Leonidas Guibas · Gao Huang · Francis Engelmann

Unveiling Chain of Step Reasoning for Vision-Language Models with Fine-grained Rewards

Honghao Chen · Xingzhou Lou · Xiaokun Feng · Kaiqi Huang · Xinlong Wang

VisualLens: Personalization through Task-Agnostic Visual History

Wang Bill Zhu · Deqing Fu · Kai Sun · Yi Lu · Zhaojiang Lin · Seungwhan Moon · Kanika Narang · MUSTAFA CANIM · Yue Liu · Anuj Kumar · Xin Dong

HermesFlow: Seamlessly Closing the Gap in Multimodal Understanding and Generation

Ling Yang · Xinchen Zhang · Ye Tian · Shiyi Zhang · Chenming Shang · Minghao Xu · Wentao Zhang · Bin CUI

First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training

Lai Wei · Yuting Li · Chen Wang · Yue Wang · Linghe Kong · Weiran Huang · Lichao Sun

Vision as a Dialect: Unifying Visual Understanding and Generation via Text-Aligned Representations

Jiaming Han · Hao Chen · Yang Zhao · Hanyu Wang · Qi Zhao · Ziyan Yang · Hao He · Xiangyu Yue · Lu Jiang

Perception Encoder: The best visual embeddings are not at the output of the network

ChA-MAEViT: Unifying Channel-Aware Masked Autoencoders and Multi-Channel Vision Transformers for Improved Cross-Channel Learning

Chau Pham · Juan C. Caicedo · Bryan Plummer

TRoVe: Discovering Error-Inducing Static Feature Biases in Temporal Vision-Language Models

Maya Varma · Jean-Benoit Delbrouck · Sophie Ostmeier · Akshay Chaudhari · Curtis Langlotz

Panoptic Captioning: An Equivalence Bridge for Image and Text

Kun-Yu Lin · Hongjun Wang · Weining Ren · Kai Han

Fine-Grained Preference Optimization Improves Spatial Reasoning in VLMs

Yifan Shen · Yuanzhe Liu · Jingyuan Zhu · Xu Cao · Xiaofeng Zhang · Yixiao He · Wenming Ye · James Rehg · Ismini Lourentzou

Towards Robust Uncertainty Calibration for Composed Image Retrieval

Yifan Wang · Wuliang Huang · Yufan Wen · Shunning Liu · Chun Yuan

OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation

Mohamed Abdelfattah · Kaouther Messaoud · Alexandre Alahi

FlowCut: Rethinking Redundancy via Information Flow for Efficient Vision-Language Models

Jintao Tong · Wenwei Jin · Pengda Qin · Anqi Li · Yixiong Zou · Yuhong Li · Yuhua Li · Ruixuan Li

JavisGPT: A Unified Multi-modal LLM for Sounding-Video Comprehension and Generation

Kai Liu · Jungang Li · Yuchong Sun · Shengqiong Wu · jianzhang gao · Daoan Zhang · Wei Zhang · Sheng Jin · Sicheng Yu · Geng Zhan · Jiayi Ji · Fan Zhou · Liang Zheng · Shuicheng Yan · Hao Fei · Tat-Seng Chua

Object Concepts Emerge from Motion

Haoqian Liang · Xiaohui Wang · Zhichao Li · Ya Yang · Naiyan Wang

Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings

Qiong Wu · Wenhao Lin · Yiyi Zhou · Weihao Ye · Zhanpeng Zeng · Xiaoshuai Sun · Rongrong Ji

MIP against Agent: Malicious Image Patches Hijacking Multimodal OS Agents

Lukas Aichberger · Alasdair Paren · Guohao Li · Philip Torr · Yarin Gal · Adel Bibi

UniGen: Enhanced Training & Test-Time Strategies for Unified Multimodal Understanding and Generation

Rui Tian · Mingfei Gao · Mingze Xu · Jiaming Hu · Jiasen Lu · Zuxuan Wu · Yinfei Yang · Afshin Dehghan

Exploiting the Asymmetric Uncertainty Structure of Pre-trained VLMs on the Unit Hypersphere

Li Ju · Max Andersson · Stina Fredriksson · Edward Glöckner · Andreas Hellander · Ekta Vats · Prashant Singh

Reliable Lifelong Multimodal Editing: Conflict-Aware Retrieval Meets Multi-Level Guidance

Qiang Zhang · Fanrui Zhang · Jiawei Liu · Ming Hu · Junjun He · Zheng-Jun Zha

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

Zhongwei Wan · Zhihao Dou · Che Liu · Yu Zhang · Dongfei Cui · Qinjian Zhao · Hui Shen · Jing Xiong · Yi Xin · Yifan Jiang · Chaofan Tao · Yangfan He · Mi Zhang · Shen Yan

Glance2Gaze: Efficient Vision-Language Models from Glance Fusion to Gaze Compression

Juan Chen · Honglin liu · Yingying Ao · Ting Zhang · Yan Huang · Xudong Liu · Biao Li · Jintao Fang

Interactive Cross-modal Learning for Text-3D Scene Retrieval

Yanglin Feng · Yongxiang Li · Yuan Sun · Yang Qin · Dezhong Peng · Peng Hu

Systematic Reward Gap Optimization for Mitigating VLM Hallucinations

Lehan He · Zeren Chen · Zhelun Shi · Tianyu Yu · Lu Sheng · Jing Shao

Self-Supervised Learning of Motion Concepts by Optimizing Counterfactuals

Stefan Stojanov · David Wendt · Seungwoo Kim · Rahul Venkatesh · Kevin Feigelis · Klemen Kotar · Khai Loong Aw · Jiajun Wu · Daniel Yamins

ESCA: Contextualizing Embodied Agents via Scene-Graph Generation

Jiani Huang · Amish Sethi · Matthew Kuo · Mayank Keoliya · Neelay Velingker · JungHo Jung · Ser Nam Lim · Ziyang Li · Mayur Naik

Scaling Laws for Robust Comparison of Open Foundation Language-Vision Models and Datasets

Marianna Nezhurina · Tomer Porian · Giovanni Puccetti · Tommie Kerssies · Romain Beaumont · Mehdi Cherti · Jenia Jitsev

Counterfactual Evolution of Multimodal Datasets via Visual Programming

Minghe Gao · Zhongqi Yue · Wenjie Yan · Yihao Hu · Wei Ji · Siliang Tang · Jun Xiao · Tat-Seng Chua · Yueting Zhuang · Juncheng Li

VLMs have Tunnel Vision: Evaluating Nonlocal Visual Reasoning in Leading VLMs

Shmuel Berman · Jia Deng

Balancing Multimodal Training Through Game-Theoretic Regularization

Konstantinos Kontras · Thomas Strypsteen · Christos Chatzichristos · Paul Liang · Matthew Blaschko · Maarten De Vos

Meta CLIP 2: A Worldwide Scaling Recipe

Yung-Sung Chuang · Yang Li · Dong Wang · Ching-Feng Yeh · Kehan Lyu · Ramya Raghavendra · Jim Glass · Lifei Huang · Jason Weston · Luke Zettlemoyer · Xinlei Chen · Zhuang Liu · Saining Xie · Scott Yih · Shang-Wen Li · Hu Xu

Co-Reinforcement Learning for Unified Multimodal Understanding and Generation

Jingjing Jiang · Chongjie Si · Jun Luo · Hanwang Zhang · Chao Ma

To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning

Ming Li · Jike Zhong · Shitian Zhao · Yuxiang Lai · Haoquan Zhang · Wang Bill Zhu · Kaipeng Zhang

Vision-centric Token Compression in Large Language Model

Ling Xing · Alex Jinpeng Wang · Rui Yan · Xiangbo Shu · Jinhui Tang

SaFiRe: Saccade-Fixation Reiteration with Mamba for Referring Image Segmentation

Zhenjie Mao · Yang Yuhuan · Chaofan Ma · Dongsheng Jiang · Jiangchao Yao · Ya Zhang · Yanfeng Wang

Mitigating Semantic Collapse in Partially Relevant Video Retrieval

WonJun Moon · MinSeok Jung · Gilhan Park · Tae-Young Kim · Cheol-Ho Cho · Woojin Jun · Jae-Pil Heo

Native Segmentation Vision Transformers

Guillem Brasó · Aljosa Osep · Laura Leal-Taixé

Brain-like Variational Inference

Hadi Vafaii · Dekel Galor · Jacob Yates

Guiding Cross-Modal Representations with MLLM Priors via Preference Alignment

Pengfei Zhao · Rongbo Luan · Wei Zhang · Peng Wu · Sifeng He

Towards Comprehensive Scene Understanding: Integrating First and Third-Person Views for LVLMs

Insu Lee · Wooje Park · Jaeyun Jang · Minyoung Noh · Kyuhong Shim · Byonghyo Shim

Walking the Schrödinger Bridge: A Direct Trajectory for Text-to-3D Generation

Ziying Li · Xuequan Lu · Xinkui Zhao · Guanjie Cheng · Shuiguang Deng · Jianwei Yin

End-to-End Vision Tokenizer Tuning

Wenxuan Wang · Fan Zhang · Yufeng Cui · Haiwen Diao · Zhuoyan Luo · Huchuan Lu · Jing Liu · Xinlong Wang

SQS: Enhancing Sparse Perception Models via Query-based Splatting in Autonomous Driving

Haiming Zhang · Yiyao Zhu · Wending Zhou · Xu Yan · Yingjie CAI · Bingbing Liu · Shuguang Cui · Zhen Li

When Thinking Drifts: Evidential Grounding for Robust Video Reasoning

Romy Luo · Zihui (Sherry) Xue · Alex Dimakis · Kristen Grauman

EgoDTM: Towards 3D-Aware Egocentric Video-Language Pretraining

Boshen Xu · Yuting Mei · liu xinbi · Sipeng Zheng · Qin Jin

NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation

Longtian Qiu · Shan Ning · Jiaxuan Sun · Xuming He

Dynam3D: Dynamic Layered 3D Tokens Empower VLM for Vision-and-Language Navigation

Zihan Wang · Seungjun Lee · Gim Hee Lee

On the rankability of visual embeddings

Ankit Sonthalia · Arnas Uselis · Seong Joon Oh

EUGens: Efficient, Unified and General Dense Layers

Sang Min Kim · Byeongchan Kim · Arijit Sehanobish · Somnath Basu Roy Chowdhury · Rahul Kidambi · Dongseok Shim · Kumar Avinava Dubey · Snigdha Chaturvedi · Min-hwan Oh · Krzysztof M Choromanski

Multi-scale Temporal Prediction via Incremental Generation and Multi-agent Collaboration

Zhitao Zeng · Guojian Yuan · Junyuan Mao · Yuxuan Wang · Xiaoshuang Jia · Yueming Jin

Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language Models

Ling Li · Yao Zhou · Yuxuan Liang · Fugee Tsung · Jiaheng Wei

DyMU: Dynamic Merging and Virtual Unmerging for Efficient Variable-Length VLMs

Zhenhailong Wang · Senthil Purushwalkam · Caiming Xiong · Silvio Savarese · Heng Ji · Ran Xu

Don't Just Chase “Highlighted Tokens” in MLLMs: Revisiting Visual Holistic Context Retention

Xin Zou · Di Lu · Yizhou Wang · Yibo Yan · Yuanhuiyi Lyu · Xu Zheng · Linfeng Zhang · Xuming Hu

SAVVY: Spatial Awareness via Audio-Visual LLMs through Seeing and Hearing

Mingfei Chen · Zijun Cui · Xiulong Liu · Jinlin Xiang · Yang Zheng · Jingyuan Li · Eli Shlizerman

SHF: Symmetrical Hierarchical Forest with Pretrained Vision Transformer Encoder for High-Resolution Medical Segmentation

Enzhi Zhang · Peng Chen · Rui Zhong · Du Wu · Jun Igarashi · Isaac Lyngaas · Xiao Wang · Masaharu Munetomo · Mohamed Wahib

Diffusion-Driven Two-Stage Active Learning for Low-Budget Semantic Segmentation

Jeongin Kim · Wonho Bae · YouLee Han · Giyeong Oh · Youngjae Yu · Danica J. Sutherland · Junhyug Noh

OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts

Shiting (Ginny) Xiao · Rishabh Kabra · Yuhang Li · Donghyun Lee · Joao Carreira · Priyadarshini Panda

ForensicHub: A Unified Benchmark & Codebase for All-Domain Fake Image Detection and Localization

Bo Du · Xuekang Zhu · Xiaochen Ma · Chenfan Qu · Kaiwen Feng · Zhe Yang · Chi-Man Pun · Jian liu · Ji-Zhe Zhou

DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?

Tianhong Zhou · xu yin · Yingtao Zhu · Chuxi Xiao · Haiyang Bian · Lei Wei · Xuegong Zhang

STACI: Spatio-Temporal Aleatoric Conformal Inference

Brandon Feng · David Park · Xihaier Luo · Arantxa Urdangarin · Shinjae Yoo · Brian Reich

Multivariate Latent Recalibration for Conditional Normalizing Flows

Victor Dheur · Souhaib Ben Taieb

Reverse-Annealed Sequential Monte Carlo for Efficient Bayesian Optimal Experiment Design

Jake Callahan · Andrew Chin · Jason Pacheco · Tommie Catanach

A Latent Multilayer Graphical Model For Complex, Interdependent Systems

Martin Ondrus · Ivor Cribben · Yang Feng

Personalized Federated Conformal Prediction with Localization

Yinjie Min · Chuchen Zhang · Liuhua Peng · Changliang Zou

S-GRPO: Early Exit via Reinforcement Learning in Reasoning Models

Muzhi Dai · Chenxu Yang · Qingyi Si

Efficient Prompt Compression with Evaluator Heads for Long-Context Transformer Inference

Weizhi Fei · Xueyan Niu · XIE GUOQING · Yingqing Liu · Bo Bai · Wei Han

Preference Learning with Lie Detectors can Induce Honesty or Evasion

Chris Cundy · Adam Gleave

To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL

Yuda Song · Dhruv Rohatgi · Aarti Singh · J. Bagnell

Alligat0R: Pre-Training through Covisibility Segmentation for Relative Camera Pose Regression

Thibaut Loiseau · Guillaume Bourmaud · Vincent Lepetit

Part-Aware Bottom-Up Group Reasoning for Fine-Grained Social Interaction Detection

Dongkeun Kim · Minsu Cho · Suha Kwak

Diffusion-Classifier Synergy: Reward-Aligned Learning via Mutual Boosting Loop for FSCIL

Ruitao Wu · Yifan Zhao · Guangyao Chen · Jia Li

GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Data

Lubin Bai · Xiuyuan Zhang · Siqi Zhang · Zepeng Zhang · Haoyu Wang · Wei Qin · Shihong Du

ADPretrain: Advancing Industrial Anomaly Detection via Anomaly Representation Pretraining

Xincheng Yao · Yan Luo · Zefeng Qian · Chongyang Zhang

DitHub: A Modular Framework for Incremental Open-Vocabulary Object Detection

Chiara Cappellino · Gianluca Mancusi · Matteo Mosconi · Angelo Porrello · SIMONE CALDERARA · Rita Cucchiara

Holistic Order Prediction in Natural Scenes

Pierre Musacchio · Hyunmin Lee · Jaesik Park

Alias-Free ViT: Fractional Shift Invariance via Linear Attention

Hagay Michaeli · Daniel Soudry

Object-Centric Representation Learning for Enhanced 3D Semantic Scene Graph Prediction

KunHo Heo · GiHyun Kim · SuYeon Kim · MyeongAh Cho

Frequency-Aware Token Reduction for Efficient Vision Transformer

DongJae Lee · Jiwan Hur · Jaehyun Choi · Jaemyung Yu · Junmo Kim

ToolRL: Reward is All Tool Learning Needs

Cheng Qian · Emre Can Acikgoz · Qi He · Hongru WANG · Xiusi Chen · Dilek Hakkani-Tur · Gokhan Tur · Heng Ji

Dual Data Alignment Makes AI-Generated Image Detector Easier Generalizable

Ruoxin Chen · Junwei Xi · Zhiyuan Yan · Ke-Yue Zhang · Shuang Wu · Jingyi Xie · Xu Chen · Lei Xu · Isabel Guan · Taiping Yao · Shouhong Ding

Evolving and Regularizing Meta-Environment Learner for Fine-Grained Few-Shot Class-Incremental Learning

Li-Jun Zhao · Zhen-Duo Chen · Yongxin Wang · Xin Luo · Xin-Shun Xu

Enhancing the Outcome Reward-based RL Training of MLLMs with Self-Consistency Sampling

Jiahao Wang · Weiye Xu · Aijun Yang · Wengang Zhou · Lewei Lu · Houqiang Li · Xiaohua Wang · Jinguo Zhu

Accelerating RL for LLM Reasoning with Optimal Advantage Regression

Kianté Brantley · Mingyu Chen · Zhaolin Gao · Jason Lee · Wen Sun · Wenhao Zhan · Xuezhou Zhang

Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes

Jiaxin Huang · Ziwen Li · Hanlue Zhang · Runnan Chen · Zhengqing Gao · Xiao He · Yandong Guo · Wenping Wang · Tongliang Liu · Mingming Gong

CVGL: Causal Learning and Geometric Topology

Songsong Ouyang · Yingying Zhu

L2RSI: Cross-view LiDAR-based Place Recognition for Large-scale Urban Scenes via Remote Sensing Imagery

Ziwei Shi · Xiaoran Zhang · Wenjing Xu · Yan Xia · Yu Zang · Siqi Shen · Cheng Wang

Single-Teacher View Augmentation: Boosting Knowledge Distillation via Angular Diversity

Seonghoon Yu · Dongjun Nam · Dina Katabi · Jeany Son

Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning

Xingjian Ran · Yixuan Li · Linning Xu · Mulin Yu · Bo Dai

Dual-Path Temporal Decoder for End-to-End Multi-Object Tracking

Hyunseop Kim · Juheon Jeong · Hanul Kim · Yeong Jun Koh

Bio-Inspired Image Restoration

Yuning Cui · Wenqi Ren · Alois Knoll

CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects

Huaijin Pi · Zhi Cen · Zhiyang Dou · Taku Komura

Dense Metric Depth Estimation via Event-based Differential Focus Volume Prompting

Boyu Li · Peiqi Duan · Zhaojun Huang · Xinyu Zhou · Yifei Xia · Boxin Shi

Injecting Frame-Event Complementary Fusion into Diffusion for Optical Flow in Challenging Scenes

Haonan Wang · Hanyu Zhou · Haoyue Liu · Luxin Yan

MobileODE: An Extra Lightweight Network

Le Yu · Jun Wu · Bo Gou · Xiangde Min · Lei Zhang · Zhang Yi · Tao He

OSCAR: One-Step Diffusion Codec Across Multiple Bit-rates

Jinpei Guo · Yifei Ji · Zheng Chen · Kai Liu · Min Liu · Wang Rao · Wenbo Li · Yong Guo · Yulun Zhang

Learn and Ensemble Bridge Adapters for Multi-domain Task Incremental Learning

Ziqi Gu · Chunyan Xu · Wenxuan Fang · Xin Liu · Yide Qiu · Zhen Cui

DeepDiver: Adaptive Web-Search Intensity Scaling via Reinforcement Learning

Wenxuan Shi · Haochen Tan · Chuqiao Kuang · Xiaoguang Li · Hanting Chen · Xiaozhe Ren · Yasheng Wang · Lu Hou · Lifeng Shang

Self-Supervised Direct Preference Optimization for Text-to-Image Diffusion Models

Liang Peng · Boxi Wu · Haoran Cheng · Yibo Zhao · Xiaofei He

ORIGEN: Zero-Shot 3D Orientation Grounding in Text-to-Image Generation

Yunhong Min · Daehyeon Choi · Kyeongmin Yeo · Jihyun Lee · Minhyuk Sung

CADGrasp: Learning Contact and Collision Aware General Dexterous Grasping in Cluttered Scenes

Jiyao Zhang · Zhiyuan Ma · Tianhao Wu · Zeyuan Chen · Hao Dong

Deployment Efficient Reward-Free Exploration with Linear Function Approximation

Zihan Zhang · Yuxin Chen · Jason Lee · Simon Du · Lin Yang · Ruosong Wang

Dynamic View Synthesis as an Inverse Problem

Hidir Yesiltepe · Pinar Yanardag

HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis

Heyuan Li · Kenkun Liu · Lingteng Qiu · Qi Zuo · Keru Zheng · Zilong Dong · Xiaoguang Han

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

Xiao Li · Zekai Zhang · Xiang Li · Siyi Chen · Zhihui Zhu · Peng Wang · Qing Qu

DualCnst: Enhancing Zero-Shot Out-of-Distribution Detection via Text-Image Consistency in Vision-Language Models

Fayi Le · Wenwu He · Chentao Cao · Dong Liang · Zhuo-Xu Cui

Bi-Level Knowledge Transfer for Multi-Task Multi-Agent Reinforcement Learning

Junkai Zhang · Jinmin He · Yifan Zhang · Yifan Zang · Ning Xu · Jian Cheng

ESCA: Enabling Seamless Codec Avatar Execution through Algorithm and Hardware Co-Optimization for Virtual Reality

Mingzhi Zhu · Ding Shang · Sai Qian Zhang

A Driving-Style-Adaptive Framework for Vehicle Trajectory Prediction

Di Wen · Yu Wang · Zhigang Wu · Zhaocheng He · Zhe Wu · Zheng Qingfang

Artificial Hivemind: The Open-Ended Homogeneity of Language Models (and Beyond)

Liwei Jiang · Yuanjun Chai · Margaret Li · Mickel Liu · Raymond Fok · Nouha Dziri · Yulia Tsvetkov · Maarten Sap · Yejin Choi

WearVQA: A Visual Question Answering Benchmark for Wearables in Egocentric Authentic Real-world scenarios

Eun Chang · Zhuangqun Huang · Yiwei Liao · Sagar Bhavsar · Amogh Param · Tammy Stark · Adel Ahmadyan · Xiao Yang · Jiaqi Wang · Ahsan Abdullah · Giang Nguyen · Akil Iyer · David Hall · Elissa Li · Nicolas Scheffer · Ahmed Kirmani · Babak Damavandi · Rakesh Wanga · Anuj Kumar · Rohit Patel · Seungwhan Moon · Xin Luna Dong

Towards Better Dental AI: A Multimodal Benchmark and Instruction Dataset for Panoramic X-ray Analysis

Jing Hao · Yuxuan Fan · Yanpeng Sun · Kaixin Guo · Lin Lizhuo · Jinrong Yang · Qiyong Ai · Lun Wong · Hao Tang · Kuo Hung

SciArena: An Open Evaluation Platform for Non-Verifiable Scientific Literature-Grounded Tasks

Yilun Zhao · Kaiyan Zhang · Tiansheng Hu · Sihong Wu · Ronan Le Bras · Yixin Liu · Robert Tang · Joseph Chee Chang · Jesse Dodge · Jonathan Bragg · Chen Zhao · Hanna Hajishirzi · Doug Downey · Arman Cohan

AnomalyCoT: A Multi-Scenario Chain-of-Thought Dataset for Multimodal Large Language Models

Jiaxi Cheng · Yuliang Xu · Shoupeng Wang · Tao Ma · Yuchen He · Jinghe Zhang · Sihang Cai · Jiawei Zhen · Jingyi Jia · Yao Wan · Yan Xia · Zhou Zhao

Asymptotic Theory of Geometric and Adaptive $k$-Means Clustering

Adam Quinn Jaffe

MODEM: A Morton-Order Degradation Estimation Mechanism for Adverse Weather Image Recovery

Hainuo Wang · Qiming Hu · Xiaojie Guo

Bits Leaked per Query: Information-Theoretic Bounds for Adversarial Attacks on LLMs

Masahiro Kaneko · Timothy Baldwin

Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning

Kaihang Pan · Yang Wu · Wendong Bu · Shen Kai · Juncheng Li · Yingting Wang · Yunfei Li · Siliang Tang · Jun Xiao · Fei Wu · ZhaoHang · Yueting Zhuang

Web-Shepherd: Advancing PRMs for Reinforcing Web Agents

Hyungjoo Chae · Seonghwan Kim · Junhee Cho · Seungone Kim · Seungjun Moon · Gyeom Hwangbo · Dongha Lim · Minjin Kim · Yeonjun Hwang · Minju Gwak · Dongwook Choi · Minseok Kang · Gwanhoon Im · ByeongUng Cho · Hyojun Kim · Jun Han · Taeyoon Kwon · Minju Kim · Beong-woo Kwak · Dongjin Kang · Jinyoung Yeo

Can Multi-Modal LLMs Provide Live Step-by-Step Task Guidance?

Apratim Bhattacharyya · Bicheng Xu · Sanjay Haresh · Reza Pourreza · Litian Liu · Sunny Panchal · Leonid Sigal · Roland Memisevic

TAI3: Testing Agent Integrity in Interpreting User Intent

Shiwei Feng · Xiangzhe Xu · Xuan Chen · Kaiyuan Zhang · Syed Ahmed · Zian Su · Mingwei Zheng · Xiangyu Zhang

JAFAR: Jack up Any Feature at Any Resolution

Paul Couairon · Loïck Chambon · Louis Serrano · Jean-Emmanuel HAUGEARD · Matthieu Cord · Nicolas THOME

SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning

Wanjia Zhao · Mert Yuksekgonul · Shirley Wu · James Zou

GRAPE: Optimize Data Mixture for Group Robust Multi-target Adaptive Pretraining

Simin Fan · Maria Ios Glarou · Martin Jaggi

DINGO: Constrained Inference for Diffusion LLMs

Tarun Suresh · Debangshu Banerjee · Shubham Ugare · Sasa Misailovic · Gagandeep Singh

OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation

Mengkang Hu · Yuhang Zhou · Wendong Fan · Yuzhou Nie · Ziyu Ye · Bowei Xia · Tao Sun · Zhaoxuan Jin · Yingru Li · Zeyu Zhang · Yifeng Wang · Qianshuo Ye · Bernard Ghanem · Ping Luo · Guohao Li

SafePTR: Token-Level Jailbreak Defense in Multimodal LLMs via Prune-then-Restore Mechanism

Beitao Chen · Xinyu Lyu · shengming yuan · Jingkuan Song · Hengtao Shen · Lianli Gao

NoPo-Avatar: Generalizable and Animatable Avatars from Sparse Inputs without Human Poses

Jing Wen · Alex Schwing · Shenlong Wang

Bootstrap Your Uncertainty: Adaptive Robust Classification Driven by Optimal-Transport

Jiawei Huang · Minming Li · Hu Ding

Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation

Sangmin Bae · Yujin Kim · Reza Bayat · Sungnyun Kim · Jiyoun Ha · Tal Schuster · Adam Fisch · Hrayr Harutyunyan · Ziwei Ji · Aaron Courville · Se-Young Yun

Enhancing LLM Watermark Resilience Against Both Scrubbing and Spoofing Attacks

Huanming Shen · Baizhou Huang · Xiaojun Wan

TS-MOF: Two-Stage Multi-Objective Fine-tuning for Long-Tailed Recognition

Zhe Zhao · Zhiheng Gong · Pengkun Wang · HaiBin Wen · Cankun Guo · Bo Xue · Xi Lin · Zhenkun Wang · Qingfu Zhang · Yang Wang

RAPID Hand: Robust, Affordable, Perception-Integrated, Dexterous Manipulation Platfrom for Embodied Intelligence

Zhaoliang Wan · Zetong Bi · Zida Zhou · Hao Ren · Yiming Zeng · Yihan Li · Lu Qi · Xu Yang · Ming-Hsuan Yang · Hui Cheng

RobotSmith: Generative Robotic Tool Design for Acquisition of Complex Manipulation Skills

Chunru Lin · Haotian Yuan · Yian Wang · Xiaowen Qiu · Tsun-Hsuan Johnson Wang · Minghao Guo · Bohan Wang · Yashraj Narang · Dieter Fox · Chuang Gan

AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking

Xiangqi Wang · Yue Huang · Yanbo Wang · Xiaonan Luo · Kehan Guo · Yujun Zhou · Xiangliang Zhang

TTRL: Test-Time Reinforcement Learning

Yuxin Zuo · Kaiyan Zhang · Li Sheng · Shang Qu · Ganqu Cui · Xuekai Zhu · Haozhan Li · yuchen zhang · Xinwei Long · Ermo Hua · Biqing Qi · Youbang Sun · Zhiyuan Ma · Lifan Yuan · Ning Ding · Bowen Zhou

Position: Benchmarking is Broken - Don't Let AI be Its Own Judge

Zerui Cheng · Stella Wohnig · Ruchika Gupta · Samiul Alam · Tassallah Abdullahi · João Alves Ribeiro · Christian Nielsen-Garcia · Saif Mir · Siran Li · Jason Orender · Seyed Ali Bahrainian · Daniel Kirste · Aaron Gokaslan · Carsten Eickhoff · Ruben Wolff

StruDiCO: Structured Denoising Diffusion with Gradient-free Inference-stage Boosting for Memory and Time Efficient Combinatorial Optimization

Yu Wang · Yang Li · Junchi Yan · Yi Chang

VAGEN: Reinforcing World Model Reasoning for Multi-Turn VLM Agents

Kangrui Wang · Pingyue Zhang · Zihan Wang · Yaning Gao · Linjie Li · Qineng Wang · Hanyang Chen · Yiping Lu · Zhengyuan Yang · Lijuan Wang · Ranjay Krishna · Jiajun Wu · Fei-Fei Li · Yejin Choi · Manling Li

VividFace: A Robost and High-Fidelity Video Face Swapping Framework

Hao Shao · Shulun Wang · Yang Zhou · Guanglu Song · Dailan He · ZHUOFAN ZONG · Shuo Qin · Yu Liu · Hongsheng Li

HOComp: Interaction-Aware Human-Object Composition

Dong Liang · Jinyuan Jia · Yuhao LIU · Rynson Lau

Generalizing Single-Frame Supervision to Event-Level Understanding for Video Anomaly Detection

Junxi Chen · Liang Li · Yunbin Tu · Li Su · Zhe Xue · Qingming Huang

Federated Multi-armed Bandits with Efficient Bit-Level Communications

Haoran Zhang · Yang Xu · Xuchuang Wang · Hao-Xu Chen · Hao Qiu · Lin Yang · Yang Gao

G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems

Guibin Zhang · Muxin Fu · Kun Wang · Guancheng Wan · Miao Yu · Shuicheng Yan

Mitigating Reward Over-optimization in Direct Alignment Algorithms with Importance Sampling

Nguyen Phuc · Ngoc-Hieu Nguyen · Duy M. H. Nguyen · Anji Liu · An Mai · Thanh Binh Nguyen · Daniel Sonntag · Khoa D Doan

Representation Entanglement for Generation: Training Diffusion Transformers Is Much Easier Than You Think

Ge Wu · Shen Zhang · Ruijing Shi · Shanghua Gao · Zhenyuan Chen · Lei Wang · Zhaowei Chen · Hongcheng Gao · Yao Tang · jian Yang · Ming-Ming Cheng · Xiang Li

Safe + Safe = Unsafe? Exploring How Safe Images Can Be Exploited to Jailbreak Large Vision-Language Models

Chenhang Cui · Gelei Deng · An Zhang · jingnan zheng · Yicong Li · Lianli Gao · Tianwei Zhang · Tat-Seng Chua

Robust and Diverse Multi-Agent Learning via Rational Policy Gradient

Niklas Lauffer · Ameesh Shah · Micah Carroll · Sanjit Seshia · Stuart J Russell · Michael Dennis

Graph-Based Attention for Differentiable MaxSAT Solving

Sota Moriyama · Katsumi Inoue

AnimateQR: Bridging Aesthetics and Functionality in Dynamic QR Code Generation

Guangyang Wu · Huayu Zheng · Siqi Luo · Guangtao Zhai · Xiaohong Liu

OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

Yihe Deng · Hritik Bansal · Fan Yin · Nanyun Peng · Wei Wang · Kai-Wei Chang

Fast Training of Large Kernel Models with Delayed Projections

Amirhesam Abedsoltan · Siyuan Ma · Parthe Pandit · Misha Belkin

The Emergence of Abstract Thought in Large Language Models Beyond Any Language

Yuxin Chen · Yiran Zhao · Yang Zhang · An Zhang · Kenji Kawaguchi · Shafiq Joty · Junnan Li · Tat-Seng Chua · Michael Qizhe Shieh · Wenxuan Zhang

Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models

Yue Wang · Qiuzhi Liu · Jiahao Xu · Tian Liang · Xingyu Chen · Zhiwei He · Linfeng Song · Dian Yu · Juntao Li · Zhuosheng Zhang · Rui Wang · Zhaopeng Tu · Haitao Mi · Dong Yu

TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs

Yuxiang Zhang · Zhengxu Yu · Weihang Pan · Zhongming Jin · Qiang Fu · Deng Cai · Binbin Lin · Jieping Ye

Variational Polya Tree

Lu Xu · Tsai Hor Chan · Lequan Yu · Kwok Lam · Guosheng Yin

Max Entropy Moment Kalman Filter for Polynomial Systems with Arbitrary Noise

Sangli Teng · Harry Zhang · David Jin · Ashkan Jasour · Ram Vasudevan · Maani Ghaffari · Luca Carlone

ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition

Daolang Huang · Xinyi Wen · Ayush Bharti · Samuel Kaski · Luigi Acerbi

An Adaptive Quantum Circuit of Dempster's Rule of Combination for Uncertain Pattern Classification

Fuyuan Xiao · Yu Zhou · Witold Pedrycz

Infinite Neural Operators: Gaussian processes on functions

Daniel Augusto de Souza · Yuchen Zhu · Jake Cunningham · Yuri Saporito · Diego Mesquita · Marc Deisenroth

Feel-Good Thompson Sampling for Contextual Bandits: a Markov Chain Monte Carlo Showdown

Emile Anand · Sarah Liaw

Approximately Aligned Decoding

Daniel Melcer · Sujan Kumar Gonugondla · Pramuditha Perera · Haifeng Qian · Wen-Hao Chiang · Yanjun Wang · Nihal Jain · Pranav Garg · Xiaofei Ma · Anoop Deoras

Reverse Diffusion Sequential Monte Carlo Samplers

Luhuan Wu · Yi Han · Christian Andersson Naesseth · John Cunningham

Constrained Sampling for Language Models Should Be Easy: An MCMC Perspective

Emmanuel Anaya Gonzalez · Sairam Vaidya · Kanghee Park · Ruyi Ji · Taylor Berg-Kirkpatrick · Loris D'Antoni

Split Gibbs Discrete Diffusion Posterior Sampling

Wenda Chu · Zihui Wu · Yifan Chen · Yang Song · Yisong Yue

The Adaptive Complexity of Minimizing Relative Fisher Information

Huanjian Zhou · Masashi Sugiyama

On scalable and efficient training of diffusion samplers

Minkyu Kim · Kiyoung Seong · Dongyeop Woo · Sungsoo Ahn · Minsu Kim

Adjoint Schrödinger Bridge Sampler

Guan-Horng Liu · Jaemoo Choi · Yongxin Chen · Benjamin K Miller · Ricky T. Q. Chen

Preconditioned Langevin Dynamics with Score-based Generative Models for Infinite-Dimensional Linear Bayesian Inverse Problems

Lorenzo Baldassari · Josselin Garnier · Knut Solna · Maarten V. de Hoop

Tree-Sliced Entropy Partial Transport

Viet-Hoang Tran · Thanh Tran · Thanh Chu · Tam Le · Tan Nguyen

Rethinking Entropy in Test-Time Adaptation: The Missing Piece from Energy Duality

Mincheol Park · Heeji Won · Won Woo Ro · Suhyun Kim

Inexact Column Generation for Bayesian Network Structure Learning via Difference-of-Submodular Optimization

Yiran Yang · Rui Chen

MISA: Memory-Efficient LLMs Optimization with Module-wise Importance Sampling

Yuxi Liu · Renjia Deng · Yutong He · xue wang · Tao Yao · Kun Yuan

Gradient-Variation Online Adaptivity for Accelerated Optimization with Hölder Smoothness

Yuheng Zhao · Yu-Hu Yan · Kfir Y. Levy · Peng Zhao

Fast Last-Iterate Convergence of SGD in the Smooth Interpolation Regime

Amit Attia · Matan Schliserman · Uri Sherman · Tomer Koren

Accelerated Distance-adaptive Methods for Hölder Smooth and Convex Optimization

Yijin Ren · Haifeng Xu · Qi Deng

PaZO: Preconditioned Accelerated Zeroth-Order Optimization for Fine-Tuning LLMs

Hanzhen Zhao · Ding Shihong · Cong Fang · Zhouchen Lin

New Perspectives on the Polyak Stepsize: Surrogate Functions and Negative Results

Francesco Orabona · Ryan D'Orazio

Probing Neural Combinatorial Optimization Models

Zhiqin Zhang · Yining Ma · Zhiguang Cao · Hoong Chuin Lau

Non-Convex Tensor Recovery from Tube-Wise Sensing

Tongle Wu · Ying Sun

On the Complexity of Finding Stationary Points in Nonconvex Simple Bilevel Optimization

Jincheng Cao · Ruichen Jiang · Erfan Yazdandoost Hamedani · Aryan Mokhtari

Extragradient Method for $(L_0, L_1)$-Lipschitz Root-finding Problems

Sayantan Choudhury · Nicolas Loizou

Affine-Invariant Global Non-Asymptotic Convergence Analysis of BFGS under Self-Concordance

Qiujiang Jin · Aryan Mokhtari

Differentiable extensions with rounding guarantees for combinatorial optimization over permutations

Robert (Riley) Nerem · Zhishang Luo · Akbar Rafiey · Yusu Wang

Convergence Rates for Gradient Descent on the Edge of Stability for Overparametrised Least Squares

Lachlan MacDonald · Hancheng Min · Leandro Palma · Salma Tarmoun · Ziqing Xu · Rene Vidal

Accelerating Optimization via Differentiable Stopping Time

Zhonglin Xie · Yiman Fong · Haoran Yuan · Zaiwen Wen

Rethinking Gradient Step Denoiser: Towards Truly Pseudo-Contractive Operator

Shuchang Zhang · Yaoyun Zeng · Kangkang Deng · Hongxia Wang

DesignX: Human-Competitive Algorithm Designer for Black-Box Optimization

Hongshu Guo · Zeyuan Ma · Yining Ma · Xinglin Zhang · Wei-Neng Chen · Yue-Jiao Gong

Rethinking Neural Combinatorial Optimization for Vehicle Routing Problems with Different Constraint Tightness Degrees

Fu Luo · Yaoxin Wu · Zhi Zheng · Zhenkun Wang

Statistical Inference for Decentralized Federated Learning

Jia Gu · Songxi Chen

Block-Diagonal LoRA for Eliminating Communication Overhead in Tensor Parallel LoRA Serving

Xinyu Wang · Jonas M. Kübler · Kailash Budhathoki · Yida Wang · Matthäus Kleindessner

Efficient Federated Learning against Byzantine Attacks and Data Heterogeneity via Aggregating Normalized Gradients

Shiyuan Zuo · Xingrun Yan · Rongfei Fan · Li Shen · Puning Zhao · Jie Xu · Han Hu

FedLPA: Local Prior Alignment for Heterogeneous Federated Generalized Category Discovery

Geeho Kim · Jinu Lee · Bohyung Han

Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable

Bicheng Ying · Zhe Li · Haibo Yang

NestedFP: High-Performance, Memory-Efficient Dual-Precision Floating Point Support for LLMs

Haeun Lee · Omin Kwon · Yeonhong Park · Jae W. Lee

Sketched Adaptive Distributed Deep Learning: A Sharp Convergence Analysis

Zhijie Chen · Qiaobo Li · Arindam Banerjee

Synergistic Tensor and Pipeline Parallelism

Mengshi Qi · Jiaxuan Peng · Jie Zhang · Juan Zhu · Yong Li · Huadong Ma

Layer-wise Update Aggregation with Recycling for Communication-Efficient Federated Learning

Jisoo Kim · Sungmin Kang · Sunwoo Lee

KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems

Hancheng Ye · Zhengqi Gao · Mingyuan Ma · Qinsi Wang · Yuzhe Fu · Ming-Yu Chung · Yueqian Lin · Zhijian Liu · Jianyi Zhang · Danyang Zhuo · Yiran Chen

Mozart: Modularized and Efficient MoE Training on 3.5D Wafer-Scale Chiplet Architectures

Shuqing Luo · Ye Han · Pingzhi Li · Jiayin Qin · Jie Peng · Yang Zhao · Yu Cao · Tianlong Chen

The Bias-Variance Tradeoff in Data-Driven Optimization: A Local Misspecification Perspective

Haixiang Lan · Luofeng Liao · Adam N. Elmachtoub · Christian Kroer · Henry Lam · Haofeng Zhang

What Data Enables Optimal Decisions? An Exact Characterization for Linear Optimization

Omar Bennouna · Amine Bennouna · Saurabh Amin · Asuman Ozdaglar

Conformal Mixed-Integer Constraint Learning with Feasibility Guarantees

Daniel Ovalle · Lorenz Biegler · Ignacio Grossmann · Carl Laird · Mateo Dulce Rubio

Conformal Risk Training: End-to-End Optimization of Conformal Risk Control

Christopher Yeh · Nicolas Christianson · Adam Wierman · Yisong Yue

Statistical Inference under Performativity

Xiang Li · Yunai Li · Huiying Zhong · Lihua Lei · Zhun Deng

Computation and Memory-Efficient Model Compression with Gradient Reweighting

Zhiwei Li · Yuesen Liao · Binrui Wu · Yuquan Zhou · Xupeng Shi · Dongsheng Jiang · Yin Li · Weizhong Zhang

Memory-Efficient Training with In-Place FFT Implementation

XINYU DING · Bangtian Liu · Siyu Liao · Zhongfeng Wang

Compress & Cache: Vision token compression for efficient generation and retrieval

Adrian Bulat · Yassine Ouali · Georgios Tzimiropoulos

Purifying Shampoo: Investigating Shampoo's Heuristics by Decomposing its Preconditioner

Runa Eschenhagen · Aaron Defazio · Tsung-Hsien Lee · Richard Turner · Hao-Jun Shi

Convergence of the Gradient Flow for Shallow ReLU Networks on Weakly Interacting Data

Léo Dana · Loucas Pillaud-Vivien · Francis Bach

PROFIT: A Specialized Optimizer for Deep Fine Tuning

Anirudh Chakravarthy · Shuai Zheng · Xin Huang · Sachithra Hemachandra · Xiao Zhang · Yuning Chai · Zhao Chen

The Rich and the Simple: On the Implicit Bias of Adam and SGD

Bhavya Vasudeva · Jung Lee · Vatsal Sharan · Mahdi Soltanolkotabi

SAD Neural Networks: Divergent Gradient Flows and Asymptotic Optimality via o-minimal Structures

Julian Kranz · Davide Gallon · Steffen Dereich · Arnulf Jentzen

KOALA++: Efficient Kalman-Based Optimization with Gradient-Covariance Products

Zixuan XIa · Aram Davtyan · Paolo Favaro

Reparameterized LLM Training via Orthogonal Equivalence Transformation

Zeju Qiu · Simon Buchholz · Tim Xiao · Maximilian Dax · Bernhard Schölkopf · Weiyang Liu

SUMO: Subspace-Aware Moment-Orthogonalization for Accelerating Memory-Efficient LLM Training

Yehonathan Refael · Guy Smorodinsky · Tom Tirer · Ofir Lindenbaum

QSCA: Quantization with Self-Compensating Auxiliary for Monocular Depth Estimation

Jincheol Yang · Jaemin Choi · Matti Zinke · Suk-Ju Kang

Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning

Jiwon Song · Dongwon Jo · Yulhwa Kim · jae-joon kim

Compress Large Language Models via Collaboration Between Learning and Matrix Approximation

Yuesen Liao · Zhiwei Li · Binrui Wu · Zihao Cheng · Su Zhao · Shuai Chen · Weizhong Zhang

MOBO-OSD: Batch Multi-Objective Bayesian Optimization via Orthogonal Search Directions

Tung Lam Ngo · Huong Ha · Jeffrey Chan · Hongyu Zhang

Omnipresent Yet Overlooked: Heat Kernels in Combinatorial Bayesian Optimization

Colin Doumont · Victor Picheny · Viacheslav (Slava) Borovitskiy · Henry Moss

Coresets for Clustering Under Stochastic Noise

Lingxiao Huang · Zhize Li · Nisheeth K. Vishnoi · Runkai Yang · Haoyu Zhao

Go to Event Page

Creative AI Session 1

Marcelo Coelho · Luba Elliott · Priya Prakash · Yingtao Tian

11:00 AM - 2:00 PM

23 Events in this session

AI as intermediary in modern-day ritual: An immersive, interactive production of the roller disco musical Xanadu at UCLA

Mira Winick · Naisha Agarwal · Chiheb Boussema · Ingrid Lee · Camilo Vargas · Jeff Burke

AI is Misled by GenAI: Stylistic Bias in Automated Assessment of Creativity in Large Language Models

Marek Urban · Petra Kmoníčková · Kamila Urban

CoTextor: Training-Free Modular Multilingual Text Editing via Layered Disentanglement and Depth-Aware Fusion

Zhenyu Yu · MOHD IDRIS · Pei Wang · Rizwan Qureshi

Digital Plankton

Vit Ruzicka

Echoes of Humanity: Exploring the Perceived Humanness of AI Music

Flavio Figueiredo · Giovanni Martinelli · Henrique Sousa · Pedro Rodrigues · Frederico Pedrosa · Lucas Ferreira

EmoNest: Crafting Emotionally-Adaptive Experiences with Generative AI

Yue Huang · Siyuan Wu

EMPATHIA: Multi-Faceted Human-AI Collaboration for Refugee Integration

Mohamed Rayan Barhdadi · Mehmet Tuncel · Erchin Serpedin · Hasan Kurban

Evaluating In Silico Creativity: An Expert Review of AI Chess Compositions

Vivek Veeriah · Federico Barbero · Marcus Chiam · Xidong Feng · Michael Dennis · Ryan Pachauri · Thomas Tumiel · Johan Obando Ceron · Jiaxin Shi · Shaobo Hou · Satinder Singh · Nenad Tomasev · Tom Zahavy

How Foundation Models are Reshaping Non-Invasive Brain–Computer Interfaces: A Case for Novel Human Expression and Alignment

Albert Barque Duran · Ada M. Llauradó Crespo

Interactive Artistic Text-To-Voice: Tungnaá and Bla Blavatar vs Jaap Blonk

Victor Shepardson · Jonathan Reus · Thor Magnusson

Large-Scale Training Data Attribution for Music Generative Models via Unlearning

Woosung Choi · Junghyun Koo · Kin Wai Cheuk · Joan Serrà · Marco Martínez-Ramírez · Yukara Ikemiya · Naoki Murata · Yuhta Takida · Wei-Hsiang Liao · Yuki Mitsufuji

Melody Slot Machine III for Automatic Fingering Saxophone using Servomotors

Masatoshi Hamanaka · Gou Koutaki

Orchestrating Emergent Storytelling with Embodied Multi-Agent Systems

Parag Mital · Seth Rosetter · Arturo Prieto · Jacobo Heredia · Breanna Browning

Painting with Paintings

Vikram Jamwal · Jeripothula Prudviraj · Abhishek Dangeti

Plan Before You Write: Improve LLM writing by planning

Yoad Lewenberg · Hila Sheftel · Yael Karov

Real-Time Intuitive AI Drawing System for Collaboration: Enhancing Human Creativity through Formal and Contextual Intent Integration

Jookyung Song · Mookyoung Kang · Nojun Kwak

Stroke Patches: Customizable Artistic Image Styling Using Regression

Ian Jaffray · John Bronskill

Surface Tension

Karyn Nakamura

Synthaesthetic Art: Human-Machine Creative Collaboration

Justin Baird · Ivy Chen · Jookyung Song · Mookyoung Kang · Richard J Savery

The Anemoia Device: A Tangible AI System for the Co-creation of Synthetic Memories through Scent

Cyrus Clarke · Jianing Yu · Melo Chen · Yuen Zou · Hiroshi Ishii

The Ghost in the Keys: A Disklavier Demo for Human-AI Musical Co-Creativity

Louis Bradshaw · Alexander Spangher · Stella Biderman · Simon Colton

The Stochastic Parrot: a physical AI Cohabitant

Ethan Chang · Quincy Kuang · Marcelo Coelho

The Sublime Ordinary: A Tool for Analysing Temporal City Soundscapes

Elina Oikonomaki · Lukas Debiasi

Go to Event Page

Panel

Design for Intelligence: Humans, Machines and Nature in Emergent Co-Creation

Jenn Leung · Chloe Loewith · Vit Ruzicka · Katie Hofstadter · Memo Akten · Dünya Baradari · Diana Mykhaylychenko

11:00 AM - 12:00 PM

What counts as intelligence when it is not human shaped, not aesthetic, not narrative and not computational? This panel explores Design for Intelligence as a continuation of earlier work on Intelligent Creative, where creative systems first began to perceive, adapt and evolve, revealing beauty as an emergent property of context and behaviour. It asks how systems create new knowledge through behaviour, relation and experience before that knowledge becomes symbolic or computational. The session examines works that move beyond top down design into living relational intelligence across human, artificial and non human environments.

... more

Expo Workshop

Multi-Agent Systems in Industry: From Research to Real-World Impact

Jinsung Yoon · Chen-Yu Lee · Tomas Pfister

12:00 PM - 1:30 PM

This workshop will bridge the gap between the theoretical advancements in multi-agent systems and their practical applications in industry. The session will feature a series of poster presentations showcasing state-of-the-art, real-world multi-agent systems that are driving innovation across various sectors. We will delve into the challenges and opportunities of deploying these systems at scale, covering topics such as:x000D
Human-in-the-loop collaboration: Designing systems where AI agents and human experts work in synergy.x000D
Scalability and efficiency: Architecting multi-agent systems for large-scale industrial applications.x000D
Safety and reliability: Ensuring the robustness and predictability of autonomous agents in critical systems.x000D
Domain-specific applications: Highlighting successful implementations in areas such as software engineering, scientific research, and creative content generation.x000D
The goal of this workshop is to foster a discussion on the practical challenges and future directions of multi-agent systems, providing attendees with actionable insights and a deeper understanding of how these technologies are shaping the future of industry.

... more

Expo Workshop

On Device/Edge AI

Cemal Bilgin · Mathias Lechner · MItesh Patel · Varun Khare · Yagil Burowski · Vijay Janapa Reddi · Felix Baum · Andrey Tovchigrechko · Karan Goel

12:00 PM - 1:30 PM

From smartphones and wearables to autonomous vehicles, robots, and AR/VR systems, the demand for models that are efficient, private, and adaptive in real-time has never been higher. Yet deploying state-of-the-art AI at the edge remains challenging: researchers and practitioners must navigate heterogeneous hardware, memory and power constraints, compression and distillation trade-offs, as well as privacy, safety, and reliability requirements.

This workshop will bring together researchers, practitioners, and industry leaders to explore the frontiers of Edge AI. Topics will include lightweight model architectures, compiler/toolchain optimizations (e.g., quantization, pruning, sparsity), advances in frameworks such as ExecuTorch and TensorRT, distributed learning across devices, privacy-preserving training, and emerging applications where latency and trust are critical. Beyond technical advances, we will examine the broader implications for democratizing AI—enabling billions of devices to act as intelligent, personalized agents while reducing dependence on the cloud.

... more

Expo Workshop

AI Assistants in the Wild: Agents, Adaptation, and Memory-Augmented Deployment

Fatih Porikli

12:00 PM - 1:30 PM

Motivation and Scope
Generative AI is evolving from offline, single modality models into interactive agentic systems that perceive, decide, and act in the real world. This shift marks a transition from static generation to dynamic, context-aware interaction. As these systems move toward deployment on edge devices such as mobile phones, augmented reality glasses, and robots, they face constraints in compute, memory, and latency. Beyond efficiency and responsiveness, a new frontier is emerging: agents equipped with persistent memory that enables long-term adaptation and personalization.

This workshop explores a timely and focused question. How do we build generative agents that are not only efficient and responsive but also able to accumulate, recall, and adapt based on personal memory over time? We aim to bring together perspectives from generative modeling, agentic learning, efficient model design, and memory systems to close the gap between lab scale prototypes and real-world deployment. x000D
x000D
Key Themes x000D
Personal Memory Systems for AI Assistants: Architectures for persistent memory, retrieval-augmented generation, and long-term personalization. x000D
Real-World Adaptation Few-shot generalization, continual learning, and task inference for evolving agent behavior. x000D
Grounded and Trustworthy Generation: Techniques for hallucination mitigation, constraint-aware generation, and safety under uncertainty. x000D
Deployment on Edge Platforms: Challenges and solutions for deploying generative agents on mobile, AR, and robotics platforms. x000D
x000D
This focused workshop aligns with emerging themes at NeurIPS including agentic learning, trustworthy AI, efficient multimodal generation, and embodied intelligence. It will spotlight the systems, algorithms, and design decisions needed to make generative AI truly adaptive and persistent, outside the data center and into the wild.

... more

Expo Workshop

Using the Virtual Cell Platform to Accelerate Machine Learning in Biology

Liz Fahsbender · Steve Herrin · Catherine Stolitzka · Manasa Venkatakrishnan · Zachary DeBruine

12:00 PM - 1:30 PM

Biology presents some of the most complex and high-impact challenges for machine learning, and single-cell transcriptomics is at the frontier of this work. In this workshop, we introduce the Virtual Cell Platform (VCP), a unified environment designed to accelerate model development and evaluation in biology. Using single-cell transcriptomics as a case study, we will demonstrate how the VCP enables researchers to train, benchmark, and interpret models in a reproducible and biologically meaningful way.

Participants will gain a primer on single-cell transcriptomics and learn how to evaluate models with cz-benchmarks, an open-source Python package providing standardized, community-driven tasks and metrics. Through the VCP CLI, attendees will pull datasets, run packaged models, and compare results programmatically. Hands-on exercises will guide participants through interactive visualizations, side-by-side model comparisons, and deep dives into model behavior using VCP’s no-code interface and BYOD (Bring Your Own Data) module.

By the end of the session, attendees will understand how to use the VCP to actively test and refine models during development, ensure biological relevance, and contribute models and benchmarks back to the community. This workshop highlights how the Virtual Cell Platform transforms ML infrastructure into a one-stop, researcher-friendly ecosystem, empowering the NeurIPS community to push the boundaries of AI in biology.

... more

Affinity Workshop

Indigenous in AI/ML

Mason Grimshaw · Andrea Delgado-Olson · Michelle L Brown

1:30 PM - 5:30 PM

Test Of Time

Test of Time Award

Shaoqing Ren · Kaiming He · Ross Girshick · Jian Sun

2:00 PM - 2:30 PM

Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks (Test of Time Award) haoqing Ren, Kaiming He, Ross Girshick, Jian Sun

Paper Abstract: State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet and Fast R-CNN have reduced the running time of these detection networks, exposing region proposal computation as a bottleneck. In this work, we introduce a Region Proposal Network (RPN) that shares full-image convolutional features with the detection network, thus enabling nearly cost-free region proposals. An RPN is a fully-convolutional network that simultaneously predicts object bounds and objectness scores at each position. RPNs are trained end-to-end to generate high-quality region proposals, which are used by Fast R-CNN for detection. With a simple alternating optimization, RPN and Fast R-CNN can be trained to share convolutional features. For the very deep VGG-16 model, our detection system has a frame rate of 5fps (including all steps) on a GPU, while achieving state-of-the-art object detection accuracy on PASCAL VOC 2007 (73.2% mAP) and 2012 (70.4% mAP) using 300 proposals per image. Code is available at https://github.com/ShaoqingRen/faster_rcnn.

... more

Invited Talk

Are We Having the Wrong Nightmares About AI?

Zeynep Tufekci

2:30 PM - 3:30 PM

Though seemingly opposite, doom and optimism regarding generative AI's spectacular rise both center on AGI or even superintelligence as a pivotal moment. But generative AI operates in a distinct manner from human intelligence, and it’s not a less intelligent human on a chip slowly getting smarter anymore than cars were mere horseless carriages. It must be understood on its own terms. And even if Terminator isn’t coming to kill us or superintelligence isn’t racing to save us, generative AI does bring profound challenges, well-beyond usual worries such as employment effects. Technology facilitates progress by transforming the difficult into easy, the rare into ubiquitous, the scarce into abundant, the manual into automated, and the artisan into mass-produced. While potentially positive long-term, these inversions are extremely destabilizing during the transition, shattering the correlations and assumptions of our social order that relied on superseded difficulties as mechanisms of proof, filtering, sorting and signaling. For example, while few would dispute the value of the printing press or books, their introduction led to such destructive upheaval that the resulting religious wars caused proportionally more deaths than all other major wars and pandemics since combined. Historically, a new technology's revolutionary impact comes from making what's already possible and desired cheap, easy, fast, and large-scale, not from outdated or ill-fitting benchmarks that technologists tend to focus on. As such, Artificial Good-Enough Intelligence can unleash chaos and destruction long before, or if ever, AGI is reached. Existing AI is good enough to blur or pulverize our existing mechanisms of proof of accuracy, effort, veracity, authenticity, sincerity, and even humanity. The tumult from such a transition will require extensive technological, regulatory, and societal effort to counter. But the first step to getting started is having the right nightmares.

... more

Speaker Bio

Zeynep Tufekci - Henry G. Bryant Professor of Sociology and Public Affairs, Princeton University; New York Times Columnist. Tufekci examines the interplay of science, technology and society through a sociological framework and complex systems lens, focusing especially on digital, computational, and artificial intelligence technologies. She was a 2022 Pulitzer Prize finalist for commentary on the COVID-19 pandemic. Her book "Twitter and Tear Gas: The Power and Fragility of Networked Protest" examines the dynamics of social movements in the digital age. She is also faculty associate at the Berkman Klein Center for Internet & Society at Harvard University.

... more

Oral

Oral 2B Deep Learning 1

3:30 PM - 4:30 PM

3 Events in this session

A multiscale analysis of mean-field transformers in the moderate interaction regime

Giuseppe Bruno · Federico Pasqualotto · Andrea Agazzi

The emergence of sparse attention: impact of data distribution and benefits of repetition

Nicolas Zucchet · Francesco D'Angelo · Andrew Lampinen · Stephanie Chan

From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics

Zheng-An Chen · Tao Luo

Go to Event Page

Oral

Oral 2A Multimodal 2

3:30 PM - 4:30 PM

3 Events in this session

Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

Xiangyu Zhao · Peiyuan Zhang · Kexian Tang · Xiaorong Zhu · Hao Li · Wenhao Chai · Zicheng Zhang · Renqiu Xia · Guangtao Zhai · Junchi Yan · Hua Yang · Xue Yang · Haodong Duan

CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding

hongyong han · Wei Wang · Gaowei Zhang · Mingjie Li · Yi Wang

OpenHOI: Open-World Hand-Object Interaction Synthesis with Multimodal Large Language Model

Zhenhao Zhang · Ye Shi · Lingxiao Yang · Suting Ni · Qi Ye · Jingya Wang

Go to Event Page

Oral

Oral 2E Theory 2

3:30 PM - 4:30 PM

3 Events in this session

Agnostic Active Learning Is Always Better Than Passive Learning

Steve Hanneke

Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks

Andrea Montanari · Pierfrancesco Urbani

Tighter CMI-Based Generalization Bounds via Stochastic Projection and Quantization

Milad Sefidgaran · Kimia Nadjahi · Abdellatif Zaidi

Go to Event Page

Oral

Oral 2D Application 1

3:30 PM - 4:30 PM

3 Events in this session

PhySense: Sensor Placement Optimization for Accurate Physics Sensing

Yuezhou Ma · Haixu Wu · Hang Zhou · Huikun Weng · Jianmin Wang · Mingsheng Long

TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability

Tonglong Wei · Yan Lin · Zeyu Zhou · Haomin Wen · Jilin Hu · Shengnan Guo · Youfang Lin · Gao Cong · Huaiyu Wan

OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata

Oussema Dhaouadi · Riccardo Marin · Johannes Meier · Jacques Kaiser · Daniel Cremers

Go to Event Page

Oral

Oral 2C Reinforcement/State-space 1

3:30 PM - 4:30 PM

3 Events in this session

PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models

Ruiqi Wang · Dezhong Zhao · Ziqin Yuan · Tianyu Shao · Guohua Chen · Dominic Kao · Sungeun Hong · Byung-Cheol Min

Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks

Korneel Van den Berghe · Stein Stroobants · Vijay Janapa Reddi · Guido de Croon

SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding

Yuan Zang · Zitian Tang · Junho Cho · Jaewook Yoo · Chen Sun

Go to Event Page

Expo Talk Panel

Building the Open AI Ecosystem: Models, Infrastructure and Community Adoption

Becky Sosnov

4:30 PM - 5:30 PM

Openness is becoming as important as scale in advancing AI. This panel brings together leaders from research, industry, and infrastructure to examine the rise of open-weight frontier models and what they enable.

Discussion will focus on the challenges of training and aligning these systems, their impact on reproducibility and safety, and the new forms of collaboration they support across academia, government, and enterprise.

Attendees will gain a clear view of how open access is reshaping AI development and deployment worldwide.

... more

Expo Talk Panel

The Co-X Framework: Versatile AI Agents for Automating and Augmenting Professional Workflows

Chen-Yu Lee · Jinsung Yoon · Yale Song · Tomas Pfister

4:30 PM - 5:30 PM

Beyond monolithic models, the future of AI in industry lies in specialized agents that collaborate with human experts. This talk introduces the "Co-X" framework, a novel approach for creating a diverse ecosystem of collaborative agents tailored to specific professional domains. We will present four key agents built on this framework: the Co-AI Researcher, the Co-ML Engineer for automating software development cycles, the Co-Data Scientist for automating data analysis and insight generation, and the Co-Director for augmenting creative content generation. We will discuss the foundational technologies that enable this versatility—including long-term memory, tool use, and human-in-the-loop feedback—and demonstrate how the Co-X framework is poised to redefine productivity and innovation across industries.

... more

Panel

Art Content Creation: When demands are met by pipelines (or not)

Zhuodi Cai · Ziyu Xu · Judah Goldfeder · Jiong Lin · Yonghyun Kim · Yuki Mitsufuji

4:30 PM - 5:30 PM

As creative projects grow in scale and complexity, artists increasingly rely on pipelines that span concept, production, and delivery. This need has become even more pronounced with the rise of powerful creative AI models. This panel explores how artists and technologists design holistic, end-to-end workflows that can hold both the promise and the volatility of generative systems. From enabling new ideas to managing intricate processes, each project reveals what is gained and what becomes fragile when automation, iteration, and human judgment converge. The discussion looks at the practical and philosophical lessons learned from building these pipelines and considers how they reshape creative agency and the emerging aesthetics of AI-assisted work.

... more

Creative AI Session 2

Marcelo Coelho · Luba Elliott · Priya Prakash · Yingtao Tian

4:30 PM - 7:30 PM

22 Events in this session

Assembloid Agency: Unreal Engine API for brain-on-a-chip platforms

Jenn Leung · Chloe Loewith

Best Friends Forever

Robert Twomey · Jesse Fleming

Brushes in Motion: Vector Guided Strokes for Computational Painting

Jeripothula Prudviraj · Vikram Jamwal

Cultural Alien Sampler: Open-ended Art Generation Balancing Originality and Coherence

Alejandro Hernandez Artiles · Hiromu Yakura · Levin Brinkmann · Mar Canet Sola · Hassan Alhaija · Ignacio Serna · Nasim Rahaman · Bernhard Schölkopf · Iyad Rahwan

Go witheFlow: Real-time Emotion Driven Audio Effects Modulation

Eddie Dervakos · Spyridon Kantarelis · Vassilis Lyberatos · Jason Liartis · Giorgos Stamou

Human-Machine Ritual: Synergic Performance through Real-Time Motion Recognition

Zhuodi Cai · Ziyu Xu · Juan Pampin

Knolling Bot: Teaching Robots the Human Notion of Tidiness

Yuhang Hu · Judah Goldfeder · Zhizhuo Zhang · Xinyue Zhu · Ruibo Liu · Philippe Wyder · Jiong Lin · Hod Lipson

Learning to Move with Style: Few-Shot Cross-Modal Style Transfer for Creative Robot Motion Generation

Kieran Woodward · Alicia Falcon-Caro · Steve Benford

LLMscape

Gottfried Haider · Jie Zhang

LUMIA: A Handheld Vision-to-Music System for Real-Time, Embodied Composition

Connie Cheng · Chung-Ta Huang

LUMIA: A Handheld Vision-to-Music System for Real-Time, Embodied Composition

Connie Cheng · Chung-Ta Huang

MCP-Driven Parametric Modeling: Integrating LLM Agents into Architectural and Landscape Design Workflows

Xun Liu · Runjia Tian

Music Arena: Live Evaluation for Text-to-Music

Yonghyun Kim · Wayne Chi · Anastasios Angelopoulos · Wei-Lin Chiang · Koichi Saito · Shinji Watanabe · Yuki Mitsufuji · Chris Donahue

Musings on AI Muses: Support for Human Creativity

John Richards · Jacquelyn Martino · Rachel Bellamy · Michael Muller

My AI Agent Feels Gray on Her Period

Leigh Levinson · Christopher Agostino · Nan Hu

Panel-by-Panel Souls: A Performative Workflow for Expressive Faces in AI-Assisted Manga Creation

Qing Zhang · JING HUANG · Yifei Huang · Jun Rekimoto

ProGress: Structured Music Generation via Graph Diffusion and Hierarchical Music Analysis

Stephen Ni-Hahn · Chao Yang · Mingchen Ma · Cynthia Rudin · Simon Mak · Yue Jiang

Prompt-Character Divergence: A Responsibility Compass for Human-AI Creative Collaboration

Maggie Wang · Wouter Haverals

Sound Clouds: Exploring ambient intelligence in public spaces to elicit deep human experience of awe, wonder, and beauty

Chengzhi Zhang · Dashiel Carrera · Daksh Kapoor · Jasmine Kaur · Jisu Kim · Brian Magerko

‘Studies for’ : A Human-AI Co-Creative Sound Artwork Using a Real-time Multi-channel Sound Generation Model

Chihiro Nagashima · Akira Takahashi · Zhi Zhong · Shusuke Takahashi · Yuki Mitsufuji

Visualizing Our Changing Earth: A Creative AI Framework for Democratizing Environmental Storytelling Through Satellite Imagery

Zhenyu Yu · MOHD IDRIS · Pei Wang

yammer

Tina Tallon

Go to Event Page

Expo Talk Panel

Cosmos World Foundation Model Platform for Physical AI

Ming-Yu Liu · James Dickerson

4:30 PM - 5:30 PM

Abstract: In this talk, I will introduce NVIDIA Cosmos, our World Foundation Model platform designed to advance Physical AI. Cosmos is built around three core pillars: Predict, Transfer, and Reason. I will provide updates on the latest releases—Predict 2.5 and Transfer 2.5—highlighting key improvements in generalization, efficiency, and scalability. In addition, I will share a preview of ongoing research directions that extend Cosmos toward richer world modeling and reasoning capabilities. Together, these developments aim to push the boundaries of how AI perceives, simulates, and interacts with complex real-world environments.

... more

Expo Talk Panel

Juries, Not Judges! Industry-Scale Evaluation of Trustworthy AI via Dynamic LLM Panels

Freddy Lecue

4:30 PM - 5:30 PM

As Large Language Models (LLMs) become central to high-stakes applications, the reliability of their evaluation systems is under intense scrutiny, especially in the financial industry. Traditional approaches - human annotation, single LLM judges, and static model juries - struggle to balance scalability, cost, and trustworthiness. We will discuss a promising framework: LLM Jury-on-Demand, a dynamic, learning-based framework that assembles an optimal panel of LLM evaluators for each task instance, leveraging predictive modeling to select and weight judges based on context-specific reliability. Our system adapts in real time, outperforming static ensembles and single judges in alignment with human expert judgment across summarization and retrieval-augmented generation benchmarks. This talk will showcase how adaptive LLM juries can transform evaluation of AI systems, offering robust, scalable, and context-aware solutions for industry and research. Attendees will gain practical insights into building trustworthy LLM evaluation pipelines, see live demos, and discuss future directions for reliable AI assessment in critical domains.

... more

Poster

San Diego Poster Session 2

4:30 PM - 7:30 PM

940 Events in this session

KARMA: Leveraging Multi-Agent LLMs for Automated Knowledge Graph Enrichment

Yuxing Lu · Wei Wu · Xukai Zhao · Rui Peng · Jinzhuo Wang

Monoculture or Multiplicity: Which Is It?

Mila Gorecki · Moritz Hardt

MultiScale Contextual Bandits for Long Term Objectives

Richa Rastogi · Yuta Saito · Thorsten Joachims

Direct Alignment with Heterogeneous Preferences

Ali Shirali · Arash Nasr-Esfahany · Abdullah Alomar · Parsa Mirtaheri · Rediet Abebe · Ariel Procaccia

MetaMind: Modeling Human Social Thoughts with Metacognitive Multi-Agent Systems

Xuanming Zhang · Yuxuan Chen · Samuel (Min-Hsuan) Yeh · Sharon Li

From Replication to Redesign: Exploring Pairwise Comparisons for LLM-Based Peer Review

Yaohui Zhang · Haijing ZHANG · Wenlong Ji · Tianyu Hua · Nick Haber · Hancheng Cao · Weixin Liang

Audits Under Resource, Data, and Access Constraints: Scaling Laws For Less Discriminatory Alternatives

Sarah Cen · Salil Goyal · Zaynah Javed · Ananya Karthik · Percy Liang · Daniel Ho

Smoothed Differentiation Efficiently Mitigates Shattered Gradients in Explanations

Adrian Hill · Neal McKee · Johannes Maeß · Stefan Bluecher · Klaus-Robert Müller

Sparse Autoencoders Learn Monosemantic Features in Vision-Language Models

Mateusz Pach · Shyamgopal Karthik · Quentin Bouniot · Serge Belongie · Zeynep Akata

Unifying Attention Heads and Task Vectors via Hidden State Geometry in In-Context Learning

Haolin Yang · Hakaze Cho · Yiqiao Zhong · Naoya Inoue

Cross City Traffic Flow Generation via Retrieval Augmented Diffusion Model

Yudong Li · Jingyuan Wang · Xie Yu · Peiyu Wang · Qian Huang

Can Large Language Models Master Complex Card Games?

Wei Wang · Fuqing Bie · Junzhe Chen · Dan Zhang · Shiyu Huang · Evgeny Kharlamov · Jie Tang

Proxy-SPEX: Sample-Efficient Interpretability via Sparse Feature Interactions in LLMs

Landon Butler · Abhineet Agarwal · Justin Kang · Yigit Efe Erginbas · Bin Yu · Kannan Ramchandran

From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit

Valérie Costa · Thomas Fel · Ekdeep S Lubana · Bahareh Tolooshams · Demba Ba

Performative Validity of Recourse Explanations

Gunnar König · Hidde Fokkema · Timo Freiesleben · Celestine Mendler-Dünner · Ulrike Luxburg

Regression-adjusted Monte Carlo Estimators for Shapley Values and Probabilistic Values

R. Teal Witter · Yurong Liu · Christopher Musco

Make Information Diffusion Explainable: LLM-based Causal Framework for Diffusion Prediction

Wenbo Shang · Zihan Feng · Yang Yajun · Xin Huang

Unveiling Concept Attribution in Diffusion Models

Nguyen Hung-Quang · Hoang Phan · Khoa D Doan

Beyond Scalars: Concept-Based Alignment Analysis in Vision Transformers

Johanna Vielhaben · Dilyara Bareeva · Jim Berend · Wojciech Samek · Nils Strodthoff

FADRM: Fast and Accurate Data Residual Matching for Dataset Distillation

Jiacheng Cui · Xinyue Bi · Yaxin Luo · Xiaohan Zhao · Jiacheng Liu · Zhiqiang Shen

Data Mixture Optimization: A Multi-fidelity Multi-scale Bayesian Framework

Thomson Yen · Andrew Siah · Haozhe Chen · C. Guetta · Tianyi Peng · Hongseok Namkoong

LayerIF: Estimating Layer Quality for Large Language Models using Influence Functions

Hadi Askari · Shivanshu Gupta · Fei Wang · Anshuman Chhabra · Muhao Chen

Diversity as a Reward: Fine-Tuning LLMs on a Mixture of Domain-Undetermined Data

Zhenqing Ling · Daoyuan Chen · Liuyi Yao · Qianli Shen · Yaliang Li · Ying Shen

The Best Instruction-Tuning Data are Those That Fit

Dylan Zhang · Qirun Dai · Hao Peng

CovMatch: Cross-Covariance Guided Multimodal Dataset Distillation with Trainable Text Encoder

Yongmin Lee · Hye Won Chung

ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning

Shulin Huang · Linyi Yang · Yan Song · Shawn Chen · Leyang Cui · Ziyu Wan · Qingcheng Zeng · Ying Wen · Kun Shao · Weinan Zhang · Jun Wang · Yue Zhang

Rethinking Evaluation of Infrared Small Target Detection

Youwei Pang · Xiaoqi Zhao · Lihe Zhang · Huchuan Lu · Georges Fakhri · Xiaofeng Liu · Shijian Lu

Robust Distortion-Free Watermark for Autoregressive Audio Generation Models

Yihan Wu · Georgios Milis · Ruibo Chen · Heng Huang

Understanding challenges to the interpretation of disaggregated evaluations of algorithmic fairness

Stephen Pfohl · Natalie Harris · Chirag Nagpal · David Madras · Vishwali Mhasawade · Olawale Salaudeen · Awa Dieng · Shannon Sequeira · Santiago Arciniegas · Lillian Sung · Nnamdi Ezeanochie · Heather Cole-Lewis · Katherine Heller · Sanmi Koyejo · Alexander D'Amour

Unmasking Puppeteers: Leveraging Biometric Leakage to Expose Impersonation in AI-Based Videoconferencing

Danial Samadi Vahdati · Tai Nguyen · Ekta Prashnani · Koki Nagano · david luebke · Orazio Gallo · Matthew Stamm

Distillation Robustifies Unlearning

Bruce W, Lee · Addie Foote · Alex Infanger · Leni Shor · Harish Kamath · Jacob Goldman-Wetzler · Bryce Woodworth · Alex Cloud · Alexander Turner

A Unified Framework for Fair Graph Generation: Theoretical Guarantees and Empirical Advances

Zichong Wang · Zhipeng Yin · Wenbin Zhang

Training-Free Safe Denoisers for Safe Use of Diffusion Models

Mingyu Kim · Dongjun Kim · Amman Yusuf · Stefano Ermon · Mi Jung Park

StableGuard: Towards Unified Copyright Protection and Tamper Localization in Latent Diffusion Models

Haoxin Yang · Bangzhen Liu · Xuemiao Xu · Cheng Xu · Yuyang Yu · Zikai Huang · Yi Wang · Shengfeng He

RespoDiff: Dual-Module Bottleneck Transformation for Responsible & Faithful T2I Generation

Silpa Vadakkeeveetil Sreelatha · Sauradip Nag · Muhammad Awais · Serge Belongie · Anjan Dutta

ErrorTrace: A Black-Box Traceability Mechanism Based on Model Family Error Space

Chuanchao Zang · Xiangtao Meng · Wenyu Chen · Tianshuo Cong · Zha Yaxing · Dong Qi · Zheng Li · Shanqing Guo

Dynamic Risk Assessments for Offensive Cybersecurity Agents

Boyi Wei · Benedikt Stroebl · Jiacen Xu · Joie Zhang · Zhou Li · Peter Henderson

R&D-Agent-Quant: A Multi-Agent Framework for Data-Centric Factors and Model Joint Optimization

Yuante Li · Xu Yang · Xiao Yang · Xisen Wang · Weiqing Liu · Jiang Bian

AI Testing Should Account for Sophisticated Strategic Behaviour

Vojta Kovarik · Eric Chen · Sami Petersen · Alexis Ghersengorin · Vincent Conitzer

Embracing Contradiction: Theoretical Inconsistency Will Not Impede the Road of Building Responsible AI Systems

Gordon Dai · Yunze Xiao

LLMs Encode Harmfulness and Refusal Separately

Jiachen Zhao · Jing Huang · Zhengxuan Wu · David Bau · Weiyan Shi

On the Coexistence and Ensembling of Watermarks

Aleksandar Petrov · Shruti Agarwal · Philip Torr · Adel Bibi · John Collomosse

Learning Gradient Boosted Decision Trees with Algorithmic Recourse

Kentaro Kanamori · Ken Kobayashi · Takuya Takagi

Representational Difference Explanations

Neehar Kondapaneni · Oisin Mac Aodha · Pietro Perona

Fixing It in Post: A Comparative Study of LLM Post-Training Data Quality and Model Performance

Aladin Djuhera · Swanand Kadhe · Syed Zawad · Farhan Ahmed · Heiko Ludwig · Holger Boche

LogicTree: Improving Complex Reasoning of LLMs via Instantiated Multi-step Synthetic Logical Data

Zehao Wang · Lin Yang · Jie Wang · Kehan Wang · Hanzhu Chen · Bin Wang · Jianye Hao · Defu Lian · Bin Li · Enhong Chen

Extremely Simple Multimodal Outlier Synthesis for Out-of-Distribution Detection and Segmentation

Moru Liu · Hao Dong · Jessica Kelly · Olga Fink · Mario Trapp

Generating Informative Samples for Risk-Averse Fine-Tuning of Downstream Tasks

Heasung Kim · Taekyun Lee · Hyeji Kim · Gustavo De Veciana

HelpSteer3-Preference: Open Human-Annotated Preference Data across Diverse Tasks and Languages

Zhilin Wang · Jiaqi Zeng · Olivier Delalleau · Hoo-Chang Shin · Felipe Soares · Alexander Bukharin · Ellie Evans · Yi Dong · Oleksii Kuchaiev

SNEAKDOOR: Stealthy Backdoor Attacks against Distribution Matching-based Dataset Condensation

He Yang · Dongyi Lv · Song Ma · Wei Xi · Jizhong Zhao

Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving

Xuan Chen · Shiwei Feng · Zikang Xiong · Shengwei An · Yunshu Mao · Lu Yan · Guanhong Tao · Wenbo Guo · Xiangyu Zhang

Language Models Are Capable of Metacognitive Monitoring and Control of Their Internal Activations

Ji-An Li · Huadong Xiong · Robert Wilson · Marcelo G Mattar · Marcus K. Benna

Continuous Concepts Removal in Text-to-image Diffusion Models

Tingxu Han · Weisong Sun · Yanrong Hu · Chunrong Fang · Yonglong zhang · Shiqing Ma · Tao Zheng · Zhenyu Chen · Zhenting Wang

Setting $\varepsilon$ is not the Issue in Differential Privacy

Edwige Cyffers

Diffusion Federated Dataset

SEOKJU HAHN · Junghye Lee

Understanding and Improving Fast Adversarial Training against $l_0$ Bounded Perturbations

Xuyang Zhong · Yixiao Huang · Chen Liu

InvisibleInk: High-Utility and Low-Cost Text Generation with Differential Privacy

Vishnu Vinod · Krishna Pillutla · Abhradeep Guha Thakurta

Privacy amplification by random allocation

Moshe Shenfeld · Vitaly Feldman

GeoClip: Geometry-Aware Clipping for Differentially Private SGD

Atefeh Gilani · Naima Tasnim · Lalitha Sankar · Oliver Kosut

Impact of Dataset Properties on Membership Inference Vulnerability of Deep Transfer Learning

Marlon Tobaben · Hibiki Ito · Joonas Jälkö · Yuan He · Antti Honkela

Mitigating the Privacy–Utility Trade-off in Decentralized Federated Learning via f-Differential Privacy

Xiang Li · Chendi Wang · Buxin Su · Qi Long · Weijie Su

Data-Free Model Extraction for Black-box Recommender Systems via Graph Convolutions

Zeyu Wang · Yidan Song · Shihao Qin · Shanqing Yu · Yujin Huang · Qi Xuan · Xin Zheng

A Fair Federated Learning Method for Handling Client Participation Probability Inconsistencies in Heterogeneous Environments

Siyuan Wu · Yongzhe Jia · Haolong Xiang · Xiaolong Xu · Xuyun Zhang · Lianyong Qi · Wanchun Dou

Detoxifying Large Language Models via Autoregressive Reward Guided Representation Editing

Yisong Xiao · Aishan Liu · Siyuan Liang · Zonghao Ying · Xianglong Liu · Dacheng Tao

Online robust locally differentially private learning for nonparametric regression

Chenfei Gu · Qiangqiang Zhang · Ting Li · Jinhan Xie · Niansheng Tang

Analogy-based Multi-Turn Jailbreak against Large Language Models

Mengjie Wu · Yihao Huang · Zhenjun Lin · Kangjie Chen · Yuyang zhang · Yuhan Huang · Run Wang · Lina Wang

Reliable Decision‑Making via Calibration‑Oriented Retrieval‑Augmented Generation

Chaeyun Jang · Deukhwan Cho · Seanie Lee · Hyungi Lee · Juho Lee

Shape it Up! Restoring LLM Safety during Finetuning

ShengYun Peng · Pin-Yu Chen · Jianfeng Chi · Seongmin Lee · Duen Horng Chau

V-CECE: Visual Counterfactual Explanations via Conceptual Edits

Nikolaos Spanos · Maria Lymperaiou · Giorgos Filandrianos · Konstantinos Thomas · Athanasios Voulodimos · Giorgos Stamou

A Theory for Worst-Case vs. Average-Case Guarantees for LLMs

Noga Amit · Shafi Goldwasser · Orr Paradise · Guy Rothblum

From Counterfactuals to Trees: Competitive Analysis of Model Extraction Attacks

Awa Khouna · Julien Ferry · Thibaut Vidal

Human Texts Are Outliers: Detecting LLM-generated Texts via Out-of-distribution Detection

Cong Zeng · Shengkun Tang · Yuanzhou Chen · Zhiqiang Shen · Wenchao Yu · Xujiang Zhao · Haifeng Chen · Wei Cheng · Zhiqiang Xu

Why Do Some Language Models Fake Alignment While Others Don't?

Abhay Sheshadri · John Hughes · Julian Michael · Alex Mallen · Arun Jose · Fabien Roger

PolyGuard: Massive Multi-Domain Safety Policy-Grounded Guardrail Dataset

Mintong Kang · Zhaorun Chen · Chejian Xu · Jiawei Zhang · Chengquan Guo · Minzhou Pan · Ivan Revilla · Yu Sun · Bo Li

BackdoorDM: A Comprehensive Benchmark for Backdoor Learning on Diffusion Model

Weilin Lin · Nanjun Zhou · Yanyun Wang · Jianze Li · Hui Xiong · Li Liu

VMDT: Decoding the Trustworthiness of Video Foundation Models

Yujin Potter · Zhun Wang · Nicholas Crispino · Kyle Montgomery · Alexander Xiong · Ethan Chang · Francesco Pinto · Yuqi Chen · Rahul Gupta · Morteza Ziyadi · Christos Christodoulopoulos · Bo Li · Chenguang Wang · Dawn Song

WASP: Benchmarking Web Agent Security Against Prompt Injection Attacks

Ivan Evtimov · Arman Zharmagambetov · Aaron Grattafiori · Chuan Guo · Kamalika Chaudhuri

OS-Harm: A Benchmark for Measuring Safety of Computer Use Agents

Thomas Kuntz · Agatha Duzan · Hao Zhao · Francesco Croce · Zico Kolter · Nicolas Flammarion · Maksym Andriushchenko

Neither Valid nor Reliable? Investigating the Use of LLMs as Judges

Khaoula Chehbouni · Mohammed Haddou · Jackie CK Cheung · Golnoosh Farnadi

Sequentially Auditing Differential Privacy

Tomás González Lara · Mateo Dulce Rubio · Aaditya Ramdas · Mónica Ribero

IF-Guide: Influence Function-Guided Detoxification of LLMs

Zachary Coalson · Juhan Bae · Nicholas Carlini · Sanghyun Hong

GLSim: Detecting Object Hallucinations in LVLMs via Global-Local Similarity

Seongheon Park · Sharon Li

Harnessing the Computation Redundancy in ViTs to Boost Adversarial Transferability

Jiani Liu · Zhiyuan Wang · Zeliang Zhang · Chao Huang · Susan Liang · Yunlong Tang · Chenliang Xu

TimeWak: Temporal Chained-Hashing Watermark for Time Series Data

Zhi Wen Soi · Chaoyi Zhu · Fouad Abiad · Aditya Shankar · Jeroen Galjaard · Huijuan Wang · Lydia Chen

LoRO: Real-Time on-Device Secure Inference for LLMs via TEE-Based Low Rank Obfuscation

Gaojian Xiong · Yu Sun · Jianhua Liu · Jian Cui · Jianwei Liu

SAFEPATH: Preventing Harmful Reasoning in Chain-of-Thought via Early Alignment

Wonje Jeung · Yoon Sangyeon · Minsuk Kahng · Albert No

Removing Concepts from Text-to-Image Models with Only Negative Samples

Hanwen Liu · Yadong Mu

Many LLMs Are More Utilitarian Than One

Anita Keshmirian · Razan Baltaji · Babak Hemmatian · Hadi Asghari · Lav Varshney

Beyond Prediction: Managing the Repercussions of Machine Learning Applications

Aline Weber · Blossom Metevier · Yuriy Brun · Philip Thomas · Bruno Silva

MetaDefense: Defending Fine-tuning based Jailbreak Attack Before and During Generation

Weisen Jiang · Sinno Pan

DCcluster-Opt: Benchmarking Dynamic Multi-Objective Optimization for Geo-Distributed Data Center Workloads

Antonio Guillen-Perez · Avisek Naug · Vineet Gundecha · Sahand Ghorbanpour · Ricardo Luna Gutierrez · Ashwin Ramesh Babu · Munther Salim · Shubhanker Banerjee · Eoin Essink · Damien Fay · Soumyendu Sarkar

CLEVER: A Curated Benchmark for Formally Verified Code Generation

Amitayush Thakur · Jasper Lee · George Tsoukalas · Meghana Sistla · Matthew Zhao · Stefan Zetzsche · Greg Durrett · Yisong Yue · Swarat Chaudhuri

GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

Yuqi Zhou · Sunhao Dai · Shuai Wang · Kaiwen Zhou · Qinglin Jia · Jun Xu

Hierarchical Demonstration Order Optimization for Many-shot In-Context Learning

Yinhan He · Wendy Zheng · Song Wang · Zaiyi Zheng · Yushun Dong · Yaochen Zhu · Jundong Li

CodeMerge: Codebook-Guided Model Merging for Robust Test-Time Adaptation in Autonomous Driving

Huitong Yang · Zhuoxiao Chen · Fengyi Zhang · Zi Huang · Yadan Luo

Latent Retrieval Augmented Generation of Cross-Domain Protein Binders

Zishen Zhang · Xiangzhe Kong · Wenbing Huang · Yang Liu

Manipulating 3D Molecules in a Fixed-Dimensional E(3)-Equivariant Latent Space

Zitao Chen · Yinjun Jia · Zitong Tian · Wei-Ying Ma · Yanyan Lan

Towards precision protein-ligand affinity prediction benchmark: A Complete and Modification-Aware DAVIS Dataset

Ming Hsiu Wu · Ziqian Xie · Shuiwang Ji · Degui Zhi

DecoyDB: A Dataset for Graph Contrastive Learning in Protein-Ligand Binding Affinity Prediction

Yupu Zhang · Zelin Xu · Tingsong Xiao · Gustavo Seabra · Yanjun Li · Chenglong Li · Zhe Jiang

BOOM: Benchmarking Out-Of-distribution Molecular Property Predictions of Machine Learning Models

Evan Antoniuk · Shehtab Zaman · Tal Ben-Nun · Peggy Li · James Diffenderfer · Busra Sahin · Obadiah Smolenski · Everett Grethel · Tim Hsu · Anna Hiszpanski · Kenneth Chiu · Bhavya Kailkhura · Brian Van Essen

OligoGym: Curated Datasets and Benchmarks for Oligonucleotide Drug Discovery

Rachapun Rotrattanadumrong · Carlo De Donno

CheMixHub: Datasets and Benchmarks for Chemical Mixture Property Prediction

Ella Miray Rajaonson · Mahyar Rajabi Kochi · Luis Martin Mejia Mendoza · Mohamad Moosavi · Benjamin Sanchez-Lengeling

MonoLift: Learning 3D Manipulation Policies from Monocular RGB via Distillation

Ziru Wang · Mengmeng Wang · Guang Dai · Yongliu Long · Jingdong Wang

MetaFind: Scene-Aware 3D Asset Retrieval for Coherent Metaverse Scene Generation

Zhenyu Pan · Yucheng Lu · Han Liu

Constrained Diffusers for Safe Planning and Control

Jichen Zhang · Liqun Zhao · Antonis Papachristodoulou · Jack Umenberger

Optimizing Distributional Geometry Alignment with Optimal Transport for Generative Dataset Distillation

Xiao Cui · Yulei Qin · Wengang Zhou · Hongsheng Li · Houqiang Li

Language Modeling by Language Models

Junyan Cheng · Peter Clark · Kyle Richardson

Enhancing Diffusion-based Unrestricted Adversarial Attacks via Adversary Preferences Alignment

Kaixun Jiang · Zhaoyu Chen · HaiJing Guo · Jinglun Li · Jiyuan Fu · Pinxue Guo · Hao Tang · Bo Li · Wenqiang Zhang

SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning

Xinbin Yuan · Jian Zhang · Kaixin Li · Zhuoxuan Cai · Lujian Yao · Jie Chen · Enguang Wang · Qibin Hou · Jinwei Chen · Peng-Tao Jiang · Bo Li

Generation as Search Operator for Test-Time Scaling of Diffusion-based Combinatorial Optimization

Yang Li · Lvda Chen · Haonan Wang · Runzhong Wang · Junchi Yan

Stitch and Tell: A Structured Data Augmentation Method for Spatial Understanding

Yin Hang · Xiaomin He · Peiwen Yuan · Yiwei Li · Jiayi Shi · Wenxiao Fan · Shaoxiong Feng · Prof. Kan

ProfiX: Improving Profile-Guided Optimization in Compilers with Graph Neural Networks

Huiri Tan · Juyong Jiang · Jiasi Shen

3D-GSRD: 3D Molecular Graph Auto-Encoder with Selective Re-mask Decoding

Chang Wu · ZHIYUAN LIU · Wen Shu · Liang Wang · Yanchen Luo · Wenqiang Lei · Yatao Bian · Junfeng Fang · Xiang Wang

3D Interaction Geometric Pre-training for Molecular Relational Learning

Namkyeong Lee · Yunhak Oh · Heewoong Noh · Gyoung S. Na · Minkai Xu · Hanchen Wang · Tianfan Fu · Chanyoung Park

Aligning Transformers with Continuous Feedback via Energy Rank Alignment

Shriram Chennakesavalu · Frank Hu · Sebastian Ibarraran · Grant Rotskoff

UMA: A Family of Universal Models for Atoms

Brandon Wood · Misko Dzamba · Xiang Fu · Meng Gao · Muhammed Shuaibi · Luis Barroso-Luque · Kareem Abdelmaqsoud · Vahe Gharakhanyan · John Kitchin · Daniel Levine · Kyle Michel · Anuroop Sriram · Taco Cohen · Abhishek Das · Sushree Sahoo · Ammar Rizvi · Zachary Ulissi · Larry Zitnick

Multiscale guidance of protein structure prediction with heterogeneous cryo-EM data

Rishwanth Raghu · Axel Levy · Gordon Wetzstein · Ellen Zhong

Universally Invariant Learning in Equivariant GNNs

Jiacheng Cen · Anyi Li · Ning Lin · Tingyang Xu · Yu Rong · Deli Zhao · Zihe Wang · Wenbing Huang

High-order Equivariant Flow Matching for Density Functional Theory Hamiltonian Prediction

Seongsu Kim · Nayoung Kim · Dongwoo Kim · Sungsoo Ahn

Curriculum Model Merging: Harmonizing Chemical LLMs for Enhanced Cross-Task Generalization

Baoyi He · Luotian Yuan · Ying Wei · Fei Wu

Retrosynthesis Planning via Worst-path Policy Optimisation in Tree-structured MDPs

Mianchu Wang · Giovanni Montana

Geometric Mixture Models for Electrolyte Conductivity Prediction

Anyi Li · Jiacheng Cen · Songyou Li · Mingze Li · YANG YU · Wenbing Huang

SeasonBench-EA: A Multi-Source Benchmark for Seasonal Prediction and Numerical Model Post-Processing in East Asia

Mengxuan Chen · Li · Zou Ziheng · Fang Wang · Jinxiao Zhang · Runmin Dong · Juepeng Zheng · Haohuan Fu

SmokeViz: A Large-Scale Satellite Dataset for Wildfire Smoke Detection and Segmentation

Rey Koki · Michael McCabe · Dhruv Kedar · Josh Myers-Dean · Annabel Wade · Jebb Stewart · Christina Kumler-Bonfanti · Jed Brown

OceanBench: A Benchmark for Data-Driven Global Ocean Forecasting systems

Anass El Aouni · Quentin Gaudel · J. Emmanuel Johnson · REGNIER Charly · Julien Le Sommer · Simon van Gennip · ronan fablet · Marie Drevillon · Yann DRILLET · Pierre Le Traon

Partial Physics Informed Diffusion Model for Ocean Chlorophyll Concentration Reconstruction

Qianxun Xu · Zuchuan Li

Learning Urban Climate Dynamics via Physics-Guided Urban Surface–Atmosphere Interactions

Jiyang Xia · Fenghua Ling · Zhenhui Jessie Li · Junjie Yu · Hongliang Zhang · David Topping · LEI BAI · Zhonghua Zheng

Measuring Scientific Capabilities of Language Models with a Systems Biology Dry Lab

Haonan Duan · Stephen Lu · Caitlin F Harrigan · Nishkrit Desai · Jiarui Lu · Michał Koziarski · Leonardo Cotta · Chris Maddison

UniZyme: A Unified Protein Cleavage Site Predictor Enhanced with Enzyme Active-Site Knowledge

Chenao Li · Shuo Yan · Enyan Dai

Curly Flow Matching for Learning Non-gradient Field Dynamics

Katarina Petrović · Lazar Atanackovic · Viggo Moro · Kacper Kapusniak · Ismail Ilkan Ceylan · Michael Bronstein · Joey Bose · Alexander Tong

DIsoN: Decentralized Isolation Networks for Out-of-Distribution Detection in Medical Imaging

Felix Wagner · Pramit Saha · Harry Anthony · Alison Noble · Konstantinos Kamnitsas

SAM2Flow: Interactive Optical Flow Estimation with Dual Memory for in vivo Microcirculation Analysis

Luojie Huang · Ryan Zhang · Marisa Morakis · Michaela Taylor-Williams · Gregory McKay · Nicholas Durr

Better Tokens for Better 3D: Advancing Vision-Language Modeling in 3D Medical Imaging

Ibrahim Ethem Hamamci · Sezgin Er · Suprosanna Shit · Hadrien Reynaud · Dong Yang · Pengfei Guo · Marc Edgar · Daguang Xu · Bernhard Kainz · Bjoern Menze

Unleashing Foundation Vision Models: Adaptive Transfer for Diverse Data-Limited Scientific Domains

Qiankun Li · Feng He · Huabao Chen · Xin Ning · Kun Wang · Zengfu Wang

MIRA: Medical Time Series Foundation Model for Real-World Health Data

Hao Li · Bowen Deng · Chang Xu · ZhiYuan Feng · Viktor Schlegel · Yu-Hao Huang · Yizheng Sun · Jingyuan Sun · Kailai Yang · Yiyao Yu · Jiang Bian

FAPEX: Fractional Amplitude-Phase Expressor for Robust Cross-Subject Seizure Prediction

Ruizhe Zheng · Lingyan Mao · DINGDING HAN · Tian Luo · Yi Wang · Jing Ding · Yuguo Yu

BrainODE: Neural Shape Dynamics for Age- and Disease-aware Brain Trajectories

Wonjung Park · Suhyun Ahn · Maria Hernandez · Susana Maniega · Jinah Park

Offline Guarded Safe Reinforcement Learning for Medical Treatment Optimization Strategies

Runze Yan · Xun Shen · Akifumi Wachi · Sebastien Gros · Anni Zhao · Xiao Hu

Reinforcement Learning for Out-of-Distribution Reasoning in LLMs: An Empirical Study on Diagnosis-Related Group Coding

Hanyin Wang · Zhenbang Wu · Gururaj Kolar · Hariprasad Korsapati · Brian Bartlett · Bryan Hull · Jimeng Sun

ClinBench: A Standardized Multi-Domain Framework for Evaluating Large Language Models in Clinical Information Extraction

Ismael Villanueva Miranda · Zifan Gu · Donghan Yang · Kuroush Nezafati · Jingwei Huang · Peifeng Ruan · Xiaowei Zhan · Guanghua Xiao · Yang Xie

EndoBench: A Comprehensive Evaluation of Multi-Modal Large Language Models for Endoscopy Analysis

Shengyuan Liu · Boyun Zheng · Wenting Chen · Zhihao Peng · Zhenfei Yin · Jing Shao · Jiancong Hu · Yixuan Yuan

TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine

Jiacheng Xie · Yang Yu · Ziyang Zhang · Shuai Zeng · Jiaxuan He · Ayush Vasireddy · Xiaoting tang · Congyu Guo · Lening Zhao · Congcong Jing · Guanghui An · Dong Xu

CogPhys: Assessing Cognitive Load via Multimodal Remote and Contact-based Physiological Sensing

Anirudh Bindiganavale Harish · Peikun Guo · Bhargav Ghanekar · Diya Gupta · Akilesh Rajavenkatanarayan · MANOJ SHARMA · Maureen August · Akane Sano · Ashok Veeraraghavan

Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models

Christopher Chiu · Silviu Pitis · Mihaela van der Schaar

Bilevel Network Learning via Hierarchically Structured Sparsity

Jiayi Fan · Jingyuan Yang · Shuangge Ma · Mengyun Wu

From Likelihood to Fitness: Improving Variant Effect Prediction in Protein and Genome Language Models

Charles W J Pugh · Paulina Nuñez-Valencia · Mafalda Dias · Jonathan Frazer

LawShift: Benchmarking Legal Judgment Prediction Under Statute Shifts

Zhuo Han · Yi Yang · Yi Feng · Wanhong Huang · Ding Xuxing · Chuanyi Li · Jidong Ge · Vincent Ng

NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions

Weizhe Yuan · Jane Yu · Song Jiang · Karthik Padthe · Yang Li · Dong Wang · Ilia Kulikov · Kyunghyun Cho · Yuandong Tian · Jason Weston · Xian Li

C-SEO Bench: Does Conversational SEO Work?

Haritz Puerto · Martin Gubri · Tommaso Green · Seong Joon Oh · Sangdoo Yun

RESPIN-S1.0: A read speech corpus of 10000+ hours in dialects of nine Indian Languages

Saurabh Kumar · Abhayjeet Singh · DEEKSHITHA G · Amartya veer · Jesuraj Bandekar · Savitha Murthy · Sumit Sharma · Sandhya Badiger · Sathvik Udupa · Amala Nagireddi · Srinivasa Raghavan K M · Rohan Saxena · Jai Nanavati · Raoul Nanavati · Janani Sridharan · Arjun Mehta · Ashish S · Sai Mora · Prashanthi Venkataramakrishnan · Gauri Date · Karthika P · Prasanta Ghosh

MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark

Junjie Xing · Yeye He · Mengyu Zhou · Haoyu Dong · Shi Han · Lingjiao Chen · Dongmei Zhang · Surajit Chaudhuri · H. V. Jagadish

Distributional LLM-as-a-Judge

Luyu Chen · Zeyu Zhang · Haoran Tan · Quanyu Dai · Yang Hao · Zhenhua Dong · Xu Chen

Cypher-RI: Reinforcement Learning for Integrating Schema Selection into Cypher Generation

Hanchen Su · Xuyuan Li · Yan Zhou · zhuoyi lu · Ziwei Chai · Haozheng Wang · Chen Zhang · YANG YANG

Cooperative Retrieval-Augmented Generation for Question Answering: Mutual Information Exchange and Ranking by Contrasting Layers

Youmin Ko · Sungjong Seo · Hyunjoon Kim

GenPO: Generative Diffusion Models Meet On-Policy Reinforcement Learning

Shutong Ding · Ke Hu · Shan Zhong · Haoyang Luo · Weinan Zhang · Jingya Wang · Jun Wang · Ye Shi

Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task

Sunqi Fan · Jiashuo Cui · Meng-Hao Guo · Shuojin Yang

Conflict-Aware Knowledge Editing in the Wild: Semantic-Augmented Graph Representation for Unstructured Text

Zhange Zhang · Zhicheng Geng · Yuqing Ma · Tianbo Wang · Kai Lv · Xianglong Liu

Word-Level Emotional Expression Control in Zero-Shot Text-to-Speech Synthesis

Tianrui Wang · Haoyu Wang · Meng Ge · Cheng Gong · Chunyu Qiang · Ziyang Ma · Zikang Huang · Guanrou Yang · Xiaobao Wang · Eng-Siong Chng · Xie Chen · Longbiao Wang · Jianwu Dang

Latent Principle Discovery for Language Model Self-Improvement

Keshav Ramji · Tahira Naseem · Ramón Astudillo

Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models

Zekai Zhao · Qi Liu · Kun Zhou · Zihan Liu · Yifei Shao · Zhiting Hu · Biwei Huang

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

Junteng Liu · Yuanxiang Fan · Jiang Zhuo · Han Ding · Yongyi Hu · Chi Zhang · Yiqi Shi · Shitong Weng · Aili Chen · Shiqi Chen · Mozhi Zhang · Pengyu Zhao · Junxian He

Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization

Haotian Luo · Haiying He · Yibo Wang · Jinluan Yang · Rui Liu · Naiqiang Tan · Xiaochun Cao · Dacheng Tao · Li Shen

SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning

Rui Pan · Yinwei Dai · Zhihao Zhang · Gabriele Oliaro · Zhihao Jia · Ravi Netravali

Calibrating Translation Decoding with Quality Estimation on LLMs

Di Wu · Yibin Lei · Christof Monz

Better Estimation of the Kullback--Leibler Divergence Between Language Models

Afra Amini · Tim Vieira · Ryan Cotterell

Signal and Noise: A Framework for Reducing Uncertainty in Language Model Evaluation

David Heineman · Valentin Hofmann · Ian Magnusson · Yuling Gu · Noah Smith · Hanna Hajishirzi · Kyle Lo · Jesse Dodge

Can Dependencies Induced by LLM-Agent Workflows Be Trusted?

Yu Yao · Yiliao (Lia) Song · Yian Xie · Mengdan Fan · Mingyu Guo · Tongliang Liu

Self Iterative Label Refinement via Robust Unlabeled Learning

Hikaru Asano · Tadashi Kozuno · Yukino Baba

AudSemThinker: Enhancing Audio-Language Models Through Reasoning over Semantics of Sound

Gijs Wijngaard · Elia Formisano · Michele Esposito · Michel Dumontier

Bridging Sign and Spoken Languages: Pseudo Gloss Generation for Sign Language Translation

Jianyuan Guo · Peike Li · Trevor Cohn

SQLens: An End-to-End Framework for Error Detection and Correction in Text-to-SQL

Yue Gong · Chuan Lei · Xiao Qin · Kapil Vaidya · Balakrishnan Narayanaswamy · Tim Kraska

KVLink: Accelerating Large Language Models via Efficient KV Cache Reuse

Jingbo Yang · Bairu Hou · Wei Wei · Yujia Bao · Shiyu Chang

Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective Optimization

Chenrui Wang · Junyi Shu · Billy Chiu · YU LI · Saleh Alharbi · Min Zhang · Jing Li

MoME: Mixture of Matryoshka Experts for Audio-Visual Speech Recognition

Umberto Cappellazzo · Minsu Kim · Pingchuan Ma · Honglie Chen · Xubo Liu · Stavros Petridis · Maja Pantic

Steering When Necessary: Flexible Steering Large Language Models with Backtracking

Zifeng Cheng · Jinwei Gan · Zhiwei Jiang · Cong Wang · Yafeng Yin · Xiang Luo · Yuchen Fu · Qing Gu

Explainable Reinforcement Learning from Human Feedback to Improve Alignment

Shicheng Liu · Siyuan Xu · Wenjie Qiu · Hangfan Zhang · Minghui Zhu

FastLongSpeech: Enhancing Large Speech-Language Models for Efficient Long-Speech Processing

Shoutao Guo · Shaolei Zhang · Qingkai Fang · Zhengrui Ma · Min Zhang · Yang Feng

Private Training Large-scale Models with Efficient DP-SGD

Liangyu Wang · Junxiao Wang · Jie Ren · Zihang Xiang · David Keyes · Di Wang

RepoMaster: Autonomous Exploration and Understanding of GitHub Repositories for Complex Task Solving

Huacan Wang · Ziyi Ni · Shuo Zhang · Shuo Lu · Sen Hu · Ziyang He · Chen Hu · Jiaye Lin · Yifu Guo · Yuntao Du · Pin Lyu

T-SHIRT: Token-Selective Hierarchical Data Selection for Instruction Tuning

Yanjun Fu · Faisal Hamman · Sanghamitra Dutta

ARM: Adaptive Reasoning Model

Tinghui Zhu · Jian Xie · yikai zhang · Aili Chen · Kai Zhang · Yu Su · Yanghua Xiao

STSBench: A Large-Scale Dataset for Modeling Neuronal Activity in the Dorsal Stream of Primate Visual Cortex

Ethan Trepka · Ruobing Xia · Shude Zhu · Sharif Saleki · Danielle Lopes · Stephen Cital · Konstantin Willeke · Mindy Kim · Tirin Moore

Listening to the Brain: Multi-Band sEEG Auditory Reconstruction via Dynamic Spatio-Temporal Hypergraphs

Xueyi Zhang · Ruicong Wang · Jialu Sun · Siqi Cai · Haizhou Li

BrainMoE: Cognition Joint Embedding via Mixture-of-Expert Towards Robust Brain Foundation Model

Ziquan Wei · Tingting Dan · Tianlong Chen · Guorong Wu

Time-Masked Transformers with Lightweight Test-Time Adaptation for Neural Speech Decoding

Ebrahim Feghhi · Shreyas Kaasyap · Nima Hadidi · Jonathan Kao

Localist Topographic Expert Routing: A Barrel Cortex-Inspired Modular Network for Sensorimotor Processing

Tianfang Zhu · Dongli Hu · Jiandong Zhou · Kai Du · Anan LI

Scaling and context steer LLMs along the same computational path as the human brain

Joséphine Raugel · Jérémy Rapin · Stéphane d'Ascoli · Valentin Wyart · Jean-Remi King

Brain-tuning Improves Generalizability and Efficiency of Brain Alignment in Speech Models

Omer Moussa · Mariya Toneva

Multiplication-Free Parallelizable Spiking Neurons with Efficient Spatio-Temporal Dynamics

Peng Xue · Wei Fang · Zhengyu Ma · Zihan Huang · Zhaokun Zhou · Yonghong Tian · Timothée Masquelier · Huihui Zhou

$i$MIND: Insightful Multi-subject Invariant Neural Decoding

Zixiang Yin · Jiarui Li · Zhengming Ding

Versatile Transferable Unlearnable Example Generator

Zhihao Li · Jiale Cai · Gezheng Xu · Hao Zheng · Qiuyue Li · Fan Zhou · Shichun Yang · Charles Ling · Boyu Wang

Vision-and-Language Training Helps Deploy Taxonomic Knowledge but Does Not Fundamentally Alter It

Yulu Qin · Dheeraj Varghese · Adam Dahlgren Lindström · Lucia Donatelli · Kanishka Misra · Najoung Kim

BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity

Lucine L Oganesian · Saba Hashemi · Maryam Shanechi

MI-TRQR: Mutual Information-Based Temporal Redundancy Quantification and Reduction for Energy-Efficient Spiking Neural Networks

Dengfeng Xue · Wenjuan Li · Yifan Lu · chunfeng yuan · Yufan Liu · Wei Liu · Man Yao · Li Yang · Guoqi Li · Bing Li · Stephen Maybank · Weiming Hu · Zhetao Li

SPINT: Spatial Permutation-Invariant Neural Transformer for Consistent Intracortical Motor Decoding

Trung Le · Hao Fang · Jingyuan Li · Tung Nguyen · Lu Mi · Amy L Orsborn · Uygar Sümbül · Eli Shlizerman

TRACE: Contrastive learning for multi-trial time series data in neuroscience

Lisa Schmors · Dominic Gonschorek · Jan Niklas Böhm · Yongrong Qiu · Na Zhou · Dmitry Kobak · Andreas Tolias · Fabian Sinz · Jacob Reimer · Katrin Franke · Sebastian Damrich · Philipp Berens

Learning the Plasticity: Plasticity-Driven Learning Framework in Spiking Neural Networks

Guobin Shen · Dongcheng Zhao · Yiting Dong · Yang Li · Feifei Zhao · Yi Zeng

Intrinsic Goals for Autonomous Agents: Model-Based Exploration in Virtual Zebrafish Predicts Ethological Behavior and Whole-Brain Dynamics

Reece Keller · Alyn Kirsch · Felix Pei · Xaq Pitkow · Leo Kozachkov · Aran Nayebi

Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods

Dennis Wei · Inkit Padhi · Soumya Ghosh · Amit Dhurandhar · Karthikeyan Natesan Ramamurthy · Maria Chang

Solving Inequality Proofs with Large Language Models

Jiayi Sheng · Luna Lyu · Jikai Jin · Tanglin Xia · Alex Gu · James Zou · Pan Lu

The Impact of Coreset Selection on Spurious Correlations and Group Robustness

Amaya Dharmasiri · William Yang · Polina Kirichenko · Lydia Liu · Olga Russakovsky

miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward

Azim Ospanov · Farzan Farnia · Roozbeh Yousefzadeh

ATLAS: Autoformalizing Theorems through Lifting, Augmentation, and Synthesis of Data

Xiaoyang Liu · Kangjie Bao · Jiashuo Zhang · Yunqi Liu · Yu Chen · Yuntian Liu · Yang Jiao · Tao Luo

RePO: Understanding Preference Learning Through ReLU-Based Optimization

Junkang Wu · Kexin Huang · xue wang · Jinyang Gao · Bolin Ding · Jiancan Wu · Xiangnan He · Xiang Wang

State-Covering Trajectory Stitching for Diffusion Planners

Kyowoon Lee · Jaesik Choi

Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces

Jifeng Hu · Sili Huang · Li Shen · Zhejian Yang · Shengchao Hu · Shisong Tang · Hechang Chen · Lichao Sun · Yi Chang · Dacheng Tao

Online Optimization for Offline Safe Reinforcement Learning

Yassine Chemingui · Aryan Deshwal · Alan Fern · Thanh Nguyen-Tang · Jana Doppa

Hamiltonian Neural PDE Solvers through Functional Approximation

Anthony Zhou · Amir Barati Farimani

UGM2N: An Unsupervised and Generalizable Mesh Movement Network via M-Uniform Loss

Zhichao Wang · Xinhai Chen · Qinglin Wang · Xiang Gao · Qingyang Zhang · Menghan Jia · Xiang Zhang · Jie Liu

Information-Driven Design of Imaging Systems

Henry Pinkard · Leyla Kabuli · Eric Markley · Tiffany Chien · Jiantao Jiao · Laura Waller

Geometry Aware Operator Transformer as an efficient and accurate neural surrogate for PDEs on arbitrary domains

Shizheng Wen · Arsh Kumbhat · Levi Lingsch · Sepehr Mousavi · Yizhou Zhao · Praveen Chandrashekar · Siddhartha Mishra

Learning Chern Numbers of Multiband Topological Insulators with Gauge Equivariant Neural Networks

Longde Huang · Oleksandr Balabanov · Hampus Linander · Mats Granath · Daniel Persson · Jan Gerken

Geometric Algebra-Enhanced Bayesian Flow Network for RNA Inverse Design

Rubo Wang · Xingyu Gao · Peilin Zhao

FlowDAS: A Stochastic Interpolant-based Framework for Data Assimilation

Siyi Chen · Yixuan Jia · Qing Qu · He Sun · Jeffrey Fessler

Flow Field Reconstruction with Sensor Placement Policy Learning

Ruoyan Li · Guancheng Wan · Zijie Huang · Zixiao Liu · Haixin Wang · Xiao Luo · Wei Wang · Yizhou Sun

PhysGym: Benchmarking LLMs in Interactive Physics Discovery with Controlled Priors

Yimeng Chen · Piotr Piękos · Mateusz Ostaszewski · Firas Laakom · Jürgen Schmidhuber

RNNs perform task computations by dynamically warping neural representations

Arthur Pellegrino · Angus Chadwick

Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning

Yixiu Mao · Yun Qu · Qi Wang · Xiangyang Ji

LUNA: Efficient and Topology-Agnostic Foundation Model for EEG Signal Analysis

Berkay Döner · Thorir Mar Ingolfsson · Luca Benini · Yawei Li

Time-Evolving Dynamical System for Learning Latent Representations of Mouse Visual Neural Activity

Liwei Huang · Zhengyu Ma · Liutao Yu · Huihui Zhou · Yonghong Tian

Scalable inference of functional neural connectivity at submillisecond timescales

Arina Medvedeva · Edoardo Balzani · Alex Williams · Stephen Keeley

Improving Task-Specific Multimodal Sentiment Analysis with General MLLMs via Prompting

Haoyu Zhang · Yinan Zhang · Chaolong Ying · Xiaoying Tang · Tianshu Yu

Joint Modeling of fMRI and EEG Imaging Using Ordinary Differential Equation-Based Hypergraph Neural Networks

Yan Zhang · Yang Gao · Min Li

Bipolar Self-attention for Spiking Transformers

Shuai Wang · Malu Zhang · Jingya Wang · Dehao Zhang · Yimeng Shan · Jieyuan (Eric) Zhang · Yichen Xiao · Honglin Cao · Haonan Zhang · Zeyu Ma · Yang Yang · Haizhou Li

Meta-Learning Objectives for Preference Optimization

Carlo Alfano · Silvia Sapora · Jakob Foerster · Patrick Rebeschini · Yee Whye Teh

Learning Human-Like RL Agents Through Trajectory Optimization With Action Quantization

Jian-Ting Guo · Yu-Cheng Chen · Ping-Chun Hsieh · Kuo-Hao Ho · Po-Wei Huang · Ti-Rong Wu · I-Chen Wu

Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data

Lingkai Kong · Haichuan Wang · Tonghan Wang · GUOJUN XIONG · Milind Tambe

Unlocking Multimodal Mathematical Reasoning via Process Reward Model

Ruilin Luo · Zhuofan Zheng · Lei Wang · Yifan Wang · Xinzhe Ni · Zicheng Lin · Songtao Jiang · Yiyao Yu · Chufan Shi · Ruihang Chu · Jin zeng · Yujiu Yang

Periodic Skill Discovery

Jonghae Park · Daesol Cho · Jusuk Lee · Dongseok Shim · Inkyu Jang · H. Jin Kim

DeltaPhi: Physical States Residual Learning for Neural Operators in Data-Limited PDE Solving

Xihang Yue · Yi Yang · Linchao Zhu

INC: An Indirect Neural Corrector for Auto-Regressive Hybrid PDE Solvers

Hao Wei · Aleksandra Franz · Björn List · Nils Thuerey

PhySense: Sensor Placement Optimization for Accurate Physics Sensing

Yuezhou Ma · Haixu Wu · Hang Zhou · Huikun Weng · Jianmin Wang · Mingsheng Long

Emerging Risks from Embodied AI Require Urgent Policy Action

Jared Perlo · Alexander Robey · Fazl Barez · Jakob Mökander

LabUtopia: High-Fidelity Simulation and Hierarchical Benchmark for Scientific Embodied Agents

Rui Li · Zixuan Hu · Wenxi Qu · Jinouwen Zhang · Zhenfei Yin · Sha Zhang · Xuantuo Huang · Hanqing Wang · Tai WANG · Jiangmiao Pang · Wanli Ouyang · LEI BAI · Wangmeng Zuo · LINGYU DUAN · Dongzhan Zhou · SHIXIANG TANG

Robo2VLM: Improving Visual Question Answering using Large-Scale Robot Manipulation Data

Kaiyuan Eric Chen · Shuangyu Xie · Zehan Ma · Pannag Sanketi · Ken Goldberg

SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound

Yunke Ao · Masoud Moghani · Mayank Mittal · Manish Prajapat · Luohong Wu · Frederic Giraud · Fabio Carrillo · Andreas Krause · Philipp Fürnstahl

Quantization-Free Autoregressive Action Transformer

Ziyad Sheebaelhamd · Michael Tschannen · Michael Muehlebach · Claire Vernade

Model-Based Policy Adaptation for Closed-Loop End-to-end Autonomous Driving

Haohong Lin · Yunzhi Zhang · Wenhao Ding · Jiajun Wu · DING ZHAO

PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models

Ruiqi Wang · Dezhong Zhao · Ziqin Yuan · Tianyu Shao · Guohua Chen · Dominic Kao · Sungeun Hong · Byung-Cheol Min

Synthesizing Photorealistic and Dynamic Urban Environments for Multimodal Robot Navigation and Collaboration

Yan Zhuang · Jiawei Ren · Xiaokang Ye · Jianzhi Shen · Ruixuan Zhang · Tianai Yue · Muhammad Faayez · Xuhong He · Xiyan Zhang · Ziqiao Ma · Lianhui Qin · Zhiting Hu · Tianmin Shu

EgoBridge: Domain Adaptation for Generalizable Imitation from Egocentric Human Data

Ryan Punamiya · Dhruv Patel · Patcharapong Aphiwetsa · Pranav Kuppili · Lawrence Zhu · Simar Kareer · Judy Hoffman · Danfei Xu

FreqPolicy: Efficient Flow-based Visuomotor Policy via Frequency Consistency

Yifei Su · Ning Liu · Dong Chen · Zhen Zhao · Kun Wu · Meng Li · Zhiyuan Xu · Zhengping Che · Jian Tang

SAMPO: Scale-wise Autoregression with Motion Prompt for Generative World Models

Sen Wang · Jingyi Tian · Le Wang · Zhimin Liao · lijiayi · Huaiyi Dong · Kun Xia · Sanping Zhou · Wei Tang · Gang Hua

Act to See, See to Act: Diffusion-Driven Perception-Action Interplay for Adaptive Policies

Jing Wang · Weiting Peng · Jing Tang · Zeyu Gong · Xihua Wang · Bo Tao · Li cheng

Building 3D Representations and Generating Motions From a Single Image via Video-Generation

Weiming Zhi · Ziyong Ma · Tianyi Zhang · Matthew Johnson-Roberson

Toward Interpretable Evaluation Measures for Time Series Segmentation

Félix Chavelli · Paul Boniol · Michaël Thomazo

Learning Pattern-Specific Experts for Time Series Forecasting Under Patch-level Distribution Shift

Yanru Sun · Zongxia Xie · Emadeldeen Eldele · Dongyue Chen · Qinghua Hu · Min Wu

FlowNet: Modeling Dynamic Spatio-Temporal Systems via Flow Propagation

Yutong Feng · Xu Liu · Yutong Xia · Yuxuan Liang

Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series

Ching Chang · Jeehyun Hwang · Yidan Shi · Haixin Wang · Wei Wang · Wen-Chih Peng · Tien-Fu Chen

SynTSBench: Rethinking Temporal Pattern Learning in Deep Learning Models for Time Series

Qitai Tan · Yiyun Chen · Mo Li · Ruiwen Gu · Yilin Su · Xiao-Ping (Steven) Zhang

CLEAR: Command Level Annotated Dataset for Ransomware Detection

Barak Bringoltz · Elisha Halperin · Ran Feraru · Evgeny Blaichman · Amit Berman

4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration

Jiahui Zhang · Yurui Chen · Yueming Xu · Ze Huang · Yanpeng Zhou · Yu-Jie Yuan · Xinyue Cai · Guowei Huang · Xingyue Quan · Hang Xu · Li Zhang

PANGEA: Projection-Based Augmentation with Non-Relevant General Data for Enhanced Domain Adaptation in LLMs

Seungyoo Lee · Giung Nam · Moonseok Choi · Hyungi Lee · Juho Lee

Adaptive Surrogate Gradients for Sequential Reinforcement Learning in Spiking Neural Networks

Korneel Van den Berghe · Stein Stroobants · Vijay Janapa Reddi · Guido de Croon

Towards Realistic Earth-Observation Constellation Scheduling: Benchmark and Methodology

Luting Wang · Le Zhuo · Hongliang Huang · Dongjun Li · Chen Gao · Si Liu

Chain-of-Action: Trajectory Autoregressive Modeling for Robotic Manipulation

Wenbo Zhang · Tianrun Hu · Hanbo Zhang · Yanyuan Qiao · Yuchu Qin · Yang Li · Jiajun Liu · Tao Kong · Lingqiao Liu · Xiao Ma

Talk2Event: Grounded Understanding of Dynamic Scenes from Event Cameras

Lingdong Kong · Dongyue Lu · Alan Liang · Rong Li · Yuhao Dong · Tianshuai Hu · Lai Xing Ng · Wei Tsang Ooi · Benoit Cottereau

Bidirectional Motion Transformer for Safety-Critical Traffic Scenario Generation

Yuxin Liu · Zhenghao (Mark) Peng · Xuanhao Cui · Bolei Zhou

Safe and Stable Control via Lyapunov-Guided Diffusion Models

Xiaoyuan Cheng · Xiaohang Tang · Yiming Yang

Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation

Yiyuan Pan · Yunzhe XU · Zhe Liu · Hesheng Wang

Learning to Control Free-Form Soft Swimmers

Changyu Hu · Yanke Qu · Qiuan Yang · Xiaoyu Xiong · Kui Wu · Wei Li · Tao Du

ReSim: Reliable World Simulation for Autonomous Driving

Jiazhi Yang · Kashyap Chitta · Shenyuan Gao · Long Chen · Yuqian Shao · Xiaosong Jia · Hongyang Li · Andreas Geiger · Xiangyu Yue · Li Chen

WeatherPrompt: Multi-modality Representation Learning for All-Weather Drone Visual Geo-Localization

Jiahao Wen · Hang Yu · Zhedong Zheng

TimePerceiver: An Encoder-Decoder Framework for Generalized Time-Series Forecasting

Jaebin Lee · Hankook Lee

Structured Temporal Causality for Interpretable Multivariate Time Series Anomaly Detection

Dongchan Cho · Jiho Han · Keumyeong Kang · Minsang Kim · Honggyu Ryu · Namsoon Jung

Constrained Posterior Sampling: Time Series Generation with Hard Constraints

Sai Shankar Narasimhan · Shubhankar Agarwal · Litu Rout · Sanjay Shakkottai · Sandeep Chinchali

Wavelet Canonical Coherence for Nonstationary Signals

Haibo Wu · Marina Knight · Keiland Cooper · Norbert Fortin · Hernando Ombao

ConnectomeBench: Can LLMs proofread the connectome?

Jeff Brown · Andrew Kirjner · Annika Vivekananthan · Edward Boyden

MLE-Dojo: Interactive Environments for Empowering LLM Agents in Machine Learning Engineering

Rushi Qiang · Yuchen Zhuang · Yinghao Li · Dingu Sagar V K · Rongzhi Zhang · ChangHao Li · Ian Wong · Sherry Yang · Percy Liang · Chao Zhang · Bo Dai

AgMMU: A Comprehensive Agricultural Multimodal Understanding Benchmark

Aruna Gauba · Irene Pi · Yunze Man · Ziqi Pang · Vikram Adve · Yu-Xiong Wang

Time Travel is Cheating: Going Live with DeepFund for Real-Time Fund Investment Benchmarking

Changlun Li · Yao SHI · Chen Wang · Qiqi Duan · Runke RUAN · Weijie Huang · Haonan Long · Lijun Huang · Nan Tang · Yuyu Luo

LiveCodeBench Pro: How Do Olympiad Medalists Judge LLMs in Competitive Programming?

Zihan Zheng · Zerui Cheng · Zeyu Shen · Shang Zhou · Kaiyuan Liu · Hansen He · Dongruixuan Li · Stanley Wei · Hangyi Hao · Jianzhu Yao · Peiyao Sheng · Zixuan Wang · Wenhao Chai · Aleksandra Korolova · Peter Henderson · Sanjeev Arora · Pramod Viswanath · Jingbo Shang · Saining Xie

BikeBench: A Bicycle Design Benchmark for Generative Models with Objectives and Constraints

Lyle Regenwetter · Yazan Abu Obaideh · Fabien Chiotti · Ioanna Lykourentzou · Faez Ahmed

MGE-LDM: Joint Latent Diffusion for Simultaneous Music Generation and Source Extraction

Yunkee Chae · Kyogu Lee

Train on Pins and Test on Obstacles for Rectilinear Steiner Minimum Tree

Xingbo Du · Ruizhe Zhong · Junchi Yan

Can Agent Fix Agent Issues?

Alfin Wijaya Rahardja · Junwei Liu · Weitong Chen · Zhenpeng Chen · Yiling Lou

Fading to Grow: Growing Preference Ratios via Preference Fading Discrete Diffusion for Recommendation

Guoqing Hu · An Zhang · Shuchang Liu · Wenyu Mao · Jiancan Wu · Xun Yang · Xiang Li · Lantao Hu · Han Li · Kun Gai · Xiang Wang

Repo2Run: Automated Building Executable Environment for Code Repository at Scale

Ruida Hu · Chao Peng · XinchenWang · Junjielong Xu · Cuiyun Gao

APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning

Azim Ospanov · Farzan Farnia · Roozbeh Yousefzadeh

TokMan:Tokenize Manhattan Mask Optimization for Inverse Lithography

Yiwen Wu · Yuyang Chen · Ye Xia · Yao Zhao · Jingya Wang · Xuming He · Hao GENG · Jingyi Yu

Co-PatcheR: Collaborative Software Patching with Component-specific Small Reasoning Models

Yuheng Tang · Hongwei Li · Kaijie Zhu · Michael Yang · Yangruibo Ding · Wenbo Guo

Breaking the Batch Barrier (B3) of Contrastive Learning via Smart Batch Mining

Raghuveer Thirukovalluru · Rui Meng · Ye Liu · Karthikeyan K · Mingyi Su · Ping Nie · Semih Yavuz · Yingbo Zhou · Wenhu Chen · Bhuwan Dhingra

Learning Without Augmenting: Unsupervised Time Series Representation Learning via Frame Projections

Berken Utku Demirel · Christian Holz

TopER: Topological Embeddings in Graph Representation Learning

Astrit Tola · Funmilola Mary Taiwo · Cuneyt Akcora · Baris Coskunuzer

Single-pass Adaptive Image Tokenization for Minimum Program Search

Shivam Duggal · Sanghyun Byun · Bill Freeman · Antonio Torralba · Phillip Isola

seq-JEPA: Autoregressive Predictive Learning of Invariant-Equivariant World Models

Hafez Ghaemi · Eilif B. Muller · Shahab Bakhtiari

MetaSlot: Break Through the Fixed Number of Slots in Object-Centric Learning

Hongjia Liu · Rongzhen Zhao · Haohan Chen · Joni Pajarinen

Follow the Energy, Find the Path: Riemannian Metrics from Energy-Based Models

Louis Bethune · David Vigouroux · Yilun Du · Rufin VanRullen · Thomas Serre · Victor Boutin

Massive Sound Embedding Benchmark (MSEB)

Georg Heigold · Ehsan Variani · Tom Bagby · Cyril Allauzen · Ji Ma · Shankar Kumar · Michael D Riley

Exploring Neural Granger Causality with xLSTMs: Unveiling Temporal Dependencies in Complex Data

Harsh Poonia · Felix Divo · Kristian Kersting · Devendra Singh Dhami

LLM-Driven Treatment Effect Estimation Under Inference Time Text Confounding

Yuchen Ma · Dennis Frauen · Jonas Schweisthal · Stefan Feuerriegel

Statistical Inference for Gradient Boosting Regression

Haimo Fang · Kevin Tan · Giles Hooker

Efficient Adaptive Experimentation with Noncompliance

Miruna Oprescu · Brian Cho · Nathan Kallus

Agents Robust to Distribution Shifts Learn Causal World Models Even Under Mediation

Matteo Ceriscioli · Karthika Mohan

Prediction-Powered Causal Inferences

Riccardo Cadei · Ilker Demirel · Piersilvio De Bartolomeis · Lukas Lindorfer · Sylvia Cremer · Cordelia Schmid · Francesco Locatello

Characterization and Learning of Causal Graphs from Hard Interventions

Zihan Zhou · Muhammad Qasim Elahi · Murat Kocaoglu

Transferring Causal Effects using Proxies

Manuel Iglesias-Alonso · Felix Schur · Julius von Kügelgen · Jonas Peters

Conditional Forecasts and Proper Scoring Rules for Reliable and Accurate Performative Predictions

Philip Boeken · Onno Zoeter · Joris Mooij

CausalDynamics: A large‐scale benchmark for structural discovery of dynamical causal models

Benjamin Herdeanu · Juan Nathaniel · Carla Roesch · Jatan Buch · Gregor Ramien · Johannes Haux · Pierre Gentine

Scalable Feature Learning on Huge Knowledge Graphs for Downstream Machine Learning

Félix Lefebvre · Gael Varoquaux

Generalized Contrastive Learning for Universal Multimodal Retrieval

Jungsoo Lee · Janghoon Cho · Hyojin Park · Durga Malladi · Kyuwoong Hwang · Fatih Porikli · Sungha Choi

Joint Hierarchical Representation Learning of Samples and Features via Informed Tree-Wasserstein Distance

Ya-Wei Eileen Lin · Ronald Coifman · Gal Mishne · Ronen Talmon

TransferTraj: A Vehicle Trajectory Learning Model for Region and Task Transferability

Tonglong Wei · Yan Lin · Zeyu Zhou · Haomin Wen · Jilin Hu · Shengnan Guo · Youfang Lin · Gao Cong · Huaiyu Wan

UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learning

Xiangyu Wang · Donglin Yang · Yue Liao · Wenhao Zheng · wenjun wu · Bin Dai · Hongsheng Li · Si Liu

Contrastive Self-Supervised Learning As Neural Manifold Packing

Guanming Zhang · David Heeger · Stefano Martiniani

Generative Data Augmentation via Diffusion Distillation, Adversarial Alignment, and Importance Reweighting

Ruyi An · haicheng huang · Huangjie Zheng · Mingyuan Zhou

Scalable Evaluation and Neural Models for Compositional Generalization

Giacomo Camposampiero · Pietro Barbiero · Michael Hersche · Roger Wattenhofer · Abbas Rahimi

Functional data analysis for multivariate distributions through Wasserstein slicing

Han Chen · Hans-Georg Müller

Reconciling Geospatial Prediction and Retrieval via Sparse Representations

YI LI · CHEN YUANLONG · Weiming Huang · Xiaoli Li · Gao Cong

Diverse Influence Component Analysis: A Geometric Approach to Nonlinear Mixture Identifiability

Hoang Son Nguyen · Xiao Fu

Enhancing Contrastive Learning with Variable Similarity

Haowen Cui · Shuo Chen · Jun Li · Jian Yang

Scalable Cross-View Sample Alignment for Multi-View Clustering with View Structure Similarity

Jun Wang · Zhenglai Li · Chang Tang · Suyuan Liu · Hao Yu · Chuan Tang · Miaomiao Li · Xinwang Liu

Bridging Arbitrary and Tree Metrics via Differentiable Gromov Hyperbolicity

Pierre Houédry · Nicolas Courty · Florestan Martin-Baillon · Laetitia Chapel · Titouan Vayer

Disentangled Representation Learning via Modular Compositional Bias

whie jung · Dong Hoon Lee · Seunghoon Hong

LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought

Cheng Yan · Felix Mohr · Tom Viering

Exploring Tradeoffs through Mode Connectivity for Multi-Task Learning

Zhipeng Zhou · Ziqiao Meng · Pengcheng Wu · Peilin Zhao · Chunyan Miao

QiMeng-NeuComBack: Self-Evolving Translation from IR to Assembly Code

Hainan Fang · Yuanbo Wen · Jun Bi · Yihan Wang · Tonghui He · Yanlin Tang · Di Huang · Jiaming Guo · Rui Zhang · Qi Guo · Yunji Chen

Scaling Up Parameter Generation: A Recurrent Diffusion Approach

Kai Wang · Dongwen Tang · Wangbo Zhao · Konstantin Schürholt · Zhangyang "Atlas" Wang · Yang You

KSP: Kolmogorov-Smirnov metric-based Post-Hoc Calibration for Survival Analysis

Jeongho Park · Daheen Kim · Cheoljun Kim · Hyungbin Park · Sangwook Kang · Gwangsu Kim

An Efficient Local Search Approach for Polarized Community Discovery in Signed Networks

Linus Aronsson · Morteza Haghir Chehreghani

MEMOIR: Lifelong Model Editing with Minimal Overwrite and Informed Retention for LLMs

Ke Wang · Yiming QIN · Nikolaos Dimitriadis · Alessandro Favero · Pascal Frossard

Buffer layers for Test-Time Adaptation

Hyeongyu Kim · GeonHui Han · Dosik Hwang

Optimization Inspired Few-Shot Adaptation for Large Language Models

Boyan Gao · Xin Wang · Yibo Yang · David Clifton

Learning to Route: Per-Sample Adaptive Routing for Multimodal Multitask Prediction

Marzieh Ajirak · Oded Bein · Ellen Bowen · Dora Kanellopoulos · Avital Falk · FAITH GUNNING · Nili Solomonov · Logan Grosenick

TabDPT: Scaling Tabular Foundation Models on Real Data

Junwei Ma · Valentin Thomas · Rasa Hosseinzadeh · Alex Labach · Jesse Cresswell · Keyvan Golestan · Guangwei Yu · Anthony L Caterini · Maks Volkovs

VIPAMIN: Visual Prompt Initialization via Embedding Selection and Subspace Expansion

Jaekyun Park · Hye Won Chung

UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights

Shijun Liang · Ismail Alkhouri · Siddhant Gautam · Qing Qu · Saiprasad Ravishankar

Transfer Faster, Price Smarter: Minimax Dynamic Pricing under Cross-Market Preference Shift

Yi Zhang · Elynn Chen · Yujun Yan

All You Need is One: Capsule Prompt Tuning with a Single Vector

Yiyang Liu · James Liang · Heng Fan · Wenhao Yang · Yiming Cui · Xiaotian Han · Lifu Huangg · Dongfang Liu · Qifan Wang · Cheng Han

Uncertainty-Informed Meta Pseudo Labeling for Surrogate Modeling with Limited Labeled Data

Xingyu Ren · Pengwei Liu · Pengkai Wang · Guanyu Chen · Qinxin Wu · Dong Ni

Training-Free Test-Time Adaptation via Shape and Style Guidance for Vision-Language Models

Shenglong Zhou · Manjiang Yin · Leiyu Sun · Shicai Yang · Di Xie · Jiang Zhu

Decoupled Entropy Minimization

Jing Ma · Hanlin Li · Xiang Xiang

MetaKoopman: Bayesian Meta-Learning of Koopman Operators for Modeling Structured Dynamics under Distribution Shifts

Mahmoud Selim · Sriharsha Bhat · Karl H. Johansson

$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning

Xiaojun Guo · Ang Li · Yifei Wang · Stefanie Jegelka · Yisen Wang

LEDiT: Your Length-Extrapolatable Diffusion Transformer without Positional Encoding

Shen Zhang · Siyuan Liang · Yaning Tan · Zhaowei Chen · Linze Li · Ge Wu · Yuhao Chen · Shuheng Li · Zhenyu Zhao · Caihua Chen · Jiajun Liang · Yao Tang

Curriculum Abductive Learning

Wen-Chao Hu · Qi-Jie Li · Lin-Han Jia · Cunjing Ge · Yu-Feng Li · Yuan Jiang · Zhi-Hua Zhou

A Few Moments Please: Scalable Graphon Learning via Moment Matching

Reza Ramezanpour · Victor Manuel Tenorio Gomez · Antonio G. Marques · Ashutosh Sabharwal · Santiago Segarra

RGNMR: A Gauss-Newton method for robust matrix completion with theoretical guarantees

Eilon Vaknin Laufer · Boaz Nadler

Scalable, Explainable and Provably Robust Anomaly Detection with One-Step Flow Matching

Zhong Li · Qi Huang · Yuxuan Zhu · Lincen Yang · Mohammad Mohammadi Amiri · Niki van Stein · Matthijs van Leeuwen

A Unified Framework for Variable Selection in Model-Based Clustering with Missing Not at Random

Binh Ho · Long Nguyen-Chi · TrungTin Nguyen · Van Hoang · Thanh Binh Nguyen · Chris Drovandi

Missing Data Imputation by Reducing Mutual Information with Rectified Flows

Jiahao Yu · Qizhen Ying · Leyang Wang · Ziyue Jiang · Song Liu

ComRank: Ranking Loss for Multi-Label Complementary Label Learning

Jing-Yi Zhu · Yi Gao · Miao Xu · Min-Ling Zhang

Tackling Feature-Classifier Mismatch in Federated Learning via Prompt-Driven Feature Transformation

Xinghao Wu · Xuefeng Liu · Jianwei Niu · Guogang Zhu · Mingjia Shi · Shaojie Tang · Jing Yuan

Thumb on the Scale: Optimal Loss Weighting in Last Layer Retraining

Nathan Stromberg · Christos Thrampoulidis · Lalitha Sankar

Contextual Online Pricing with (Biased) Offline Data

Yixuan Zhang · Ruihao Zhu · Qiaomin Xie

Parsimonious Predictions for Strategyproof Scheduling

Richard Cole · Anupam Gupta · Pranav Jangir

Incentivizing Truthful Language Models via Peer Elicitation Games

Baiting Chen · Tong Zhu · Jiale Han · Lexin Li · Gang Li · Xiaowu Dai

Explaining the Law of Supply and Demand via Online Learning

Stratis Skoulakis

Smoothed Agnostic Learning of Halfspaces over the Hypercube

Yiwen Kou · Raghu Meka

Tightening Regret Lower and Upper Bounds in Restless Rising Bandits

Cristiano Migali · Marco Mussi · Gianmarco Genalti · Alberto Maria Metelli

Understanding LLM Behaviors via Compression: Data Generation, Knowledge Acquisition and Scaling Laws

Zhixuan Pan · Shaowen Wang · Liao Pengfei · Jian Li

Bandit and Delayed Feedback in Online Structured Prediction

Yuki Shibukawa · Taira Tsuchiya · Shinsaku Sakaue · Kenji Yamanishi

On Learning Verifiers and Implications to Chain-of-Thought Reasoning

Maria-Florina Balcan · Avrim Blum · Zhiyuan Li · Dravyansh Sharma

Non-stationary Bandit Convex Optimization: A Comprehensive Study

Xiaoqi Liu · Dorian Baudry · Julian Zimmert · Patrick Rebeschini · Arya Akhavan

Walking the Tightrope: Autonomous Disentangling Beneficial and Detrimental Drifts in Non-Stationary Custom-Tuning

Xiaoyu Yang · Jie Lu · En Yu

Rescaled Influence Functions: Accurate Data Attribution in High Dimension

Ittai Rubinstein · Samuel Hopkins

A duality framework for analyzing random feature and two-layer neural networks

Hongrui Chen · Jihao Long · Lei Wu

Impartial Selection with Predictions

Javier Cembrano · Felix Fischer · Max Klimm

Stochastic Principal-Agent Problems: Computing and Learning Optimal History-Dependent Policies

Jiarui Gan · R Majumdar · Debmalya Mandal · Goran Radanovic

Procurement Auctions with Predictions: Improved Frugality for Facility Location

Eric Balkanski · Nicholas DeFilippis · Vasilis Gkatzelis · Xizhi Tan

Strategic Hypothesis Testing

Yatong Chen · Safwan Hossain · Yiling Chen

The Price of Opportunity Fairness in Matroid Allocation Problems

Rémi Castera · Felipe Garrido-Lucero · Patrick Loiseau · Simon Mauras · Mathieu Molina · Vianney Perchet

The Burden of Interactive Alignment with Inconsistent Preferences

Ali Shirali

No-Regret Learning Under Adversarial Resource Constraints: A Spending Plan Is All You Need!

Francesco Emanuele Stradi · Matteo Castiglioni · Alberto Marchesi · Nicola Gatti · Christian Kroer

Near-Optimal Quantum Algorithms for Computing (Coarse) Correlated Equilibria of General-Sum Games

Tongyang Li · Xinzhao Wang · Yexin Zhang

HMARL-CBF – Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems

H M Sabbir Ahmad · Ehsan Sabouni · Alexander Wasilkoff · Param Budhraja · Zijian Guo · Songyuan Zhang · Chuchu Fan · Christos G Cassandras · Wenchao Li

Precise Asymptotics and Refined Regret of Variance-Aware UCB

Yingying Fan · Yuxuan Han · Jinchi Lv · Xiaocong Xu · Zhengyuan Zhou

Establishing Linear Surrogate Regret Bounds for Convex Smooth Losses via Convolutional Fenchel–Young Losses

Yuzhou Cao · Han Bao · Lei Feng · Bo An

The Persistence of Neural Collapse Despite Low-Rank Bias

Connall Garrod · Jonathan Keating

A Unified Stability Analysis of SAM vs SGD: Role of Data Coherence and Emergence of Simplicity Bias

WEI-KAI CHANG · Rajiv Khanna

Towards the Resistance of Neural Network Fingerprinting to Fine-tuning

Ling Tang · YueFeng Chen · Hui Xue' · Quanshi Zhang

Dynamical Decoupling of Generalization and Overfitting in Large Two-Layer Networks

Andrea Montanari · Pierfrancesco Urbani

Riemannian Proximal Sampler for High-accuracy Sampling on Manifolds

Yunrui Guan · Krishnakumar Balasubramanian · Shiqian Ma

Algorithm- and Data-Dependent Generalization Bounds for Diffusion Models

Benjamin Dupuis · Dario Shariatian · Maxime Haddouche · Alain Durmus · Umut Simsekli

Attention Mechanism, Max-Affine Partition, and Universal Approximation

Hude Liu · Jerry Yao-Chieh Hu · Zhao Song · Han Liu

Minimax-Optimal Univariate Function Selection in Sparse Additive Models: Rates, Adaptation, and the Estimation-Selection Gap

Shixiang Liu

Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)

Ruaridh Mon-Williams · Max Taylor-Davies · Elizabeth Mieczkowski · Natalia Vélez · Neil Bramley · Yanwei Wang · Tom Griffiths · Christopher G Lucas

In-context Learning of Linear Dynamical Systems with Transformers: Approximation Bounds and Depth-separation

Frank Cole · Yuxuan Zhao · Yulong Lu · Tianhao Zhang

Tackling Biased Evaluators in Dueling Bandits

Ming Tang · Yuxuan Zhou · Chao Huang

Regularized least squares learning with heavy-tailed noise is minimax optimal

Mattes Mollenhauer · Nicole Muecke · Dimitri Meunier · Arthur Gretton

Improved Confidence Regions and Optimal Algorithms for Online and Offline Linear MNL Bandits

Yuxuan Han · Jose Blanchet · Zhengyuan Zhou

Risk Bounds For Distributional Regression

Carlos Misael Madrid Padilla · OSCAR HERNAN MADRID PADILLA · Sabyasachi Chatterjee

Agnostic Active Learning Is Always Better Than Passive Learning

Steve Hanneke

Robust learning of halfspaces under log-concave marginals

Jane Lange · Arsen Vasilyan

Learning Equilibria from Data: Provably Efficient Multi-Agent Imitation Learning

Till Freihaut · Luca Viano · Volkan Cevher · Matthieu Geist · Giorgia Ramponi

Win Fast or Lose Slow: Balancing Speed and Accuracy in Latency-Sensitive Decisions of LLMs

Hao Kang · Qingru Zhang · Han Cai · Weiyuan Xu · Tushar Krishna · Yilun Du · Tsachy Weissman

PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization

Federico Berto · Chuanbo Hua · Laurin Luttmann · Jiwoo Son · Junyoung Park · Kyuree Ahn · Changhyun Kwon · Lin Xie · Jinkyoo Park

Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners

Michal Nauman · Marek Cygan · Carmelo Sferrazza · Aviral Kumar · Pieter Abbeel

Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning

Yaorui Shi · Sihang Li · Chang Wu · ZHIYUAN LIU · Junfeng Fang · Hengxing Cai · An Zhang · Xiang Wang

EDELINE: Enhancing Memory in Diffusion-based World Models via Linear-Time Sequence Modeling

Jia-Hua Lee · Bor-Jiun Lin · Wei-Fang Sun · Chun-Yi Lee

General-Reasoner: Advancing LLM Reasoning Across All Domains

Xueguang Ma · Qian Liu · Dongfu Jiang · Ge Zhang · Zejun MA · Wenhu Chen

SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning

Peixian Ma · Xialie Zhuang · Chengjin Xu · Xuhui Jiang · Ran Chen · Jian Guo

Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning

Sid Bharthulwar · Stone Tao · Hao Su

Accelerating data-driven algorithm selection for combinatorial partitioning problems

Vaggos Chatziafratis · Ishani Karmarkar · Yingxi Li · Ellen Vitercik

Provable Watermarking for Data Poisoning Attacks

Yifan Zhu · Lijia Yu · Xiao-Shan Gao

Improved Bounds for Swap Multicalibration and Swap Omniprediction

Haipeng Luo · Spandan Senapati · Vatsal Sharan

Instance-Dependent Regret Bounds for Nonstochastic Linear Partial Monitoring

Federico Di Gennaro · Khaled Eldowa · Nicolò Cesa-Bianchi

Kernel Learning with Adversarial Features: Numerical Efficiency and Adaptive Regularization

Antonio Ribeiro · David Vävinggren · Dave Zachariah · Thomas Schön · Francis Bach

On the Stability and Generalization of Meta-Learning: the Impact of Inner-Levels

Wenjun Ding · Jingling Liu · Lixing Chen · Xiu Su · Tao Sun · Fan Wu · Zhe Qu

The Parameterized Complexity of Computing the VC-Dimension

Florent Foucaud · Harmender Gahlawat · Fionn Mc Inerney · Prafullkumar Tale

Kernel conditional tests from learning-theoretic bounds

Pierre-François Massiani · Christian Fiedler · Lukas Haverbeck · Friedrich Solowjow · Sebastian Trimpe

Private Online Learning against an Adaptive Adversary: Realizable and Agnostic Settings

Bo Li · Wei Wang · Peng Ye

Distributed Multi-Agent Bandits Over Erdős-Rényi Random Networks

Jingyuan Liu · Hao Qiu · Lin Yang · Mengfan Xu

Mixture-of-Experts Meets In-Context Reinforcement Learning

Wenhao Wu · Fuhong Liu · Haoru Li · Zican Hu · Daoyi Dong · Chunlin Chen · Zhi Wang

Revisiting Agnostic Boosting

Arthur da Cunha · Mikael Møller Høgsgaard · Andrea Paudice · Yuxin Sun

Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model

Jingcheng Hu · Yinmin Zhang · Qi Han · Daxin Jiang · Xiangyu Zhang · Heung-Yeung Shum

Incentivizing LLMs to Self-Verify Their Answers

Fuxiang Zhang · Jiacheng Xu · Chaojie Wang · Ce Cui · Yang Liu · Bo An

Reasoning Models Hallucinate More: Factuality-Aware Reinforcement Learning for Large Reasoning Models

Junyi Li · Hwee Tou Ng

AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws

Oren Neumann · Claudius Gros

COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space

Pengyi Li · Hongyao Tang · Yifu Yuan · Jianye Hao · Zibin Dong · YAN ZHENG

Block Coordinate Descent for Neural Networks Provably Finds Global Minima

Shunta Akiyama

Dimension-adapted Momentum Outscales SGD

Damien Ferbach · Katie Everett · Gauthier Gidel · Elliot Paquette · Courtney Paquette

Comparing Uniform Price and Discriminatory Multi-Unit Auctions through Regret Minimization

Marius Potfer · Vianney Perchet

Posterior Contraction for Sparse Neural Networks in Besov Spaces with Intrinsic Dimensionality

Kyeongwon Lee · Lizhen Lin · Jaewoo Park · Seonghyun Jeong

Lyapunov-Stable Adaptive Control for Multimodal Concept Drift

Tianyu Pan · Mengdi Zhu · Alexa Cole · Ronald Wilson · Damon Woodard

Tight Generalization Bounds for Large-Margin Halfspaces

Kasper Green Larsen · Natascha Schalburg

Performative Risk Control: Calibrating Models for Reliable Deployment under Performativity

Victor Li · Baiting Chen · Yuzhen Mao · Qi Lei · Zhun Deng

On the Convergence of Projected Policy Gradient for Any Constant Step Sizes

Jiacai Liu · Wenye Li · Dachao Lin · Ke Wei · Zhihua Zhang

A Principled Path to Fitted Distributional Evaluation

Sungee Hong · Jiayi Wang · Zhengling Qi · Raymond K. W. Wong

Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions

Kehan Long · Jorge Cortes · Nikolay Atanasov

On the Convergence of Single-Timescale Actor-Critic

Navdeep Kumar · Priyank Agrawal · Giorgia Ramponi · Kfir Y. Levy · Shie Mannor

Kernel von Mises Formula of the Influence Function

Yaroslav Mukhin

Fully Dynamic Algorithms for Chamfer Distance

Gramoz Goranci · Shaofeng Jiang · Peter Kiss · Eva Szilagyi · Qiaoyuan Yang

Minimum Width for Deep, Narrow MLP: A Diffeomorphism Approach

Geonho Hwang

Conformal Prediction Beyond the Seen: A Missing Mass Perspective for Uncertainty Quantification in Generative Models

Sima Noorani · Shayan Kiyani · George J. Pappas · Hamed Hassani

LLM Query Scheduling with Prefix Reuse and Latency Constraints

Gregory Dexter · Shao Tang · Ata Fatahi · Qingquan Song · Tejas Dharamsi · Aman Gupta

Rewind-to-Delete: Certified Machine Unlearning for Nonconvex Functions

Siqiao Mu · Diego Klabjan

Machine Unlearning under Overparameterization

Jacob Block · Aryan Mokhtari · Sanjay Shakkottai

Adversarial Robustness of Nonparametric Regression

Parsa Moradi · Hanzaleh Nodehi · Mohammad Maddah-Ali

Conformal Inference under High-Dimensional Covariate Shifts via Likelihood-Ratio Regularization

Sunay Joshi · Shayan Kiyani · George J. Pappas · Edgar Dobriban · Hamed Hassani

Maximizing the Value of Predictions in Control: Accuracy Is Not Enough

Yiheng Lin · Christopher Yeh · Zaiwei Chen · Adam Wierman

Efficient $k$-Sparse Band–Limited Interpolation with Improved Approximation Ratio

Yang Cao · Xiaoyu Li · Zhao Song · Chiwun Yang

DCAD-2000: A Multilingual Dataset across 2000+ Languages with Data Cleaning as Anomaly Detection

Yingli Shen · Wen Lai · Shuo Wang · Xueren Zhang · Kangyang Luo · Alexander Fraser · Maosong Sun

Efficient Preference-Based Reinforcement Learning: Randomized Exploration meets Experimental Design

Andreas Schlaginhaufen · Reda Ouhamma · Maryam Kamgarpour

Greedy Sampling Is Provably Efficient For RLHF

Di Wu · Chengshuai Shi · Jing Yang · Cong Shen

Don’t Trade Off Safety: Diffusion Regularization for Constrained Offline RL

Junyu guo · Zhi Zheng · Donghao Ying · Ming Jin · Shangding Gu · Costas J Spanos · Javad Lavaei

Variance-Aware Feel-Good Thompson Sampling for Contextual Bandits

Xuheng Li · Quanquan Gu

Eluder dimension: localise it!

Alireza Bakhtiari · Alex Ayoub · Samuel Robertson · David Janz · Csaba Szepesvari

Towards Provable Emergence of In-Context Reinforcement Learning

Jiuqi Wang · Rohan Chandra · Shangtong Zhang

Avoiding exp(R) scaling in RLHF through Preference-based Exploration

Mingyu Chen · Yiding Chen · Wen Sun · Xuezhou Zhang

Optimal Nuisance Function Tuning for Estimating a Doubly Robust Functional under Proportional Asymptotics

Sean McGrath · Debarghya Mukherjee · Rajarshi Mukherjee · Zixiao Jolene Wang

Product Distribution Learning with Imperfect Advice

Arnab Bhattacharyya · XianJun, Davin Choo · Philips George John · Themis Gouleakis

Adaptive Prediction-Powered AutoEval with Reliability and Efficiency Guarantees

Sangwoo Park · Matteo Zecchin · Osvaldo Simeone

Network two-sample test for block models

Chung Kyong Nguen · Arash Amini · OSCAR HERNAN MADRID PADILLA

The Logical Expressiveness of Temporal GNNs via Two-Dimensional Product Logics

Marco Sälzer · Przemyslaw Walega · Martin Lange

metaTextGrad: Automatically optimizing language model optimizers

Guowei Xu · Mert Yuksekgonul · Carlos Guestrin · James Zou

Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning

Jie Cheng · Gang Xiong · Ruixi Qiao · Lijun Li · Chao Guo · Junle Wang · Yisheng Lv · Fei-Yue Wang

Self-Challenging Language Model Agents

Yifei Zhou · Sergey Levine · Jason Weston · Xian Li · Sainbayar Sukhbaatar

DOVE: Efficient One-Step Diffusion Model for Real-World Video Super-Resolution

Zheng Chen · Zichen Zou · Kewei Zhang · Xiongfei Su · Xin Yuan · Yong Guo · Yulun Zhang

GradMetaNet: An Equivariant Architecture for Learning on Gradients

Yoav Gelberg · Yam Eitan · Aviv Navon · Aviv Shamsian · Theo Putterman · Michael Bronstein · Haggai Maron

AcuRank: Uncertainty-Aware Adaptive Computation for Listwise Reranking

Soyoung Yoon · Gyuwan Kim · Gyu-Hwung Cho · seung-won hwang

Rethinking Residual Distribution in Locate-then-Edit Model Editing

Xiaopeng Li · Shangwen Wang · Shasha Li · Shezheng Song · Bin Ji · Ma Jun · Jie Yu

ParetoQ: Improving Scaling Laws in Extremely Low-bit LLM Quantization

Zechun Liu · Changsheng Zhao · Hanxian Huang · Sijia Chen · Jing Zhang · Jiawei Zhao · Scott Roy · Lisa Jin · Yunyang Xiong · Yangyang Shi · Lin Xiao · Yuandong Tian · Bilge Soran · Raghuraman Krishnamoorthi · Tijmen Blankevoort · Vikas Chandra

Harmony in Divergence: Towards Fast, Accurate, and Memory-efficient Zeroth-order LLM Fine-tuning

Qitao Tan · Jun Liu · Zheng Zhan · Caiwen Ding · Yanzhi Wang · Xiaolong Ma · Jaewoo Lee · Jin Lu · Geng Yuan

Learning to Rank for In-Context Example Retrieval

Yuwen Ji · Luodan Zhang · Ambyer han · Haoran Que · Lei Shi · Wang Chao · Yue Zhang

GVPO: Group Variance Policy Optimization for Large Language Model Post-Training

Kaichen Zhang · Yuzhong Hong · Junwei Bao · Hongfei Jiang · Yang Song · Hong Dingqian · Hui Xiong

Pre-Trained Policy Discriminators are General Reward Models

Shihan Dou · Shichun Liu · Yuming Yang · Yicheng Zou · Yunhua Zhou · Shuhao Xing · Chenhao Huang · Qiming Ge · haijun Lv · Demin Song · Songyang Gao · Chengqi Lyu · Enyu Zhou · Honglin Guo · Zhiheng Xi · Qipeng Guo · Wenwei Zhang · Tao Gui · Qi Zhang · Xipeng Qiu · Xuanjing Huang · Kai Chen

X-Mahalanobis: Transformer Feature Mixing for Reliable OOD Detection

Tong Wei · Bolin Wang · Jiang-Xin Shi · Yu-Feng Li · Min-Ling Zhang

Wider or Deeper? Scaling LLM Inference-Time Compute with Adaptive Branching Tree Search

Yuichi Inoue · Kou Misaki · Yuki Imajuku · So Kuroki · Taishi Nakamura · Takuya Akiba

IPFormer: Visual 3D Panoptic Scene Completion with Context-Adaptive Instance Proposals

Markus Gross · Aya Fahmy · Danit Niwattananan · Dominik Muhle · Rui Song · Daniel Cremers · Henri Meeß

CAT: Circular-Convolutional Attention for Sub-Quadratic Transformers

Yoshihiro Yamada

Dynamics of Spontaneous Topic Changes in Next Token Prediction with Self-Attention

Mumin Jia · Jairo Diaz-Rodriguez

Infinite-Width Limit of a Single Attention Layer: Analysis via Tensor Programs

Mana Sakai · Ryo Karakida · Masaaki Imaizumi

FAME: Adaptive Functional Attention with Expert Routing for Function-on-Function Regression

Yifei Gao · Yong Chen · Chen Zhang

PaTH Attention: Position Encoding via Accumulating Householder Transformations

Songlin Yang · Yikang Shen · Kaiyue Wen · Shawn Tan · Mayank Mishra · Liliang Ren · Rameswar Panda · Yoon Kim

MonarchAttention: Zero-Shot Conversion to Fast, Hardware-Aware Structured Attention

Can Yaras · Alec Xu · Pierre Abillama · Changwoo Lee · Laura Balzano

A multiscale analysis of mean-field transformers in the moderate interaction regime

Giuseppe Bruno · Federico Pasqualotto · Andrea Agazzi

PAROAttention: Pattern-Aware ReOrdering for Efficient Sparse and Quantized Attention in Visual Generation Models

Tianchen Zhao · Ke Hong · Xinhao Yang · Xuefeng Xiao · Huixia Li · Feng Ling · Ruiqi Xie · SiQi Chen · Hongyu Zhu · Zhang Yichong · Yu Wang

Scale-invariant attention

Ben Anson · Xi Wang · Laurence Aitchison

ZeroS: Zero‑Sum Linear Attention for Efficient Transformers

Jiecheng Lu · Xu Han · Yan Sun · Viresh Pati · Yubin Kim · Siddhartha Somani · Shihao Yang

LoRASuite: Efficient LoRA Adaptation Across Large Language Model Upgrades

Yanan Li · Fanxu Meng · Muhan Zhang · Shiai Zhu · Shangguang Wang · Mengwei Xu

SageAttention3: Microscaling FP4 Attention for Inference and An Exploration of 8-Bit Training

Jintao Zhang · Jia wei · Haoxu Wang · Pengle Zhang · Xiaoming Xu · Haofeng Huang · Kai Jiang · Jun Zhu · Jianfei Chen

Degrees of Freedom for Linear Attention: Distilling Softmax Attention with Optimal Feature Efficiency

Naoki Nishikawa · Rei Higuchi · Taiji Suzuki

Quantum Doubly Stochastic Transformers

Jannis Born · Filip Skogh · Kahn Rhrissorrakrai · Filippo Utro · Nico Wagner · Aleksandros Sobczyk

Normalize Filters! Classical Wisdom for Deep Vision

Gustavo Perez · Stella X. Yu

Dimensional Collapse in VQVAEs: Evidence and Remedies

Jiayou Zhang · Yifan Shen · Guangyi Chen · Le Song · Eric Xing

Corrector Sampling in Language Models

Itai Gat · Neta Shaul · Uriel Singer · Yaron Lipman

Efficient Hybrid Language Model Compression through Group-Aware SSM Pruning

Ali Taghibakhshi · Sharath Turuvekere Sreenivas · Saurav Muralidharan · Marcin Chochowski · Yashaswi Karnati · Raviraj Joshi · Ameya Mahabaleshwarkar · ZIJIA CHEN · Yoshi Suhara · Oluwatobi Olabiyi · Daniel Korzekwa · Mostofa Patwary · Mohammad Shoeybi · Jan Kautz · Bryan Catanzaro · Ashwath Aithal · Nima Tajbakhsh · Pavlo Molchanov

Dense Backpropagation Improves Training for Sparse Mixture-of-Experts

Ashwinee Panda · Vatsal Baherwani · Zain Sarwar · Benjamin Thérien · Sambit Sahu · Tom Goldstein · Supriyo Chakraborty

SAS: Simulated Attention Score

Chuanyang Zheng · Jiankai Sun · Yihang Gao · Yuehao Wang · Peihao Wang · Jing Xiong · Liliang Ren · Hao Cheng · Janardhan Kulkarni · yelong shen · Zhangyang "Atlas" Wang · Mac Schwager · Anderson Schneider · Xiaodong Liu · Jianfeng Gao

SALS: Sparse Attention in Latent Space for KV Cache Compression

Junlin Mu · Hantao Huang · Jihang Zhang · Minghui Yu · Tao Wang · Yidong Li

REAL: Benchmarking Autonomous Agents on Deterministic Simulations of Real Websites

Div Garg · Diego Caples · Andis Draguns · Nikil Ravi · Pranav Putta · Naman Garg · Prannay Hebbar · Youngchul Joo · Jindong Gu · Charles London · Christian Schroeder de Witt · Sumeet Motwani

PoGDiff: Product-of-Gaussians Diffusion Models for Imbalanced Text-to-Image Generation

Ziyan Wang · Sizhe Wei · Xiaoming Huo · Hao Wang

ReDi: Rectified Discrete Flow

Jaehoon Yoo · Wonjung Kim · Seunghoon Hong

On-Policy Optimization with Group Equivalent Preference for Multi-Programming Language Understanding

Haoyuan Wu · Rui Ming · Jilong Gao · Hangyu Zhao · Xueyi Chen · Yikai Yang · Haisheng Zheng · Zhuolun He · Bei Yu

The Rise of Parameter Specialization for Knowledge Storage in Large Language Models

Yihuai Hong · Yiran Zhao · Wei Tang · Yang Deng · Yu Rong · Wenxuan Zhang

AltLoRA: Towards Better Gradient Approximation in Low-Rank Adaptation with Alternating Projections

Xin Yu · Yujia Wang · Jinghui Chen · Lingzhou Xue

Exploring the Design Space of Diffusion Bridge Models

Shaorong Zhang · Yuanbin Cheng · Greg Ver Steeg

Multitask Learning with Stochastic Interpolants

Hugo Negrel · Florentin Coeurdoux · Michael Albergo · Eric Vanden-Eijnden

See through the Dark: Learning Illumination-affined Representations for Nighttime Occupancy Prediction

Yuan Wu · Zhiqiang Yan · Yigong Zhang · Xiang Li · Jian Yang

Posterior Sampling by Combining Diffusion Models with Annealed Langevin Dynamics

Zhiyang Xun · Shivam Gupta · Eric Price

COME: Adding Scene-Centric Forecasting Control to Occupancy World Model

Yining Shi · Kun Jiang · Qiang Meng · Ke Wang · JiaBao Wang · Wenchao Sun · Tuopu Wen · mengmeng yang · diange yang

Entropic Time Schedulers for Generative Diffusion Models

Dejan Stancevic · Florian Handke · Luca Ambrogioni

zip2zip: Inference-Time Adaptive Tokenization via Online Compression

Saibo Geng · Nathan Ranchin · Yunzhen Yao · Maxime Peyrard · Chris Wendler · Michael Gastpar · Robert West

ROOT: Rethinking Offline Optimization as Distributional Translation via Probabilistic Bridge

Cuong Dao · The Hung Tran · Phi Le Nguyen · Truong Thao Nguyen · Nghia Hoang

Optical Coherence Tomography Harmonization with Anatomy-Guided Latent Metric Schrödinger Bridges

Shuwen Wei · Samuel Remedios · Blake Dewey · Zhangxing Bian · Shimeng Wang · Junyu Chen · Bruno Jedynak · shiv saidha · Peter Calabresi · Aaron Carass · Jerry L Prince

Beyond Scores: Proximal Diffusion Models

Zhenghan Fang · Mateo Diaz · Sam Buchanan · Jeremias Sulam

Learning to Integrate Diffusion ODEs by Averaging the Derivatives

Wenze Liu · Xiangyu Yue

DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization

Gang Li · Ming Lin · Tomer Galanti · Zhengzhong Tu · Tianbao Yang

LayerNavigator: Finding Promising Intervention Layers for Efficient Activation Steering in Large Language Models

Hao Sun · Huailiang Peng · Qiong Dai · Xu Bai · Yanan Cao

Why Masking Diffusion Works: Condition on the Jump Schedule for Improved Discrete Diffusion

Alan Amin · Nate Gruver · Andrew Wilson

Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators

Jongwoo Ko · Sungnyun Kim · Sungwoo Cho · Se-Young Yun

SAEMark: Steering Personalized Multilingual LLM Watermarks with Sparse Autoencoders

Zhuohao Yu · Xingru Jiang · Weizheng Gu · Yidong Wang · Qingsong Wen · Shikun Zhang · Wei Ye

Training-Free Guidance Beyond Differentiability: Scalable Path Steering with Tree Search in Diffusion and Flow Models

Yingqing Guo · Yukang Yang · Hui Yuan · Mengdi Wang

Efficiently Scaling LLM Reasoning Programs with Certaindex

Yichao Fu · Junda Chen · Siqi Zhu · Fu · Zhongdongming Dai · Yonghao Zhuang · Yian Ma · Aurick Qiao · Tajana S Rosing · Ion Stoica · Hao Zhang

Nested Learning: The Illusion of Deep Learning Architectures

Ali Behrouz · Meisam Razaviyayn · Peilin Zhong · Vahab Mirrokni

RoMa: A Robust Model Watermarking Scheme for Protecting IP in Diffusion Models

Yingsha Xie · Rui Min · Zeyu Qin · Fei Ma · Li Shen · Fei Yu · Xiaochun Cao

Tracing the Roots: Leveraging Temporal Dynamics in Diffusion Trajectories for Origin Attribution

Andreas Floros · Seyed-Mohsen Moosavi-Dezfooli · Pier Luigi Dragotti

Zebra-Llama: Towards Extremely Efficient Hybrid Models

Mingyu Yang · Mehdi Rezagholizadeh · Guihong Li · Vikram Appia · Emad Barsoum

High-Order Flow Matching: Unified Framework and Sharp Statistical Rates

Maojiang Su · Jerry Yao-Chieh Hu · Yi-Chen Lee · Ning Zhu · Jui-Hui Chung · Shang Wu · Zhao Song · Minshuo Chen · Han Liu

Towards General Modality Translation with Contrastive and Predictive Latent Diffusion Bridge

Nimrod Berman · Omkar Joglekar · Eitan Kosman · Dotan Di Castro · Omri Azencot

Think Only When You Need with Large Hybrid-Reasoning Models

Lingjie Jiang · Xun Wu · Shaohan Huang · Qingxiu Dong · Zewen Chi · Li Dong · Xingxing Zhang · Tengchao Lv · Lei Cui · Furu Wei

Kuramoto Orientation Diffusion Models

Yue Song · Andy Keller · Sevan Brodjian · Takeru Miyato · Yisong Yue · Pietro Perona · Max Welling

Joint Relational Database Generation via Graph-Conditional Diffusion Models

Mohamed Amine Ketata · David Lüdke · Leo Schwinn · Stephan Günnemann

On the Empirical Power of Goodness-of-Fit Tests in Watermark Detection

Weiqing He · Xiang Li · Tianqi Shang · Li Shen · Weijie Su · Qi Long

Once Upon an Input: Reasoning via Per-Instance Program Synthesis

Adam Stein · Neelay Velingker · Mayur Naik · Eric Wong

CDFlow: Building Invertible Layers with Circulant and Diagonal Matrices

XUCHEN FENG · Siyu Liao

Ask a Strong LLM Judge when Your Reward Model is Uncertain

Zhenghao Xu · Qin Lu · Qingru Zhang · Liang Qiu · Ilgee Hong · Changlong Yu · Wenlin Yao · Yao Liu · Haoming Jiang · Lihong Li · Hyokun Yun · Tuo Zhao

GraphLand: Evaluating Graph Machine Learning Models on Diverse Industrial Data

Gleb Bazhenov · Oleg Platonov · Liudmila Prokhorenkova

CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning

Teresa Huang · Richard Stiskalek · Jun-Young Lee · Adrian Bayer · Charles Margossian · Christian Kragh Jespersen · Lucia Perez · Lawrence Saul · Francisco Villaescusa

MiNT: Multi-Network Transfer Benchmark for Temporal Graph Learning

Kiarash Shamsi · Tran Gia Bao Ngo · Razieh Shirzadkhani · Shenyang Huang · Farimah Poursafaei · Poupak Azad · Reihaneh Rabbany · Baris Coskunuzer · Guillaume Rabusseau · Cuneyt Akcora

GFM-RAG: Graph Foundation Model for Retrieval Augmented Generation

LINHAO LUO · Zicheng Zhao · Reza Haffari · Dinh Phung · Chen Gong · Shirui Pan

Hierarchical Shortest-Path Graph Kernel Network

Jiaxin Wang · Wenxuan Tu · Jieren Cheng

Out-of-Distribution Generalized Graph Anomaly Detection with Homophily-aware Environment Mixup

Sibo Tian · Xin Wang · Zeyang Zhang · Haibo Chen · Wenwu Zhu

Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement

Yinlin Zhu · Xunkai Li · Jishuo Jia · Miao Hu · Di Wu · Meikang Qiu

Influence Functions for Edge Edits in Non-Convex Graph Neural Networks

Jaeseung Heo · Kyeongheung Yun · Seokwon Yoon · MoonJeong Park · Jungseul Ok · Dongwoo Kim

MoEMeta: Mixture-of-Experts Meta Learning for Few-Shot Relational Learning

Han Wu · Jie Yin

Optimal Graph Clustering without Edge Density Signals

Maximilien Dreveton · Elaine Liu · Matthias Grossglauser · Patrick Thiran

Equivariance Everywhere All At Once: A Recipe for Graph Foundation Models

Ben Finkelshtein · Ismail Ilkan Ceylan · Michael Bronstein · Ron Levie

Future Link Prediction Without Memory or Aggregation

Lu Yi · Runlin Lei · Fengran Mo · Yanping Zheng · Zhewei Wei · Yuhang Ye

Pruning Spurious Subgraphs for Graph Out-of-Distribution Generalization

Tianjun Yao · Haoxuan Li · Yongqiang Chen · Tongliang Liu · Le Song · Eric Xing · Zhiqiang Shen

MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning

Guancheng Wan · Fengyuan Ran · Ruikang Zhang · Wenke Huang · Xuankun Rong · Guibin Zhang · Yuxin Wu · Bo Du · Mang Ye

Subgraph Federated Learning via Spectral Methods

Javad Aliakbari · Johan Oestman · Ashkan Panahi · Alexandre Graell i Amat

Logical Expressiveness of Graph Neural Networks with Hierarchical Node Individualization

Arie Soeteman · Balder ten Cate

Torch-Uncertainty: Deep Learning Uncertainty Quantification

Adrien Lafage · Olivier Laurent · Firas Gabetni · Gianni Franchi

SNAP: Low-Latency Test-Time Adaptation with Sparse Updates

Hyeongheon Cha · Dong Min Kim · Hye Won Chung · Taesik Gong · Sung-Ju Lee

Competitive Advantage Attacks to Decentralized Federated Learning

Yuqi Jia · Minghong Fang · Neil Gong

CCL: Causal-aware In-context Learning for Out-of-Distribution Generalization

Hoyoon Byun · Gyeongdeok Seo · Joonseong Kang · Taero Kim · Jihee Kim · Kyungwoo Song

Generalization vs Specialization under Concept Shift

Alex Nguyen · David Schwab · Vudtiwat Ngampruetikorn

Improved Scaling Laws in Linear Regression via Data Reuse

Licong Lin · Jingfeng Wu · Peter Bartlett

The emergence of sparse attention: impact of data distribution and benefits of repetition

Nicolas Zucchet · Francesco D'Angelo · Andrew Lampinen · Stephanie Chan

On the Surprising Effectiveness of Large Learning Rates under Standard Width Scaling

Moritz Haas · Sebastian Bordt · Ulrike Luxburg · Leena Chennuru Vankadara

From Condensation to Rank Collapse: A Two-Stage Analysis of Transformer Training Dynamics

Zheng-An Chen · Tao Luo

Go With the Flow: Fast Diffusion for Gaussian Mixture Models

George Rapakoulias · Ali Reza Pedram · Fengjiao Liu · Lingjiong Zhu · Panagiotis Tsiotras

Exact Expressive Power of Transformers with Padding

Will Merrill · Ashish Sabharwal

Lost in Transmission: When and Why LLMs Fail to Reason Globally

Tobias Schnabel · Kiran Tomlinson · Adith Swaminathan · Jennifer Neville

How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?

Wei Huang · Andi Han · Yujin Song · Yilan Chen · Denny Wu · Difan Zou · Taiji Suzuki

Nonparametric Quantile Regression with ReLU-Activated Recurrent Neural Networks

Hang Yu · Lyumin Wu · Wenxin Zhou · Zhao Ren

RSAVQ: Riemannian Sensitivity-Aware Vector Quantization for Large Language Models

Zukang Xu · Xing Hu · Qiang Wu · Dawei Yang

The Implicit Bias of Structured State Space Models Can Be Poisoned With Clean Labels

Yonatan Slutzky · ‪Yotam Alexander‬‏ · Noam Razin · Nadav Cohen

Reproducing Kernel Banach Space Models for Neural Networks with Application to Rademacher Complexity Analysis

Alistair Shilton · Sunil Gupta · Santu Rana · Svetha Venkatesh

Deep Nonlinear Sufficient Dimension Reduction

Yinfeng Chen · Yuling Jiao · Rui Qiu · Zhou Yu

Scaling Data-Driven Probabilistic Robustness Analysis for Semantic Segmentation Neural Networks

Navid Hashemi · Samuel Sasaki · Ipek Oguz · Meiyi Ma · Taylor Johnson

Fit the Distribution: Cross-Image/Prompt Adversarial Attacks on Multimodal Large Language Models

Hai Yan · Haijian Ma · Xiaowen Cai · Daizong Liu · Zenghui Yuan · Xiaoye Qu · Jianfeng Dong · Runwei Guan · Xiang Fang · Hongyang He · Yulai Xie · Pan Zhou

Scalable Neural Network Geometric Robustness Validation via Hölder Optimisation

Yanghao Zhang · Panagiotis Kouvaros · Alessio Lomuscio

Towards Building Model/Prompt-Transferable Attackers against Large Vision-Language Models

Xiaowen Cai · Daizong Liu · Xiaoye Qu · Xiang Fang · Jianfeng Dong · Keke Tang · Pan Zhou · Lichao Sun · Wei Hu

Robustness in Both Domains: CLIP Needs a Robust Text Encoder

Elias Abad Rocamora · Christian Schlarmann · Naman Deep Singh · Yongtao Wu · Matthias Hein · Volkan Cevher

Latency NMS Attacks: Is It Real Life or Is It Just Fantasy?

Jean-Philippe Monteuuis · Cong Chen · Jonathan Petit

ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning

Ziyu Wan · Yunxiang Li · Xiaoyu Wen · Yan Song · Hanjing Wang · Linyi Yang · Mark Schmidt · Jun Wang · Weinan Zhang · Shuyue Hu · Ying Wen

Don't be lazy: CompleteP enables compute-efficient deep transformers

Nolan Dey · Bin Zhang · Lorenzo Noci · Mufan Li · Blake Bordelon · Shane Bergsma · Cengiz Pehlevan · Boris Hanin · Joel Hestness

From Shortcut to Induction Head: How Data Diversity Shapes Algorithm Selection in Transformers

Ryotaro Kawata · Yujin Song · Alberto Bietti · Naoki Nishikawa · Taiji Suzuki · Samuel Vaiter · Denny Wu

What One Cannot, Two Can: Two-Layer Transformers Provably Represent Induction Heads on Any-Order Markov Chains

Chanakya Ekbote · Ashok Vardhan Makkuva · Marco Bondaschi · Nived Rajaraman · Michael Gastpar · Jason Lee · Paul Liang

Streaming Attention Approximation via Discrepancy Theory

Ekaterina Kochetkova · Kshiteej Jitesh Sheth · Insu Han · Amir Zandieh · Michael Kapralov

MoE-CAP: Benchmarking Cost, Accuracy and Performance of Sparse Mixture-of-Experts Systems

Yinsicheng Jiang · Yao Fu · Yeqi Huang · Ping Nie · Zhan Lu · Leyang Xue · Congjie He · Man-Kit Sit · Jilong Xue · Li Dong · Ziming Miao · DaYou Du · Tairan Xu · Kai Zou · Edoardo Maria Ponti · Luo Mai

Self-Verifying Reflection Helps Transformers with CoT Reasoning

Zhongwei Yu · Wannian Xia · Xue Yan · Bo Xu · Haifeng Zhang · Yali Du · Jun Wang

Beyond Components: Singular Vector-Based Interpretability of Transformer Circuits

Areeb Ahmad · Abhinav Joshi · Ashutosh Modi

Masked Diffusion Models as Energy Minimization

Sitong Chen · Shen Nie · Jiacheng Sun · Zijin Feng · Zhenguo Li · Ji-Rong Wen · Chongxuan LI

Representation Consistency for Accurate and Coherent LLM Answer Aggregation

Junqi Jiang · Tom Bewley · Salim I. Amoukou · Francesco Leofante · Antonio Rago · Saumitra Mishra · Francesca Toni

The Lighthouse of Language: Enhancing LLM Agents via Critique-Guided Improvement

Ruihan Yang · Fanghua Ye · Jian Li · Siyu Yuan · yikai zhang · Zhaopeng Tu · Xiaolong Li · Deqing Yang

GSO: Challenging Software Optimization Tasks for Evaluating SWE-Agents

Manish Shetty · Naman Jain · Jinjian Liu · Vijay Kethanaboyina · Koushik Sen · Ion Stoica

Towards Fully FP8 GEMM LLM Training at Scale

Alejandro Hernández Cano · Dhia Garbaya · Imanol Schlag · Martin Jaggi

Do Language Models Use Their Depth Efficiently?

Róbert Csordás · Christopher D Manning · Chris Potts

Chain of Execution Supervision Promotes General Reasoning in Large Language Models

Nuo Chen · Zehua Li · Keqin Bao · Junyang Lin · Dayiheng Liu

Efficient Multi-bit Quantization Network Training via Weight Bias Correction and Bit-wise Coreset Sampling

Jinhee Kim · Jae Jun An · Kang Eun Jeon · Jong Hwan Ko

Sherlock: Self-Correcting Reasoning in Vision-Language Models

Yi Ding · Ruqi Zhang

Thinkless: LLM Learns When to Think

Gongfan Fang · Xinyin Ma · Xinchao Wang

BLEUBERI: BLEU is a surprisingly effective reward for instruction following

Yapei Chang · Yekyung Kim · Michael Krumdick · Amir Zadeh · Chuan Li · Chris Tanner · Mohit Iyyer

ZEUS: Zero-shot Embeddings for Unsupervised Separation of Tabular Data

Patryk Marszałek · Tomasz Kuśmierczyk · Witold Wydmański · Jacek Tabor · Marek Śmieja

Continuous Subspace Optimization for Continual Learning

Quan Cheng · Yuanyu Wan · Lingyu Wu · Chenping Hou · Lijun Zhang

Self-Evolving Pseudo-Rehearsal for Catastrophic Forgetting with Task Similarity in LLMs

Jun Wang · Liang Ding · Shuai Wang · Hongyu Li · Yong Luo · Huangxuan Zhao · Han Hu · Bo Du

TheAgentCompany: Benchmarking LLM Agents on Consequential Real World Tasks

Frank (Fangzheng) Xu · Yufan Song · Boxuan Li · Yuxuan Tang · Kritanjali Jain · Mengxue Bao · Zora Wang · Xuhui Zhou · Zhitong Guo · Murong Cao · Mingyang Yang · Hao Yang Lu · Amaad Martin · Zhe Su · Leander Maben · Raj Mehta · Wayne Chi · Lawrence Jang · Yiqing Xie · Shuyan Zhou · Graham Neubig

EVAAA: A Virtual Environment Platform for Essential Variables in Autonomous and Adaptive Agents

Sungwoo Lee · Jungmin Lee · Sohee Kim · Hyebhin Yoon · Shinwon Park · Junhyeok Park · Jaehyuk Bae · Seok-Jun Hong · Choong-Wan Woo

KL Penalty Control via Perturbation for Direct Preference Optimization

Sangkyu Lee · Janghoon Han · Hosung Song · Stanley Jungkyu Choi · Honglak Lee · Youngjae Yu

Continuous Soft Actor-Critic: An Off-Policy Learning Method Robust to Time Discretization

Huimin Han · Shaolin Ji

Learning Parameterized Skills from Demonstrations

Vedant Gupta · Haotian Fu · Calvin Luo · Yiding Jiang · George Konidaris

Diffusion Guided Adversarial State Perturbations in Reinforcement Learning

Xiaolin Sun · Feidi Liu · Zhengming Ding · Zizhan Zheng

Reinforcement learning for one-shot DAG scheduling with comparability identification and dense reward

Xumai Qi · Dongdong Zhang · Taotao Liu · Hongcheng Wang

STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning

Yao Luan · Ni Mu · Yiqin Yang · Bo Xu · Qing-Shan Jia

A Generalized Bisimulation Metric of State Similarity between Markov Decision Processes: From Theoretical Propositions to Applications

Zhenyu Tao · Wei Xu · Xiaohu You

Rendering-Aware Reinforcement Learning for Vector Graphics Generation

Juan Rodriguez · Haotian Zhang · Abhay Puri · Rishav Pramanik · Aarash Feizi · Pascal Wichmann · Arnab Mondal · Mohammad R. Samsami · Rabiul Awal · Perouz Taslakian · Spandana Gella · Sai Rajeswar Mudumba · David Vazquez · Chris Pal · Marco Pedersoli

MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models

Hang Hua · Ziyun Zeng · Yizhi Song · Yunlong Tang · Liu He · Daniel Aliaga · Wei Xiong · Jiebo Luo

EgoVid-5M: A Large-Scale Video-Action Dataset for Egocentric Videos Generation

Xiaofeng Wang · Kang Zhao · Feng Liu · Jiayu Wang · Guosheng Zhao · Xiaoyi Bao · Zheng Zhu · Yingya Zhang

OverLayBench: A Benchmark for Layout-to-Image Generation with Dense Overlaps

Bingnan Li · Chen-Yu Wang · Haiyang Xu · Xiang Zhang · Ethan Armand · Divyansh Srivastava · Shan Xiaojun · Zeyuan Chen · Jianwen Xie · Zhuowen Tu

AdaSPEC: Selective Knowledge Distillation for Efficient Speculative Decoders

Yuezhou Hu · Jiaxin Guo · Xinyu Feng · Tuo Zhao

70% Size, 100% Accuracy: Lossless LLM Compression for Efficient GPU Inference via Dynamic-Length Float (DFloat11)

Tianyi Zhang · Mohsen Hariri · Shaochen (Henry) Zhong · Vipin Chaudhary · Yang Sui · Xia Hu · Anshumali Shrivastava

Searching Efficient Semantic Segmentation Architectures via Dynamic Path Selection

Yuxi Liu · Min Liu · Shuai Jiang · Yi Tang · Yaonan Wang

Listwise Preference Diffusion Optimization for User Behavior Trajectories Prediction

Hongtao Huang · Chengkai Huang · Junda Wu · Tong Yu · Julian McAuley · Lina Yao

DP-LLM: Runtime Model Adaptation with Dynamic Layer-wise Precision Assignment

Sangwoo Kwon · Seong Hoon Seo · Jae W. Lee · Yeonhong Park

CAS-Spec: Cascade Adaptive Self-Speculative Decoding for On-the-Fly Lossless Inference Acceleration of LLMs

Zhiyuan Ning · Jiawei Shao · Ruge Xu · Xinfei Guo · Jun Zhang · Chi Zhang · Xuelong Li

SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data

Wenkai Fang · Shunyu Liu · Yang Zhou · Kongcheng Zhang · Tongya Zheng · Kaixuan Chen · Mingli Song · Dacheng Tao

GOOD: Training-Free Guided Diffusion Sampling for Out-of-Distribution Detection

Xin Gao · Jiyao Liu · Guanghao Li · Yueming Lyu · Jianxiong Gao · Weichen Yu · Ningsheng Xu · Liang Wang · Caifeng Shan · Ziwei Liu · Chenyang Si

CORE: Reducing UI Exposure in Mobile Agents via Collaboration Between Cloud and Local LLMs

Gucongcong Fan · Chaoyue Niu · Chengfei Lyu · Fan Wu · Guihai Chen

Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning

Xiaoxue Cheng · Junyi Li · Zhenduo Zhang · Xinyu Tang · Xin Zhao · Xinyu Kong · Zhiqiang Zhang

Skill-Driven Neurosymbolic State Abstractions

Alper Ahmetoglu · Steven James · Cameron Allen · Sam Lobel · David Abel · George Konidaris

Approximating Shapley Explanations in Reinforcement Learning

Daniel Beechey · Özgür Şimşek

Rectifying Shortcut Behaviors in Preference-based Reward Learning

Wenqian Ye · Guangtao Zheng · Aidong Zhang

Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization

Xiyue Peng · Hengquan Guo · Jiawei Zhang · Dongqing Zou · Ziyu Shao · Honghao Wei · Xin Liu

XVerse: Consistent Multi-Subject Control of Identity and Semantic Attributes via DiT Modulation

Bowen Chen · Brynn zhao · Haomiao Sun · Li Chen · Xu Wang · Daniel Du · Xinglong Wu

Mind-the-Glitch: Visual Correspondence for Detecting Inconsistencies in Subject-Driven Generation

Abdelrahman Eldesokey · Aleksandar Cvejić · Bernard Ghanem · Peter Wonka

Self-diffusion for Solving Inverse Problems

Guanxiong Luo · Shoujin Huang

Let the LLM Stick to Its Strengths: Learning to Route Economical LLM

Yi-Kai Zhang · Shiyin Lu · Qingguo Chen · Weihua Luo · De-Chuan Zhan · Han-Jia Ye

PanoWan: Lifting Diffusion Video Generation Models to 360$^\circ$ with Latitude/Longitude-aware Mechanisms

Yifei Xia · Shuchen Weng · Siqi Yang · Jingqi Liu · Chengxuan Zhu · Minggui Teng · Zijian Jia · Han Jiang · Boxin Shi

Imagine360: Immersive 360 Video Generation from Perspective Anchor

Jing Tan · Shuai Yang · Tong Wu · Jingwen He · Yuwei Guo · Ziwei Liu · Dahua Lin

Training-Free Efficient Video Generation via Dynamic Token Carving

Yuechen Zhang · Jinbo Xing · bin xia · Shaoteng Liu · Bohao PENG · Xin Tao · Pengfei Wan · Eric Lo · Jiaya Jia

Stable Cinemetrics : Structured Taxonomy and Evaluation for Professional Video Generation

Agneet Chatterjee · Rahim Entezari · Maksym Zhuravinskyi · Maksim Lapin · Reshinth Adithyan · Amit Raj · Chitta Baral · 'YZ' Yezhou Yang · Varun Jampani

RoomEditor: High-Fidelity Furniture Synthesis with Parameter-Sharing U-Net

Zhenyi Lin · Xiaofan Ming · Qilong Wang · Dongwei Ren · Wangmeng Zuo · Qinghua Hu

Dimension-Reduction Attack! Video Generative Models are Experts on Controllable Image Synthesis

Hengyuan Cao · Yutong Feng · Biao Gong · Yijing Tian · Yunhong Lu · Chuang Liu · Bin Wang

Smooth and Flexible Camera Movement Synthesis via Temporal Masked Generative Modeling

Chenghao Xu · guangtao lyu · Jiexi Yan · Muli Yang · Cheng Deng

FreeInv: Free Lunch for Improving DDIM Inversion

Yuxiang Bao · Huijie Liu · xun gao · Huan Fu · Guoliang Kang

Seg2Any: Open-set Segmentation-Mask-to-Image Generation with Precise Shape and Semantic Control

Danfeng Li · Hui Zhang · Sheng Wang · Jiacheng Li · Zuxuan Wu

Improving Video Generation with Human Feedback

Jie Liu · Gongye Liu · Jiajun Liang · Ziyang Yuan · Xiaokun Liu · Mingwu Zheng · Xiele Wu · Qiulin Wang · Menghan Xia · Xintao Wang · Xiaohong Liu · Fei Yang · Pengfei Wan · Di ZHANG · Kun Gai · Yujiu Yang · Wanli Ouyang

Autoregressive Adversarial Post-Training for Real-Time Interactive Video Generation

Shanchuan Lin · Ceyuan Yang · Hao He · Jianwen Jiang · Yuxi Ren · Xin Xia · Yang Zhao · Xuefeng Xiao · Lu Jiang

HiFlow: Training-free High-Resolution Image Generation with Flow-Aligned Guidance

Jiazi Bu · Pengyang Ling · Yujie Zhou · Pan Zhang · Tong Wu · Xiaoyi Dong · Yuhang Zang · Yuhang Cao · Dahua Lin · Jiaqi Wang

SViMo: Synchronized Diffusion for Video and Motion Generation in Hand-object Interaction Scenarios

Lingwei Dang · Ruizhi Shao · Hongwen Zhang · Wei MIN · Yebin Liu · Qingyao Wu

DINO-Foresight: Looking into the Future with DINO

Efstathios Karypidis · Ioannis Kakogeorgiou · Spyridon Gidaris · Nikos Komodakis

Universal Few-shot Spatial Control for Diffusion Models

Kiet Nguyen · Chanhyuk Lee · Donggyun Kim · Dong Hoon Lee · Seunghoon Hong

A Gradient Guidance Perspective on Stepwise Preference Optimization for Diffusion Models

Joshua Tian Jin Tee · Hee Suk Yoon · Abu Hanif Muhammad Syarubany · Eunseop Yoon · Chang Yoo

IntrinsiX: High-Quality PBR Generation using Image Priors

Peter Kocsis · Lukas Höllein · Matthias Niessner

Diffusion Model as a Noise-Aware Latent Reward Model for Step-Level Preference Optimization

Tao Zhang · Cheng Da · Kun Ding · Huan Yang · kun jin · Yan Li · Tingting Gao · Di ZHANG · SHIMING XIANG · Chunhong Pan

DiCo: Revitalizing ConvNets for Scalable and Efficient Diffusion Modeling

Yuang Ai · Qihang Fan · Xuefeng Hu · Zhenheng Yang · Ran He · Huaibo Huang

Localizing Knowledge in Diffusion Transformers

Arman Zarei · Samyadeep Basu · Keivan Rezaei · Zihao Lin · Sayan Nag · Soheil Feizi

MoCha: Towards Movie-Grade Talking Character Generation

Cong Wei · Bo Sun · Haoyu Ma · Ji Hou · Felix Juefei-Xu · Zecheng He · Xiaoliang Dai · Luxin Zhang · Kunpeng Li · Tingbo Hou · Animesh Sinha · Peter Vajda · Wenhu Chen

DEFT: Decompositional Efficient Fine-Tuning for Text-to-Image Models

Komal Kumar · Rao Anwer · Fahad Shahbaz Khan · Salman Khan · Ivan Laptev · Hisham Cholakkal

PairEdit: Learning Semantic Variations for Exemplar-based Image Editing

Haoguang Lu · Jiacheng Chen · Zhenguo Yang · Aurele Gnanha · Fu Lee Wang · Qing Li · Xudong Mao

Native-Resolution Image Synthesis

ZiDong Wang · LEI BAI · Xiangyu Yue · Wanli Ouyang · Yiyuan Zhang

The Matrix: Infinite-Horizon World Generation with Real-Time Moving Control

Ruili Feng · Han Zhang · Zhilei Shu · Zhantao Yang · Longxiang Tang · Zhicai Wang · Andy Zheng · Jie Xiao · Zhiheng Liu · Ruihang Chu · Yukun Huang · Yu Liu · Hongyang Zhang

Image Editing As Programs with Diffusion Models

Yujia Hu · Songhua Liu · Zhenxiong Tan · Xingyi Yang · Xinchao Wang

Hawk: Leveraging Spatial Context for Faster Autoregressive Text-to-Image Generation

Zhi-Kai Chen · Jun-Peng Jiang · Han-Jia Ye · De-Chuan Zhan

Simple Distillation for One-Step Diffusion Models

Huaisheng Zhu · Teng Xiao · Shijie Zhou · Zhimeng Guo · Hangfan Zhang · Siyuan Xu · Vasant Honavar

Solving Inverse Problems with FLAIR

Julius Erbach · Dominik Narnhofer · Andreas Dombos · Bernt Schiele · Jan Eric Lenssen · Konrad Schindler

ROSE: Remove Objects with Side Effects in Videos

Chenxuan Miao · Yutong Feng · Jianshu Zeng · Zixiang Gao · Hantang Liu · Yunfeng Yan · Donglian Qi · Xi Chen · Bin Wang · Hengshuang Zhao

Towards a Golden Classifier-Free Guidance Path via Foresight Fixed Point Iterations

Kaibo Wang · Jianda Mao · Tong Wu · Yang Xiang

MotionRAG: Motion Retrieval-Augmented Image-to-Video Generation

Chenhui Zhu · Yilu Wu · Shuai Wang · Gangshan Wu · Limin Wang

Hi3DEval: Advancing 3D Generation Evaluation with Hierarchical Validity

Yuhan Zhang · Long Zhuo · Ziyang Chu · Tong Wu · Zhibing Li · Liang Pan · Dahua Lin · Ziwei Liu

C3Po: Cross-View Cross-Modality Correspondence by Pointmap Prediction

Kuan Wei Huang · Brandon Li · Bharath Hariharan · Noah Snavely

GS2E: Gaussian Splatting is an Effective Data Generator for Event Stream Generation

Yuchen Li · Chaoran Feng · Zhenyu Tang · Kaiyuan Deng · Wangbo Yu · Yonghong Tian · Li Yuan

RGB-Only Supervised Camera Parameter Optimization in Dynamic Scenes

Fang Li · Hao Zhang · Narendra Ahuja

ODG: Occupancy Prediction Using Dual Gaussians

Yunxiao Shi · Yinhao Zhu · Herbert Cai · Shizhong Han · Jisoo Jeong · Amin Ansari · Fatih Porikli

PBR-SR: Mesh PBR Texture Super Resolution from 2D Image Priors

Yujin Chen · Yinyu Nie · Benjamin Ummenhofer · Reiner Birkl · Michael Paulitsch · Matthias Niessner

I2-NeRF: Learning Neural Radiance Fields Under Physically-Grounded Media Interactions

Shuhong Liu · Lin Gu · Ziteng Cui · Xuangeng Chu · Tatsuya Harada

Learning Neural Exposure Fields for View Synthesis

Michael Niemeyer · Fabian Manhardt · Marie-Julie Rakotosaona · Michael Oechsle · Christina Tsalicoglou · Keisuke Tateno · Jonathan Barron · Federico Tombari

RaySt3R: Predicting Novel Depth Maps for Zero-Shot Object Completion

Bardienus Duisterhof · Jan Oberst · Bowen Wen · Stan Birchfield · Deva Ramanan · Jeffrey Ichnowski

Dynamic Gaussian Splatting from Defocused and Motion-blurred Monocular Videos

Xuankai Zhang · Junjin Xiao · Qing Zhang

Omnidirectional 3D Scene Reconstruction from Single Image

Ren Yang · Jiahao Li · Yan Lu

X-Field: A Physically Informed Representation for 3D X-ray Reconstruction

Feiran Wang · Jiachen Tao · Junyi Wu · Haoxuan Wang · Bin Duan · Kai Wang · Zongxin Yang · Yan Yan

SRHand: Super-Resolving Hand Images and 3D Shapes via View/Pose-aware Neural Image Representations and Explicit Meshes

Minje Kim · Tae-Kyun Kim

FlexWorld: Progressively Expanding 3D Scenes for Flexible-View Exploration

Luxi Chen · Zihan Zhou · Min Zhao · Yikai Wang · Ge Zhang · Wenhao Huang · Hao Sun · Ji-Rong Wen · Chongxuan LI

ROGR: Relightable 3D Objects using Generative Relighting

Jiapeng Tang · Matthew Levine · Dor Verbin · Stephan Garbin · Matthias Niessner · Ricardo Martin Brualla · Pratul Srinivasan · Philipp Henzler

LangSplatV2: High-dimensional 3D Language Gaussian Splatting with 450+ FPS

Wanhua Li · Yujie Zhao · Minghan Qin · Yang Liu · Yuanhao Cai · Chuang Gan · Hanspeter Pfister

OrthoLoC: UAV 6-DoF Localization and Calibration Using Orthographic Geodata

Oussema Dhaouadi · Riccardo Marin · Johannes Meier · Jacques Kaiser · Daniel Cremers

Face-Human-Bench: A Comprehensive Benchmark of Face and Human Understanding for Multi-modal Assistants

Lixiong Qin · Shilong Ou · Miaoxuan Zhang · Jiangning Wei · Yuhang Zhang · Xiaoshuai Song · Yuchen Liu · Mei Wang · Weiran Xu

CHOICE: Benchmarking the Remote Sensing Capabilities of Large Vision-Language Models

Xiao An · Jiaxing Sun · Zihan Gui · Wei He

MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Models

Chaoyou Fu · Peixian Chen · Yunhang Shen · Yulei Qin · Mengdan Zhang · Xu Lin · Jinrui Yang · Xiawu Zheng · Ke Li · Xing Sun · Yunsheng Wu · Rongrong Ji · Caifeng Shan · Ran He

EmoNet-Face: An Expert-Annotated Benchmark for Synthetic Emotion Recognition

Christoph Schuhmann · Robert Kaczmarczyk · Gollam Rabby · Maurice Kraus · Felix Friedrich · Huu Nguyen · Kalyan Sai Krishna · Kourosh Nadi · Kristian Kersting · Sören Auer

Intend to Move: A Multimodal Dataset for Intention-Aware Human Motion Understanding

Ryo Umagami · Liu Yue · Xuangeng Chu · Ryuto Fukushima · Tetsuya Narita · Yusuke Mukuta · Tomoyuki Takahata · Jianfei Yang · Tatsuya Harada

HAIF-GS: Hierarchical and Induced Flow-Guided Gaussian Splatting for Dynamic Scene

Jianing Chen · Zehao Li · Yujun Cai · Hao Jiang · Chengxuan Qian · Juyuan Kang · Shuqin Gao · Honglong Zhao · Tianlu Mao · Yucheng Zhang

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory

Yuqi Wu · Wenzhao Zheng · Jie Zhou · Jiwen Lu

Segment then Splat: Unified 3D Open-Vocabulary Segmentation via Gaussian Splatting

Yiren Lu · Yunlai Zhou · Yiran Qiao · Chaoda Song · Tuo Liang · Jing Ma · Huan Wang · Yu Yin

ARMesh: Autoregressive Mesh Generation via Next-Level-of-Detail Prediction

Jiabao Lei · Kewei Shi · Zhihao Liang · Kui Jia

Rig3R: Rig-Aware Conditioning and Discovery for 3D Reconstruction

Samuel Li · Pujith Kachana · Prajwal Chidananda · Saurabh Nair · Yasutaka Furukawa · Matthew A Brown

3D Visual Illusion Depth Estimation

Chengtang Yao · Zhidan Liu · Jiaxi Zeng · Lidong Yu · Yuwei Wu · Yunde Jia

ShapeCraft: LLM Agents for Structured, Textured and Interactive 3D Modeling

Shuyuan Zhang · ChenHan Jiang · Zuoou Li · Jiankang Deng

Fin3R: Fine-tuning Feed-forward 3D Reconstruction Models via Monocular Knowledge Distillation

Weining Ren · Hongjun Wang · Xiao Tan · Kai Han

LuxDiT: Lighting Estimation with Video Diffusion Transformer

Ruofan Liang · Kai He · Zan Gojcic · Igor Gilitschenski · Sanja Fidler · Nandita Vijaykumar · Zian Wang

Towards Generalizable 3D Human Pose Estimation via Ensembles on Flat Loss Landscapes

Jumin Han · Jun-Hui Kim · Seong-Whan Lee

RPG360: Robust 360 Depth Estimation with Perspective Foundation Models and Graph Optimization

Dongki Jung · Jaehoon Choi · Yonghan Lee · Dinesh Manocha

Learning Generalizable Shape Completion with SIM(3) Equivariance

Yuqing Wang · Zhaiyu Chen · Xiaoxiang Zhu

QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction

Sicheng Zuo · Wenzhao Zheng · Xiaoyong Han · Longchao Yang · Yong Pan · Jiwen Lu

MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds

Bingquan Dai · Luo Li · Qihong Tang · Jie Wang · Xinyu Lian · Hao Xu · Minghan Qin · Xudong XU · Bo Dai · Haoqian Wang · Zhaoyang Lyu · Jiangmiao Pang

Situat3DChange: Situated 3D Change Understanding Dataset for Multimodal Large Language Model

Ruiping Liu · Junwei Zheng · Yufan Chen · Zirui Wang · Kunyu Peng · Kailun Yang · Jiaming Zhang · Marc Pollefeys · Rainer Stiefelhagen

SMMILE: An expert-driven benchmark for multimodal medical in-context learning

Melanie Rieff · Maya Varma · Ossian Rabow · Subathra Adithan · Julie Kim · Ken Chang · Hannah Lee · Nidhi Rohatgi · Christian Bluethgen · Mohamed Muneer · Jean-Benoit Delbrouck · Michael Moor

EgoBlind: Towards Egocentric Visual Assistance for the Blind

Junbin Xiao · Nanxin Huang · Hao Qiu · Zhulin Tao · Xun Yang · Richang Hong · Meng Wang · Angela Yao

3EED: Ground Everything Everywhere in 3D

Rong Li · Yuhao Dong · Tianshuai Hu · Alan Liang · Youquan Liu · Dongyue Lu · Liang Pan · Lingdong Kong · Junwei Liang · Ziwei Liu

DynamicVL: Benchmarking Multimodal Large Language Models for Dynamic City Understanding

Weihao Xuan · Junjue Wang · Heli Qi · Zihang Chen · Zhuo Zheng · Yanfei Zhong · Junshi Xia · Naoto YOKOYA

Model-Guided Dual-Role Alignment for High-Fidelity Open-Domain Video-to-Audio Generation

Kang Zhang · Trung X. Pham · Suyeon Lee · Axi Niu · Arda Senocak · Joon Son Chung

UniPixel: Unified Object Referring and Segmentation for Pixel-Level Visual Reasoning

Ye Liu · Zongyang Ma · Junfu Pu · Zhongang Qi · Yang Wu · Ying Shan · Chang Chen

Simulation-Based Inference for Adaptive Experiments

Brian Cho · Aurelien Bibaut · Nathan Kallus

VL-Rethinker: Incentivizing Self-Reflection of Vision-Language Models with Reinforcement Learning

Haozhe Wang · Chao Qu · Zuming Huang · Wei Chu · Fangzhen Lin · Wenhu Chen

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Jang Hyun Cho · Andrea Madotto · Effrosyni Mavroudi · Triantafyllos Afouras · Tushar Nagarajan · Muhammad Maaz · Yale Song · Tengyu Ma · Shuming Hu · Suyog Jain · Miguel Martin · Huiyu Wang · Hanoona Bangalath · Peize Sun · Po-Yao Huang · Daniel Bolya · Nikhila Ravi · Shashank Jain · Tammy Stark · Seungwhan Moon · Babak Damavandi · Vivian Lee · Andrew Westbury · Salman Khan · Philipp Kraehenbuehl · Piotr Dollar · Lorenzo Torresani · Kristen Grauman · Christoph Feichtenhofer

Multi-Kernel Correlation-Attention Vision Transformer for Enhanced Contextual Understanding and Multi-Scale Integration

Hongkang Zhang · Shao-Lun Huang · Ercan KURUOGLU · Yanlong Wang

InfMasking: Unleashing Synergistic Information by Contrastive Multimodal Interactions

Liangjian Wen · Qun Dai · Jianzhuang Liu · Jiangtao Zheng · Yong Dai · Dongkai Wang · Zhao Kang · Jun Wang · Zenglin Xu · Jiang Duan

LaViDa: A Large Diffusion Model for Vision-Language Understanding

Shufan Li · Konstantinos Kallidromitis · Hritik Bansal · Akash Gokul · Yusuke Kato · Kazuki Kozuka · Jason Kuen · Zhe Lin · Kai-Wei Chang · Aditya Grover

Show-o2: Improved Native Unified Multimodal Models

Jinheng Xie · Zhenheng Yang · Mike Zheng Shou

OpenBox: Annotate Any Bounding Boxes in 3D

In-Jae Lee · Mungyeom Kim · Kwonyoung Ryu · Pierre Musacchio · Jaesik Park

Unified Reinforcement and Imitation Learning for Vision-Language Models

Byung-Kwan Lee · Ryo Hachiuma · Yong Man Ro · Frank Wang · Yueh-Hua Wu

FRN: Fractal-Based Recursive Spectral Reconstruction Network

Ge Meng · Zhongnan Cai · Ruizhe Chen · Jingyan Tu · Yingying Wang · Yue Huang · Xinghao Ding

FOCUS: Internal MLLM Representations for Efficient Fine-Grained Visual Question Answering

Liangyu Zhong · Fabio Philipp Rosenthal · Joachim Sicking · Fabian Hüger · Thorsten Bagdonat · Hanno Gottschalk · Leo Schwinn

INST-IT: Boosting Instance Understanding via Explicit Visual Prompt Instruction Tuning

Wujian Peng · Lingchen Meng · Yitong Chen · Yiweng Xie · Yang Liu · Tao Gui · Hang Xu · Xipeng Qiu · Zuxuan Wu · Yu-Gang Jiang

OpenMMEgo: Enhancing Egocentric Understanding for LMMs with Open Weights and Data

Hao Luo · Zihao Yue · Wanpeng Zhang · Yicheng Feng · Sipeng Zheng · Deheng Ye · Zongqing Lu

Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding

Ye Wang · Ziheng Wang · Boshen Xu · Yang Du · Kejun Lin · Zihan Xiao · Zihao Yue · Jianzhong Ju · Liang Zhang · Dingyi Yang · Xiangnan Fang · Zewen He · Zhenbo Luo · Wenxuan Wang · Junqi Lin · Jian Luan · Qin Jin

REOrdering Patches Improves Vision Models

Declan Kutscher · David Chan · Yutong Bai · Trevor Darrell · Ritwik Gupta

MERIT: Multilingual Semantic Retrieval with Interleaved Multi-Condition Query

Wei Chow · Yuan Gao · Linfeng Li · Xian Wang · Qi Xu · Hang Song · Lingdong Kong · Ran Zhou · Yi Zeng · Yidong Cai · Botian Jiang · Shilin Xu · Jiajunzhang · Minghui Qiu · Xiangtai Li · Tianshu Yang · Siliang Tang · Juncheng Li

One Token per Highly Selective Frame: Towards Extreme Compression for Long Video Understanding

Zheyu Zhang · Ziqi Pang · Shixing Chen · Xiang Hao · Vimal Bhat · Yu-Xiong Wang

OnlineSplatter: Pose-Free Online 3D Reconstruction for Free-Moving Objects

Mark H. Huang · Lin Geng Foo · Christian Theobalt · Ying Sun · De Wen Soh

Vision Transformers with Self-Distilled Registers

Zipeng Yan · Yinjie Chen · Chong Zhou · Bo Dai · Andrew Luo

ExGra-Med: Extended Context Graph Alignment for Medical Vision-Language Models

Duy M. H. Nguyen · Nghiem Diep · Trung Nguyen · Hoang-Bao Le · Tai Nguyen · Anh-Tien Nguyen · TrungTin Nguyen · Nhat Ho · Pengtao Xie · Roger Wattenhofer · Daniel Sonntag · James Zou · Mathias Niepert

UFM: A Simple Path towards Unified Dense Correspondence with Flow

Yuchen Zhang · Nikhil Keetha · Chenwei Lyu · Bhuvan Jhamb · Yutian Chen · Yuheng Qiu · Jay Karhade · Shreyas Jha · Yaoyu Hu · Deva Ramanan · Sebastian Scherer · Wenshan Wang

ReID5o: Achieving Omni Multi-modal Person Re-identification in a Single Model

Jialong Zuo · Yongtai Deng · Mengdan Tan · Rui Jin · Dongyue Wu · Nong Sang · Liang Pan · Changxin Gao

VITRIX-UniViTAR: Unified Vision Transformer with Native Resolution

Limeng Qiao · Yiyang Gan · Bairui Wang · Jie Qin · Shuang Xu · Siqi Yang · Lin Ma

Towards Self-Refinement of Vision-Language Models with Triangular Consistency

Yunlong Deng · Guangyi Chen · Tianpei Gu · Lingjing Kong · Yan Li · Zeyu Tang · Kun Zhang

Confusion-Driven Self-Supervised Progressively Weighted Ensemble Learning for Non-Exemplar Class Incremental Learning

Kai Hu · Zhang Yu · Yuan Zhang · Zhineng Chen · Xieping Gao

VL-SAM-V2: Open-World Object Detection with General and Specific Query Fusion

Zhiwei Lin · Yongtao Wang

MEgoHand: Multimodal Egocentric Hand-Object Interaction Motion Generation

Bohan Zhou · Yi Zhan · Zhongbin Zhang · Zongqing Lu

Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning

Fanrui Zhang · Dian Li · Qiang Zhang · Chenjun · sinbadliu · Junxiong Lin · Jiahong Yan · Jiawei Liu · Zheng-Jun Zha

SegMASt3R: Geometry Grounded Segment Matching

Rohit Jayanti · Swayam Agrawal · Vansh Garg · Siddharth Tourani · Muhammad Haris Khan · Sourav Garg · Madhava Krishna

RePIC: Reinforced Post-Training for Personalizing Multi-Modal Language Models

Yeongtak Oh · Dohyun Chung · Juhyeon Shin · Sangha Park · Johan Barthelemy · Jisoo Mok · Sungroh Yoon

Event-Guided Consistent Video Enhancement with Modality-Adaptive Diffusion Pipeline

Kanghao Chen · Zixin Zhang · Guoqiang Liang · Lutao Jiang · Zeyu Wang · Yingcong Chen

Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs

Qizhe Zhang · Mengzhen Liu · Lichen Li · Ming Lu · Yuan Zhang · Junwen Pan · Qi She · Shanghang Zhang

EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT

Baoqi Pei · Yifei Huang · Jilan Xu · Yuping He · Guo Chen · Fei Wu · Jiangmiao Pang · Yu Qiao

Chirality in Action: Time-Aware Video Representation Learning by Latent Straightening

Piyush Nitin Bagad · Andrew Zisserman

Taming generative video models for zero-shot optical flow extraction

Seungwoo Kim · Khai Loong Aw · Klemen Kotar · Cristobal Eyzaguirre · Wanhee Lee · Yunong Liu · Jared Watrous · Stefan Stojanov · Juan Carlos Niebles · Jiajun Wu · Daniel Yamins

MixPrompt: Efficient Mixed Prompting for Multimodal Semantic Segmentation

Zhiwei Hao · Zhongyu Xiao · Jianyuan Guo · Li Shen · Yong Luo · Han Hu · Dan Zeng

Where Does It Exist from the Low-Altitude: Spatial Aerial Video Grounding

Yang Zhan · Yuan Yuan

iFinder: Structured Zero-Shot Vision-Based LLM Grounding for Dash-Cam Video Reasoning

Manyi Yao · Bingbing Zhuang · Sparsh Garg · Amit Roy-Chowdhury · Christian Shelton · Manmohan Chandraker · Abhishek Aich

From Human Attention to Diagnosis: Semantic Patch-Level Integration of Vision-Language Models in Medical Imaging

Dmitry Lvov · Ilya Pershin

SCOPE: Saliency-Coverage Oriented Token Pruning for Efficient Multimodel LLMs

Jinhong Deng · Wen Li · Joey Tianyi Zhou · Yang He

CausalVTG: Towards Robust Video Temporal Grounding via Causal Inference

Qiyi Wang · Senda Chen · Ying Shen

TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs

Yunheng Li · Jing Cheng · Shaoyong Jia · Hangyi Kuang · Shaohui Jiao · Qibin Hou · Ming-Ming Cheng

From Forecasting to Planning: Policy World Model for Collaborative State-Action Prediction

Zhida Zhao · Talas Fu · Yifan Wang · Lijun Wang · Huchuan Lu

Automatic Synthetic Data and Fine-grained Adaptive Feature Alignment for Composed Person Retrieval

Delong Liu · Haiwen Li · Zhaohui Hou · Zhicheng Zhao · Fei Su · Yuan Dong

MotionBind: Multi-Modal Human Motion Alignment for Retrieval, Recognition, and Generation

Kaleab Kinfu · Rene Vidal

Scaling Image Geo-Localization to Continent Level

Philipp Lindenberger · Paul-Edouard Sarlin · Jan Hosang · Marc Pollefeys · Simon Lynen · Eduard Trulls

Balanced Token Pruning: Accelerating Vision Language Models Beyond Local Optimization

kaiyuan Li · Xiaoyue Chen · Chen Gao · Yong Li · Xinlei Chen

InstructRestore: Region-Customized Image Restoration with Human Instructions

Shuaizheng Liu · Jianqi Ma · Lingchen Sun · Xiangtao Kong · Lei Zhang

SpaceServe: Spatial Multiplexing of Complementary Encoders and Decoders for Multimodal LLMs

zhicheng li · Shuoming Zhang · Jiacheng Zhao · Siqi Li · Xiyu Shi · Yangyu Zhang · Shuaijiang Li · Donglin Yu · Zheming Yang · YUAN WEN · Huimin Cui

HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios

Kunyu Peng · Junchao Huang · Xiangsheng Huang · Di Wen · Junwei Zheng · Yufan Chen · Kailun Yang · Jiamin Wu · Chongqing Hao · Rainer Stiefelhagen

Distil-E2D: Distilling Image-to-Depth Priors for Event-Based Monocular Depth Estimation

Jie Long Lee · Gim Hee Lee

Iterative Tool Usage Exploration for Multimodal Agents via Step-wise Preference Tuning

Pengxiang Li · Zhi Gao · Bofei Zhang · Yapeng Mi · Xiaojian (Shawn) Ma · Chenrui Shi · Tao Yuan · Yuwei Wu · Yunde Jia · Song-Chun Zhu · Qing Li

BioCLIP 2: Emergent Properties from Scaling Hierarchical Contrastive Learning

Jianyang Gu · Sam Stevens · Elizabeth Campolongo · Matthew Thompson · Net Zhang · Jiaman Wu · Andrei Kopanev · Zheda Mai · Alexander White · James Balhoff · Wasila Dahdul · Daniel Rubenstein · Hilmar Lapp · Tanya Berger-Wolf · Wei-Lun (Harry) Chao · Yu Su

Learning the Wrong Lessons: Syntactic-Domain Spurious Correlations in Language Models

Chantal Shaib · Vinith Suriyakumar · Byron Wallace · Marzyeh Ghassemi

Interaction-Centric Knowledge Infusion and Transfer for Open Vocabulary Scene Graph Generation

Lin Li · Chuhan ZHANG · Dong Zhang · Chong Sun · Chen Li · Long Chen

CQ-DINO: Mitigating Gradient Dilution via Category Queries for Vast Vocabulary Object Detection

Zhichao Sun · Huazhang Hu · Yidong Ma · Gang Liu · Yibo Chen · Xu Tang · Yao Hu · Yongchao Xu

Knowledge Graph Enhanced Generative Multi-modal Models for Class-Incremental Learning

Xusheng Cao · Haori Lu · Linlan Huang · Fei Yang · Xialei Liu · Ming-Ming Cheng

OmniGaze: Reward-inspired Generalizable Gaze Estimation in the Wild

Hongyu Qu · Jianan Wei · Xiangbo Shu · Yazhou Yao · Wenguan Wang · Jinhui Tang

Diffusing DeBias: Synthetic Bias Amplification for Model Debiasing

Massimiliano Ciranni · Vito Paolo Pastore · Roberto Di Via · Enzo Tartaglione · Francesca Odone · Vittorio Murino

Dual-Space Semantic Synergy Distillation for Continual Learning of Unlabeled Streams

Donghao Sun · Xi Wang · Xu Yang · Kun Wei · Cheng Deng

CoralVQA: A Large-Scale Visual Question Answering Dataset for Coral Reef Image Understanding

hongyong han · Wei Wang · Gaowei Zhang · Mingjie Li · Yi Wang

egoEMOTION: Egocentric Vision and Physiological Signals for Emotion and Personality Recognition in Real-world Tasks

Matthias Jammot · Björn Braun · Paul Streli · Rafael Wampfler · Christian Holz

Mamba Goes HoME: Hierarchical Soft Mixture-of-Experts for 3D Medical Image Segmentation

Szymon Płotka · Gizem Mert · Maciej Chrabaszcz · Ewa Szczurek · Arkadiusz Sitek

Differentiable Hierarchical Visual Tokenization

Marius Aasan · Martine Hjelkrem Tan · Nico Catalano · Changkyu Choi · Adín Ramírez Rivera

Continual Gaussian Mixture Distribution Modeling for Class Incremental Semantic Segmentation

Guilin Zhu · Runmin Wang · Yuanjie Shao · Wei dong Yang · Nong Sang · Changxin Gao

Towards Unsupervised Domain Bridging via Image Degradation in Semantic Segmentation

Wangkai Li · Rui Sun · Huayu Mai · Tianzhu Zhang

MATCH: Multi-faceted Adaptive Topo-Consistency for Semi-Supervised Histopathology Segmentation

Meilong Xu · Xiaoling Hu · Shahira Abousamra · Chen Li · Chao Chen

Gate to the Vessel: Residual Experts Restore What SAM Overlooks

Weili Jiang · Jinrong Lv · Xun Gong · Xiaomeng Li · Chubin Ou

CamSAM2: Segment Anything Accurately in Camouflaged Videos

Yuli Zhou · Yawei Li · Yuqian Fu · Luca Benini · Ender Konukoglu · Guolei Sun

VQ-Seg: Vector-Quantized Token Perturbation for Semi-Supervised Medical Image Segmentation

Sicheng Yang · Zhaohu Xing · Lei Zhu

GauSAM: Contour‑Guided 2D Gaussian Fields for Multi‑Scale Medical Image Segmentation with Segment Anything

Jinxuan Wu · Jiange Wang · Dongdong Zhang

Bringing SAM to new heights: leveraging elevation data for tree crown segmentation from drone imagery

Mélisande Teng · Arthur Ouaknine · Etienne Laliberté · Yoshua Bengio · David Rolnick · Hugo Larochelle

C-LoRA: Contextual Low-Rank Adaptation for Uncertainty Estimation in Large Language Models

Amir Hossein Rahmati · Sanket Jantre · Weifeng Zhang · Yucheng Wang · Byung-Jun Yoon · Nathan Urban · Xiaoning Qian

Convolution Goes Higher-Order: A Biologically Inspired Mechanism Empowers Image Classification

Simone Azeglio · Olivier Marre · Peter Neri · Ulisse Ferrari

Smooth Regularization for Efficient Video Recognition

Gil Goldman · Raja Giryes · Mahadev Satyanarayanan

PartNeXt: A Next-Generation Dataset for Fine-Grained and Hierarchical 3D Part Understanding

Penghao Wang · Yiyang He · Xin Lv · Yukai Zhou · Lan Xu · Jingyi Yu · Jiayuan Gu

AGC-Drive: A Large-Scale Dataset for Real-World Aerial-Ground Collaboration in Driving Scenarios

Yunhao Hou · Bochao Zou · Min Zhang · 燃陈 · Shangdong Yang · Yanmei Zhang · Junbao Zhuo · Siheng Chen · Jiansheng Chen · Huimin Ma

HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object Interaction

Jikai Wang · Qifan Zhang · Yu-Wei Chao · Bowen Wen · Xiaohu Guo · Yu Xiang

UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception

Karthikeyan Chandra Sekaran · Markus Geisler · Dominik Rößle · Adithya Mohan · Daniel Cremers · Wolfgang Utschick · Michael Botsch · Werner Huber · Torsten Schön

How to Scale Second-Order Optimization

Charlie Chen · Shikai Qiu · Hoang Phan · Qi Lei · Andrew Wilson

GTR-Loc: Geospatial Text Regularization Assisted Outdoor LiDAR Localization

Shangshu Yu · Wen Li · Xiaotian Sun · Zhimin Yuan · Xin Wang · Sijie Wang · Rui She · Cheng Wang

Unraveling Metameric Dilemma for Spectral Reconstruction: A High-Fidelity Approach via Semi-Supervised Learning

Xingxing Yang · Jie Chen · Zaifeng Yang

DualEqui: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules

Junjie Xu · Jiahao Zhang · Mangal Prakash · Xiang Zhang · Suhang Wang

VIKING: Deep variational inference with stochastic projections

Samuel Matthiesen · Hrittik Roy · Nicholas Krämer · Yevgen Zainchkovskyy · Stas Syrota · Alejandro Valverde Mahou · Carl Henrik Ek · Søren Hauberg

FRBNet: Revisiting Low-Light Vision through Frequency-Domain Radial Basis Network

Fangtong Sun · Congyu Li · Ke Yang · Yuchen Pan · Hanwen Yu · Xichuan Zhang · Yiying Li

Instant Video Models: Universal Adapters for Stabilizing Image-Based Networks

Matthew Dutson · Nathan Labiosa · Yin Li · Mohit Gupta

ELDET: Early-Learning Distillation with Noisy Labels for Object Detection

Dongmin Choi · Sangbin Lee · EungGu Yun · Jonghyuk Baek · Frank Park

Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning

Ankan Deria · Adinath Dukre · feilong tang · Sara Atito · Sudipta Roy · Muhammad Awais · Muhammad Haris Khan · Imran Razzak

SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Tracking

Shubo Lin · Yutong Kou · Zirui Wu · Shaoru Wang · Bing Li · Weiming Hu · Jin Gao

Under the Shadow: Exploiting Opacity Variation for Fine-grained Shadow Detection

Xiaotian Qiao · Ke Xu · Xianglong Yang · Ruijie Dong · Xiaofang Xia · Jiangtao Cui

BitMark: Watermarking Bitwise Autoregressive Image Generative Models

Louis Kerner · Michel Meintz · Bihe Zhao · Franziska Boenisch · Adam Dziedzic

Spiking Meets Attention: Efficient Remote Sensing Image Super-Resolution with Attention Spiking Neural Networks

Yi Xiao · Qiangqiang Yuan · Kui Jiang · Wenke Huang · Qiang Zhang · Tingting Zheng · Chia-Wen Lin · Liangpei Zhang

3DPE-Gaze:Unlocking the Potential of 3D Facial Priors for Generalized Gaze Estimation

Yangshi Ge · Yiwei Bao · Feng Lu

Bézier Splatting for Fast and Differentiable Vector Graphics Rendering

Xi Liu · Chaoyi Zhou · Nanxuan Zhao · Siyu Huang

Bayesian Concept Bottleneck Models with LLM Priors

Jean Feng · Avni Kothari · Lucas Zier · Chandan Singh · Yan Shuo Tan

Personalized Bayesian Federated Learning with Wasserstein Barycenter Aggregation

Ting Wei · Biao Mei · Junliang Lyu · Renquan Zhang · Feng Zhou · Yifan Sun

How many measurements are enough? Bayesian recovery in inverse problems with general distributions

Ben Adcock · Zi Yuan (Nick) Huang

Quantifying Uncertainty in the Presence of Distribution Shifts

Yuli Slavutsky · David Blei

Conformal Prediction for Ensembles: Improving Efficiency via Score-Based Aggregation

Yash Patel · Eduardo Ochoa Rivera · Ambuj Tewari

Synergy Between the Strong and the Weak: Spiking Neural Networks are Inherently Self-Distillers

Yongqi Ding · Lin Zuo · Mengmeng Jing · Kunshan Yang · Pei He · Tonglan Xie

Smooth Sailing: Lipschitz-Driven Uncertainty Quantification for Spatial Associations

David Burt · Renato Berlinghieri · Stephen Bates · Tamara Broderick

SING: SDE Inference via Natural Gradients

Amber Hu · Henry Smith · Scott Linderman

Conformal Prediction for Time-series Forecasting with Change Points

Sophia Sun · Rose Yu

Can LLMs Correct Themselves? A Benchmark of Self-Correction in LLMs

Guiyao Tie · Zenghui Yuan · Zeli Zhao · Chaoran Hu · Tianhe Gu · Ruihang Zhang · Sizhe Zhang · Junran Wu · Xiaoyue Tu · Ming Jin · Qingsong Wen · Lixing Chen · Pan Zhou · Lichao Sun

SoMi-ToM: Evaluating Multi-Perspective Theory of Mind in Embodied Social Interactions

Xianzhe Fan · Xuhui Zhou · Chuanyang Jin · Kolby Nottingham · Hao Zhu · Maarten Sap

PSMBench: A Benchmark and Dataset for Evaluating LLMs Extraction of Protocol State Machines from RFC Specifications

Zilin Shen · Xinyu Luo · Imtiaz Karim · Elisa Bertino

BMMR: A Large-Scale Bilingual Multimodal Multi-Discipline Reasoning Dataset

Zhiheng Xi · Guanyu Li · Yutao Fan · Honglin Guo · Yufang Liu · Xiaoran Fan · Jiaqi Liu · dingjinchao · Wangmeng Zuo · Zhenfei Yin · LEI BAI · Tao Ji · Tao Gui · Qi Zhang · Xuanjing Huang

Position: Towards Bidirectional Human-AI Alignment

Hua Shen · Tiffany Knearem · Reshmi Ghosh · Kenan Alkiek · Kundan Krishna · Liu Yachuan · Savvas Petridis · Yi-Hao Peng · Li Qiwei · Chenglei Si · Yutong Xie · Jeffrey Bigham · Frank Bentley · Joyce Chai · Zachary Lipton · Qiaozhu Mei · Michael Terry · Diyi Yang · Meredith Morris · Paul Resnick · David Jurgens

Statistics Caching Test-Time Adaptation for Vision-Language Models

Zenghao Guan · Yucan Zhou · Wu Liu · Xiaoyan Gu

Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection

Gongzhe Li · Linwei Qiu · Peibei Cao · Fengying Xie · Xiangyang Ji · Qilin Sun

Concerto: Joint 2D-3D Self-Supervised Learning Emerges Spatial Representations

Yujia Zhang · Xiaoyang Wu · Yixing Lao · Chengyao Wang · Zhuotao Tian · Naiyan Wang · Hengshuang Zhao

3D Gaussian Splatting based Scene-independent Relocalization with Unidirectional and Bidirectional Feature Fusion

Junyi Wang · Yuze Wang · Wantong Duan · Meng Wang · Yue Qi

RayFusion: Ray Fusion Enhanced Collaborative Visual Perception

Shaohong Wang · Lu Bin · Xinyu Xiao · Hanzhi Zhong · Bowen Pang · Tong Wang · Zhiyu Xiang · Hangguan Shan · Eryun Liu

Flow based approach for Dynamic Temporal Causal models with non-Gaussian or Heteroscedastic Noises

Abdellah Rahmani · Pascal Frossard

Event-Driven Dynamic Scene Depth Completion

Zhiqiang Yan · Jianhao Jiao · Zhengxue Wang · Gim Hee Lee

Breaking the Discretization Barrier of Continuous Physics Simulation Learning

Fan Xu · Hao Wu · Nan Wang · Lilan Peng · Kun Wang · Wei Gong · Xibin Zhao

Deep Continuous-Time State-Space Models for Marked Event Sequences

Yuxin Chang · Alex Boyd · Cao (Danica) Xiao · Taha Kass-Hout · Parminder Bhatia · Padhraic Smyth · andrew warrington

Towards Robust Zero-Shot Reinforcement Learning

Kexin ZHENG · Lauriane Teyssier · Yinan Zheng · Yu Luo · Xianyuan Zhan

Zero-shot World Models via Search in Memory

Federico Malato · Ville Hautamäki

Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction

Junhong Shen · Hao Bai · Lunjun Zhang · Yifei Zhou · Amrith Setlur · Peter Tong · Diego Caples · Nan Jiang · Tong Zhang · Ameet Talwalkar · Aviral Kumar

Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning

Yuhao Zhou · Yiheng Wang · Xuming He · Ruoyao Xiao · Zhiwei Li · Qiantai Feng · Zijie Guo · Yuejin Yang · Hao Wu · Wenxuan Huang · Jiaqi Wei · Dan Si · YAO XIUQI · Jia Bu · Haiwen Huang · Tianfan Fu · SHIXIANG TANG · Ben Fei · Dongzhan Zhou · Fenghua Ling · Yan Lu · Siqi Sun · Chenhui Li · Guanjie Zheng · Jiancheng Lv · Wenlong Zhang · LEI BAI

OmniBench: Towards The Future of Universal Omni-Language Models

Yizhi Li · Ge Zhang · Yinghao Ma · Ruibin Yuan · Zhu · Hangyu Guo · Yiming Liang · Jiaheng Liu · Noah Wang · Jian Yang · Siwei Wu · Xingwei Qu · Jinjie Shi · Xinyue Zhang · Zhenzhu Yang · Yidan WEN · Yanghai Wang · Shihao Li · ZHAO-XIANG ZHANG · Ruibo Liu · Emmanouil Benetos · Wenhao Huang · Chenghua Lin

Envisioning Beyond the Pixels: Benchmarking Reasoning-Informed Visual Editing

Xiangyu Zhao · Peiyuan Zhang · Kexian Tang · Xiaorong Zhu · Hao Li · Wenhao Chai · Zicheng Zhang · Renqiu Xia · Guangtao Zhai · Junchi Yan · Hua Yang · Xue Yang · Haodong Duan

KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models

Yongliang Wu · Zonghui Li · Xinting Hu · Xinyu Ye · Xianfang Zeng · Gang Yu · Wenbo Zhu · Bernt Schiele · Ming-Hsuan Yang · Xu Yang

AHa-Bench: Benchmarking Audio Hallucinations in Large Audio-Language Models

Xize Cheng · Dongjie Fu · Chenyuhao Wen · Shannon Yu · Zehan Wang · Shengpeng Ji · Siddhant Arora · Tao Jin · Shinji Watanabe · Zhou Zhao

GenSpace: Benchmarking Spatially-Aware Image Generation

Zehan Wang · Jiayang Xu · Ziang Zhang · Tianyu Pang · Chao Du · Hengshuang Zhao · Zhou Zhao

Online Time Series Forecasting with Theoretical Guarantees

Zijian Li · Changze Zhou · Minghao Fu · Sanjay Manjunath · Fan Feng · Guangyi Chen · Yingyao Hu · Ruichu Cai · Kun Zhang

VLMs can Aggregate Scattered Training Patches

Zhanhui Zhou · Lingjie Chen · Chao Yang · Chaochao Lu

FlowPrune: Accelerating Attention Flow Calculation by Pruning Flow Network

Shuo Xu · Yu Chen · Shuxia Lin · Xin Geng · Xu Yang

4D-LRM: Large Space-Time Reconstruction Model From and To Any View at Any Time

Ziqiao Ma · Xuweiyi Chen · Shoubin Yu · Sai Bi · Kai Zhang · Ziwen Chen · Sihan Xu · Jianing Yang · Zexiang Xu · Kalyan Sunkavalli · Mohit Bansal · Joyce Chai · Hao Tan

Learning to Generalize: An Information Perspective on Neural Processes

Hui Li · Huafeng Liu · Shuyang Lin · Jingyue Shi · Yiran Fu · Liping Jing

OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-time Emotional Speech Synthesis

Run Luo · Ting-En Lin · Haonan Zhang · Yuchuan Wu · Xiong Liu · Yongbin Li · Longze Chen · Jiaming Li · Lei Zhang · Xiaobo Xia · Hamid Alinejad-Rokny · Fei Huang · Min Yang

REMI: Reconstructing Episodic Memory During Internally Driven Path Planning

Zhaoze Wang · Genela Morris · Dori Derdikman · Pratik Chaudhari · Vijay Balasubramanian

Why and How LLMs Hallucinate: Connecting the Dots with Subsequence Associations

Yiyou Sun · Yu Gai · Lijie Chen · Abhilasha Ravichander · Yejin Choi · Nouha Dziri · Dawn Song

Differentially Private Bilevel Optimization: Efficient Algorithms with Near-Optimal Rates

Andrew Lowy · Daogao Liu

CoCoA: A Minimum Bayes Risk Framework Bridging Confidence and Consistency for Uncertainty Quantification in LLMs

Roman Vashurin · Maiya Goloburda · Albina Ilina · Aleksandr Rubashevskii · Preslav Nakov · Artem Shelmanov · Maxim Panov

4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos

Mengqi Guo · Bo Xu · Yanyan Li · Gim Hee Lee

FOCUS: Unified Vision-Language Modeling for Interactive Editing Driven by Referential Segmentation

Fan Yang · Yousong Zhu · Xin Li · Yufei Zhan · Hongyin Zhao · Shurong Zheng · Yaowei Wang · Ming Tang · Jinqiao Wang

Class-aware Domain Knowledge Fusion and Fission for Continual Test-Time Adaptation

Jiahuan Zhou · Chao Zhu · Zhenyu Cui · Zichen Liu · Xu Zou · Gang Hua

Generative RLHF-V: Learning Principles from Multi-modal Human Preference

Jiayi Zhou · Jiaming Ji · Boyuan Chen · Jiapeng Sun · wenqi chen · Donghai Hong · Sirui Han · Yike Guo · Yaodong Yang

Fast Projection-Free Approach (without Optimization Oracle) for Optimization over Compact Convex Set

Chenghao Liu · Enming Liang · Minghua Chen

Balancing Positive and Negative Classification Error Rates in Positive-Unlabeled Learning

Ximing Li · Yuanchao Dai · Bing Wang · Changchun Li · Jianfeng Qu · Renchu Guan

Solving the Asymmetric Traveling Salesman Problem via Trace-Guided Cost Augmentation

Zhen Zhang · Prof Javen Qinfeng Shi · Wee Sun Lee

Measuring AI Ability to Complete Long Software Tasks

Thomas Kwa · Ben West · Joel Becker · Amy Deng · Katharyn Garcia · Max Hasin · Sami Jawhar · Megan Kinniment · Nate Rush · Sydney Von Arx · Ryan Bloom · Thomas Broadley · Haoxing Du · Brian Goodrich · Nikola Jurkovic · Luke Miles · Seraphina Nix · Tao Lin · Neev Parikh · David Rein · Lucas Jun Koba Sato · Hjalmar Wijk · Daniel Ziegler · Elizabeth Barnes · Lawrence Chan

Guarantees for Alternating Least Squares in Overparameterized Tensor Decompositions

Dionysis Arvanitakis · Vaidehi Srinivas · Aravindan Vijayaraghavan

Feedback Guidance of Diffusion Models

Felix Koulischer · Florian Handke · Johannes Deleu · Thomas Demeester · Luca Ambrogioni

On Geometry-Enhanced Parameter-Efficient Fine-Tuning for 3D Scene Segmentation

Liyao Tang · Zhe Chen · Dacheng Tao

SIFusion: A Unified Fusion Framework for Multi-granularity Arctic Sea Ice Forecasting

Jingyi Xu · Shengnan Wang · Weidong Yang · Keyi Liu · Yeqi Luo · Ben Fei · LEI BAI

On the SAC-BL Algorithm for Anomaly Detection

Xinsong Ma · Jie Wu · Weiwei Liu

Towards Visualization-of-Thought Jailbreak Attack against Large Visual Language Models

HongQiong Zhong · Qingyang Teng · Baolin Zheng · Guanlin Chen · Yingshui Tan · Zhendong Liu · Jiaheng Liu · Wenbo Su · Xiaoyong Zhu · Bo Zheng · Kaifu Zhang

URLs Help, Topics Guide: Understanding Metadata Utility in LLM Training

Dongyang Fan · Vinko Sabolčec · Martin Jaggi

MPS-Prover: Advancing Stepwise Theorem Proving by Multi-Perspective Search and Data Curation

Zhenwen Liang · Linfeng Song · Yang Li · TAO YANG · Haitao Mi · Dong Yu

Length Generalization via Auxiliary Tasks

Pranjal Awasthi · Anupam Gupta · Ravi Kumar

CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward

Yandong Guan · Xilin Wang · XiMing Xing · Jing Zhang · Dong Xu · Qian Yu

DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data

Ruiqi Wu · Xinjie wang · Liu.Liu · Chun-Le Guo · Jiaxiong Qiu · Chongyi Li · Lichao Huang · Zhizhong Su · Ming-Ming Cheng

ShiQ: Bringing back Bellman to LLMs

Pierre Clavier · Nathan Grinsztajn · Raphaël Avalos · Yannis Flet-Berliac · Irem Ergun · Omar Darwiche Domingues · Olivier Pietquin · Pierre Richemond · Florian Strub · Matthieu Geist

FlexAC: Towards Flexible Control of Associative Reasoning in Multimodal Large Language Models

shengming yuan · Xinyu Lyu · Shuailong Wang · Beitao Chen · Jingkuan Song · Lianli Gao

Probing Hidden Knowledge Holes in Unlearned LLMs

Myeongseob Ko · Hoang Anh Just · Charles Fleming · Ming Jin · Ruoxi Jia

Generative Trajectory Stitching through Diffusion Composition

Yunhao Luo · Utkarsh Mishra · Yilun Du · Danfei Xu

Alignment of Large Language Models with Constrained Learning

Botong Zhang · Shuo Li · Ignacio Hounie · Osbert Bastani · Dongsheng Ding · Alejandro Ribeiro

Composition and Alignment of Diffusion Models using Constrained Learning

Shervin Khalafi · Ignacio Hounie · Dongsheng Ding · Alejandro Ribeiro

JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent

Yunlong Lin · Zixu Lin · Kunjie Lin · Jinbin Bai · Panwang Pan · Chenxin Li · Haoyu Chen · Zhongdao Wang · Xinghao Ding · Wenbo Li · Shuicheng Yan

Unified Transferability Metrics for Time Series Foundation Models

Weiyang Zhang · Xinyang Chen · Xiucheng Li · Kehai Chen · Weili Guan · Liqiang Nie

VeriThinker: Learning to Verify Makes Reasoning Model Efficient

Zigeng Chen · Xinyin Ma · Gongfan Fang · Ruonan Yu · Xinchao Wang

KGGen: Extracting Knowledge Graphs from Plain Text with Language Models

Belinda Mo · Kyssen Yu · Joshua Kazdan · Proud Mpala · Lisa Yu · Charilaos Kanatsoulis · Sanmi Koyejo

Is Your Diffusion Model Actually Denoising?

Daniel Pfrommer · Zehao Dou · Christopher Scarvelis · Max Simchowitz · Ali Jadbabaie

AlignedGen: Aligning Style Across Generated Images

Jiexuan Zhang · Yiheng Du · Qian Wang · Weiqi Li · Yu Gu · Jian Zhang

Meta-learning how to Share Credit among Macro-Actions

Ionel-Alexandru Hosu · Traian Rebedea · Razvan Pascanu

Generalized and Invariant Single-Neuron In-Vivo Activity Representation Learning

Wei Wu · Yuxing Lu · Zhengrui Guo · Chi Zhang · Can Liao · Yifan Bu · Fangxu Zhou · Jinzhuo Wang

Hardware-aligned Hierarchical Sparse Attention for Efficient Long-term Memory Access

Xiang Hu · Jiaqi Leng · Jun Zhao · Kewei Tu · Wei Wu

DIFFSSR: Stereo Image Super-resolution Using Differential Transformer

Dafeng Zhang

Large Language Bayes

Justin Domke

Spiking Neural Networks Need High-Frequency Information

Yuetong Fang · Deming Zhou · Ziqing Wang · Hongwei Ren · zeng zecui · Lusong Li · shibo zhou · Renjing Xu

Rebalancing Return Coverage for Conditional Sequence Modeling in Offline Reinforcement Learning

Wensong Bai · Chufan Chen · Yichao Fu · Qihang Xu · zhang chao · Hui Qian

Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment

Woojun Kim · Katia Sycara

RoME: Domain-Robust Mixture-of-Experts for MILP Solution Prediction across Domains

Tianle Pu · Zijie Geng · Haoyang Liu · Shixuan Liu · Jie Wang · Li Zeng · Chao Chen · Changjun Fan

OWMM-Agent: Open World Mobile Manipulation With Multi-modal Agentic Data Synthesis

Junting Chen · Haotian Liang · Lingxiao Du · Weiyun Wang · Mengkang Hu · Yao Mu · Wenhai Wang · Jifeng Dai · Ping Luo · Wenqi Shao · Lin Shao

Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO

Chengzhuo Tong · Ziyu Guo · Renrui Zhang · Wenyu Shan · Xinyu Wei · Zhenghao Xing · Hongsheng Li · Pheng-Ann Heng

Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets

Yuandong Tian

Enhancing CLIP Robustness via Cross-Modality Alignment

Xingyu Zhu · Beier Zhu · Shuo Wang · Kesen Zhao · Hanwang Zhang

A Set of Generalized Components to Achieve Effective Poison-only Clean-label Backdoor Attacks with Collaborative Sample Selection and Triggers

Zhixiao Wu · Yao Lu · Jie Wen · Hao Sun · Qi Zhou · Guangming Lu

Vinci: Deep Thinking in Text-to-Image Generation using Unified Model with Reinforcement Learning

wang lin · Wentao Hu · Liyu Jia · Kaihang Pan · Majun Zhang · Zhou Zhao · Fei Wu · Jingyuan Chen · Hanwang Zhang

Object-centric 3D Motion Field for Robot Learning from Human Videos

Zhao-Heng Yin · Sherry Yang · Pieter Abbeel

SAGE: A Unified Framework for Generalizable Object State Recognition with State-Action Graph Embedding

Yuan Zang · Zitian Tang · Junho Cho · Jaewook Yoo · Chen Sun

A Closer Look to Positive-Unlabeled Learning from Fine-grained Perspectives: An Empirical Study

Yuanchao Dai · Zhengzhang Hou · Changchun Li · Yuanbo Xu · En Wang · Ximing Li

Fast exact recovery of noisy matrix from few entries: the infinity norm approach

BaoLinh Tran · Van Vu

UniLumos: Fast and Unified Image and Video Relighting with Physics-Plausible Feedback

Pengwei Liu · Hangjie Yuan · Bo Dong · Jiazheng Xing · Jinwang Wang · Rui Zhao · Weihua Chen · Fan Wang

Gaussian Processes for Shuffled Regression

Masahiro Kohjima

A Black-Box Debiasing Framework for Conditional Sampling

Han Cui · Jingbo Liu

Sampling by averaging: A multiscale approach to score estimation

Paula Cordero-Encinar · Andrew Duncan · Sebastian Reich · O. Deniz Akyildiz

Sampling from multi-modal distributions with polynomial query complexity in fixed dimension via reverse diffusion

Adrien Vacher · Omar Chehab · Anna Korba

Learning Latent Variable Models via Jarzynski-adjusted Langevin Algorithm

James Cuin · Davide Carbone · O. Deniz Akyildiz

Asymptotically exact variational flows via involutive MCMC kernels

Zuheng (David) Xu · Trevor Campbell

Small Resamples, Sharp Guarantees: Convergence Rates for Resampled Studentized Quantile Estimators

Imon Banerjee · Sayak Chakrabarty

Discrete Neural Flow Samplers with Locally Equivariant Transformer

Zijing Ou · Ruixiang Zhang · Yingzhen Li

SimpleStrat: Diversifying Language Model Generation with Stratification

Justin Wong · Yury Orlovskiy · Alexander Shypula · Michael Luo · Sanjit Seshia · Joseph Gonzalez

Low-Rank Graphon Learning for Networks

Xinyuan Fan · Feiyan Ma · Chenlei Leng · Weichi Wu

Neural Stochastic Flows: Solver-Free Modelling and Inference for SDE Solutions

Naoki Kiyohara · Edward Johns · Yingzhen Li

RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation

Songhao Han · Boxiang Qiu · Yue Liao · Siyuan Huang · Chen Gao · Shuicheng Yan · Si Liu

MetaBox-v2: A Unified Benchmark Platform for Meta-Black-Box Optimization

Zeyuan Ma · Yue-Jiao Gong · Hongshu Guo · Wenjie Qiu · Sijie Ma · Hongqiao Lian · Jiajun Zhan · Kaixu Chen · Chen Wang · Zhiyang Huang · Zechuan Huang · Guojun Peng · Ran Cheng · Yining Ma

How Memory in Optimization Algorithms Implicitly Modifies the Loss

Matias Cattaneo · Boris Shigida

GraLoRA: Granular Low-Rank Adaptation for Parameter-Efficient Fine-Tuning

Yeonjoon Jung · Daehyun Ahn · Hyungjun Kim · Taesu Kim · Eunhyeok Park

UniteFormer: Unifying Node and Edge Modalities in Transformers for Vehicle Routing Problems

Dian Meng · Zhiguang Cao · Jie Gao · Yaoxin Wu · Yaqing Hou

Bridging Crypto with ML-based Solvers: the SAT Formulation and Benchmarks

Xinhao Zheng · Xinhao Song · Bolin Qiu · Yang Li · Zhongteng Gui · Junchi Yan

Fractional Langevin Dynamics for Combinatorial Optimization via Polynomial-Time Escape

Shiyue Wang · Ziao Guo · Changhong Lu · Junchi Yan

Efficiently Escaping Saddle Points under Generalized Smoothness via Self-Bounding Regularity

Daniel Cao · August Chen · Karthik Sridharan · Benjamin Tang

Enhanced Cyclic Coordinate Descent Methods for Elastic Net Penalized Linear Models

Yixiao Wang · Zishan Shao · Ting Jiang · Aditya Devarakonda

Deep learning for continuous-time stochastic control with jumps

Patrick Cheridito · Jean-Loup Dupret · Donatien Hainaut

Decreasing Entropic Regularization Averaged Gradient for Semi-Discrete Optimal Transport

Ferdinand Genans · Antoine Godichon-Baggioni · François-Xavier Vialard · Olivier Wintenberger

Natural Gradient VI: Guarantees for Non-Conjugate Models

Fangyuan Sun · Ilyas Fatkhullin · Niao He

On the Convergence of Stochastic Smoothed Multi-Level Compositional Gradient Descent Ascent

Xinwen Zhang · Hongchang Gao

Isotropic Noise in Stochastic and Quantum Convex Optimization

Annie Marsden · Liam O'Carroll · Aaron Sidford · Chenyi Zhang

Constrained Optimization From a Control Perspective via Feedback Linearization

Runyu Zhang · Arvind Raghunathan · Jeff Shamma · Na Li

Problem-Parameter-Free Decentralized Bilevel Optimization

Zhiwei Zhai · Wenjing Yan · Ying-Jun Zhang

Fast Zeroth-Order Convex Optimization with Quantum Gradient Methods

Junhyung Lyle Kim · Brandon Augustino · Dylan Herman · Enrico Fontana · Jacob Watkins · Marco Pistoia · Shouvanik Chakrabarti

Sharper Convergence Rates for Nonconvex Optimisation via Reduction Mappings

Evan Markou · Thalaiyasingam Ajanthan · Stephen Gould

Quantum Speedups for Minimax Optimization and Beyond

Chengchang Liu · Zongqi Wan · Institute of Computing Jialin Zhang · Institute of Computing Xiaoming Sun · John C. S. Lui

CATransformers: Carbon Aware Transformers Through Joint Model-Hardware Optimization

Irene Wang · Mostafa Elhoushi · H Ekin Sumbul · Samuel Hsia · Daniel Jiang · Newsha Ardalani · Divya Mahajan · Carole-Jean Wu · Bilge Acun

DPAIL: Training Diffusion Policy for Adversarial Imitation Learning without Policy Optimization

Yunseon Choi · Minchan Jeong · Soobin Um · Kee-Eung Kim

Differentiation Through Black-Box Quadratic Programming Solvers

Connor Magoon · Fengyu Yang · Noam Aigerman · Shahar Kovalsky

Generative diffusion for perceptron problems: statistical physics analysis and efficient algorithms

Davide Straziota · Elizaveta Demyanenko · Carlo Baldassi · Carlo Lucibello

Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation

Mingfeng Fan · Jianan Zhou · Yifeng Zhang · Yaoxin Wu · Jinbiao Chen · Guillaume Sartoretti

Neural Combinatorial Optimization for Time Dependent Traveling Salesman Problem

Ruixiao Yang · Chuchu Fan

Online Two-Stage Submodular Maximization

Iasonas Nikolaou · Miltiadis Stouras · Stratis Ioannidis · Evimaria Terzi

A Unified Approach to Submodular Maximization Under Noise

Kshipra Bhawalkar · Yang Cai · Zhe Feng · Christopher Liaw · Tao Lin

Improved Algorithms for Fair Matroid Submodular Maximization

Sepideh Mahabadi · Sherry Sarkar · Jakub Tarnawski

Dynamic Configuration for Cutting Plane Separators via Reinforcement Learning on Incremental Graph

Mingxuan Ye · Jie Wang · Fangzhou · Zhihai Wang · Yufei Kuang · Xijun Li · Weilin Luo · Jianye Hao · Feng Wu

Efficient Algorithms for Robust and Partial Semi-Discrete Optimal Transport

Pankaj Agarwal · Sharath Raghvendra · Pouyan Shirzadian · Keegan Yao

PipeFusion: Patch-level Pipeline Parallelism for Diffusion Transformers Inference

Jiarui Fang · Jinzhe Pan · Aoyu Li · Xibo Sun · WANG Jiannan

Revisiting 1-peer exponential graph for enhancing decentralized learning efficiency

Kenta Niwa · Yuki Takezawa · Guoqiang Zhang · W. Kleijn

FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling

Hong Huang · Jinhai Yang · Yuan Chen · Jiaxun Ye · Dapeng Wu

Error Feedback under $(L_0,L_1)$-Smoothness: Normalization and Momentum

SARIT KHIRIRAT · Abdurakhmon Sadiev · Artem Riabinin · Eduard Gorbunov · Peter Richtarik

DUO: No Compromise to Accuracy Degradation

Jinda Jia · Cong Xie · Hanlin Lu · Fanjiang Ye · Hao Feng · Daoce Wang · Haibin Lin · Zhi Zhang · Xin Liu

Efficient Pre-Training of LLMs via Topology-Aware Communication Alignment on More Than 9600 GPUs

Guoliang He · Youhe Jiang · Wencong Xiao · Jiang Kaihua · Shuguang Wang · Jun Wang · Du Zixian · Zhuo Jiang · Xinlei Zhang · Binhang Yuan · Eiko Yoneki

Preference Optimization on Pareto Sets: On a Theory of Multi-Objective Optimization

Abhishek Roy · Geelon So · Yian Ma

Distributionally Robust Performative Optimization

Zhuangzhuang Jia · Yijie Wang · Roy Dong · Grani A. Hanasusanto

Smart Surrogate Losses for Contextual Stochastic Linear Optimization with Robust Constraints

Hyungki Im · Wyame Benslimane · Paul Grigas

FSNet: Feasibility-Seeking Neural Network for Constrained Optimization with Guarantees

Hoang Nguyen · Priya Donti

Prior Forgetting and In-Context Overfitting

Sungyoon Lee

Gradient Multi-Normalization for Efficient LLM Training

Meyer Scetbon · Chao Ma · Wenbo Gong · Ted Meeds

ASGO: Adaptive Structured Gradient Optimization

Kang An · Yuxing Liu · Rui Pan · Yi Ren · Shiqian Ma · Donald Goldfarb · Tong Zhang

On the $O(\frac{\sqrt{d}}{K^{1/4}})$ Convergence Rate of AdamW Measured by $\ell_1$ Norm

Huan Li · Yiming Dong · Zhouchen Lin

Energy Landscape-Aware Vision Transformers: Layerwise Dynamics and Adaptive Task-Specific Training via Hopfield States

Runze Xia · Richard Jiang

Exploring Landscapes for Better Minima along Valleys

Tong Zhao · Jiacheng Li · Yuanchang Zhou · Guangming Tan · Weile Jia

Pay Attention to Small Weights

chao zhou · Tom Jacobs · Advait Gadhikar · Rebekka Burkholz

Understanding Adam Requires Better Rotation Dependent Assumptions

Tianyue Zhang · Lucas Maes · Alan Milligan · Alexia Jolicoeur-Martineau · Ioannis Mitliagkas · Damien Scieur · Simon Lacoste-Julien · Charles Guille-Escuret

ACCO: Accumulate While You Communicate for Communication-Overlapped Sharded LLM Training

Adel Nabli · Louis Fournier · Pierre ERBACHER · Louis Serrano · Eugene Belilovsky · Edouard Oyallon

A Stable Whitening Optimizer for Efficient Neural Network Training

Kevin Frans · Sergey Levine · Pieter Abbeel

FSEO: Few-Shot Evolutionary Optimization via Meta-Learning for Expensive Multi-Objective Optimization

Xunzhao Yu

PRESTO: Preimage-Informed Instruction Optimization for Prompting Black-Box LLMs

Jaewon Chu · Seunghun Lee · Hyunwoo J. Kim

Why Popular MOEAs are Popular: Proven Advantages in Approximating the Pareto Front

Mingfeng Li · Qiang Zhang · Weijie Zheng · Benjamin Doerr

BO4Mob: Bayesian Optimization Benchmarks for High-Dimensional Urban Mobility Problem

Seunghee Ryu · Donghoon Kwon · Seongjin Choi · Aryan Deshwal · Seungmo Kang · Carolina Osorio

Preference-Guided Diffusion for Multi-Objective Offline Optimization

Yashas Annadani · Syrine Belakaria · Stefano Ermon · Stefan Bauer · Barbara Engelhardt

Near-Optimal Regret-Queue Length Tradeoff in Online Learning for Two-Sided Markets

Zixian Yang · Sushil Varma · Lei Ying

Go to Event Page

Social

The Role of AI in Scientific Peer Review

Thanh Gia Hieu Khuong · Isabelle Guyon · Benedictus Kent Rachmat · Ihsan Ullah · Zach Xu

7:00 PM - 9:00 PM

This social event will explore the role of Artificial Intelligence (AI) in addressing the current challenges and shaping the future of scientific peer review. We will examine how AI can be applied across the entire scholarly publishing process, from authoring to reviewing, editing, and even readership. The event will foster critical discussion on the ethical implications, potential benefits, and practical implementation of AI in this critical scientific process. Our goal is to bring together researchers, practitioners, and stakeholders from diverse fields in an interactive format to build community and explore actionable solutions for a more efficient, fair, and transparent peer review system.

... more

Social

Learning Theory Alliance

Gautam Kamath · Surbhi Goel

7:00 PM - 9:00 PM

This social will consist of a fireside chat with an established researcher in learning theory, followed by mentorship tables.

... more

Social

Agents Safety Panel

Connor Smith · Shannon Yang

7:00 PM - 9:00 PM

As AI systems become increasingly capable and widely deployed, ensuring their safety and reliability is more important than ever. Join us for a 30-minute panel discussion on the safety of agents from development to deployment, followed by a brief Q&A session. The rest of the event will consist of discussion and mingling among attendees. We will provide drinks and snacks. This event is co-organized by the Center for AI Safety (CAIS) and UK AI Security Institute (AISI).

... more

Reception

Muslims in ML Reception

7:00 PM - 9:00 PM

MusIML @ NeurIPS 2025 Social Event Guest of Honor: Professor Mubarak Shah (University of Central Florida) Special Guests: Abubakar Abid (Head of Applications @ Hugging Face) Industry Partner: Amazon

Join the social with Professor Mubarak Shah as the Guest of Honor, whose pioneering work in computer vision continues to inspire generations of ML researchers across the world, and Abubakar Abid from Hugging Face, who will join the social to connect with the next wave of AI innovators and discuss opportunities through the Fatima Fellowship.

The event will feature an exclusive 10-minute talk and an interactive booth hosted by Amazon, offering insights into industry-academia partnerships and research opportunities.

The MusIML Social Event at NeurIPS 2025 will be an evening of connection and sharing among AI/ML researchers across academia and industry. The gathering will bring together leading scholars, practitioners, and emerging researchers from the global Muslim AI/ML community. Snacks will be served.

... more

Social

Nonprofits Working on Openness and Trust in AI

Chia Hwu · Christopher Petrillo · Steven Pousty · Neil Majithia

7:00 PM - 9:00 PM

Join us for an in-person social event at NeurIPS 2025, to explore the intersections between generative ai data and open trusted datasets. This session will feature representatives from the Wikimedia Foundation, ML Comons and AI Alliance, offering an opportunity to connect with nonprofits committed to using technology for academic and social missions. The event will begin with presentations from both organizations, highlighting their goals, projects and research (e.g., Wikipedia, AI Alliance’s Open Trusted Data Initiative, MLCommon’s Croissant data standards) and challenges with trust and responsible data usage in AI. Following the presentations, the session will transition into roundtable discussions focused on current initiatives and an open Q&A.

... more