NeurIPS 2025 Thursday 12/4

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 Art of (Artificial) Reasoning

Yejin Choi

8:30 AM - 9:30 AM

Scaling laws suggest that “more is more” — brute-force scaling of data and compute leads to stronger AI capabilities. However, despite rapid progress on benchmarks, state-of-the-art models still exhibit "jagged intelligence," indicating that current scaling approaches may have limitations in terms of sustainability and robustness. Additionally, while the volume of papers on arXiv continues to grow rapidly, our scientific understanding of artificial intelligence hasn't kept pace with engineering advances, and the current literature presents seemingly contradictory findings that can be difficult to reconcile. In this talk, I will discuss key insights into the strengths and limitations of LLMs, examine when reinforcement learning succeeds or struggles in reasoning tasks, and explore methods for enhancing reasoning capabilities in smaller language models to help them close the gap against their larger counterparts in specific domains.

... more

Speaker Bio

Yejin Choi - Professor of Computer Science, Stanford University; Dieter Schwarz Foundation Senior Fellow, Stanford HAI; Distinguished Scientist, NVIDIA research focuses on natural language processing, with emphasis on commonsense reasoning and language understanding. She is a 2022 MacArthur Fellow and was named to Time's Most Influential People in AI in 2023. She has received multiple Test of Time Awards from ACL and CVPR, and Best Paper Awards at venues including ACL, EMNLP, ICML, and NeurIPS. She previously held positions at the University of Washington and Allen Institute for AI.

... more

Affinity Workshop

Queer in AI

Franziska Sofia Hafner · Sarthak Arora

9:00 AM - 5:00 PM

Talk

Exhibitor Spot Talks - Session 3

9:30 AM - 4:45 PM

23 Events in this session

Optimizing AI Efficiency from Silicon to Model

Jeehoon Kang

EMM-1: Expanding embedding space to be multimodal and multilingual

Jennifer Ding

Exhibitor Talk - NEC

Haifeng Chen

Towards reference models for Engineering Abstract

Johannes Brandstetter

How GM builds Practical AI for the Physical World

Modular Agents and Orchestrated Coordination using Open Agentic Protocols: Foundations for the Next Wave of Agentic AI

Matt White

Reasoning in Motion: How Agents Learn to Think

Meiqi Sun

Takes two to Tangle: showcasing an experimentation platform with the focus on collaboration and ease of editing

LFM2: Capable and efficient on-device multimodal foundation models.

Jimmy Smith

tsuzumi: Advanced and Sovereign Japanese LLM

Mio Nagai · Kyosuke Nishida

Ling 2.0 and Ling-1T: Scaling Knowledge-Enhanced Large Language Models for Reasoning and Efficiency

Wei Fu

Exhibitor Talk - Thomson Reuters

ATOM: RBC’s proprietary AI Foundation Model for Financial Services

Exhibitor Talk - Intuit

Kamalika Das

Exhibitor Talk - Datadog

Exhibitor Talk - Boson.AI Talk to me - engineering conversational intelligence

Unify Vector and Relational Search for Smarter, Faster Applications

Weiwei Gong

Semantic latent variables inference for improved generative modeling

Aaron Courville · Samuel Lavoie

Empowering Financial Services with Trustworthy Frontier AI at Wells Fargo

Freddy Lecue · Swarup Pogalur

Exhibitor Talk - Lightning AI

Scaling Agentic AI with Compute Orchestration and Local Runners

Building an Open Agentic Future

Samuel Colvin

How to make your AI models faster, smaller, cheaper, greener?

Bertrand Charpentier

Go to Event Page

Oral

Oral 3B Deep Learning 2

10:00 AM - 11:00 AM

3 Events in this session

Auto-Compressing Networks

Evangelos Dorovatas · Georgios Paraskevopoulos · Alexandros Potamianos

Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks

Steffen Schotthöfer · Lexie Yang · Stefan Schnake

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression

Tom Burgert · Oliver Stoll · Paolo Rota · Begum Demir

Go to Event Page

Oral

Oral 3C Position Paper Orals

10:00 AM - 11:00 AM

3 Events in this session

Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?

Josu Eguíluz · Axel Brando · Migle Laukyte · Marc Serra-Vidal

More effort is needed to protect pedestrian privacy in the era of AI

Xingchen Zhang · Zixian Zhao

Real-Time Hyper-Personalized Generative AI Should Be Regulated to Prevent the Rise of "Digital Heroin"

Raad Khraishi · Cristovao Iglesias de Oliveira · Devesh Batra · Peter Gostev · Giulio Pelosio · Ramin Okhrati · Greig Cowan

Go to Event Page

Oral

Oral 3E Theory 3

10:00 AM - 11:00 AM

3 Events in this session

Identifiability of Deep Polynomial Neural Networks

Konstantin Usevich · Ricardo Borsoi · Clara Dérand · Marianne Clausel

Depth-Bounds for Neural Networks via the Braid Arrangement

Moritz Grillo · Christoph Hertrich · Georg Loho

Learning Linear Attention in Polynomial Time

Morris Yau · Ekin Akyürek · Jiayuan Mao · Josh Tenenbaum · Stefanie Jegelka · Jacob Andreas

Go to Event Page

Oral

Oral 3D Application 2

10:00 AM - 11:00 AM

3 Events in this session

ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts

Linfeng Tang · Yeda Wang · Zhanchuan Cai · Junjun Jiang · Jiayi Ma

Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables

Zhongnan Cai · Yingying Wang · Hui Zheng · Panwang Pan · Zixu Lin · Ge Meng · Chenxin Li · Chunming He · Jiaxin Xie · Yunlong Lin · Junbin Lu · Yue Huang · Xinghao Ding

FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution

Qiusheng Huang · Yuan Niu · Xiaohui Zhong · AnboyuGuo · Lei Chen · dianjun zhang · Xuefeng Zhang · Hao Li

Go to Event Page

Oral

Oral 3A Reinforcement/State-space 2

10:00 AM - 11:00 AM

3 Events in this session

State Entropy Regularization for Robust Reinforcement Learning

Yonatan Ashlag · Uri Koren · Mirco Mutti · Esther Derman · Pierre-Luc Bacon · Shie Mannor

A Clean Slate for Offline Reinforcement Learning

Matthew T Jackson · Uljad Berdica · Jarek Liesen · Shimon Whiteson · Jakob Foerster

Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies

Felix Chalumeau · Daniel Rajaonarivonivelomanantsoa · Ruan John de Kock · Juan Formanek · Sasha Abramowitz · Omayma Mahjoub · Wiem Khlifi · Simon Du Toit · Louay Nessir · Refiloe Shabe · Arnol Fokam · Siddarth Singh · Ulrich Armel Mbou Sob · Arnu Pretorius

Go to Event Page

Creative AI Session 3

Marcelo Coelho · Luba Elliott · Priya Prakash · Yingtao Tian

11:00 AM - 2:00 PM

24 Events in this session

8bit-GPT: Exploring Human-AI Interaction on Obsolete Macintosh Operating Systems

Hala Sheta

A(I)nimism: Re-enchanting the World Through AI-Mediated Object Interaction

Maisha thasin · Dünya Baradari · Diana Mykhaylychenko · Charmelle Mhungu

Artism: AI-Driven Dual-Engine System for Art Generation and Critique

Shuai Liu · Yiqing Tian · Yang Chen · Mar Canet Sola

ArtPeer: Artistic Alignment via Reflection-based Prompt Evolution with Simulated Artist

Kaustubh Kumar · Ashutosh Ranjan · Vivek Srivastava · Shirish Karande

AugTwins

Anushhka Thakur · Mateo Larrea · Dünya Baradari · Lars Langenbach

CraftGraffiti: Exploring Human Identity with Custom Graffiti Art via Facial-Preserving Diffusion Models

Ayan Banerjee · Fernando Vilariño · Josep Llados

Encoding Values: Injecting Morality into Machines via Prompt-Conditioned Moral Frames

Arjun Balaji · Aarushi Nema · Neha Kamath · Jyothika Raju Raju

Experiencing of Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art

Noah Bissell · Ethan Paley · Joshua Harrison · Juliano Calil · Myungin Lee

Exploring Human-AI Conceptual Alignment through the Prism of Chess

Semyon Lomasov · Judah Goldfeder · Mehmet Erol · Matthew So · Yao Yan · Addison Howard · Nathan Kutz · Ravid Shwartz-Ziv

Gaze to the Stars: AI and Public Art from Personal Affect and Collective Empathy

Behnaz Farahi · Sergio Mutis · Yaluo Wang · Suwan Kim · Chenyue "xdd44" Dai · Haolei Zhang

Gaze to the Stars: AI, Storytelling and Public Art

Behnaz Farahi · Haolei Zhang · Suwan Kim · Sergio Mutis · Yaluo Wang · Chenyue "xdd44" Dai

Human-AI Co-Development of a Geometric Algorithm for Infinite Shuriken Artwork Design Generation

Saleem Al Dajani

Large Language Label

Ekanem Okeke · Alex Stewart · Kyrylo Beskorovainyi

Live Music Models

Antoine Caillon · Brian McWilliams · Cassie Tarakajian · Ian Simon · Ilaria Manco · Jesse Engel · Noah Constant · Yunpeng Li · Timo Denk · Alberto Lalama · Andrea Agostinelli · Anna Huang · Ethan Manillow · George Brower · Hakan Erdogan · Heidi Lei · Itai Rolnick · Ivan Grishchenko · Manu Orsini · Matej Kastelic · Mauricio Zuluaga · Mauro Verzetti · Michael Dooley · Ondrej Skopek · Rafael Ferrer · Zalán Borsos · Aaron van den Oord · Douglas Eck · Eli Collins · Jason Baldridge · Tom Hume · Chris Donahue · Kehang Han · Adam Roberts

MambaKit: Towards Modular Intelligence - Cognitive Scaffolding in Next-Generation Drum Synthesis

Ófeigur Steindórsson

Neural Palate Kueh

Immanuel Koh

Pareiduo: A Human–LLM Dialogue in Sand

Jiao Zhao · Qian Xiang

Possible You: AI-Generated Digital Twins as Creative Mirrors for Future Self Modeling

Pat Pataranutaporn · Kavin Winson · Peggy Yin · Auttasak Lapapirojn · Thanawit Prasongpongchai · Monchai Lertsutthiwong · Patricia Maes · Hal Hershfield

princi/pal: A Moral Dilemma Tamagotchi Game

Tiffany Wang

ReTracing: An Archaeological Approach Through Body, Machine, and Generative Systems

Yitong Wang · Yue Yao

Semantic Glitch: Agency and Artistry in an Autonomous Pixel Cloud

Qing Zhang · JING HUANG · Mingyang Xu · Jun Rekimoto

Sensorium Arc: AI Agent System for Oceanic Data Exploration and Interactive Eco-Art

Noah Bissell · Ethan Paley · Joshua Harrison · Juliano Calil · Myungin Lee

Supporting Creative Ownership through Deep Learning-Based Music Variation

Stephen Krol · Maria Llano · Jon McCormack

Text to Robotic Assembly of Multi Component Objects using 3D Generative AI and Vision Language Models

Alexander Htet Kyaw · Richa Gupta · Anoop Sinha · Dhruv Shah · Kory Mathewson · Stefanie Pender · Sachin Chitta · Yotto koga · Faez Ahmed · Lawrence Sass · Randall Davis

Go to Event Page

Poster

San Diego Poster Session 3

11:00 AM - 2:00 PM

950 Events in this session

Channel Matters: Estimating Channel Influence for Multivariate Time Series

Muyao Wang · Zeke Xie · Bo Chen · Hongwei Liu · James Kwok

A Regularized Newton Method for Nonconvex Optimization with Global and Local Complexity Guarantees

Yuhao Zhou · Jintao Xu · Bingrui Li · Chenglong Bao · Chao Ding · Jun Zhu

Per-Architecture Training-Free Metric Optimization for Neural Architecture Search

Mingzhuo Lin · Jianping Luo

SDPGO: Efficient Self-Distillation Training Meets Proximal Gradient Optimization

Tongtong Su · Yun Liao · Fengbo Zheng

Learning Memory-Enhanced Improvement Heuristics for Flexible Job Shop Scheduling

Jiaqi Wang · Zhiguang Cao · Peng Zhao · Rui Cao · YuBin Xiao · YUAN JIANG · You Zhou

PseuZO: Pseudo-Zeroth-Order Algorithm for Training Deep Neural Networks

Pengyun Yue · Xuanlin Yang · Mingqing Xiao · Zhouchen Lin

ReplaceMe: Network Simplification via Depth Pruning and Transformer Block Linearization

Dmitriy Shopkhoev · Ammar Ali · Magauiya Zhussip · Valentin Malykh · Stamatios Lefkimmiatis · Nikos Komodakis · Sergey Zagoruyko

MeCeFO: Enhancing LLM Training Robustness via Fault-Tolerant Optimization

Rizhen Hu · Yutong He · Ran Yan · Mou Sun · Binhang Yuan · Kun Yuan

Real-Time Hyper-Personalized Generative AI Should Be Regulated to Prevent the Rise of "Digital Heroin"

Raad Khraishi · Cristovao Iglesias de Oliveira · Devesh Batra · Peter Gostev · Giulio Pelosio · Ramin Okhrati · Greig Cowan

Rigor in AI: Doing Rigorous AI Work Requires a Broader, Responsible AI-Informed Conception of Rigor

Alexandra Olteanu · Su Lin Blodgett · Agathe Balayn · Angelina Wang · Fernando Diaz · Flavio Calmon · Margaret Mitchell · Michael Ekstrand · Reuben Binns · Solon Barocas

World Models Should Prioritize the Unification of Physical and Social Dynamics

Xiaoyuan Zhang · Chengdong Ma · Yizhe Huang · Weidong Huang · Siyuan Qi · Song-Chun Zhu · Xue Feng · Yaodong Yang

KAIROS: Scalable Model-Agnostic Data Valuation

Jiongli Zhu · Parjanya Prashant · Alex Cloninger · Babak Salimi

Knowledge Distillation Detection for Open-weights Models

Qin Shi · Amber Yijia Zheng · Qifan Song · Raymond A. Yeh

Incentivizing Desirable Effort Profiles in Strategic Classification: The Role of Causality and Uncertainty

Valia Efthymiou · Chara Podimata · Diptangshu Sen · Juba Ziani

The Future Unmarked: Watermark Removal in AI-Generated Images via Next-Frame Prediction

Huming Qiu · Zhaoxiang Wang · Mi Zhang · Xiaohan Zhang · Xiaoyu You · Min Yang

A Statistical Framework of Watermarks for Large Language Models: Pivot, Detection Efficiency and Optimal Rules

Xiang Li · Feng Ruan · Huiyuan Wang · Qi Long · Weijie Su

We Should Chart an Atlas of All the World's Models

Eliahu Horwitz · Nitzan Kurer · Jonathan Kahana · Liel Amar · Yedid Hoshen

Military AI Needs Technically-Informed Regulation to Safeguard AI Research and its Applications

Riley Simmons-Edler · Jean Dong · Paul Lushenko · Kanaka Rajan · Ryan Badman

BenchmarkCards: Standardized Documentation for Large Language Model Benchmarks

Anna Sokol · Elizabeth Daly · Michael Hind · David Piorkowski · Xiangliang Zhang · Nuno Moniz · Nitesh Chawla

Quality-Driven Curation of Remote Sensing Vision-Language Data via Learned Scoring Models

Dilxat Muhtar · Enzhuo Zhang · Zhenshi Li · Feng Gu · Yanglangxing He · Pengfeng Xiao · Xueliang Zhang

Analyzing Similarity Metrics for Data Selection for Language Model Pretraining

Dylan Sam · Ayan Chakrabarti · Afshin Rostamizadeh · Srikumar Ramalingam · Gui Citovsky · Sanjiv Kumar

EnzyControl: Adding Functional and Substrate-Specific Control for Enzyme Backbone Generation

Chao Song · ZHIYUAN LIU · Han Huang · Liang Wang · Qiong Wang · Jian-Yu Shi · Hui Yu · Yihang Zhou · Yang Zhang

Graph Data Selection for Domain Adaptation: A Model-Free Approach

Ting-Wei Li · Ruizhong Qiu · Hanghang Tong

SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents

Ibragim Badertdinov · Alexander Golubev · Maksim Nekrashevich · Anton Shevtsov · Simon Karasik · Andrei Andriushchenko · Maria Trofimova · Daria Litvintseva · Boris Yangel

Measuring what Matters: Construct Validity in Large Language Model Benchmarks

Andrew M. Bean · Ryan Othniel Kearns · Angelika Romanou · Franziska Sofia Hafner · Harry Mayne · Jan Batzner · Negar Foroutan Eghlidi · Chris Schmitz · Karolina Korgul · Hunar Batra · Oishi Deb · Emma Beharry · Cornelius Emde · Thomas Foster · Anna Gausen · María Grandury · Sophia Han · Valentin Hofmann · Lujain Ibrahim · Hazel Kim · Hannah Rose Kirk · Fangru Lin · Gabrielle Liu · Lennart Luettgau · Jabez Magomere · Jonathan Rystrøm · Anna Sotnikova · Yushi Yang · Yilun Zhao · Adel Bibi · Antoine Bosselut · Ronald Clark · Arman Cohan · Jakob Foerster · Yarin Gal · Scott Hale · Deborah Raji · Christopher Summerfield · Philip Torr · Cozmin Ududec · Luc Rocher · Adam Mahdi

Measuring Fingerprints of Web-filtered Text Datasets and Fingerprint Propagation Through Training

Youssef Mansour · Reinhard Heckel

AGI-Elo: How Far Are We From Mastering A Task?

Shuo Sun · Yimin Zhao · Christina Lee · JIAWEI SUN · Chengran Yuan · Zefan Huang · Dongen Li · Justin Yeoh · Alok Prakash · Thomas Malone · Marcelo Ang Jr

Why Do Multi-Agent LLM Systems Fail?

Mert Cemri · Melissa Z Pan · Shuyi Yang · Lakshya A Agrawal · Bhavya Chopra · Rishabh Tiwari · Kurt Keutzer · Aditya Parameswaran · Dan Klein · Kannan Ramchandran · Matei A Zaharia · Joseph Gonzalez · Ion Stoica

Dense SAE Latents Are Features, Not Bugs

Xiaoqing Sun · Alessandro Stolfo · Joshua Engels · Ben Wu · Senthooran Rajamanoharan · Mrinmaya Sachan · Max Tegmark

EAP-GP: Mitigating Saturation Effect in Gradient-based Automated Circuit Identification

Lin Zhang · Wenshuo Dong · Zhuoran Zhang · Shu Yang · Lijie Hu · Ninghao Liu · Pan Zhou · Di Wang

Collective Counterfactual Explanations: Balancing Individual Goals and Collective Dynamics

Ahmad-Reza Ehyaei · Ali Shirali · Samira Samadi

CHiQPM: Calibrated Hierarchical Interpretable Image Classification

Thomas Norrenbrock · Timo Kaiser · Sovan Biswas · Neslihan Kose · Ramesh Manuvinakurike · Bodo Rosenhahn

Layer-Wise Modality Decomposition for Interpretable Multimodal Sensor Fusion

Jaehyun Park · Konyul Park · Daehun Kim · Junseo Park · Jun Won Choi

Angular Steering: Behavior Control via Rotation in Activation Space

Minh Hieu Vu · Tan Nguyen

Transferring Linear Features Across Language Models With Model Stitching

Alan Chen · Jack Merullo · Alessandro Stolfo · Ellie Pavlick

A Unified Framework for Provably Efficient Algorithms to Estimate Shapley Values

Tyler Chen · Akshay Seshadri · Mattia Jacopo Villani · Pradeep Niroula · Shouvanik Chakrabarti · Archan Ray · Pranav Deshpande · Romina Yalovetzky · Marco Pistoia · Niraj Kumar

Contimask: Explaining Irregular Time Series via Perturbations in Continuous Time

Max Moebus · Björn Braun · Christian Holz

ElliCE: Efficient and Provably Robust Algorithmic Recourse via the Rashomon Sets

Bohdan Turbal · Iryna Voitsitska · Lesia Semenova

DATE-LM: Benchmarking Data Attribution Evaluation for Large Language Models

Cathy Jiao · Yijun Pan · Emily Xiao · Daisy Sheng · Niket Jain · Hanzhang Zhao · Ishita Dasgupta · Jiaqi Ma · Chenyan Xiong

FLAME: Fast Long-context Adaptive Memory for Event-based Vision

Biswadeep Chakraborty · Saibal Mukhopadhyay

Same Task, Different Circuits: Disentangling Modality-Specific Mechanisms in VLMs

Yaniv Nikankin · Dana Arad · Yossi Gandelsman · Yonatan Belinkov

Detecting High-Stakes Interactions with Activation Probes

Alex McKenzie · Urja Pawar · Phil Blandfort · William Bankes · David Krueger · Ekdeep S Lubana · Dmitrii Krasheninnikov

Robust Explanations of Graph Neural Networks via Graph Curvatures

Yazheng Liu · Xi Zhang · Sihong Xie · Hui Xiong

IPAD: Inverse Prompt for AI Detection - A Robust and Interpretable LLM-Generated Text Detector

Zheng CHEN · Yushi Feng · Jisheng Dang · Changyang He · Yue Deng · Hongxi Pu · Haoxuan Li · Bo Li

Additive Models Explained: A Computational Complexity Approach

Shahaf Bassan · Michal Moshkovitz · Guy Katz

Clean First, Align Later: Benchmarking Preference Data Cleaning for Reliable LLM Alignment

Samuel (Min-Hsuan) Yeh · Sharon Li

QUT-DV25: A Dataset for Dynamic Analysis of Next-Gen Software Supply Chain Attacks

Sk Tanzir Mehedi · Raja Jurdak · Chadni Islam · Gowri Sankar Ramachandran

Enabling Differentially Private Federated Learning for Speech Recognition: Benchmarks, Adaptive Optimizers, and Gradient Clipping

Martin Pelikan · Shams Azam · Vitaly Feldman · Jan Silovsky · Kunal Talwar · Christopher Brinton · Tatiana Likhomanenko

Puzzles: Unbounded Video-Depth Augmentation for Scalable End-to-End 3D Reconstruction

Jiahao Ma · Lei Wang · Miaomiao Liu · David Ahmedt-Aristizabal · Chuong Nguyen

MASTER: Enhancing Large Language Model via Multi-Agent Simulated Teaching

Liang Yue · Yihong Tang · Kehai Chen · Jie Liu · Min Zhang

FACE: Faithful Automatic Concept Extraction

Dipkamal Bhusal · Michael Clifford · Sara Rampazzi · Nidhi Rastogi

Uncovering a Universal Abstract Algorithm for Modular Addition in Neural Networks

Gavin McCracken · Gabriela Moisescu-Pareja · Vincent Létourneau · Doina Precup · Jonathan Love

Collective Bargaining in the Information Economy Can Address AI-Driven Power Concentration

Nicholas Vincent · Matt Prewitt · Hanlin Li

SafeVid: Toward Safety Aligned Video Large Multimodal Models

Yixu Wang · Jiaxin Song · Yifeng Gao · Xin Wang · YANG YAO · Yan Teng · Xingjun Ma · Yingchun Wang · Yu-Gang Jiang

Video-SafetyBench: A Benchmark for Safety Evaluation of Video LVLMs

Xuannan Liu · Zekun Li · Zheqi He · Peipei Li · shuhan xia · Xing Cui · Huaibo Huang · Xi Yang · Ran He

Path-specific effects for pulse-oximetry guided decisions in critical care

Kevin Zhang · Yonghan Jung · Divyat Mahajan · Karthikeyan Shanmugam · Shalmali Joshi

On Fairness of Unified Multimodal Large Language Model for Image Generation

Ming Liu · Hao Chen · Jindong Wang · Liwen Wang · Bhiksha Raj · Wensheng Zhang

Grounding Language with Vision: A Conditional Mutual Information Calibrated Decoding Strategy for Reducing Hallucinations in LVLMs

Hao Fang · Changle Zhou · Jiawei Kong · Kuofeng Gao · Bin Chen · Tao Liang · Guojun Ma · Shu-Tao Xia

CTRL-ALT-DECEIT Sabotage Evaluations for Automated AI R&D

Francis Ward · Teun van der Weij · Hanna Gábor · Sam Martin · Raja Moreno · Harel Lidar · Louis Makower · Thomas Jodrell · Lauren Robson

EVOREFUSE: Evolutionary Prompt Optimization for Evaluation and Mitigation of LLM Over-Refusal to Pseudo-Malicious Instructions

Xiaorui Wu · Fei Li · Xiaofeng Mao · Xin Zhang · Li Zheng · Yuxiang Peng · Chong Teng · Donghong Ji · Zhuang Li

Fairness-aware Anomaly Detection via Fair Projection

Feng Xiao · Xiaoying Tang · Jicong Fan

Truth over Tricks: Measuring and Mitigating Shortcut Learning in Misinformation Detection

Herun Wan · Jiaying Wu · Minnan Luo · Zhi Zeng · Zhixiong Su

Unifying Proportional Fairness in Centroid and Non-Centroid Clustering

Benjamin Cookson · Nisarg Shah · Ziqi Yu

Who Speaks for the Trigger? Dynamic Expert Routing in Backdoored Mixture-of-Experts Transformers

Xin Zhao · Xiaojun Chen · Bingshan Liu · Haoyu Gao · Zhendong Zhao · Yilong Chen

DataSIR: A Benchmark Dataset for Sensitive Information Recognition

Fan Mo · Bo Liu · Yuan Fan · Kun Qin · Yizhou Zhao · Jinhe Zhou · Jia Sun · Jinfei Liu · Kui Ren

FracFace: Breaking The Visual Clues—Fractal-Based Privacy-Preserving Face Recognition

Wanying Dai · Beibei Li · Naipeng Dong · Guangdong Bai · Jin Song Dong

Non-exchangeable Conformal Prediction with Optimal Transport: Tackling Distribution Shift with Unlabeled Data

Alvaro Correia · Christos Louizos

KScope: A Framework for Characterizing the Knowledge Status of Language Models

Yuxin Xiao · Shan Chen · Jack Gallifant · Danielle Bitterman · Tom Hartvigsen · Marzyeh Ghassemi

Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach

Haiyun He · Yepeng Liu · Ziqiao Wang · Yongyi Mao · Yuheng Bu

Advancing Machine-Generated Text Detection from an Easy to Hard Supervision Perspective

Chenwang Wu · Yiu-ming Cheung · Bo Han · Defu Lian

DualOptim: Enhancing Efficacy and Stability in Machine Unlearning with Dual Optimizers

Xuyang Zhong · Haochen Luo · Chen Liu

SteerConf: Steering LLMs for Confidence Elicitation

Ziang Zhou · Tianyuan Jin · Jieming Shi · Qing Li

GASP: Efficient Black-Box Generation of Adversarial Suffixes for Jailbreaking LLMs

Advik Basani · Xiao Zhang

Jailbreak-AudioBench: In-Depth Evaluation and Analysis of Jailbreak Threats for Large Audio Language Models

Hao Cheng · Erjia Xiao · Jing Shao · Yichi Wang · Le Yang · Chao Shen · Philip Torr · Jindong Gu · Renjing Xu

Position: If Innovation in AI systematically Violates Fundamental Rights, Is It Innovation at All?

Josu Eguíluz · Axel Brando · Migle Laukyte · Marc Serra-Vidal

Differentially Private Quantiles with Smaller Error

Jacob Imola · Fabrizio Boninsegna · Hannah Keller · Anders Aamand · Amrita Roy Chowdhury · Rasmus Pagh

Efficient Verified Unlearning For Distillation

Yijun Quan · Zushu Li · Giovanni Montana

Quantifying Cross-Modality Memorization in Vision-Language Models

Yuxin Wen · Yangsibo Huang · Tom Goldstein · Ravi Kumar · Badih Ghazi · Chiyuan Zhang

Private Statistical Estimation via Truncation

Manolis Zampetakis · Felix Zhou

Controlling The Spread of Epidemics on Networks with Differential Privacy

Dũng Nguyen · Aravind Srinivasan · Renata Valieva · Anil Vullikanti · Jiayi Wu

Multi-Class Support Vector Machine with Differential Privacy

Jinseong Park · Yujin Choi · Jaewook Lee

Your Pre-trained LLM is Secretly an Unsupervised Confidence Calibrator

Beier Luo · Shuoyuan Wang · Sharon Li · Hongxin Wei

Wisdom is Knowing What not to Say: Hallucination-Free LLMs Unlearning via Attention Shifting

Chenchen Tan · Youyang Qu · Xinghao Li · Hui Zhang · Shujie Cui · Cunjian Chen · Longxiang Gao

Keeping an Eye on LLM Unlearning: The Hidden Risk and Remedy

Jie Ren · Zhenwei Dai · Xianfeng Tang · Yue XING · Shenglai Zeng · Hui Liu · Jingying Zeng · Qiankun Peng · Samarth Varshney · Suhang Wang · Qi He · Charu Aggarwal · Hui Liu

MixAT: Combining Continuous and Discrete Adversarial Training for LLMs

Csaba Dékány · Stefan Balauca · Dimitar I. Dimitrov · Robin Staab · Martin Vechev

BAM-ICL: Causal Hijacking In-Context Learning with Budgeted Adversarial Manipulation

Rui Chu · Bingyin Zhao · Hanling Jiang · Shuchin Aeron · Yingjie Lao

FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning

Zhiqin Yang · Yonggang Zhang · Chenxin Li · Yiu-ming Cheung · Bo Han · Yixuan Yuan

DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images

Ozgur Kara · Harris Nisar · James Rehg

Fortifying Time Series: DTW-Certified Robust Anomaly Detection

Shijie Liu · Tansu Alpcan · Christopher Leckie · Sarah Erfani

Unveiling Environmental Sensitivity of Individual Gains in Influence Maximization

Xinyan Su · Zhiheng Zhang · Jiyan Qiu · Zhaojuan Yue · Jun Li

Let a Neural Network be Your Invariant

Mirco Giacobbe · Daniel Kroening · Abhinandan Pal · Michael Tautschnig

HyperGraphRAG: Retrieval-Augmented Generation via Hypergraph-Structured Knowledge Representation

Haoran Luo · Haihong E · Guanting Chen · Yandan Zheng · Xiaobao Wu · Yikai Guo · Qika Lin · Yu Feng · Zemin Kuang · Meina Song · Yifan Zhu · Anh Tuan Luu

The Mirage of Performance Gains: Why Contrastive Decoding Fails to Mitigate Object Hallucinations in MLLMs?

Hao Yin · Guangzong Si · Zilei Wang

Utility Engineering: Analyzing and Controlling Emergent Value Systems in AIs

Mantas Mazeika · Xuwang Yin · Rishub Tamirisa · Jaehyuk Lim · Bruce W, Lee · Richard Ren · Long Phan · Norman Mu · Oliver Zhang · Dan Hendrycks

Look-Ahead Reasoning on Learning Platforms

Haiqing Zhu · Tijana Zrnic · Celestine Mendler-Dünner

Unveiling the Uncertainty in Embodied and Operational Carbon of Large AI Models through a Probabilistic Carbon Accounting Model

Xiaoyang Zhang · He Fang · Yang Deng · Dan Wang

Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning

Zhe Hu · Jing Li · Zhongzhu Pu · Hou Pong (Ken) Chan · Yu Yin

Role-aware Multi-agent Reinforcement Learning for Coordinated Emergency Traffic Control

Ming Cheng · Hao Chen · Zhiqing Li · Jia Wang · Senzhang Wang

A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis

Dongheng Lin · Mengxue Qu · Kunyang Han · Jianbo Jiao · Xiaojie Jin · Yunchao Wei

CoIDO: Efficient Data Selection for Visual Instruction Tuning via Coupled Importance-Diversity Optimization

Yichen Yan · Ming Zhong · Qi Zhu · Xiaoling Gu · Jinpeng Chen · Huan Li

MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement

Jaehyun Nam · Jinsung Yoon · Jiefeng Chen · Jinwoo Shin · Sercan Arik · Tomas Pfister

Protein Design with Dynamic Protein Vocabulary

Nuowei Liu · Jiahao Kuang · Yanting Liu · Tao Ji · Changzhi Sun · Man Lan · Yuanbin Wu

Ultra-high Resolution Watermarking Framework Resistant to Extreme Cropping and Scaling

Nan Sun · LuYu Yuan · Han Fang · Yuxing Lu · Hefei Ling · Sijing Xie · Chengxin Zhao

MiCADangelo: Fine-Grained Reconstruction of Constrained CAD Models from 3D Scans

Ahmet Karadeniz · Dimitrios Mallis · Danila Rukhovich · Kseniya Cherenkova · Anis Kacem · Djamila Aouada

Tail-Optimized Caching for LLM Inference

Wenxin Zhang · Yueying Li · Ciamac C Moallemi · Tianyi Peng

OpenCUA: Open Foundations for Computer-Use Agents

Xinyuan Wang · Bowen Wang · Dunjie Lu · Junlin Yang · Tianbao Xie · Junli Wang · Jiaqi Deng · Xiaole Guo · Yiheng Xu · Chen Wu · Zhennan Shen · Zhuokai Li · Ryan Li · Xiaochuan Li · Junda Chen · Boyuan Zheng · LI PEIHANG · Fangyu Lei · Ruisheng Cao · Yeqiao Fu · Dongchan Shin · Martin Shin · Hu Jiarui · Yuyan Wang · Jixuan Chen · Yuxiao Ye · Danyang Zhang · Yipu Wang · Heng Wang · Diyi Yang · Victor Zhong · Y.Charles · Zhilin Yang · Tao Yu

TranSUN: A Preemptive Paradigm to Eradicate Retransformation Bias Intrinsically from Regression Models in Recommender Systems

Jiahao Yu · Haozhuang Liu · Yeqiu Yang · Lu Chen · Jian Wu · Yuning Jiang · Bo Zheng

CURV: Coherent Uncertainty-Aware Reasoning in Vision-Language Models for X-Ray Report Generation

Ziao Wang · Sixing Yan · Kejing Yin · Xiaofeng Zhang · William K. Cheung

RealMath: A Continuous Benchmark for Evaluating Language Models on Research-Level Mathematics

Jie Zhang · Cezara Petrui · Kristina Nikolić · Florian Tramer

Evaluating Program Semantics Reasoning with Type Inference in System $F$

Yifeng He · Luning Yang · Christopher Gonzalo · Hao Chen

Crucible: Quantifying the Potential of Control Algorithms through LLM Agents

Lianchen Jia · Chaoyang Li · Qian Houde · Tianchi Huang · Jiangchuan Liu · Lifeng Sun

FailureSensorIQ: A Multi-Choice QA Dataset for Understanding Sensor Relationships and Failure Modes

Christodoulos Constantinides · Dhaval Patel · Shuxin Lin · Claudio Guerrero · Sunil Patil · Jayant Kalagnanam

Position: Biology is the Challenge Physics-Informed ML Needs to Evolve

Julien Martinelli

When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration

Quan Shi · Carlos Jimenez · Shunyu Yao · Nick Haber · Diyi Yang · Karthik Narasimhan

FuXi-Ocean: A Global Ocean Forecasting System with Sub-Daily Resolution

Qiusheng Huang · Yuan Niu · Xiaohui Zhong · AnboyuGuo · Lei Chen · dianjun zhang · Xuefeng Zhang · Hao Li

Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go

Yichuan Ma · Linyang Li · Yongkang Chen · Peiji Li · Jiasheng Ye · Qipeng Guo · Dahua Lin · Kai Chen

QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation

Changxin Ke · Rui Zhang · Shuo Wang · Li Ding · Guangli Li · Yuanbo Wen · Shuoming Zhang · Ruiyuan Xu · Jin Qin · Jiaming Guo · Chenxi Wang · Ling Li · Qi Guo · Yunji Chen

From Pose to Muscle: Multimodal Learning for Piano Hand Muscle Electromyography

RUOFAN LIU · YICHEN PENG · Takanori Oku · Chen-Chieh Liao · Erwin Wu · Shinichi Furuya · Hideki Koike

PreFM: Online Audio-Visual Event Parsing via Predictive Future Modeling

Xiao Yu · Yan Fang · Yao Zhao · Yunchao Wei

REDOUBT: Duo Safety Validation for Autonomous Vehicle Motion Planning

Shuguang Wang · Qian Zhou · Kui Wu · Dapeng Wu · Wei-Bin Lee · Jianping Wang

3D Human Pose Estimation with Muscles

Kevin Zhu · AliAsghar MohammadiNasrabadi · Alexander Wong · John McPhee

Which Algorithms Have Tight Generalization Bounds?

Michael Gastpar · Ido Nachum · Jonathan Shafer · Thomas Weinberger

A Standardized Benchmark for Multilabel Antimicrobial Peptide Classification

Sebastian Ojeda · Rafael Velasquez · Nicolás Aparicio · Juanita Puentes · Paula Cárdenas · Nicolás Andrade · Gabriel González · Sergio Rincón · Carolina Muñoz-Camargo · Pablo Arbelaez

Rationalized All-Atom Protein Design with Unified Multi-Modal Bayesian Flow

Hanlin Wu · Yuxuan Song · Zhe Zhang · Zhilong Zhang · Hao Zhou · Wei-Ying Ma · Jingjing Liu

DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform

Peizhi Niu · Yu-Hsiang Wang · Vishal Rana · Chetan Rupakheti · Abhishek Pandey · Olgica Milenkovic

LLM Meets Diffusion: A Hybrid Framework for Crystal Material Generation

Subhojyoti Khastagir · KISHALAY DAS · Pawan Goyal · Seung-Cheol Lee · Satadeep Bhattacharjee · niloy ganguly

Reaction Prediction via Interaction Modeling of Symmetric Difference Shingle Sets

Runhan Shi · Letian Chen · Gufeng Yu · Yang Yang

Unified all-atom molecule generation with neural fields

Matthieu Kirchmeyer · Pedro O. Pinheiro · Emma Willett · Karolis Martinkus · Joseph Kleinhenz · Emily Makowski · Andrew Watkins · Vladimir Gligorijevic · Richard Bonneau · Saeed Saremi

Amortized Sampling with Transferable Normalizing Flows

Charlie Tan · Majdi Hassan · Leon Klein · Saifuddin Syed · Dominique Beaini · Michael Bronstein · Alexander Tong · Kirill Neklyudov

HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing

Johann Flemming Gloy · Simon Olsson

MS-BART: Unified Modeling of Mass Spectra and Molecules for Structure Elucidation

Yang Han · Pengyu Wang · Kai Yu · xin chen · Lu Chen

CodeAssistBench (CAB): Dataset & Benchmarking for Multi-turn Chat-Based Code Assistance

Myeongsoo Kim · Shweta Garg · Baishakhi Ray · Varun Kumar · Anoop Deoras

AlphaFold Database Debiasing for Robust Inverse Folding

Cheng Tan · Zhenxiao Cao · Zhangyang Gao · Siyuan Li · Yufei Huang · Stan Z. Li

Unsupervised Trajectory Optimization for 3D Registration in Serial Section Electron Microscopy using Neural ODEs

Zhenbang Zhang · Jingtong Feng · Hongjia Li · Haythem El-Messiry · Zhiqiang Xu · Renmin Han

CGBench: Benchmarking Language Model Scientific Reasoning for Clinical Genetics Research

Owen Queen · Harrison Zhang · James Zou

Augmenting Biological Fitness Prediction Benchmarks with Landscapes Features from GraphFLA

Mingyu Huang · Shasha Zhou · Ke Li

PIPE: Physics-Informed Position Encoding for Alignment of Satellite Images and Time Series in Typhoon Forecasting

Haobo Li · Eunseo Jung · Zixin CHEN · Zhaowei Wang · Yueya WANG · Huamin Qu · Alexis Lau

Causal Climate Emulation with Bayesian Filtering

Sebastian H. M. Hickman · Ilija Trajković · Julia Kaltenborn · Francis Pelletier · Alex Archibald · Yaniv Gurwicz · Peer Nowack · David Rolnick · Julien Boussard

NUTS: Eddy-Robust Reconstruction of Surface Ocean Nutrients via Two-Scale Modeling

Hao Zheng · Shiyu Liang · Yuting Zheng · Chaofan Sun · LEI BAI · Enhui Liao

OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales

Tung Nguyen · Tuan Pham · Troy Arcomano · Rao Kotamarthi · Ian Foster · Sandeep Madireddy · Aditya Grover

Scalable and Cost-Efficient de Novo Template-Based Molecular Generation

Piotr Gaiński · Oussama Boussif · Andrei Rekesh · Dmytro Shevchuk · Ali Parviz · Mike Tyers · Robert Batey · Michał Koziarski

Sampling 3D Molecular Conformers with Diffusion Transformers

J. Thorben Frank · Winfried Ripken · Gregor Lied · Klaus-Robert Müller · Oliver Unke · Stefan Chmiela

Flash Invariant Point Attention

Andrew Liu · Axel Elaldi · Nicholas Franklin · Nathan Russell · Gurinder Atwal · Yih-En Ban · Olivia Viessmann

Flexible MOF Generation with Torsion-Aware Flow Matching

Nayoung Kim · Seongsu Kim · Sungsoo Ahn

RiboFlow: Conditional De Novo RNA Co-Design via Synergistic Flow Matching

Runze Ma · Zhongyue Zhang · Zichen Wang · Chenqing Hua · Jiahua Rao · Zhuomin Zhou · Shuangjia Zheng

Controllable 3D Molecular Generation for Structure-Based Drug Design Through Bayesian Flow Networks and Gradient Integration

Seungyeon Choi · Hwanhee Kim · Chihyun Park · Dahyeon Lee · Seungyong Lee · Yoonju Kim · Hyoungjoon Park · Sein Kwon · Youngwan Jo · Sanghyun Park

Ambient Proteins - Training Diffusion Models on Noisy Structures

Giannis Daras · Jeffrey Ouyang-Zhang · Krithika Ravishankar · Constantinos Daskalakis · Adam Klivans · Daniel Diaz

E2Former: An Efficient and Equivariant Transformer with Linear-Scaling Tensor Products

Yunyang Li · Lin Huang · Zhihao Ding · Xinran Wei · Chu Wang · Han Yang · Zun Wang · Chang Liu · Yu Shi · Peiran Jin · Tao Qin · Mark Gerstein · Jia Zhang

SAINT: Sequence-Aware Integration for Spatial Transcriptomics Multi-View Clustering

Zeyu Zhu · KE LIANG · Lingyuan Meng · Meng Liu · Suyuan Liu · Renxiang Guan · Miaomiao Li · Wanwei Liu · Xinwang Liu

Variational Regularized Unbalanced Optimal Transport: Single Network, Least Action

Yuhao Sun · Zhenyi Zhang · Zihan Wang · Tiejun Li · Peijie Zhou

Ctrl-DNA: Controllable Cell-Type-Specific Regulatory DNA Design via Constrained RL

Xingyu Chen · Shihao Ma · Runsheng Lin · Jiecong Lin · Bo Wang

HiPoNet: A Multi-View Simplicial Complex Network for High Dimensional Point-Cloud and Single-Cell data

Siddharth Viswanath · Hiren Madhu · Dhananjay Bhaskar · Jake Kovalic · Dave Johnson · Christopher Tape · Ian Adelstein · Rex Ying · Michael Perlmutter · Smita Krishnaswamy

Securing the Language of Life: Inheritable Watermarks from DNA Language Models to Proteins

ZAIXI ZHANG · Ruofan Jin · Le Cong · Mengdi Wang

Learning Crossmodal Interaction Patterns via Attributed Bipartite Graphs for Single-Cell Omics

Xiaotang Wang · Xuanwei Lin · Yun Zhu · Hao Li · Yongqi Zhang

ChromFound: Towards A Universal Foundation Model for Single-Cell Chromatin Accessibiltiy Data

Yifeng Jiao · Yuchen Liu · Yu Zhang · Xin Guo · Yushuai Wu · Chen Jiang · Jiyang Li · Hongwei Zhang · LIMEI HAN · Xin Gao · Yuan Qi · Yuan Cheng

GeneFlow: Translation of Single-cell Gene Expression to Histopathological Images via Rectified Flow

Mengbo Wang · Shourya Verma · Aditya Malusare · Luopin Wang · Yiyang Lu · Vaneet Aggarwal · Mario Sola · Ananth Grama · Nadia Lanman

RAM-W600: A Multi-Task Wrist Dataset and Benchmark for Rheumatoid Arthritis

YANG SONGXIAO · Haolin Wang · Yao Fu · Ye Tian · Tamostu Kamishima · Masayuki Ikebe · Yafei Ou · Masatoshi Okutomi

Democratizing Clinical Risk Prediction with Cross-Cohort Cross-Modal Knowledge Transfer

Qiannan Zhang · Manqi Zhou · Zilong Bai · Chang Su · Fei Wang

Doctor Approved: Generating Medically Accurate Skin Disease Images through AI-Expert Feedback

Janet Wang · Yunbei Zhang · Zhengming Ding · Jihun Hamm

RAD: Towards Trustworthy Retrieval-Augmented Multi-modal Clinical Diagnosis

Haolin Li · Tianjie Dai · Zhe Chen · Siyuan Du · Jiangchao Yao · Ya Zhang · Yanfeng Wang

Dual-Res Tandem Mamba-3D: Bilateral Breast Lesion Detection and Classification on Non-contrast Chest CT

Jiaheng Zhou · Wei Fang · Luyuan Xie · Yanfeng Zhou · Lianyan Xu · Minfeng Xu · Ge Yang · Yuxing Tang

Timely Clinical Diagnosis through Active Test Selection

Silas Ruhrberg Estévez · Nicolás Astorga · Mihaela van der Schaar

Towards Generalizable Retina Vessel Segmentation with Deformable Graph Priors

Ke Liu · Shangde Gao · Yichao Fu · Shangqi Gao

EuroSpeech: A Multilingual Speech Corpus

Samuel Pfisterer · Florian Grötschla · Luca Lanzendörfer · Florian Yan · Roger Wattenhofer

ReSearch: Learning to Reason with Search for LLMs via Reinforcement Learning

Mingyang Chen · Linzhuang Sun · Tianpeng Li · Haoze Sun · ZhouYijie · Chenzheng Zhu · Haofen Wang · Jeff Pan · Wen Zhang · Huajun Chen · Fan Yang · Zenan Zhou · weipeng chen

MoonCast: High-Quality Zero-Shot Podcast Generation

Zeqian Ju · Dongchao Yang · Shen Kai · YICHONG LENG · Zhengtao Wang · Songxiang Liu · Xinyu Zhou · Tao Qin · Xiangyang Li · Jianwei Yu · Xu Tan

ReliabilityRAG: Effective and Provably Robust Defense for RAG-based Web-Search

Zeyu Shen · Basileal Imana · Tong Wu · Chong Xiang · Prateek Mittal · Aleksandra Korolova

Exploiting LLMs for Automatic Hypothesis Assessment via a Logit-Based Calibrated Prior

Yue Gong · Raul Fernandez

CAM: A Constructivist View of Agentic Memory for LLM-Based Reading Comprehension

Rui Li · Zeyu Zhang · Xiaohe Bo · Zihang Tian · Xu Chen · Quanyu Dai · Zhenhua Dong · Ruiming Tang

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

Xiaoxi Li · Jiajie Jin · Guanting Dong · Hongjin Qian · Yongkang Wu · Ji-Rong Wen · Yutao Zhu · Zhicheng Dou

Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?

Yang Yue · Zhiqi Chen · Rui Lu · Andrew Zhao · Zhaokai Wang · Yang Yue · Shiji Song · Gao Huang

Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging

Hongjin Qian · Zheng Liu

Automated Composition of Agents: A Knapsack Approach for Agentic Component Selection

Michelle Yuan · Khushbu Pahwa · Shuaichen Chang · Mustafa Kaba · MONICA SUNKARA · Jiarong Jiang · Xiaofei Ma · Yi Zhang

Explaining and Mitigating Crosslingual Tokenizer Inequities

Catherine Arnett · Tyler Chang · Stella Biderman · Benjamin Bergen

MLRC-Bench: Can Language Agents Solve Machine Learning Research Challenges?

Yunxiang Zhang · Muhammad Khalifa · Shitanshu Bhushan · Grant Murphy · Lajanugen Logeswaran · Jaekyeom Kim · Moontae Lee · Honglak Lee · Lu Wang

A Controllable Examination for Long-Context Language Models

Yijun Yang · Zeyu Huang · Wenhao Zhu · Zihan Qiu · Fei Yuan · Jeff Pan · Ivan Titov

Toward Engineering AGI: Benchmarking the Engineering Design Capabilities of LLMs

Xingang Guo · Yaxin Li · XiangYi Kong · YILAN JIANG · Xiayu Zhao · Zhihua Gong · Yufan Zhang · Daixuan Li · Tianle Sang · Beixiao Zhu · Gregory Jun · Yingbing Huang · Yiqi Liu · Yuqi Xue · Rahul Dev Kundu · Qi Lim · Yizhou Zhao · Luke Granger · Mohamed Younis · Darioush Keivan · Nippun Sabharwal · Shreyanka Sinha · Prakhar Agarwal · Kojo Vandyck · Hanlin Mai · Zichen Wang · Aditya Venkatesh · Ayush Barik · Jiankun Yang · Chongying Yue · Jingjie He · Libin Wang · Licheng Xu · Hao Chen · Jinwen Wang · Liujun Xu · Rushabh Shetty · Ziheng Guo · Dahui Song · Manvi Jha · Weijie Liang · Weiman Yan · Bryan Zhang · Sahil Bhandary Karnoor · Jialiang Zhang · Rutva Pandya · Xinyi Gong · Mithesh Ganesh · Feize Shi · Ruiling Xu · Yifan Zhang · Yanfeng Ouyang · Lianhui Qin · Elyse Rosenbaum · Corey Snyder · Peter Seiler · Geir Dullerud · Xiaojia Zhang · Zuofu Cheng · Pavan Kumar Hanumolu · Jian Huang · Mayank Kulkarni · Mahdi Namazifar · Huan Zhang · Bin Hu

SeniorTalk: A Chinese Conversation Dataset with Rich Annotations for Super-Aged Seniors

chen yang · Hui Wang · Shiyao Wang · Junyang Chen · Jiabei He · Jiaming Zhou · Xi Yang · Yequan Wang · Yonghua Lin · Yong Qin

AVerImaTeC: A Dataset for Automatic Verification of Image-Text Claims with Evidence from the Web

RUI CAO · Zifeng Ding · Zhijiang Guo · Michael Schlichtkrull · Andreas Vlachos

Mind2Web 2: Evaluating Agentic Search with Agent-as-a-Judge

Boyu Gou · Zanming Huang · Yuting Ning · Yu Gu · Michael Lin · Weijian Qi · Andrei Kopanev · Botao Yu · Bernal Jimenez Gutierrez · Yiheng Shu · Chan Hee (Luke) Song · Jiaman Wu · Shijie Chen · Hanane Moussa · TIANSHU ZHANG · Jian Xie · Yifei Li · Tianci Xue · Zeyi Liao · Kai Zhang · Boyuan Zheng · Zhaowei Cai · Viktor Rozgic · Morteza Ziyadi · Huan Sun · Yu Su

CoreaSpeech: Korean Speech Corpus via JAMO-based Coreset Selection for Efficient and Robust Korean Speech Generation

Ki-Joong Kwon · Junho So · Sang-Hoon Lee

Scaling Code-Assisted Chain-of-Thoughts and Instructions for Model Reasoning

Honglin Lin · Qizhi Pei · Zhuoshi Pan · Yu Li · Xin Gao · Juntao Li · Conghui He · Lijun Wu

ARECHO: Autoregressive Evaluation via Chain-Based Hypothesis Optimization for Speech Multi-Metric Estimation

Jiatong Shi · Yifan Cheng · Bo-Hao Su · Hye-jin Shim · Jinchuan Tian · Samuele Cornell · Yiwen Zhao · Siddhant Arora · Shinji Watanabe

Metis: A Foundation Speech Generation Model with Masked Generative Pre-training

Yuancheng Wang · Jiachen Zheng · Junan Zhang · Xueyao Zhang · Huan Liao · Zhizheng Wu

Codifying Character Logic in Role-Playing

Letian Peng · Jingbo Shang

Distilling LLM Agent into Small Models with Retrieval and Code Tools

Minki Kang · Jongwon Jeong · Seanie Lee · Jaewoong Cho · Sung Ju Hwang

Retrieval is Not Enough: Enhancing RAG through Test-Time Critique and Optimization

Jiaqi Wei · Hao Zhou · Xiang Zhang · Di Zhang · Zijie Qiu · Noah Wei · Jinzhe Li · Wanli Ouyang · Siqi Sun

Causal LLM Routing: End-to-End Regret Minimization from Observational Data

Asterios Tsiourvas · Wei Sun · Georgia Perakis

Hyper-Modality Enhancement for Multimodal Sentiment Analysis with Missing Modalities

Yan Zhuang · Minhao Liu · Wei Bai · Yanru Zhang · Wei Li · Jiawen Deng · Fuji Ren

Enhancing Personalized Multi-Turn Dialogue with Curiosity Reward

Yanming Wan · Jiaxing Wu · Marwa Abdulhai · Lior Shani · Natasha Jaques

Mellow: a small audio language model for reasoning

Soham Deshmukh · Satvik Dixit · Rita Singh · Bhiksha Raj

Feedback-Aware MCTS for Goal-Oriented Information Seeking

Harshita Chopra · Chirag Shah

Hyperbolic Dataset Distillation

Wenyuan Li · Guang Li · Keisuke Maeda · Takahiro Ogawa · Miki Haseyama

Learning “Partner-Aware” Collaborators in Multi-Party Collaboration

Abhijnan Nath · Nikhil Krishnaswamy

Heterogeneous Swarms: Jointly Optimizing Model Roles and Weights for Multi-LLM Systems

Shangbin Feng · Zifeng Wang · Palash Goyal · Yike Wang · Weijia Shi · Huang Xia · Hamid Palangi · Luke Zettlemoyer · Yulia Tsvetkov · Chen-Yu Lee · Tomas Pfister

CleverBirds: A Multiple-Choice Benchmark for Fine-grained Human Knowledge Tracing

Leonie Bossemeyer · Samuel Heinrich · Grant Van Horn · Oisin Mac Aodha

EyeBench: Predictive Modeling from Eye Movements in Reading

Omer Shubi · David Robert Reich · Keren Gruteke Klein · Yuval Angel · Paul Prasse · Lena A. Jäger · Yevgeni Berzak

MUniverse: A Simulation and Benchmarking Suite for Motor Unit Decomposition

Pranav Mamidanna · Thomas Klotz · Dimitrios Chalatsis · Agnese Grison · Irene Mendez Guerra · Shihan Ma · Arnault Caillet · Simon Avrillon · Robin Rohlén · Dario Farina

Group-in-Group Policy Optimization for LLM Agent Training

Lang Feng · Zhenghai Xue · Tingcong Liu · Bo An

OPHR: Mastering Volatility Trading with Multi-Agent Deep Reinforcement Learning

Zeting Chen · Xinyu Cai · Molei Qin · Bo An

Influence Guided Context Selection for Effective Retrieval-Augmented Generation

Jiale Deng · Yanyan Shen · Ziyuan Pei · Youmin Chen · Linpeng Huang

A Sustainable AI Economy Needs Data Deals That Work for Generators

Ruoxi Jia · Luis Oala · Wenjie Xiong · Suqin Ge · Jiachen (Tianhao) Wang · Feiyang Kang · Dawn Song

Position: AI Should Sense Better, Not Just Scale Bigger: Adaptive Sensing as a Paradigm Shift

Eunsu Baek · Keondo Park · Jeonggil Ko · Min-hwan Oh · Taesik Gong · Hyung-Sin Kim

OctoNet: A Large-Scale Multi-Modal Dataset for Human Activity Understanding Grounded in Motion-Captured 3D Pose Labels

Dongsheng Yuan · Xie Zhang · Weiying Hou · Sheng Lyu · Yuemin Yu · Luca Jiang-Tao Yu · Chengxiao Li · Chenshu Wu

Structural Entropy Guided Agent for Detecting and Repairing Knowledge Deficiencies in LLMs

Yifan Wei · Xiaoyan Yu · Tengfei Pan · Angsheng Li · Li Du

A Clean Slate for Offline Reinforcement Learning

Matthew T Jackson · Uljad Berdica · Jarek Liesen · Shimon Whiteson · Jakob Foerster

Adaptable Safe Policy Learning from Multi-task Data with Constraint Prioritized Decision Transformer

Ruiqi Xue · Ziqian Zhang · Lihe Li · Cong Guan · Lei Yuan · Yang Yu

Flattening Hierarchies with Policy Bootstrapping

John Zhou · Jonathan Kao

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization

Subhojyoti Mukherjee · Viet Lai · Raghavendra Addanki · Ryan Rossi · Seunghyun Yoon · Trung Bui · Anup B. Rao · Jayakumar Subramanian · Branislav Kveton

Modeling Dynamic Neural Activity by combining Naturalistic Video Stimuli and Stimulus-independent Latent Factors

Finn Schmidt · Polina Turishcheva · Suhas Shrinivasan · Fabian Sinz

Efficient Training of Minimal and Maximal Low-Rank Recurrent Neural Networks

Anushri Arora · Jonathan Pillow

Seemingly Redundant Modules Enhance Robust Odor Learning in Fruit Flies

HaiYang Li · Liao Yu · Qiang Yu · Yunliang Zang

BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals

Qinfan Xiao · Ziyun Cui · Chi Zhang · SiQi Chen · Wen Wu · Andrew Thwaites · Alexandra Woolgar · Bowen Zhou · Chao Zhang

Quantifying Task-relevant Similarities in Representations Using Decision Variable Correlations

Yu (Eric) Qian · Wilson Geisler · Xue-Xin Wei

Flexible inference for animal learning rules using neural networks

Yuhan Helena Liu · Victor Geadah · Jonathan Pillow

Spike-timing-dependent Hebbian learning as noisy gradient descent

Niklas Dexheimer · Sascha Gaudlitz · Johannes Schmidt-Hieber

Neurons as Detectors of Coherent Sets in Sensory Dynamics

Joshua L Pughe-Sanford · Xuehao Ding · Jason Moore · Anirvan Sengupta · Charles Epstein · Philip Greengard · Dmitri Chklovskii

Brain-Inspired fMRI-to-Text Decoding via Incremental and Wrap-Up Language Modeling

Wentao Lu · Dong Nie · Pengcheng Xue · Zheng Cui · Piji Li · Daoqiang Zhang · Xuyun Wen

Toward Relative Positional Encoding in Spiking Transformers

Changze Lv · Yansen Wang · Dongqi Han · Yifei Shen · Xiaoqing Zheng · Xuanjing Huang · Dongsheng Li

FANS: A Flatness-Aware Network Structure for Generalization in Offline Reinforcement Learning

Da Wang · Yi Ma · Ting Guo · Hongyao Tang · Wei Wei · Jiye Liang

AI-Generated Video Detection via Perceptual Straightening

Christian Internò · Robert Geirhos · Markus Olhofer · Sunny Liu · Barbara Hammer · David Klindt

Characterizing control between interacting subsystems with deep Jacobian estimation

Adam J. Eisen · Mitchell Ostrow · Sarthak Chandra · Leo Kozachkov · Earl Miller · Ila Fiete

Identifying interactions across brain areas while accounting for individual-neuron dynamics with a Transformer-based variational autoencoder

Qi Xin · Robert E Kass

Anatomically inspired digital twins capture hierarchical object representations in visual cortex

Emanuele Luconi · Dario Liscai · Carlo Baldassi · Alessandro Marin Vargas · Alessandro Sanzeni

Self supervised learning for in vivo localization of microelectrode arrays using raw local field potential

Tianxiao He · Malhar Patel · Chenyi Li · Anna Maslarova · Mihály Vöröslakos · Nalini Ramanathan · Wei-Lun Hung · Gyorgy Buzsaki · Erdem Varol

Does Object Binding Naturally Emerge in Large Pretrained Vision Transformers?

Yihao Li · Saeed Salehi · Lyle Ungar · Konrad Kording

Dynamics-Aligned Latent Imagination in Contextual World Models for Zero-Shot Generalization

Frank Röder · Jan Benad · Manfred Eppe · Pradeep Banerjee

Leveraging Conditional Dependence for Efficient World Model Denoising

Shaowei Zhang · Jiahan Cao · Dian Cheng · Xunlan Zhou · Shenghua Wan · Le Gan · De-Chuan Zhan

Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision

Shilin Zhang · Zican Hu · Wenhao Wu · Xinyi Xie · Jianxiang Tang · Chunlin Chen · Daoyi Dong · Yu Cheng · Zhenhong Sun · Zhi Wang

Optimal Dynamic Regret by Transformers for Non-Stationary Reinforcement Learning

Baiyuan Chen · Shinji Ito · Masaaki Imaizumi

Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning

Vittorio Giammarino · Ruiqi Ni · Ahmed Qureshi

BrainFlow: A Holistic Pathway of Dynamic Neural System on Manifold

Zhixuan Zhou · Tingting Dan · Guorong Wu

Dimensionality Mismatch Between Brains and Artificial Neural Networks

Santiago Galella · Maren Wehrheim · Matthias Kaschube

TractoTransformer: Diffusion MRI Streamline Tractography using CNN and Transformer Networks

Itzik Waizman · Yakov Gusakov · Itay Benou · Tammy Riklin Raviv

BioOSS: A Bio-Inspired Oscillatory State System with Spatio-Temporal Dynamics

Zhongju Yuan · Geraint Wiggins · Dick Botteldooren

Predicting Functional Brain Connectivity with Context-Aware Deep Neural Networks

Alexander Ratzan · Sidharth Goel · Junhao Wen · Christos Davatzikos · Erdem Varol

$\mu$PC: Scaling Predictive Coding to 100+ Layer Networks

Francesco Innocenti · El Mehdi Achour · Christopher L Buckley

Contrastive Consolidation of Top-Down Modulations Achieves Sparsely Supervised Continual Learning

Viet Anh Khoa Tran · Emre Neftci · Willem Wybo

Are Large Language Models Sensitive to the Motives Behind Communication?

Addison J. Wu · Ryan Liu · Kerem Oktar · Ted Sumers · Tom Griffiths

Far from the Shallow: Brain-Predictive Reasoning Embedding through Residual Disentanglement

Linyang He · Tianjun Zhong · Richard Antonello · Gavin Mischler · Micah Goldblum · Nima Mesgarani

Modeling Neural Activity with Conditionally Linear Dynamical Systems

Victor Geadah · Amin Nejatbakhsh · David Lipshutz · Jonathan Pillow · Alex Williams

FAIR Universe HiggsML Uncertainty Dataset and Competition

Wahid Bhimji · Ragansu Chakkappai · Po-Wen Chang · Yuan-Tang Chou · Sascha Diefenbacher · Jordan Dudley · Ibrahim Elsharkawy · Steven Farrell · Aishik Ghosh · Cristina Giordano · Isabelle Guyon · Chris Harris · Yota Hashizume · Shih-Chieh Hsu · Elham E Khoda · Claudius Krause · Ang Li · Benjamin Nachman · David Rousseau · Robert Schöfbeck · Maryam Shooshtari · Dennis Schwarz · Ihsan Ullah · Daohan Wang · Yulei Zhang

ConStellaration: A dataset of QI-like stellarator plasma boundaries and optimization benchmarks

Santiago Cadena · Andrea Merlo · Emanuel Laude · Alexander Bauer · Atul Agrawal · Maria Pascu · Marija Savtchouk · Lukas Bonauer · Enrico Guiraud · Stuart Hudson · Markus Kaiser

GlobalTomo: A global dataset for physics-ML seismic wavefield modeling and FWI

Shiqian Li · Zhi Li · Zhancun Mu · Shiji Xin · Zhixiang Dai · Kuangdai Leng · Rita Zhang · Xiaodong Song · Yixin Zhu

STAR: A Benchmark for Astronomical Star Fields Super-Resolution

WU KUO-CHENG · Guohang Zhuang · Jinyang Huang · Xiang Zhang · Wanli Ouyang · Yan Lu

UniFoil: A Universal Dataset of Airfoils in Transitional and Turbulent Regimes for Subsonic and Transonic Flows

Rohit Kanchi · Benjamin Melanson · Nithin Somasekharan · Shaowu Pan · Sicheng He

A Physics-preserved Transfer Learning Method for Differential Equations

Hao-Ran Yang · Chuan-Xian Ren

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World

MingMing Yu · Fei Zhu · Wenzhuo Liu · Yirong Yang · Qunbo Wang · wenjun wu · Jing Liu

Real-World Reinforcement Learning of Active Perception Behaviors

Edward Hu · Jie Wang · Xingfang Yuan · Fiona Luo · Muyao Li · Gaspard Lambrechts · Oleh Rybkin · Dinesh Jayaraman

Dynamic Focused Masking for Autoregressive Embodied Occupancy Prediction

Yuan Sun · Julio Contreras · Jorge Ortiz

Taccel: Scaling Up Vision-based Tactile Robotics via High-performance GPU Simulation

Yuyang Li · Wenxin Du · Chang Yu · Puhao Li · Zihang Zhao · Tengyu Liu · Chenfanfu Jiang · Yixin Zhu · Siyuan Huang

MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering

Qiwen Gu · Xufei Wang · Junqiao Zhao · Siyue Tao · Tiantian Feng · Ziqiao Wang · Guang Chen

CogVLA: Cognition-Aligned Vision-Language-Action Models via Instruction-Driven Routing & Sparsification

Wei Li · Renshan Zhang · Rui Shao · Jie He · Liqiang Nie

Towards Reliable LLM-based Robots Planning via Combined Uncertainty Estimation

Shiyuan Yin · Chenjia Bai · Zihao Zhang · Junwei Jin · Xinxin Zhang · Chi Zhang · Xuelong Li

Fast-in-Slow: A Dual-System VLA Model Unifying Fast Manipulation within Slow Reasoning

Hao Chen · Jiaming Liu · Chenyang Gu · Zhuoyang Liu · Renrui Zhang · Xiaoqi Li · Xiao He · Yandong Guo · Chi-Wing Fu · Shanghang Zhang · Pheng-Ann Heng

Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents

Zhizhen Zhang · Lei Zhu · Zhen Fang · Zi Huang · Yadan Luo

DEAL: Diffusion Evolution Adversarial Learning for Sim-to-Real Transfer

Wentao Xu · Huiqiao Fu · Haoyu Dong · Zhehao Zhou · Chunlin Chen

Gradient Alignment in Physics-informed Neural Networks: A Second-Order Optimization Perspective

Sifan Wang · Ananyae bhartari · Bowen Li · Paris Perdikaris

SpiderSolver: A Geometry-Aware Transformer for Solving PDEs on Complex Geometries

KAI QI · Fan Wang · Zhewen Dong · Jian Sun

GyroSwin: 5D Surrogates for Gyrokinetic Plasma Turbulence Simulations

Fabian Paischer · Gianluca Galletti · William Hornsby · Paul Setinek · Lorenzo Zanisi · Naomi Carey · Stanislas Pamela · Johannes Brandstetter

SymMaP: Improving Computational Efficiency in Linear Solvers through Symbolic Preconditioning

Hong Wang · Jie Wang · Minghao Ma · Haoran Shao · Haoyang Liu

Learning non-equilibrium diffusions with Schrödinger bridges: from exactly solvable to simulation-free

Stephen Zhang · Michael Stumpf

Local-Global Associative Frames for Symmetry-Preserving Crystal Structure Modeling

haowei hua · Wanyu Lin

Hybrid Boundary Physics-Informed Neural Networks for Solving Navier-Stokes Equations with Complex Boundary

ChuYu Zhou · Tianyu Li · Chenxi Lan · Rongyu Du · Guoguo Xin · Wei Li · Guoqing Wang · Xun Liu · Hangzhou Yang

Hybrid Latent Representations for PDE Emulation

Ali Can Bekar · Siddhant Agarwal · Christian Hüttig · Nicola Tosi · David Greenberg

Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

Xinyue Zhu · Binghao Huang · Yunzhu Li

SAFE: Multitask Failure Detection for Vision-Language-Action Models

Qiao Gu · Yuanliang Ju · Shengxiang Sun · Igor Gilitschenski · Haruki Nishimura · Masha Itkina · Florian Shkurti

PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning

Xiaogang Jia · Qian Wang · Anrui Wang · Han Wang · Balázs Gyenes · Emiliyan Gospodinov · Xinkai Jiang · Ge Li · Hongyi Zhou · Weiran Liao · Xi Huang · Maximilian Beck · Moritz Reuss · Rudolf Lioutikov · Gerhard Neumann

$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks

Pei Zhou · Wanting Yao · Qian Luo · Xunzhe Zhou · Yanchao Yang

Reinventing Multi-Agent Collaboration through Gaussian-Image Synergy in Diffusion Policies

Ziye Wang · Li Kang · Yiran Qin · Jiahua Ma · zhanglin peng · LEI BAI · Ruimao Zhang

Human-assisted Robotic Policy Refinement via Action Preference Optimization

Wenke Xia · Yichu Yang · Hongtao Wu · Xiao Ma · Tao Kong · Di Hu

A Practical Guide for Incorporating Symmetry in Diffusion Policy

Dian Wang · Boce Hu · Shuran Song · Robin Walters · Robert Platt

A Smooth Sea Never Made a Skilled SAILOR: Robust Imitation via Learning to Search

Arnav Kumar Jain · Vibhakar Mohta · Subin Kim · Atiksh Bhardwaj · Juntao Ren · Yunhai Feng · Sanjiban Choudhury · Gokul Swamy

DanmakuTPPBench: A Multi-modal Benchmark for Temporal Point Process Modeling and Understanding

Yue Jiang · Jichu Li · Yang Liu · Dingkang Yang · Feng Zhou · Quyu Kong

MAESTRO : Adaptive Sparse Attention and Robust Learning for Multimodal Dynamic Time Series

Payal Mohapatra · Yueyuan Sui · Akash Pandey · Stephen Xia · Qi Zhu

Delving into Large Language Models for Effective Time-Series Anomaly Detection

JUN WOO PARK · Kyudan Jung · Dohyun Lee · Hyuck Lee · DAEHOON GWAK · ChaeHun Park · Jaegul Choo · Jaewoong Cho

Eulerian Neural Network Informed by Chemical Transport for Air Quality Forecasting

Xukai Zhang · Shuliang Wang · Guangyin Jin · Ziqiang Yuan · Hanning Yuan · Sijie Ruan

AliO: Output Alignment Matters in Long-Term Time Series Forecasting

Kwangryeol Park · Jaeho Kim · Seulki Lee

ShapeX: Shapelet-Driven Post Hoc Explanations for Time Series Classification Models

Bosong Huang · Ming Jin · Yuxuan Liang · Johan Barthelemy · Debo Cheng · Qingsong Wen · Chenghao Liu · Shirui Pan

Improving Time Series Forecasting via Instance-aware Post-hoc Revision

Zhiding Liu · Mingyue Cheng · Guanhao Zhao · Jiqian Yang · Qi Liu · Enhong Chen

FlowMixer: A Depth-Agnostic Neural Architecture for Interpretable Spatiotemporal Forecasting

Fares Mehouachi · Saif Eddin Jabari

Topology-Aware Conformal Prediction for Stream Networks

Jifan Zhang · Fangxin Wang · Zihe Song · Philip S Yu · Kaize Ding · Shixiang Zhu

Let's Revise Step-by-Step: A Unified Local Search Framework for Code Generation with LLMs

Zhiyi Lyu · Jianguo Huang · Yanchen Deng · Steven Hoi · Bo An

CausalVerse: Benchmarking Causal Representation Learning with Configurable High-Fidelity Simulations

Guangyi Chen · Yunlong Deng · Peiyuan Zhu · Yan Li · Yifan Shen · Zijian Li · Kun Zhang

AutoData: A Multi-Agent System for Open Web Data Collection

Tianyi Ma · Yiyue Qian · Zheyuan Zhang · Zehong Wang · Xiaoye Qian · Feifan Bai · Yifan Ding · Xuwei Luo · Shinan Zhang · Keerthiram Murugesan · Chuxu Zhang · Yanfang Ye

Photography Perspective Composition: Towards Aesthetic Perspective Recommendation

Lujian Yao · Siming Zheng · Xinbin Yuan · Zhuoxuan Cai · Pu Wu · Jinwei Chen · Bo Li · Peng-Tao Jiang

Improving Data Efficiency for LLM Reinforcement Fine-tuning Through Difficulty-targeted Online Data Selection and Rollout Replay

Yifan Sun · Jingyan Shen · Yibin Wang · Tianyu Chen · Zhendong Wang · Mingyuan Zhou · Huan Zhang

Mitigating Instability in High Residual Adaptive Sampling for PINNs via Langevin Dynamics

Minseok Jeong · Giup Seo · Euiseok Hwang

MIHC: Multi-View Interpretable Hypergraph Neural Networks with Information Bottleneck for Chip Congestion Prediction

Zeyue Zhang · Heng Ping · Peiyu Zhang · Nikos Kanakaris · Xiaoling LU · Paul Bogdan · Xiongye Xiao

SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks

Hwiwon Lee · Ziqi Zhang · Hanxiao Lu · LINGMING ZHANG

How to Auto-optimize Prompts for Domain Tasks? Adaptive Prompting and Reasoning through Evolutionary Domain Knowledge Adaptation

Yang Zhao · Pu Wang · Hao Frank Yang

MathArena: Evaluating LLMs on Uncontaminated Math Competitions

Mislav Balunovic · Jasper Dekoninck · Ivo Petrov · Nikola Jovanović · Martin Vechev

AgentRecBench: Benchmarking LLM Agent-based Personalized Recommender Systems

Yu Shang · Peijie Liu · Yuwei Yan · Zijing Wu · Leheng Sheng · Yuanqing Yu · Chumeng Jiang · An Zhang · Fengli Xu · Yu Wang · Min Zhang · Yong Li

Satellites Reveal Mobility: A Commuting Origin-destination Flow Generator for Global Cities

Can Rong · Xin Zhang · Yanxin Xi · HONGJIE SUI · Jingtao Ding · Yong Li

SGN: Shifted Window-Based Hierarchical Variable Grouping for Multivariate Time Series Classification

Zenan Ying · Zhi Zheng · huijun hou · Tong Xu · Qi Liu · Jinke Wang · Wei Chen

Investigating Hallucinations of Time Series Foundation Models through Signal Subspace Analysis

Yufeng Zou · Zijian Wang · Diego Klabjan · Han Liu

On the Integration of Spatial-Temporal Knowledge: A Lightweight Approach to Atmospheric Time Series Forecasting

Yisong Fu · Fei Wang · Zezhi Shao · Boyu Diao · Lin Wu · Zhulin An · Chengqing Yu · Yujie Li · Yongjun Xu

Glocal Information Bottleneck for Time Series Imputation

Jie Yang · Kexin Zhang · Guibin Zhang · Philip S Yu · Kaize Ding

Selective Learning for Deep Time Series Forecasting

Yisong Fu · Zezhi Shao · Chengqing Yu · Yujie Li · Zhulin An · Qi Wang · Yongjun Xu · Fei Wang

Learning to Factorize Spatio-Temporal Foundation Models

Siru Zhong · Junjie Qiu · Yangyu Wu · Xingchen Zou · Zhongwen Rao · Bin Yang · Chenjuan Guo · Hao Xu · Yuxuan Liang

PMLF: A Physics-Guided Multiscale Loss Framework for Structurally Heterogeneous Time Series

Xinghong Chen · Weilin Wu · Kunping Yang · Guannan Chen

Learning Counterfactual Outcomes Under Rank Preservation

Peng Wu · Haoxuan Li · Chunyuan Zheng · Yan Zeng · Jiawei Chen · Yang Liu · Ruocheng Guo · Kun Zhang

A Cautionary Tale on Integrating Studies with Disparate Outcome Measures for Causal Inference

Harsh Parikh · Trang Nguyen · Elizabeth Stuart · Kara Rudolph · Caleb Miles

An Analysis of Causal Effect Estimation using Outcome Invariant Data Augmentation

Uzair Akbar · Niki Kilbertus · Hao Shen · Krikamol Muandet · Bo Dai

Non-Stationary Structural Causal Bandits

Yeahoon Kwon · Yesong Choe · Soungmin Park · Neil Dhir · Sanghack Lee

Estimation of Treatment Effects in Extreme and Unobserved Data

Jiyuan Tan · Vasilis Syrgkanis · Jose Blanchet

Universal Causal Inference in a Topos

Sridhar Mahadevan

Score-informed Neural Operator for Enhancing Ordering-based Causal Discovery

Jiyeon Kang · Songseong Kim · Chanhui Lee · Doyeong Hwang · Joanie Chung · Yunkyung Ko · Sumin Lee · Sungwoong Kim · Sungbin Lim

Meta-D2AG: Causal Graph Learning with Interventional Dynamic Data

Tian Gao · Songtao Lu · Junkyu Lee · Elliot Nelson · Debarun Bhattacharjya · Yue Yu · Miao Liu

Disentangling misreporting from genuine adaptation in strategic settings: a causal approach

Dylan Zapzalka · Trenton Chang · Lindsay Warrenburg · Sae-Hwan Park · Daniel Shenfeld · Ravi Parikh · Jenna Wiens · Maggie Makar

Counterfactual Image Editing with Disentangled Causal Latent Space

Yushu Pan · Elias Bareinboim

DGCBench: A Deep Graph Clustering Benchmark

Benyu Wu · Yue Liu · Qiaoyu Tan · Xinwang Liu · Wei Du · Jun Wang · Guoxian Yu

Theory-Driven Label-Specific Representation for Incomplete Multi-View Multi-Label Learning

Quanjiang Li · Tianxiang Xu · Tingjin Luo · Yan Zhong · Yang Li · Yiyun Zhou · Chenping Hou

A TRIANGLE Enables Multimodal Alignment Beyond Cosine Similarity

Giordano Cicchetti · Eleonora Grassucci · Danilo Comminiello

Connecting Neural Models Latent Geometries with Relative Geodesic Representations

Hanlin Yu · Berfin Inal · Georgios Arvanitidis · Søren Hauberg · Francesco Locatello · Marco Fumero

Bit-swapping Oriented Twin-memory Multi-view Clustering in Lifelong Incomplete Scenarios

Shengju Yu · Pei Zhang · Siwei Wang · Suyuan Liu · Xinhang Wan · Zhibin Dong · Tiejun Li · Xinwang Liu

DUAL: Learning Diverse Kernels for Aggregated Two-sample and Independence Testing

Zhijian Zhou · Xunye Tian · Liuhua Peng · Chao Lei · Antonin Schrab · Danica J. Sutherland · Feng Liu

Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection

Shenzhi Yang · Junbo Zhao · Sharon Li · Shouqing Yang · Dingyu Yang · Xiaofang Zhang · Haobo Wang

Hypergraph-Enhanced Contrastive Learning for Multi-View Clustering with Hyper-Laplacian Regularization

Zhibin Gu · weili wang

IA-GGAD: Zero-shot Generalist Graph Anomaly Detection via Invariant and Affinity Learning

Xiong Zhang · Zhenli He · Changlong Fu · Cheng Xie

Heterogeneous Adversarial Play in Interactive Environments

Manjie Xu · Xinyi Yang · Jiayu Zhan · Wei Liang · Chi Zhang · Yixin Zhu

Are Greedy Task Orderings Better Than Random in Continual Linear Regression?

Matan Tsipory · Ran Levinstein · Itay Evron · Mark Kong · Deanna Needell · Daniel Soudry

Covariances for Free: Exploiting Mean Distributions for Training-free Federated Learning

Dipam Goswami · Simone Magistri · Kai Wang · Bartłomiej Twardowski · Andrew Bagdanov · Joost van de Weijer

A compressive-expressive communication framework for compositional representations

Rafael Elberg · Felipe del Río · Mircea Petrache · Denis Parra

Minimal Semantic Sufficiency Meets Unsupervised Domain Generalization

Tan Pan · Kaiyu Guo · Dongli Xu · Zhaorui Tan · Chen Jiang · Deshu Chen · Xin Guo · Brian Lovell · LIMEI HAN · Yuan Cheng · Mahsa Baktashmotlagh

Thought Communication in Multiagent Collaboration

Yujia Zheng · Zhuokai Zhao · Zijian Li · Yaqi Xie · Mingze Gao · Lizhu Zhang · Kun Zhang

Exploring Structural Degradation in Dense Representations for Self-supervised Learning

Siran Dai · Qianqian Xu · Peisong Wen · Yang Liu · Qingming Huang

Understanding Contrastive Learning via Gaussian Mixture Models

Parikshit Bansal · Ali Kavis · Sujay Sanghavi

CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning

Ronghao Lin · Qiaolin He · Sijie Mai · Ying Zeng · Aolin Xiong · Li Huang · Yap-Peng Tan · Haifeng Hu

Auto-Compressing Networks

Evangelos Dorovatas · Georgios Paraskevopoulos · Alexandros Potamianos

Place Cells as Multi-Scale Position Embeddings: Random Walk Transition Kernels for Path Planning

Minglu Zhao · Dehong Xu · Deqian Kong · Wen-Hao Zhang · Ying Nian Wu

Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces

Alejandro García-Castellanos · David Wessels · Nicky J. van den Berg · Remco Duits · Daniel M. Pelt · Erik Bekkers

The Structure of Relation Decoding Linear Operators in Large Language Models

Miranda Anna Christ · Adrián Csiszárik · Gergely Becsó · Dániel Varga

Soft Task-Aware Routing of Experts for Equivariant Representation Learning

Jaebyeong Jeon · Hyunseo Jang · Jy-yong Sohn · Kibok Lee

Random Forest Autoencoders for Guided Representation Learning

Adrien Aumon · Shuang Ni · Myriam Lizotte · Guy Wolf · Kevin Moon · Jake Rhodes

Exploiting Task Relationships in Continual Learning via Transferability-Aware Task Embeddings

Yanru Wu · Jianning Wang · Xiangyu Chen · Aurora · Yang Tan · Hanbing Liu · Yang Li

Diffusion-Driven Progressive Target Manipulation for Source-Free Domain Adaptation

Yuyang Huang · Yabo Chen · Junyu Zhou · Wenrui Dai · XIAOPENG ZHANG · Junni Zou · Hongkai Xiong · Qi Tian

Transfer Learning for Benign Overfitting in High-Dimensional Linear Regression

Yeichan Kim · Ilmun Kim · Seyoung Park

Towards Large-Scale In-Context Reinforcement Learning by Meta-Training in Randomized Worlds

Fan Wang · Pengtao Shao · Yiming Zhang · Bo Yu · Shaoshan Liu · Ning Ding · Yang Cao · Yu Kang · Haifeng Wang

Mixed-Sample SGD: an End-to-end Analysis of Supervised Transfer Learning

Yuyang Deng · Samory Kpotufe

A High-Dimensional Statistical Method for Optimizing Transfer Quantities in Multi-Source Transfer Learning

Qingyue Zhang · Haohao Fu · Guanbo Huang · Yaoyuan Liang · Chang Chu · Tianren Peng · Yanru Wu · Qi Li · Yang Li · Shao-Lun Huang

MoORE: SVD-based Model MoE-ization for Conflict- and Oblivion-Resistant Multi-Task Adaptation

Shen Yuan · Yin Zheng · Taifeng Wang · BINBINLIU · Hongteng Xu

Self-Training with Dynamic Weighting for Robust Gradual Domain Adaptation

Zixi Wang · Yushe Cao · Yubo Huang · Jinzhu Wei · Jingzehua Xu · Shuai Zhang · Xin Lai

SMRS: advocating a unified reporting standard for surrogate models in the artificial intelligence era.

Elizaveta Semenova · Siobhan Mackenzie Hall · Timothy James Hitge · Alisa Sheinkman · Jon Cockayne

TabArena: A Living Benchmark for Machine Learning on Tabular Data

Nick Erickson · Lennart Purucker · Andrej Tschalzev · David Holzmüller · Prateek Desai · David Salinas · Frank Hutter

Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning

Zhonghao He · Tianyi (Alex) Qiu · Hirokazu Shirado · Maarten Sap

WALL-E: World Alignment by NeuroSymbolic Learning improves World Model-based LLM Agents

Siyu Zhou · Tianyi Zhou · Yijun Yang · Guodong Long · Deheng Ye · Jing Jiang · Chengqi Zhang

Improving Decision Trees through the Lens of Parameterized Local Search

Juha Harviainen · Frank Sommer · Manuel Sorge

Semi-supervised Vertex Hunting, with Applications in Network and Text Analysis

Yicong Jiang · Zheng Tracy Ke

Provable Scaling Laws for the Test-Time Compute of Large Language Models

Yanxi Chen · Xuchen Pan · Yaliang Li · Bolin Ding · Jingren Zhou

Two‑Stage Learning of Stabilizing Neural Controllers via Zubov Sampling and Iterative Domain Expansion

Haoyu Li · Xiangru Zhong · Bin Hu · Huan Zhang

Matching Markets Meet LLMs: Algorithmic Reasoning with Ranked Preferences

Hadi Hosseini · Samarth Khanna · Ronak Singh

GUARD: Constructing Realistic Two-Player Matrix and Security Games for Benchmarking Game-Theoretic Algorithms

Noah Krever · Jakub Cerny · Moise Blanchard · Christian Kroer

Parameter Dynamics of Online Machine Learning and Test-time Adaptation

Jae-Hong Lee

SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks

Xinyu Luo · Kecheng Chen · Pao-Sheng Sun · Chris Xing TIAN · Arindam Basu · Haoliang Li

Vicinity-Guided Discriminative Latent Diffusion for Privacy-Preserving Domain Adaptation

Jing Wang · Wonho Bae · Jiahong Chen · Wenxu Wang · Junhyug Noh

Controlled Visual Hallucination via Thalamus-Driven Decoupling Network for Domain Adaptation of Black-Box Predictors

Yuwu Lu · Chunzhi Liu

Vertical Federated Feature Screening

Huajun Yin · Liyuan Wang · Yingqiu Zhu · Liping Zhu · Danyang Huang

CTSketch: Compositional Tensor Sketching for Scalable Neurosymbolic Learning

Seewon Choi · Alaia Solko-Breslin · Rajeev Alur · Eric Wong

Exploiting Dynamic Sparsity in Einsum

Christoph Staudt · Mark Blacher · Tim Hoffmann · Kaspar Kasche · Olaf Beyersdorff · Joachim Giesen

SHGR: A Generalized Maximal Correlation Coefficient

Samuel Stocksieker · Denys Pommeret

Improving Monte Carlo Tree Search for Symbolic Regression

Zhengyao Huang · Daniel Huang · Tiannan Xiao · Dina Ma · Zhenyu Ming · Hao Shi · Yuanhui Wen

A$^3$E: Towards Compositional Model Editing

Hongming Piao · Hao Wang · Dapeng Wu · Ying Wei

Conformal Online Learning of Deep Koopman Linear Embeddings

Ben Gao · Jordan Patracone · Stephane Chretien · Olivier Alata

Gradient-Guided Epsilon Constraint Method for Online Continual Learning

Song Lai · Changyi Ma · Fei Zhu · Zhe Zhao · Xi Lin · GAOFENG MENG · Qingfu Zhang

HQA-VLAttack: Towards High Quality Adversarial Attack on Vision-Language Pre-Trained Models

Han Liu · Jiaqi Li · Zhi Xu · Xiaotong Zhang · Xiaoming Xu · Fenglong Ma · Yuanman Li · Hong Yu

Fourier Clouds: Fast Bias Correction for Imbalanced Semi-Supervised Learning

Jiawei Gu · Yidi Wang · Qingqiang Sun · Xinming Li · Xiao Luo · Ziyue Qiao

You Can Trust Your Clustering Model: A Parameter-free Self-Boosting Plug-in for Deep Clustering

Hanyang Li · Yuheng Jia · Hui LIU · Junhui Hou

Thinker: Learning to Think Fast and Slow

Stephen Chung · Wenyu Du · Jie Fu

A Cramér–von Mises Approach to Incentivizing Truthful Data Sharing

Alex Clinton · Thomas Zeng · Yiding Chen · Jerry Zhu · Kirthevasan Kandasamy

Certifying Concavity and Monotonicity in Games via Sum-of-Squares Hierarchies

Vincent Leon · Iosif Sakos · Ryann Sim · Antonios Varvitsiotis

Clustering via Hedonic Games: New Concepts and Algorithms

Gergely Csáji · Alexander Gundert · Jörg Rothe · Ildikó Schlotter

Learning from Delayed Feedback in Games via Extra Prediction

Yuma Fujimoto · Kenshi Abe · Kaito Ariu

Beyond Last-Click: An Optimal Mechanism for Ad Attribution

Nan An · Weian Li · Qi Qi · Changyuan Yu · Liang Zhang

Online Strategic Classification With Noise and Partial Feedback

Tianrun Zhao · Xiaojie Mao · Yong Liang

Multidimensional Bayesian Utility Maximization: Tight Approximations to Welfare

Kira Goldner · Taylor Lundy

Strategic Classification with Non-Linear Classifiers

Benyamin Trachtenberg · Nir Rosenfeld

Metritocracy: Representative Metrics for Lite Benchmarks

Ariel Procaccia · Ben Schiffer · Serena Wang · Shirley Zhang

Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks

Fanghui Liu · Leello Tadesse Dadi · Volkan Cevher

Memory-Enhanced Neural Solvers for Routing Problems

Felix Chalumeau · Refiloe Shabe · Noah De Nicola · Arnu Pretorius · Tom Barrett · Nathan Grinsztajn

Reconstruction and Secrecy under Approximate Distance Queries

Shay Moran · Elizaveta Nesterova

A solvable model of learning generative diffusion: theory and insights

Hugo Cui · Cengiz Pehlevan · Yue Lu

On Agnostic PAC Learning in the Small Error Regime

Julian Asilis · Mikael Møller Høgsgaard · Grigoris Velegkas

Selective Omniprediction and Fair Abstention

Sílvia Casacuberta · Varun Kanade

Statistical Guarantees for High-Dimensional Stochastic Gradient Descent

Jiaqi Li · Zhipeng Lou · Johannes Schmidt-Hieber · Wei Biao Wu

Principled Long-Tailed Generative Modeling via Diffusion Models

Pranoy Das · Kexin Fu · Abolfazl Hashemi · Vijay Gupta

On the sample complexity of semi-supervised multi-objective learning

Tobias Wegel · Geelon So · Junhyung Park · Fanny Yang

Understanding Data Influence in Reinforcement Finetuning

Haoru Tan · Xiuzhe Wu · Sitong Wu · Shaofeng Zhang · Yanfeng Chen · Xingwu Sun · Jeanne Shen · Xiaojuan Qi

Uni-RL: Unifying Online and Offline RL via Implicit Value Regularization

Haoran Xu · Liyuan Mao · Hui Jin · Weinan Zhang · Xianyuan Zhan · Amy Zhang

Horizon Reduction Makes RL Scalable

Seohong Park · Kevin Frans · Deepinder Mann · Benjamin Eysenbach · Aviral Kumar · Sergey Levine

Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning

Wenlin Zhang · Xiangyang Li · Kuicai Dong · Yichao Wang · Pengyue Jia · Xiaopeng Li · Yingyi Zhang · Derong Xu · Zhaocheng Du · Huifeng Guo · Ruiming Tang · Xiangyu Zhao

Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models

Jiajun Fan · Tong Wei · Chaoran Cheng · Yuxin Chen · Ge Liu

Multi-Objective Reinforcement Learning with Max-Min Criterion: A Game-Theoretic Approach

woohyeon Byeon · Giseung Park · Jongseong Chae · Amir Leshem · Youngchul Sung

Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning

Younggyo Seo · Pieter Abbeel

LLM-Explorer: A Plug-in Reinforcement Learning Policy Exploration Enhancement Driven by Large Language Models

Qianyue Hao · Yiwen Song · Qingmin Liao · Jian Yuan · Yong Li

Improving Regret Approximation for Unsupervised Dynamic Environment Generation

Harry Mead · Bruno Lacerda · Jakob Foerster · Nick Hawes

Continuous Q-Score Matching: Diffusion Guided Reinforcement Learning for Continuous-Time Control

Chengxiu HUA · Jiawen Gu · Yushun Tang

Minimax Adaptive Online Nonparametric Regression over Besov spaces

Paul Liautaud · Pierre Gaillard · Olivier Wintenberger

Tractable Multinomial Logit Contextual Bandits with Non-Linear Utilities

Taehyun Hwang · Dahngoon Kim · Min-hwan Oh

Non-Uniform Multiclass Learning with Bandit Feedback

Steve Hanneke · Amirreza Shaeiri · Hongao Wang

Generalizing while preserving monotonicity in comparison-based preference learning models

Julien Fageot · Peva Blanchard · Gilles Bareilles · Lê-Nguyên Hoang

Self-Boost via Optimal Retraining: An Analysis via Approximate Message Passing

Adel Javanmard · Rudrajit Das · Alessandro Epasto · Vahab Mirrokni

Robust Minimax Boosting with Performance Guarantees

Santiago Mazuelas · Veronica Alvarez

Improved Robust Estimation for Erdős-Rényi Graphs: The Sparse Regime and Optimal Breakdown Point

Hongjie Chen · Jingqiu Ding · Yiding Hua · Stefan Tiegel

Implicit Bias of Spectral Descent and Muon on Multiclass Separable Data

Chen Fan · Mark Schmidt · Christos Thrampoulidis

Finite Sample Analyses for Continuous-time Linear Systems: System Identification and Online Control

Hongyi Zhou · Jingwei Li · Jingzhao Zhang

Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies

Dynamic Algorithm for Explainable $k$-medians Clustering under $\ell_p$ Norm

Konstantin Makarychev · Ilias Papanikolaou · Liren Shan

Learning Preferences without Interaction for Cooperative AI: A Hybrid Offline-Online Approach

Haitong Ma · Haoran Yu · Haobo Fu · Shuai Li

Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning

Yunpeng Jiang · Jianshu Hu · Paul Weng · Yutong Ban

$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training

Jin Zhou · Kaiwen Wang · Jonathan Chang · Zhaolin Gao · Nathan Kallus · Kilian Weinberger · Kianté Brantley · Wen Sun

Training a Scientific Reasoning Model for Chemistry

Siddharth Narayanan · James Braza · Ryan-Rhys Griffiths · Albert Bou · Geemi Wellawatte · Mayk Caldas Ramos · Ludovico Mitchener · Michael Pieler · Sam Rodriques · Andrew White

A Bayesian Fast-Slow Framework to Mitigate Interference in Non-Stationary Reinforcement Learning

Yihuan Mao · Chongjie Zhang

The Price of Sparsity: Sufficient Conditions for Sparse Recovery using Sparse and Sparsified Measurements

Youssef Chaabouni · David Gamarnik

Kernel Regression in Structured Non-IID Settings: Theory and Implications for Denoising Score Learning

Dechen Zhang · Zhenmei Shi · Zhang · Yingyu Liang · Difan Zou

Tradeoffs between Mistakes and ERM Oracle Calls in Online and Transductive Online Learning

Idan Attias · Steve Hanneke · Arvind Ramaswami

Benign Overfitting in Single-Head Attention

Roey Magen · Shuning Shang · Zhiwei Xu · Spencer Frei · Wei Hu · Gal Vardi

Optimal Best Arm Identification under Differential Privacy

Marc Jourdan · Achraf Azize

Asymptotic theory of SGD with a general learning-rate

Or Goldreich · Ziyang Wei · SOHAM BONNERJEE · Jiaqi Li · Wei Biao Wu

Accelerating Feature Conformal Prediction via Taylor Approximation

Zihao Tang · Boyuan Wang · Chuan Wen · Jiaye Teng

Mean-Field Sampling for Cooperative Multi-Agent Reinforcement Learning

Emile Anand · Ishani Karmarkar · Guannan Qu

Scalable Policy-Based RL Algorithms for POMDPs

Ameya Anjarlekar · S. Rasoul Etesami · R. Srikant

Improved Best-of-Both-Worlds Regret for Bandits with Delayed Feedback

Ofir Schlisselberg · Tal Lancewicki · Peter Auer · Yishay Mansour

Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code

Augusto B. Corrêa · André G. Pereira · Jendrik Seipp

FedEL: Federated Elastic Learning for Heterogeneous Devices

Letian Zhang · Bo Chen · Jieming Bian · Lei Wang · Jie Xu

Accelerating Block Coordinate Descent for LLM Finetuning via Landscape Expansion

Qijun Luo · Yifei Shen · Liangzu Peng · Dongsheng Li · Xiao Li

TADA: Improved Diffusion Sampling with Training-free Augmented DynAmics

Tianrong Chen · Huangjie Zheng · David Berthelot · Jiatao Gu · Joshua Susskind · Shuangfei Zhai

HoPE: Hybrid of Position Embedding for Long Context Vision-Language Models

Haoran Li · Yingjie Qin · Baoyuan Ou · Lai Xu · Ruiwen Xu

Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation

Erfan Baghaei Potraghloo · Seyedarmin Azizi · Souvik Kundu · Massoud Pedram

Improving Formal Reasoning of Transformer with State Stack

Kechi Zhang · Ge Li · Jia Li · Huangzhao Zhang · Yihong Dong · Jia Li · Jingjing Xu · Zhi Jin

ChunkKV: Semantic-Preserving KV Cache Compression for Efficient Long-Context LLM Inference

Xiang Liu · Zhenheng Tang · Peijie Dong · Zeyu Li · Liuyue · Bo Li · Xuming Hu · Xiaowen Chu

Gaussian Process Upper Confidence Bound Achieves Nearly-Optimal Regret in Noise-Free Gaussian Process Bandits

Shogo Iwazaki

Multi-modal contrastive learning adapts to intrinsic dimensions of shared latent variables

Yu Gui · Cong Ma · Zongming Ma

Heavy-Ball Momentum Method in Continuous Time and Discretization Error Analysis

Bochen Lyu · Xiaojing Zhang · Fangyi Zheng · He Wang · Zheng Wang · Zhanxing Zhu

Generalized Top-k Mallows Model for Ranked Choices

Shahrzad Haddadan · Sara Ahmadian

Exponential Convergence Guarantees for Iterative Markovian Fitting

Marta Gentiloni Silveri · Giovanni Conforti · Alain Durmus

On the Hardness of Conditional Independence Testing In Practice

Zheng He · Roman Pogodin · Yazhe Li · Namrata Deka · Arthur Gretton · Danica J. Sutherland

Risk-Averse Constrained Reinforcement Learning with Optimized Certainty Equivalents

Jane Lee · Baturay Saglam · Spyridon Pougkakiotis · Amin Karbasi · Dionysis Kalogerias

Offline imitation learning in $Q^\pi$-realizable MDPs without expert realizability

Antoine Moulin · Gergely Neu · Luca Viano

Interactive and Hybrid Imitation Learning: Provably Beating Behavior Cloning

Yichen Li · Chicheng Zhang

Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

Toshinori Kitamura · Arnob Ghosh · Tadashi Kozuno · Wataru Kumagai · Kazumi Kasaura · Kenta Hoshino · Yohei Hosoe · Yutaka Matsuo

A Near-optimal, Scalable and Parallelizable Framework for Stochastic Bandits Robust to Adversarial Corruptions and Beyond

Zicheng Hu · Cheng Chen

Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs

Xiangcheng Zhang · Yige Hong · Weina Wang

Gains: Fine-grained Federated Domain Adaptation in Open Set

Zhengyi Zhong · Wenzheng Jiang · Weidong Bao · Ji Wang · Qi Wang · Guanbo Wang · Yongheng Deng · Ju Ren

AmorLIP: Efficient Language-Image Pretraining via Amortization

Haotian Sun · Yitong Li · Yuchen Zhuang · Niao He · Hanjun Dai · Bo Dai

Fixed-Point RNNs: Interpolating from Diagonal to Dense

Sajad Movahedi · Felix Sarnthein · Nicola Muca Cirone · Antonio Orvieto

Teaching Transformers to Solve Combinatorial Problems through Efficient Trial & Error

Panagiotis Giannoulis · Yorgos Pantis · Christos Tzamos

Pan-LUT: Efficient Pan-sharpening via Learnable Look-Up Tables

Zhongnan Cai · Yingying Wang · Hui Zheng · Panwang Pan · Zixu Lin · Ge Meng · Chenxin Li · Chunming He · Jiaxin Xie · Yunlong Lin · Junbin Lu · Yue Huang · Xinghao Ding

Alleviating Hallucinations in Large Language Models through Multi-Model Contrastive Decoding and Dynamic Hallucination Detection

Chenyu Zhu · Yefeng Liu · Hao Zhang · Aowen Wang · Yangxue · Guanhua Chen · Longyue Wang · Weihua Luo · Kaifu Zhang

Quartet: Native FP4 Training Can Be Optimal for Large Language Models

Roberto Castro · Andrei Panferov · Rush Tabesh · Oliver Sieberling · Jiale Chen · Mahdi Nikdan · Saleh Ashkboos · Dan Alistarh

InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models

Yanggan Gu · Yuanyi Wang · Zhaoyi Yan · Yiming Zhang · Qi Zhou · Fei Wu · Hongxia Yang

GoRA: Gradient-driven Adaptive Low Rank Adaptation

haonan he · Peng Ye · Yuchen Ren · yuan yuan · LuyangZhou · ShucunJu · lei chen

Learning in Compact Spaces with Approximately Normalized Transformer

Jörg Franke · Urs Spiegelhalter · Marianna Nezhurina · Jenia Jitsev · Frank Hutter · Michael Hefenbrock

FP4 All the Way: Fully Quantized Training of Large Language Models

Brian Chmiel · Maxim Fishman · Ron Banner · Daniel Soudry

Adaptive Latent-Space Constraints in Personalized Federated Learning

Sana Ayromlou · David B. Emerson

Language Ranker: A Lightweight Ranking framework for LLM Decoding

Chenheng Zhang · Tianqi Du · Jizhe Zhang · Mingqing Xiao · Yifei Wang · Yisen Wang · Zhouchen Lin

The Primacy of Magnitude in Low-Rank Adaptation

Zicheng Zhang · Haoran Li · Yifeng Zhang · Guoqiang Gong · Jiaxing Wang · Pengzhang Liu · Qixia Jiang · Junxing Hu

Scaling Laws for Optimal Data Mixtures

Mustafa Shukor · Louis Bethune · Dan Busbridge · David Grangier · Enrico Fini · Alaaeldin El-Nouby · Pierre Ablin

DISCO: DISCrete nOise for Conditional Control in Text-to-Image Diffusion Models

Longquan Dai · Wu Ming · Dejiao Xue · wang he · Jinhui Tang

From Softmax to Score: Transformers Can Effectively Implement In-Context Denoising Steps

Paul Rosu · Lawrence Carin · Xiang Cheng

FlashBias: Fast Computation of Attention with Bias

Haixu Wu · Minghao Guo · Yuezhou Ma · Yuanxu Sun · Jianmin Wang · Wojciech Matusik · Mingsheng Long

Inference-Time Hyper-Scaling with KV Cache Compression

Adrian Łańcucki · Konrad Staniszewski · Piotr Nawrot · Edoardo Maria Ponti

GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

Qianhui Wu · Kanzhi Cheng · Rui Yang · Chaoyun Zhang · Jianwei Yang · Huiqiang Jiang · Jian Mu · Baolin Peng · Bo Qiao · Reuben Tan · Si Qin · Lars Liden · Qingwei Lin · Huan Zhang · Tong Zhang · Jianbing Zhang · Dongmei Zhang · Jianfeng Gao

MJ-Bench: Is Your Multimodal Reward Model Really a Good Judge for Text-to-Image Generation?

Zhaorun Chen · Zichen Wen · Yichao Du · Yiyang Zhou · Chenhang Cui · Siwei Han · Jen Weng · Chaoqi Wang · Zhengwei Tong · Leria HUANG · Canyu Chen · Haoqin Tu · Qinghao Ye · Zhihong Zhu · Yuqing Zhang · Jiawei Zhou · Zhuokai Zhao · Rafael Rafailov · Chelsea Finn · Huaxiu Yao

LIFEBENCH: Evaluating Length Instruction Following in Large Language Models

Wei Zhang · Zhenhong Zhou · Kun Wang · Junfeng Fang · Rongwu Xu · Yuanhe Zhang · Rui Wang · Ge Zhang · Xinfeng Li · Li Sun · Lingjuan Lyu · Yang Liu · Sen Su

Prompting as Scientific Inquiry

Ari Holtzman · Chenhao Tan

Large Language Models Miss the Multi-agent Mark

Emanuele La Malfa · Gabriele La Malfa · Samuele Marro · Jie Zhang · Elizabeth Black · Michael Luck · Philip Torr · Michael Wooldridge

Single GPU Task Adaptation of Pathology Foundation Models for Whole Slide Image Analysis

Neeraj Kumar · Chad Vanderbilt

DePass: Unified Feature Attributing by Simple Decomposed Forward Pass

Xiangyu Hong · Che Jiang · Kai Tian · Biqing Qi · Youbang Sun · Ning Ding · Bowen Zhou

ZeCO: Zero-Communication Overhead Sequence Parallelism for Linear Attention

Yuhong CHOU · Zehao Liu · Rui-Jie Zhu · Xinyi Wan · Tianjian Li · Congying Chu · Qian Liu · Jibin Wu · Zejun MA

Understanding Differential Transformer Unchains Pretrained Self-Attentions

Chaerin Kong · Jiho Jang · Nojun Kwak

Tiled Flash Linear Attention: More Efficient Linear RNN and xLSTM Kernels

Maximilian Beck · Korbinian Pöppel · Phillip Lippe · Sepp Hochreiter

One SPACE to Rule Them All: Jointly Mitigating Factuality and Faithfulness Hallucinations in LLMs

Pengbo Wang · Chaozhuo Li · Chenxu Wang · Liwen Zheng · Litian Zhang · Xi Zhang

Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers

Woomin Song · Sai Muralidhar Jayanthi · Srikanth Ronanki · Kanthashree Mysore Sathyendra · Jinwoo Shin · Aram Galstyan · Shubham Katiyar · Sravan Babu Bodapati

Accurate KV Cache Eviction via Anchor Direction Projection for Efficient LLM Inference

Zijie Geng · Jie Wang · Ziqi Liu · Feng Ju · Yiming Li · Xing Li · Mingxuan Yuan · Jianye Hao · Defu Lian · Enhong Chen · Feng Wu

TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup

Fanxu Meng · Pingzhi Tang · Zengwei Yao · Xing Sun · Muhan Zhang

DeltaProduct: Improving State-Tracking in Linear RNNs via Householder Products

Julien Siems · Timur Carstensen · Arber Zela · Frank Hutter · Massimiliano Pontil · Riccardo Grazzi

Learning Linear Attention in Polynomial Time

Morris Yau · Ekin Akyürek · Jiayuan Mao · Josh Tenenbaum · Stefanie Jegelka · Jacob Andreas

What are you sinking? A geometric approach on attention sink

Valeria Ruscio · Umberto Nanni · Fabrizio Silvestri

Delta Attention: Fast and Accurate Sparse Attention Inference by Delta Correction

Jeffrey Willette · Heejun Lee · Sung Ju Hwang

Polyline Path Masked Attention for Vision Transformer

Zhongchen Zhao · Chaodong Xiao · Hui LIN · Qi Xie · Lei Zhang · Deyu Meng

Linear Differential Vision Transformer: Learning Visual Contrasts via Pairwise Differentials

Yifan Pu · Jixuan Ying · Qixiu Li · Tianzhu Ye · Dongchen Han · Xiaochen Wang · Ziyi Wang · shao xinyu · Gao Huang · Xiu Li

A Closer Look at Model Collapse: From a Generalization-to-Memorization Perspective

Lianghe Shi · Meng Wu · Huijie Zhang · Zekai Zhang · Molei Tao · Qing Qu

Latent Zoning Network: A Unified Principle for Generative Modeling, Representation Learning, and Classification

Zinan Lin · Enshu Liu · Xuefei Ning · Junyi Zhu · Wenyu Wang · Sergey Yekhanin

Traversal Verification for Speculative Tree Decoding

Yepeng Weng · Qiao Hu · Xujie Chen · Li Liu · Dianwen Mei · Huishi Qiu · Jiang Tian · zhongchao shi

Information-Theoretic Discrete Diffusion

Moongyu Jeon · Sangwoo Shin · Dongjae Jeon · Albert No

Router-R1: Teaching LLMs Multi-Round Routing and Aggregation via Reinforcement Learning

Haozhen Zhang · Tao Feng · Jiaxuan You

Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models

Luca Eyring · Shyamgopal Karthik · Alexey Dosovitskiy · Nataniel Ruiz · Zeynep Akata

Quantifying Elicitation of Latent Capabilities in Language Models

Elizabeth Donoway · Hailey Joren · Arushi Somani · Henry Sleight · Julian Michael · Michael Deweese · John Schulman · Ethan Perez · Fabien Roger · Jan Leike

Learning to Generate Human-Human-Object Interactions from Textual Descriptions

Jeonghyeon Na · Sangwon Baik · Inhee Lee · Junyoung Lee · Hanbyul Joo

From Bytes to Ideas: Language Modeling with Autoregressive U-Nets

Mathurin VIDEAU · Badr Youbi Idrissi · Alessandro Leite · Marc Schoenauer · Olivier Teytaud · David Lopez-Paz

Scaling Speculative Decoding with Lookahead Reasoning

Yichao Fu · Rui Ge · Zelei Shao · Zhijie Deng · Hao Zhang

Inv-Entropy: A Fully Probabilistic Framework for Uncertainty Quantification in Language Models

Haoyi Song · Ruihan Ji · Naichen Shi · Fan Lai · Raed AL Kontar

BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning

Xuechen Zhang · Zijian Huang · Yingcong Li · Chenshun Ni · Jiasi Chen · Samet Oymak

From Style to Facts: Mapping the Boundaries of Knowledge Injection with Finetuning

Eric Zhao · Pranjal Awasthi · Nika Haghtalab

SPACE: Noise Contrastive Estimation Stabilizes Self-Play Fine-Tuning for Large Language Models

Yibo Wang · Guangda Huzhang · Qingguo Chen · Zhao Xu · Weihua Luo · Kaifu Zhang · Lijun Zhang

When and how can inexact generative models still sample from the data manifold?

Nisha Chandramoorthy · Adriaan de Clercq

One-Step Offline Distillation of Diffusion-based Models via Koopman Modeling

Nimrod Berman · Ilan Naiman · Moshe Eliasof · Hedi Zisling · Omri Azencot

Improving the Euclidean Diffusion Generation of Manifold Data by Mitigating Score Function Singularity

Zichen Liu · Wei Zhang · Tiejun Li

Training-Free Constrained Generation With Stable Diffusion Models

Stefano Zampini · Jacob K Christopher · Luca Oneto · Davide Anguita · Ferdinando Fioretto

Continuous Diffusion Model for Language Modeling

Jaehyeong Jo · Sung Ju Hwang

CORAL: Disentangling Latent Representations in Long-Tailed Diffusion

Esther Rodriguez · Monica Welfert · Samuel McDowell · Nathan Stromberg · Julian Camarena · Lalitha Sankar

MESS+: Dynamically Learned Inference-Time LLM Routing in Model Zoos with Service Level Guarantees

Herbert Woisetschläger · Ryan Zhang · Shiqiang Wang · Hans Arno Jacobsen

Support Vector Generation: Kernelizing Large Language Models for Efficient Zero‑Shot NLP

Shohei Ohsawa

Disentangled Cross-Modal Representation Learning with Enhanced Mutual Supervision

Lu Gao · Wenlan Chen · Daoyuan Wang · Fei Guo · Cheng Liang

On the Edge of Memorization in Diffusion Models

Sam Buchanan · Druv Pai · Yi Ma · Valentin De Bortoli

Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation

Xinyu Yang · Yuwei An · Hongyi Liu · Tianqi Chen · Beidi Chen

InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion

Yuanyi Wang · Zhaoyi Yan · Yiming Zhang · Qi Zhou · Yanggan Gu · Fei Wu · Hongxia Yang

LaM-SLidE: Latent Space Modeling of Spatial Dynamical Systems via Linked Entities

Florian Sestak · Artur Toshev · Andreas Fürst · Günter Klambauer · Andreas Mayr · Johannes Brandstetter

Asymmetric Dual Self-Distillation for 3D Self-Supervised Representation Learning

Remco Leijenaar · Hamidreza Kasaei

ALTo: Adaptive-Length Tokenizer for Autoregressive Mask Generation

Lingfeng Wang · Hualing Lin · Senda Chen · Tao Wang · Changxu Cheng · Yangyang Zhong · Dong Zheng · Wuyue Zhao

Gemstones: A Model Suite for Multi-Faceted Scaling Laws

Sean McLeish · John Kirchenbauer · David Miller · Siddharth Singh · Abhinav Bhatele · Micah Goldblum · Ashwinee Panda · Tom Goldstein

Online Feedback Efficient Active Target Discovery in Partially Observable Environments

Anindya Sarkar · Binglin Ji · Yevgeniy Vorobeychik

Learnable Sampler Distillation for Discrete Diffusion Models

Feiyang Fu · Tongxian Guo · Zhaoqiang Liu

Training-Free Safe Text Embedding Guidance for Text-to-Image Diffusion Models

Byeonghu Na · Mina Kang · Jiseok Kwak · Minsang Park · Jiwoo Shin · SeJoon Jun · Gayoung Lee · Jin-Hwa Kim · Il-chul Moon

Neural Entropy

Akhil Premkumar

Weaver: Shrinking the Generation-Verification Gap by Scaling Compute for Verification

Jon Saad-Falcon · Estefany Kelly Buchanan · Mayee Chen · Tzu-Heng (Brian) Huang · Brendan McLaughlin · Tanvir Bhathal · Shang Zhu · Ben Athiwaratkun · Frederic Sala · Scott Linderman · Azalia Mirhoseini · Christopher Ré

TreeGen: A Bayesian Generative Model for Hierarchies

Marcel Kollovieh · Nils Fleischmann · Filippo Guerranti · Bertrand Charpentier · Stephan Günnemann

System-Embedded Diffusion Bridge Models

Bartlomiej Sobieski · Matthew Tivnan · Yuang Wang · Siyeop yoon · Pengfei Jin · Dufan Wu · Quanzheng Li · Przemyslaw Biecek

GPO: Learning from Critical Steps to Improve LLM Reasoning

Jiahao Yu · Zelei Cheng · Xian Wu · Xinyu Xing

Optimal Neural Compressors for the Rate-Distortion-Perception Tradeoff

Eric Lei · Hamed Hassani · Shirin Saeedi Bidokhti

Pairwise Optimal Transports for Training All-to-All Flow-Based Condition Transfer Model

Kotaro Ikeda · Masanori Koyama · Jinzhe Zhang · Kohei Hayashi · Kenji Fukumizu

Diffusion on Demand: Selective Caching and Modulation for Efficient Generation

Hee Min Choi · Hyoa Kang · Dokwan Oh · Nam Ik Cho

PID-controlled Langevin Dynamics for Faster Sampling on Generative Models

Hongyi Chen · Jianhai Shu · Jingtao Ding · Yong Li · Xiao-Ping (Steven) Zhang

Spectral Analysis of Diffusion Models with Application to Schedule Design

Roi Benita · Miki Elad · Joseph Keshet

NeedleInATable: Exploring Long-Context Capability of Large Language Models towards Long-Structured Tables

Lanrui Wang · Mingyu Zheng · Hongyin Tang · Zheng Lin · Yanan Cao · Jingang Wang · Xunliang Cai · Weiping Wang

RDB2G-Bench: A Comprehensive Benchmark for Automatic Graph Modeling of Relational Databases

Dongwon Choi · Sunwoo Kim · Juyeon Kim · Kyungho Kim · Geon Lee · Shinhwan Kang · Myunghwan Kim · Kijung Shin

GC4NC: A Benchmark Framework for Graph Condensation on Node Classification with New Insights

Shengbo Gong · Juntong Ni · Noveen Sachdeva · Carl Yang · Wei Jin

Random Search Neural Networks for Efficient and Expressive Graph Learning

Michael Ito · Danai Koutra · Jenna Wiens

Effects of Dropout on Performance in Long-range Graph Learning Tasks

Jasraj Singh · Keyue Jiang · Brooks Paige · Laura Toni

Conditional Diffusion Anomaly Modeling on Graphs

Chunyu Wei · Haozhe Lin · Yueguo Chen · Yunhai Wang

Preference-driven Knowledge Distillation for Few-shot Node Classification

Xing Wei · Chunchun Chen · Rui Fan · Xiaofeng Cao · Sourav Medya · Wei Ye

AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction

Niklas Freymuth · Tobias Würth · Nicolas Schreiber · Balázs Gyenes · Andreas Boltres · Johannes Mitsch · Aleksandar Taranovic · Tai Hoang · Philipp Dahlinger · Philipp Becker · Luise Kärger · Gerhard Neumann

GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks

Xingbo Fu · Zhenyu Lei · Zihan Chen · Binchi Zhang · Chuxu Zhang · Jundong Li

HubGT: Fast Graph Transformer with Decoupled Hierarchy Labeling

Ningyi Liao · Zihao Yu · Siqiang Luo · Gao Cong

GAMMA: Gated Multi-hop Message Passing for Homophily-Agnostic Node Representation in GNNs

Amir Ghazizadeh · Rickard Ewetz · Hao Zheng

Disentangling Hyperedges through the Lens of Category Theory

Yoonho Lee · Junseok Lee · Sangwoo Seo · Sungwon Kim · Yeongmin Kim · Chanyoung Park

Pseudo-Riemannian Graph Transformer

Viet Quan Le · Cuong Viet Ta

Where Graph Meets Heterogeneity: Multi-View Collaborative Graph Experts

Zhihao Wu · Jinyu Cai · Yunhe Zhang · Jielong Lu · Zhaoliang Chen · Shuman Zhuang · Haishuai Wang

Memorization in Graph Neural Networks

Adarsh Jamadandi · Jing Xu · Adam Dziedzic · Franziska Boenisch

Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs

Zhehao Li · Zhehao Li · Kangbo Lyu · Yixuan Li · Tao Du · Ligang Liu

Enhancing Graph Classification Robustness with Singular Pooling

Sofiane Ennadir · Oleg Smirnov · Yassine ABBAHADDOU · Lele Cao · Johannes Lutzeyer

Characterizing the Expressivity of Fixed-Precision Transformer Language Models

Jiaoda Li · Ryan Cotterell

Interpretable Global Minima of Deep ReLU Neural Networks on Sequentially Separable Data

Thomas Chen · Patricia Muñoz Ewald

RepGuard: Adaptive Feature Decoupling for Robust Backdoor Defense in Large Language Models

Chenxu Niu · Jie Zhang · Yanbing Liu · Yunpeng Li · Jinta Weng · Yue Hu

Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows

Adriel Sosa Marco · John D. Kirwan · Alexia Toumpa · Simos Gerasimou

Monitoring Risks in Test-Time Adaptation

Mona Schirmer · Metod Jazbec · Christian Andersson Naesseth · Eric Nalisnick

Fuz-RL: A Fuzzy-Guided Robust Framework for Safe Reinforcement Learning under Uncertainty

Xu Wan · Chao Yang · Cheng Yang · Jie Song · Mingyang Sun

Ditch the Denoiser: Emergence of Noise Robustness in Self-Supervised Learning from Data Curriculum

Wenquan Lu · Jiaqi Zhang · Hugues Van Assel · Randall Balestriero

Consensus-Robust Transfer Attacks via Parameter and Representation Perturbations

Shixin Li · Zewei Li · Xiaojing Ma · Xiaofan Bai · Pingyi Hu · Dongmei Zhang · Bin Zhu

MIBP-Cert: Certified Training against Data Perturbations with Mixed-Integer Bilinear Programs

Tobias Lorenz · Marta Kwiatkowska · Mario Fritz

Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning

Zhifang Zhang · Shuo He · Haobo Wang · Bingquan Shen · Lei Feng

Robust LLM Alignment via Distributionally Robust Direct Preference Optimization

Zaiyan Xu · Sushil Vemuri · Kishan Panaganti · Dileep Kalathil · Rahul Jain · Deepak Ramachandran

From Faults to Features: Pretraining to Learn Robust Representations against Sensor Failures

Jens U. Brandt · Noah Christoph Pütz · Marcus Greiff · Thomas Lew · John Subosits · Marc Hilbert · Thomas Bartz-Beielstein

Dynamical Low-Rank Compression of Neural Networks with Robustness under Adversarial Attacks

Steffen Schotthöfer · Lexie Yang · Stefan Schnake

Impact of Layer Norm on Memorization and Generalization in Transformers

Rishi Singhal · Jung-Eun Kim

TransferBench: Benchmarking Ensemble-based Black-box Transfer Attacks

Fabio Brau · Maura Pintor · Antonio Cinà · Raffaele Mura · Luca Scionis · Luca Oneto · Fabio Roli · Battista Biggio

Learning to Flow from Generative Pretext Tasks for Neural Architecture Encoding

Sunwoo Kim · Hyunjin Hwang · Kijung Shin

Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models

Li Sun · Zhenhao Huang · Ming Zhang · Philip S Yu

GD$^2$: Robust Graph Learning under Label Noise via Dual-View Prediction Discrepancy

Kailai Li · Jiong Lou · Jiawei Sun · Honghong Zeng · Wen Li · Chentao Wu · Yuan Luo · Wei Zhao · shouguo du · Jie LI

MaNGO — Adaptable Graph Network Simulators via Meta-Learning

Philipp Dahlinger · Tai Hoang · Denis Blessing · Niklas Freymuth · Gerhard Neumann

Rethinking Tokenized Graph Transformers for Node Classification

Jinsong Chen · Chenyang Li · Gaichao Li · John Hopcroft · Kun He

What Can RL Bring to VLA Generalization? An Empirical Study

Jijia Liu · Feng Gao · Bingwen Wei · Xinlei Chen · Qingmin Liao · YI WU · Chao Yu · Yu Wang

Unveiling Transformer Perception by Exploring Input Manifolds

Alessandro Benfenati · Alfio Ferrara · Alessio Marta · Davide Riva · Elisabetta Rocchetti

Neural Collapse is Globally Optimal in Deep Regularized ResNets and Transformers

Peter Súkeník · Christoph Lampert · Marco Mondelli

Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks

Chaoyue Liu · Han Bi · Like Hui · Xiao Liu

Stable Minima of ReLU Neural Networks Suffer from the Curse of Dimensionality: The Neural Shattering Phenomenon

Tongtong Liang · Dan Qiao · Yu-Xiang Wang · Rahul Parhi

Born a Transformer -- Always a Transformer? On the Effect of Pretraining on Architectural Abilities

Mayank Jobanputra · Yana Veitsman · Yash Sarrof · Aleksandra Bakalova · Vera Demberg · Ellie Pavlick · Michael Hahn

Contrastive Learning with Data Misalignment: Feature Purity, Training Dynamics and Theoretical Generalization Guarantees

Jiawei Sun · Shuai Zhang · Hongkang Li · Meng Wang

Agnostic Learning under Targeted Poisoning: Optimal Rates and the Role of Randomness

Bogdan Chornomaz · Yonatan Koren · Shay Moran · Tom Waknine

The Nuclear Route: Sharp Asymptotics of ERM in Overparameterized Quadratic Networks

Vittorio Erba · Emanuele Troiani · Lenka Zdeborová · Florent Krzakala

Identifiability of Deep Polynomial Neural Networks

Konstantin Usevich · Ricardo Borsoi · Clara Dérand · Marianne Clausel

Attention-based clustering

Rodrigo Maulen Soto · Pierre Marion · Claire Boyer

Intrinsic Benefits of Categorical Distributional Loss: Uncertainty-aware Regularized Exploration in Reinforcement Learning

Ke Sun · Yingnan Zhao · Enze Shi · Yafei Wang · Xiaodong Yan · Bei Jiang · Linglong Kong

Spectral Conditioning of Attention Improves Transformer Performance

Hemanth Saratchandran · Simon Lucey

Is Grokking a Computational Glass Relaxation?

Xiaotian Zhang · Yue Shang · Entao Yang · Ge Zhang

Partial Information Decomposition via Normalizing Flows in Latent Gaussian Distributions

Wenyuan Zhao · Adithya Balachandran · Chao Tian · Paul Liang

Depth-Bounds for Neural Networks via the Braid Arrangement

Moritz Grillo · Christoph Hertrich · Georg Loho

Continuity and Isolation Lead to Doubts or Dilemmas in Large Language Models

Hector Pasten · Felipe Urrutia · Hector Orellana · Cristian Buc Calderon · Cristobal Rojas · Alexander Kozachinskiy

Learning to Add, Multiply, and Execute Algorithmic Instructions Exactly with Neural Networks

Artur Back de Luca · George Giapitzakis · Kimon Fountoulakis

Emergence and scaling laws in SGD learning of shallow neural networks

Yunwei Ren · Eshaan Nichani · Denny Wu · Jason Lee

Flatness is Necessary, Neural Collapse is Not: Rethinking Generalization via Grokking

Ting Han · Linara Adilova · Henning Petzka · Jens Kleesiek · Michael Kamp

Compositional Reasoning with Transformers, RNNs, and Chain of Thought

Gilad Yehudai · Noah Amsel · Joan Bruna

Analyzing the Power of Chain of Thought through Memorization Capabilities

Lijia Yu · Xiao-Shan Gao · Lijun Zhang

Learnable Burst-Encodable Time-of-Flight Imaging for High-Fidelity Long-Distance Depth Sensing

Manchao Bao · Shengjiang Fang · Tao Yue · Xuemei Hu

Adaptive Context Length Optimization with Low-Frequency Truncation for Multi-Agent Reinforcement Learning

Wenchang Duan · Yaoliang Yu · Jiwan He · Yi Shi

HyperMARL: Adaptive Hypernetworks for Multi-Agent RL

Kale-ab Tessera · Muhammad Arrasy Rahman · Amos Storkey · Stefano Albrecht

Inner Speech as Behavior Guides: Steerable Imitation of Diverse Behaviors for Human-AI coordination

Rakshit Trivedi · Kartik Sharma · David Parkes

Scalable Neural Incentive Design with Parameterized Mean-Field Approximation

Nathan Corecco · Batuhan Yardim · Vinzenz Thoma · Zebang Shen · Niao He

Planning with Quantized Opponent Models

XiaoPeng Yu · Kefan Su · Zongqing Lu

ForceVLA: Enhancing VLA Models with a Force-aware MoE for Contact-rich Manipulation

Jiawen Yu · Hairuo Liu · Qiaojun Yu · Jieji Ren · Ce Hao · Haitong Ding · Guangyu Huang · Guofan Huang · Yan Song · Panpan Cai · Wenqiang Zhang · Cewu Lu

Spectral Learning for Infinite-Horizon Average-Reward POMDPs

Alessio Russo · Alberto Maria Metelli · Marcello Restelli

Learning Interactive World Model for Object-Centric Reinforcement Learning

Fan Feng · Phillip Lippe · Sara Magliacane

SEGA: Shaping Semantic Geometry for Robust Hashing under Noisy Supervision

Yiyang Gu · Bohan Wu · Qinghua Ran · Rong-Cheng Tu · Xiao Luo · Zhiping Xiao · Wei Ju · Dacheng Tao · Ming Zhang

HM3: Hierarchical Multi-Objective Model Merging for Pretrained Models

Yu Zhou · Xingyu Wu · Jibin Wu · Liang Feng · KC Tan

Cognitive Mirrors: Exploring the Diverse Functional Roles of Attention Heads in LLM Reasoning

Xueqi Ma · Jun Wang · Yanbei Jiang · Sarah Erfani · Tongliang Liu · James Bailey

Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens

Xixian Yong · Xiao Zhou · Yingying Zhang · Jinlin Li · Yefeng Zheng · Xian Wu

On the Loss of Context Awareness in General Instruction Fine-tuning

Yihan Wang · Andrew Bai · Nanyun Peng · Cho-Jui Hsieh

LLM Layers Immediately Correct Each Other

Arjun Patrawala · Jiahai Feng · Erik Jones · Jacob Steinhardt

Less is More: Improving LLM Alignment via Preference Data Selection

Xun Deng · Han Zhong · Rui Ai · Fuli Feng · Zheng Wang · Xiangnan He

RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models

Jiarui Zhang · Xiangyu Liu · Yong Hu · Chaoyue Niu · Fan Wu · Guihai Chen

RidgeLoRA: Matrix Ridge Enhanced Low-Rank Adaptation of Large Language Models

Junda Zhu · Jun Ai · Yujun Li · Yichun Yin · Yasheng Wang · Lifeng Shang · Qun Liu

The Leaderboard Illusion

Shivalika Singh · Yiyang Nan · Alex Wang · Daniel Dsouza · Sayash Kapoor · Ahmet Üstün · Sanmi Koyejo · Yuntian Deng · Shayne Longpre · Noah Smith · Beyza Ermis · Marzieh Fadaee · Sara Hooker

Robust Reinforcement Learning in Finance: Modeling Market Impact with Elliptic Uncertainty Sets

Shaocong Ma · Heng Huang

Linearization Explains Fine-Tuning in Large Language Models

Zahra Rahimi Afzal · Tara Esmaeilbeig · Mojtaba Soltanalian · Mesrob I Ohannessian

Alternating Gradient Flows: A Theory of Feature Learning in Two-layer Neural Networks

Daniel Kunin · Giovanni Luca Marchetti · Feng Chen · Dhruva Karkada · James Simon · Michael Deweese · Surya Ganguli · Nina Miolane

Progress Reward Model for Reinforcement Learning via Large Language Models

Xiuhui Zhang · Ning Gao · Xingyu Jiang · Yihui Chen · Yuheng Pan · Mohan Zhang · Yue Deng

Exploring Data Scaling Trends and Effects in Reinforcement Learning from Human Feedback

Wei Shen · Guanlin Liu · Yu Yue · Ruofei Zhu · Qingping Yang · Chao Xin · Lin Yan

Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems

Christian Walder · Deep Tejas Karkhanis

Reinforcement Learning with Action Chunking

Qiyang Li · Zhiyuan (Paul) Zhou · Sergey Levine

RF-Agent: Automated Reward Function Design via Language Agent Tree Search

Ning Gao · Xiuhui Zhang · Xingyu Jiang · Mukang You · Mohan Zhang · Yue Deng

Flat Channels to Infinity in Neural Loss Landscapes

Flavio Martinelli · Alexander van Meegen · Berfin Simsek · Wulfram Gerstner · Johanni Brea

FedRW: Efficient Privacy-Preserving Data Reweighting for Enhancing Federated Learning of Language Models

Pukang Ye · Luo Junwei · Jiachen Shen · Saipan Zhou · Shangmin Dou · Zhenfu Cao · Hanzhe Yao · Xiaolei Dong · Yunbo Yang

Distribution-Aware Tensor Decomposition for Compression of Convolutional Neural Networks

Alper KALLE · Théo Rudkiewicz · Mohamed Ouerfelli · Mohamed Tamaazousti

EventMG: Efficient Multilevel Mamba-Graph Learning for Spatiotemporal Event Representation

Sheng Wu · Lin Jin · Hui Feng · Bo Hu

Mamba Modulation: On the Length Generalization of Mamba Models

Peng Lu · Jerry Huang · QIUHAO Zeng · Xinyu Wang · Boxing Chen · Philippe Langlais · Yufei CUI

Aligning Text-to-Image Diffusion Models to Human Preference by Classification

Longquan Dai · Xiaolu Wei · wang he · Shaomeng Wang · Jinhui Tang

Small Singular Values Matter: A Random Matrix Analysis of Transformer Models

Max Staats · Matthias Thamm · Bernd Rosenow

GeoRanker: Distance-Aware Ranking for Worldwide Image Geolocalization

Pengyue Jia · Seongheon Park · Song Gao · Xiangyu Zhao · Sharon Li

LLM Safety Alignment is Divergence Estimation in Disguise

Rajdeep Haldar · Ziyi Wang · Guang Lin · Yue XING · Qifan Song

Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks

Hongyuan Tao · Ying Zhang · Zhenhao Tang · Hongen Peng · Xukun Zhu · Bingchang Liu · Yingguang Yang · Ziyin Zhang · Zhaogui Xu · Haipeng Zhang · Linchao Zhu · Rui Wang · Hang Yu · Jianguo Li · Peng Di

Recursive Inference Scaling: A Winning Path to Scalable Inference in Language and Multimodal Systems

Ibrahim Alabdulmohsin · Xiaohua Zhai

Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning

Lei Wang · Jieming Bian · Letian Zhang · Jie Xu

Reinforcement Learning Meets Masked Generative Models: Mask-GRPO for Text-to-Image Generation

Yifu Luo · Xinhao Hu · Keyu Fan · Haoyuan Sun · Zeyu Chen · Bo Xia · Tiantian Zhang · Yongzhe Chang · Xueqian Wang

EchoShot: Multi-Shot Portrait Video Generation

Jiahao Wang · Hualian Sheng · Sijia Cai · Weizhan Zhang · Caixia Yan · Yachuang Feng · Bing Deng · Jieping Ye

CoT-lized Diffusion: Let's Reinforce T2I Generation Step-by-step

Zheyuan Liu · Munan Ning · Qihui Zhang · Shuo Yang · Zhongrui Wang · Yiwei Yang · Xianzhe Xu · Yibing Song · Weihua Chen · Fan Wang · Li Yuan

OmniZoom: A Universal Plug-and-Play Paradigm for Cross-Device Smooth Zoom Interpolation

Xiaoan Zhu · Yue Zhao · Tianyang Hu · Jiaming Guo · Yulan Zeng · Renjing Pei · Fenglong Song · Huajun Feng

Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer

Zechuan Zhang · Ji Xie · Yu Lu · Zongxin Yang · Yi Yang

MJ-Video: Benchmarking and Rewarding Video Generation with Fine-Grained Video Preference

Haibo Tong · Zhaoyang Wang · Zhaorun Chen · Haonian Ji · Shi Qiu · Siwei Han · Kexin Geng · Zhongkai Xue · Yiyang Zhou · Peng Xia · Mingyu Ding · Rafael Rafailov · Chelsea Finn · Huaxiu Yao

Tortoise and Hare Guidance: Accelerating Diffusion Model Inference with Multirate Integration

Yunghee Lee · Byeonghyun Pak · Junwha Hong · Hoseong Kim

CamEdit: Continuous Camera Parameter Control for Photorealistic Image Editing

Xinran Qin · Zhixin Wang · Fan Li · Haoyu Chen · Renjing Pei · Wenbo Li · Xiaochun Cao

UniRelight: Learning Joint Decomposition and Synthesis for Video Relighting

Kai He · Ruofan Liang · Jacob Munkberg · Jon Hasselgren · Nandita Vijaykumar · Alexander Keller · Sanja Fidler · Igor Gilitschenski · Zan Gojcic · Zian Wang

VideoUFO: A Million-Scale User-Focused Dataset for Text-to-Video Generation

Wenhao Wang · Yi Yang

FineGRAIN: Evaluating Failure Modes of Text-to-Image Models with Vision Language Model Judges

Kevin Hayes · Micah Goldblum · Vikash Sehwag · Gowthami Somepalli · Ashwinee Panda · Tom Goldstein

vHector and HeisenVec: Scalable Vector Graphics Generation Through Large Language Models

Leonardo Zini · Elia Frigieri · Sebastiano Aloscari · Lorenzo Baraldi

OneIG-Bench: Omni-dimensional Nuanced Evaluation for Image Generation

Jingjing Chang · Yixiao Fang · Peng Xing · Shuhan Wu · Wei Cheng · Rui Wang · Xianfang Zeng · Gang Yu · Hai-Bao Chen

Sekai: A Video Dataset towards World Exploration

Zhen Li · Chuanhao Li · Xiaofeng Mao · Shaoheng Lin · Ming Li · Shitian Zhao · Zhaopan Xu · Xinyue Li · Yukang Feng · Jianwen Sun · Zizhen Li · Fanrui Zhang · Jiaxin Ai · Zhixiang Wang · Yuwei Wu · Tong He · Yunde Jia · Kaipeng Zhang

An Analysis of Concept Bottleneck Models: Measuring, Understanding, and Mitigating the Impact of Noisy Annotations

Seonghwan Park · Jueun Mun · Donghyun Oh · Namhoon Lee

Breaking the Compression Ceiling: Data-Free Pipeline for Ultra-Efficient Delta Compression

Xiaohui Wang · Peng Ye · Chenyu Huang · Shenghe Zheng · Bo Zhang · LEI BAI · Wanli Ouyang · Tao Chen

ConTextTab: A Semantics-Aware Tabular In-Context Learner

Marco Spinaci · Marek Polewczyk · Maximilian Schambach · Sam Thelin

SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models

Emil Biju · Shayan Talaei · Zhemin Huang · Mohammadreza Pourreza · Azalia Mirhoseini · Amin Saberi

REPA Works Until It Doesn’t: Early-Stopped, Holistic Alignment Supercharges Diffusion Training

Ziqiao Wang · Wangbo Zhao · Yuhao Zhou · Zekai Li · Zhiyuan Liang · Mingjia Shi · Xuanlei Zhao · Pengfei Zhou · Kaipeng Zhang · Zhangyang "Atlas" Wang · Kai Wang · Yang You

Think before Recommendation: Autonomous Reasoning-enhanced Recommender

Xiaoyu Kong · Junguang Jiang · Bin Liu · Ziru Xu · Han Zhu · Jian Xu · Bo Zheng · Jiancan Wu · Xiang Wang

Text to Sketch Generation with Multi-Styles

Tengjie Li · Shikui Tu · Lei Xu

FreqExit: Enabling Early-Exit Inference for Visual Autoregressive Models via Frequency-Aware Guidance

Ying Li · Chengfei Lyu · Huan Wang

REGen: Multimodal Retrieval-Embedded Generation for Long-to-Short Video Editing

Weihan Xu · Yimeng Ma · Jingyue Huang · Yang Li · Wenye Ma · Taylor Berg-Kirkpatrick · Julian McAuley · Paul Liang · Hao-Wen Dong

Improving Diffusion-based Inverse Algorithms under Few-Step Constraint via Linear Extrapolation

Jiawei Zhang · Ziyuan Liu · Leon Yan · Gen Li · Yuantao Gu

ViewPoint: Panoramic Video Generation with Pretrained Diffusion Models

Zixun Fang · Kai Zhu · Zhiheng Liu · Yu Liu · Wei Zhai · Yang Cao · Zheng-Jun Zha

Seg4Diff: Unveiling Open-Vocabulary Semantic Segmentation in Text-to-Image Diffusion Transformers

Chaehyun Kim · Heeseong Shin · Eunbeen Hong · Heeji Yoon · Anurag Arnab · Paul Hongsuck Seo · Sunghwan Hong · Seungryong Kim

Video World Models with Long-term Spatial Memory

Tong Wu · Shuai Yang · Ryan Po · Yinghao Xu · Ziwei Liu · Dahua Lin · Gordon Wetzstein

Stable Part Diffusion 4D: Multi-View RGB and Kinematic Parts Video Generation

Hao Zhang · Chun-Han Yao · Simon Donné · Narendra Ahuja · Varun Jampani

DCI: Dual-Conditional Inversion for Boosting Diffusion-Based Image Editing

Zixiang Li · Haoyu Wang · Wei Wang · Chuangchuang Tan · Yunchao Wei · Yao Zhao

DNAEdit: Direct Noise Alignment for Text-Guided Rectified Flow Editing

Chenxi Xie · Minghan Li · Shuai Li · Yuhui Wu · Qiaosi Yi · Lei Zhang

RepLDM: Reprogramming Pretrained Latent Diffusion Models for High-Quality, High-Efficiency, High-Resolution Image Generation

Boyuan Cao · Jiaxin Ye · Yujie Wei · Hongming Shan

When Are Concepts Erased From Diffusion Models?

Kevin Lu · Nicky Kriplani · Rohit Gandikota · Minh Pham · David Bau · Chinmay Hegde · Niv Cohen

StateSpaceDiffuser: Bringing Long Context to Diffusion World Models

Nedko Savov · Naser Kazemi · Deheng Zhang · Danda Pani Paudel · Xi Wang · Luc V Gool

PixPerfect: Seamless Latent Diffusion Local Editing with Discriminative Pixel-Space Refinement

Haitian Zheng · Yuan Yao · yongsheng yu · Yuqian Zhou · Jiebo Luo · Zhe Lin

Boosting Generative Image Modeling via Joint Image-Feature Synthesis

Theodoros Kouzelis · Efstathios Karypidis · Ioannis Kakogeorgiou · Spyridon Gidaris · Nikos Komodakis

OmniVCus: Feedforward Subject-driven Video Customization with Multimodal Control Conditions

Yuanhao Cai · HE Zhang · Xi Chen · Jinbo Xing · Yiwei Hu · Yuqian Zhou · Kai Zhang · Zhifei Zhang · Soo Ye Kim · Tianyu Wang · Yulun Zhang · Xiaokang Yang · Zhe Lin · Alan Yuille

Accelerating Parallel Diffusion Model Serving with Residual Compression

Jiajun Luo · Yicheng Xiao · Jianru Xu · Yangxiu You · Rongwei Lu · Chen Tang · Jingyan Jiang · Zhi Wang

Image Stitching in Adverse Condition: A Bidirectional-Consistency Learning Framework and Benchmark

Zengxi Zhang · Junchen Ge · Zhiying Jiang · Miao Zhang · Jinyuan Liu

GenColor: Generative and Expressive Color Enhancement with Pixel-Perfect Texture Preservation

Yi Dong · Yuxi Wang · Xianhui Lin · Wenqi Ouyang · Zhiqi Shen · Peiran Ren · Ruoxi Fan · Rynson Lau

InstanceAssemble: Layout-Aware Image Generation via Instance Assembling Attention

Qiang Xiang · Shuang Sun · Binglei Li · Dejia Song · Huaxia Li · Yibo Chen · Xu Tang · Yao Hu · Junping Zhang

Quantifying and Alleviating Co-Adaptation in Sparse-View 3D Gaussian Splatting

Kangjie Chen · Yingji Zhong · Zhihao Li · Jiaqi Lin · Youyu Chen · Minghan Qin · Haoqian Wang

Multimodal LiDAR-Camera Novel View Synthesis with Unified Pose-free Neural Fields

Weiyi Xue · Fan Lu · Yunwei Zhu · Zehan Zheng · Haiyun Wei · Sanqing Qu · Jiangtong Li · Ya Wu · Guang Chen

AtlasGS: Atlanta-world Guided Surface Reconstruction with Implicit Structured Gaussians

Xiyu Zhang · Chong Bao · YiPeng Chen · Hongjia Zhai · Yitong Dong · Hujun Bao · Zhaopeng Cui · Guofeng Zhang

Flux4D: Flow-based Unsupervised 4D Reconstruction

Jingkang Wang · Henry Che · Yun Chen · Ze Yang · Lily Goli · Sivabalan Manivasagam · Raquel Urtasun

Fused View-Time Attention and Feedforward Reconstruction for 4D Scene Generation

Chaoyang Wang · Ashkan Mirzaei · Vidit Goel · Willi Menapace · Aliaksandr Siarohin · Michael Vasilkovsky · Ivan Skorokhodov · Vladislav Shakhrai · Sergei Korolev · Sergey Tulyakov · Peter Wonka

Metropolis-Hastings Sampling for 3D Gaussian Reconstruction

Hyunjin Kim · Haebeom Jung · Jaesik Park

IBGS: Image-Based Gaussian Splatting

Hoang Chuong Nguyen · Wei Mao · Jose M. Alvarez · Miaomiao Liu

Cue3D: Quantifying the Role of Image Cues in Single-Image 3D Generation

Xiang Li · Zirui Wang · Zixuan Huang · James Rehg

Complete Structure Guided Point Cloud Completion via Cluster- and Instance-Level Contrastive Learning

Yang Chen · Yirun Zhou · Weizhong Zhang · Cheng Jin

LiteReality: Graphic-Ready 3D Scene Reconstruction from RGB-D Scans

Zhening Huang · Xiaoyang Wu · Fangcheng Zhong · Hengshuang Zhao · Matthias Niessner · Joan Lasenby

SurfelSplat: Learning Efficient and Generalizable Gaussian Surfel Representations for Sparse-View Surface Reconstruction

Chensheng Dai · Shengjun Zhang · Min Chen · Yueqi Duan

PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers

Yuchen Lin · Chenguo Lin · Panwang Pan · Honglei Yan · Feng Yiqiang · Yadong Mu · Katerina Fragkiadaki

InFlux: A Benchmark for Self-Calibration of Dynamic Intrinsics of Video Cameras

Erich Liang · Roma Bhattacharjee · Sreemanti Dey · Rafael Moschopoulos · Caitlin Wang · Michel Liao · Grace Tan · Andrew Wang · Karhan Kayan · Stamatis Alexandropoulos · Jia Deng

Depth-Supervised Fusion Network for Seamless-Free Image Stitching

Zhiying Jiang · Ruhao Yan · Zengxi Zhang · Bowei Zhang · Jinyuan Liu

VETA-DiT: Variance-Equalized and Temporally Adaptive Quantization for Efficient 4-bit Diffusion Transformers

Qinkai XU · yijin liu · YangChen · Lin Yang · Li Li · Yuxiang Fu

Policy Optimized Text-to-Image Pipeline Design

Uri Gadot · Rinon Gal · Yftah Ziser · Gal Chechik · Shie Mannor

Role Bias in Diffusion Models: Diagnosing and Mitigating through Intermediate Decomposition

Sina Malakouti · Adriana Kovashka

LightFair: Towards an Efficient Alternative for Fair T2I Diffusion via Debiasing Pre-trained Text Encoders

Boyu Han · Qianqian Xu · Shilong Bao · Zhiyong Yang · Kangli Zi · Qingming Huang

EditInfinity: Image Editing with Binary-Quantized Generative Models

Jiahuan Wang · Yuxin Chen · Jun Yu · Guangming Lu · Wenjie Pei

PolyJuice Makes It Real: Black-Box, Universal Red Teaming for Synthetic Image Detectors

Sepehr Dehdashtian · Mashrur Mahmud Morshed · Jacob Seidman · Gaurav Bharaj · Vishnu Boddeti

Instant4D: 4D Gaussian Splatting in Minutes

Zhanpeng Luo · Haoxi Ran · Li Lu

Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates

Seunghyeok Shin · Dabin Kim · Hongki Lim

LODGE: Level-of-Detail Large-Scale Gaussian Splatting with Efficient Rendering

Jonas Kulhanek · Marie-Julie Rakotosaona · Fabian Manhardt · Christina Tsalicoglou · Michael Niemeyer · Torsten Sattler · Songyou Peng · Federico Tombari

Pose Splatter: A 3D Gaussian Splatting Model for Quantifying Animal Pose and Appearance

Jack Goffinet · Youngjo Min · Carlo Tomasi · David Carlson

MV-CoLight: Efficient Object Compositing with Consistent Lighting and Shadow Generation

Kerui Ren · Jiayang Bai · Linning Xu · Lihan Jiang · Jiangmiao Pang · Mulin Yu · Bo Dai

WildCAT3D: Appearance-Aware Multi-View Diffusion in the Wild

Morris Alper · David Novotny · Filippos Kokkinos · Hadar Averbuch-Elor · Tom Monnier

PyraMotion: Attentional Pyramid-Structured Motion Integration for Co-Speech 3D Gesture Synthesis

Zhizhuo Yin · Yuk Hang Tsui · Pan Hui

Visual Sync: Multi‑Camera Synchronization via Cross‑View Object Motion

Shaowei Liu · David Yao · Saurabh Gupta · Shenlong Wang

Test3R: Learning to Reconstruct 3D at Test Time

Yuheng Yuan · Qiuhong Shen · Shizun Wang · Xingyi Yang · Xinchao Wang

Restage4D: Reanimating Deformable 3D Reconstruction from a Single Video

Jixuan He · Chieh Lin · Lu Qi · Ming-Hsuan Yang

Non-Line-of-Sight 3D Reconstruction with Radar

Haowen Lai · Zitong Lan · Mingmin Zhao

Repurposing Marigold for Zero-Shot Metric Depth Estimation via Defocus Blur Cues

Chinmay Talegaonkar · Nikhil Gandudi Suresh · Zachary Novack · Yash Belhe · Priyanka Nagasamudra · Nicholas Antipa

Towards Dynamic 3D Reconstruction of Hand-Instrument Interaction in Ophthalmic Surgery

Ming Hu · Zhengdi Yu · feilong tang · Kaiwen Chen · Yulong Li · Imran Razzak · Junjun He · Tolga Birdal · Kai-Jing Zhou · Zongyuan Ge

Deep Gaussian from Motion: Exploring 3D Geometric Foundation Models for Gaussian Splatting

Yu Chen · Rolandos Alexandros Potamias · Evangelos Ververas · Jifei Song · Jiankang Deng · Gim Hee Lee

Wukong's 72 Transformations: High-fidelity Textured 3D Morphing via Flow Models

Minghao Yin · Yukang Cao · Kai Han

DAVE: Diagnostic benchmark for Audio Visual Evaluation

Gorjan Radevski · Teodora Popordanoska · Matthew Blaschko · Tinne Tuytelaars

MMPB: It’s Time for Multi-Modal Personalization

Jaeik Kim · Woojin Kim · Woohyeon Park · Jaeyoung Do

From Play to Replay: Composed Video Retrieval for Temporally Fine-Grained Videos

Animesh Gupta · Jay Parmar · Ishan Rajendrakumar Dave · Mubarak Shah

ConViS-Bench: Estimating Video Similarity Through Semantic Concepts

Benedetta Liberatori · Alessandro Conti · Lorenzo Vaquero · Yiming Wang · Elisa Ricci · Paolo Rota

Toward a Vision-Language Foundation Model for Medical Data: Multimodal Dataset and Benchmarks for Vietnamese PET/CT Report Generation

Tien Nguyen · Dac Nguyen · Duc Nguyen The Minh · Trung Thanh Nguyen · Truong Thao Nguyen · Hieu Pham · Johan Barthelemy · Tran Minh Quan · Quoc Viet Hung Nguyen · Thanh Tam Nguyen · Mai Son · Chau Anh · Thanh Nguyen · Phi Le Nguyen

More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models

Zhongxing Xu · Chengzhi Liu · Qingyue Wei · Juncheng Wu · James Zou · Xin Wang · Yuyin Zhou · Sheng Liu

Unveiling the Compositional Ability Gap in Vision-Language Reasoning Model

Tianle Li · Jihai Zhang · Yongming Rao · Yu Cheng

With Limited Data for Multimodal Alignment, Let the STRUCTURE Guide You

Fabian Gröger · Shuo Wen · Huyen Le · Maria Brbic

When One Moment Isn't Enough: Multi-Moment Retrieval with Cross-Moment Interactions

Zhuo Cao · Heming Du · Bingqing Zhang · Xin Yu · Xue Li · Sen Wang

Multimodal Causal Reasoning for UAV Object Detection

Nianxin Li · Mao Ye · Lihua Zhou · Shuaifeng Li · Song Tang · Luping Ji · Ce Zhu

Unleashing the Potential of Multimodal LLMs for Zero-Shot Spatio-Temporal Video Grounding

Zaiquan Yang · Yuhao LIU · Gerhard Hancke · Rynson Lau

MemEIC: A Step Toward Continual and Compositional Knowledge Editing

Jin Seong · Jiyun Park · Wencke Liermann · Hongseok Choi · Yoonji Nam · Hyun Kim · Soojong Lim · Namhoon Lee

Elevating Visual Perception in Multimodal LLMs with Visual Embedding Distillation

Jitesh Jain · Zhengyuan Yang · Humphrey Shi · Jianfeng Gao · Jianwei Yang

CoFFT: Chain of Foresight-Focus Thought for Visual Language Models

Xinyu Zhang · Yuxuan Dong · Lingling Zhang · Chengyou Jia · Zhuohang Dang · Basura Fernando · Jun Liu · Mike Zheng Shou

A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1

Zhaoyi Li · Xiaohan Zhao · Dong-Dong Wu · Jiacheng Cui · Zhiqiang Shen

Pancakes: Consistent Multi-Protocol Image Segmentation Across Biomedical Domains

Marianne Rakic · Siyu Gai · Etienne Chollet · John Guttag · Adrian Dalca

VaMP: Variational Multi-Modal Prompt Learning for Vision-Language Models

Silin Cheng · Kai Han

VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction

Chaoyou Fu · Haojia Lin · Xiong Wang · yifan zhang · Yunhang Shen · Xiaoyu Liu · Haoyu Cao · Zuwei Long · Heting Gao · Ke Li · Long MA · Xiawu Zheng · Rongrong Ji · Xing Sun · Caifeng Shan · Ran He

SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation

Zekun Qi · Wenyao Zhang · Yufei Ding · Runpei Dong · XinQiang Yu · Jingwen Li · Lingyun Xu · Baoyu Li · Xialin He · Guofan Fan · Jiazhao Zhang · Jiawei He · Jiayuan Gu · Xin Jin · Kaisheng Ma · Zhizheng Zhang · He Wang · Li Yi

MMOT: The First Challenging Benchmark for Drone-based Multispectral Multi-Object Tracking

Tianhao Li · Tingfa Xu · Ying Wang · Haolin Qin · Xu Lin · Jianan Li

DisasterM3: A Remote Sensing Vision-Language Dataset for Disaster Damage Assessment and Response

Junjue Wang · Weihao Xuan · Heli Qi · Zhihao Liu · Kunyi Liu · Yuhan Wu · Hongruixuan Chen · JIAN SONG · Junshi Xia · Zhuo Zheng · Naoto YOKOYA

ColorBench: Can VLMs See and Understand the Colorful World? A Comprehensive Benchmark for Color Perception, Reasoning, and Robustness

Yijun Liang · Ming Li · Chenrui Fan · Ziyue Li · Dang Nguyen · Kwesi Cobbina · Shweta Bhardwaj · Jiuhai Chen · Fuxiao Liu · Tianyi Zhou

Towards Understanding Camera Motions in Any Video

Zhiqiu Lin · Siyuan Cen · Daniel Jiang · Jay Karhade · Hewei Wang · Chancharik Mitra · Yu Tong Tiffany Ling · Yuhan Huang · Rushikesh Zawar · Xue Bai · Yilun Du · Chuang Gan · Deva Ramanan

MVU-Eval: Towards Multi-Video Understanding Evaluation for Multimodal LLMs

Tianhao Peng · Haochen Wang · Yuanxing Zhang · Noah Wang · Zili Wang · Ge Zhang · Jian Yang · Shihao Li · Yanghai Wang · Xintao Wang · Houyi Li · Wei Ji · Pengfei Wan · Wenhao Huang · ZHAO-XIANG ZHANG · Jiaheng Liu

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?

Yuqian Yuan · Ronghao Dang · long li · Wentong Li · Dian Jiao · Xin Li · Deli Zhao · Fan Wang · Wenqiao Zhang · Jun Xiao · Yueting Zhuang

MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO

Yicheng Xiao · Lin Song · Yukang Chen · Yingmin Luo · Yuxin Chen · Yukang Gan · Wei Huang · Xiu Li · Xiaojuan Qi · Ying Shan

Decoupling Contrastive Decoding: Robust Hallucination Mitigation in Multimodal Large Language Models

Wei Chen · Xin Yan · Bin Wen · Fan Yang · Tingting Gao · Di ZHANG · Long Chen

SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement

Xiyao Wang · Zhengyuan Yang · Chao Feng · Hongjin Lu · Linjie Li · Chung-Ching Lin · Kevin Lin · Furong Huang · Lijuan Wang

SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models

Pingyi Chen · Yujing Lou · Shen Cao · Jinhui Guo · Lubin Fan · Yue Wu · Lin Yang · Lizhuang Ma · Jieping Ye

VisionThink: Smart and Efficient Vision Language Model via Reinforcement Learning

Senqiao Yang · Junyi Li · Xin Lai · Jinming Wu · Wei Li · Zejun MA · Bei Yu · Hengshuang Zhao · Jiaya Jia

GUIDED: Granular Understanding via Identification, Detection, and Discrimination for Fine-Grained Open-Vocabulary Object Detection

Jiaming Li · Zhijia Liang · Weikai Chen · Lin Ma · Guanbin Li

QuARI: Query Adaptive Retrieval Improvement

Eric Xing · Abby Stylianou · Robert Pless · Nathan Jacobs

Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence

Diankun Wu · Fangfu Liu · Yi-Hsin Hung · Yueqi Duan

Efficient Rectified Flow for Image Fusion

Zirui Wang · Jiayi Zhang · Tianwei Guan · Yuhan Zhou · Xingyuan Li · Minjing Dong · Jinyuan Liu

Towards General Continuous Memory for Vision-Language Models

Wenyi WU · Zixuan Song · Kun Zhou · Yifei Shao · Zhiting Hu · Biwei Huang

Few-Shot Learning from Gigapixel Images via Hierarchical Vision-Language Alignment and Modeling

Bryan Wong · Jongwoo Kim · Huazhu Fu · Mun Yi

ControlFusion: A Controllable Image Fusion Network with Language-Vision Degradation Prompts

Linfeng Tang · Yeda Wang · Zhanchuan Cai · Junjun Jiang · Jiayi Ma

One-Step Diffusion for Detail-Rich and Temporally Consistent Video Super-Resolution

Yujing Sun · Lingchen Sun · Shuaizheng Liu · Rongyuan Wu · Zhengqiang ZHANG · Lei Zhang

Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models

zhentao he · Can Zhang · Ziheng Wu · Zhenghao Chen · Yufei Zhan · Yifan Li · Zhao Zhang · Xian Wang · Minghui Qiu

SAMA: Towards Multi-Turn Referential Grounded Video Chat with Large Language Models

Ye Sun · Hao Zhang · Henghui Ding · Tiehua Zhang · Xingjun Ma · Yu-Gang Jiang

UniTok: a Unified Tokenizer for Visual Generation and Understanding

Chuofan Ma · Yi Jiang · Junfeng Wu · Jihan Yang · Xin Yu · Zehuan Yuan · BINGYUE PENG · Xiaojuan Qi

FlowFeat: Pixel-Dense Embedding of Motion Profiles

Nikita Araslanov · Anna Sonnweber · Daniel Cremers

InfiniPot-V: Memory-Constrained KV Cache Compression for Streaming Video Understanding

Minsoo Kim · Kyuhong Shim · Jungwook Choi · Simyung Chang

On Epistemic Uncertainty of Visual Tokens for Object Hallucinations in Large Vision-Language Models

Hoigi Seo · Dong Un Kang · Hyunjin Cho · Joohoon Lee · Se Young Chun

R1-ShareVL: Incentivizing Reasoning Capabilities of Multimodal Large Language Models via Share-GRPO

Huanjin Yao · Qixiang Yin · Jingyi Zhang · Min Yang · Yibo Wang · Wenhao Wu · Fei Su · Li Shen · Minghui Qiu · Dacheng Tao · Jiaxing Huang

Point or Line? Using Line-based Representation for Panoptic Symbol Spotting in CAD Drawings

Xingguang Wei · Haomin Wang · Shenglong Ye · Ruifeng Luo · Zhang · Lixin Gu · Jifeng Dai · Yu Qiao · Wenhai Wang · Hongjie Zhang

Novel Class Discovery for Point Cloud Segmentation via Joint Learning of Causal Representation and Reasoning

Yang Li · Aming WU · Zihao Zhang · Yahong Han

Seg-VAR:Image Segmentation with Visual Autoregressive Modeling

Rongkun Zheng · Lu Qi · Xi Chen · Yi Wang · Kun Wang · Hengshuang Zhao

OmniSegmentor: A Flexible Multi-Modal Learning Framework for Semantic Segmentation

Bo-Wen Yin · Jiao-Long Cao · Xuying Zhang · Yuming Chen · Ming-Ming Cheng · Qibin Hou

UniMRSeg: Unified Modality-Relax Segmentation via Hierarchical Self-Supervised Compensation

Xiaoqi Zhao · Youwei Pang · Chenyang Yu · Lihe Zhang · Huchuan Lu · Shijian Lu · Georges Fakhri · Xiaofeng Liu

UFO: A Unified Approach to Fine-grained Visual Perception via Open-ended Language Interface

Hao Tang · Chen-Wei Xie · Haiyang Wang · Xiaoyi Bao · Tingyu Weng · Pandeng Li · Yun Zheng · Liwei Wang

OpenHype: Hyperbolic Embeddings for Hierarchical Open-Vocabulary Radiance Fields

Lisa Weijler · Sebastian Koch · Fabio Poiesi · Timo Ropinski · Pedro Hermosilla

Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning

Junhao Shen · Haiteng Zhao · Yuzhe Gu · Songyang Gao · Kuikun Liu · Haian Huang · Jianfei Gao · Dahua Lin · Wenwei Zhang · Kai Chen

Hierarchical Semantic-Augmented Navigation: Optimal Transport and Graph-Driven Reasoning for Vision-Language Navigation

Xiang Fang · Wanlong Fang · Changshuo Wang

PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding

Ansel Blume · Jeonghwan Kim · Hyeonjeong Ha · Elen Chatikyan · Xiaomeng Jin · Khanh Nguyen · Nanyun Peng · Kai-Wei Chang · Derek Hoiem · Heng Ji

When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding

Yan Shu · Hangui Lin · Yexin Liu · Yan Zhang · Gangyan Zeng · Yan Li · Yu Zhou · Ser Nam Lim · Harry Yang · Nicu Sebe

VidEmo: Affective-Tree Reasoning for Emotion-Centric Video Foundation Models

Zhicheng Zhang · Weicheng Wang · Yongjie Zhu · Wenyu Qin · Pengfei Wan · Di ZHANG · Jufeng Yang

SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent

Yandan Yang · Baoxiong Jia · Shujie Zhang · Siyuan Huang

MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning

Xinyan Chen · Renrui Zhang · Dongzhi JIANG · Aojun Zhou · Shilin Yan · Weifeng Lin · Hongsheng Li

Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior

Yulin Li · Haokun GUI · Ziyang Fan · Junjie Wang · Bin Kang · BIN CHEN · Zhuotao Tian

Poison as Cure: Visual Noise for Mitigating Object Hallucinations in LVMs

Kejia Zhang · Keda TAO · Jiasheng Tang · Huan Wang

Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

Weifeng Lin · Xinyu Wei · Ruichuan An · Tianhe Ren · Tingwei Chen · Renrui Zhang · Ziyu Guo · Wentao Zhang · Lei Zhang · Hongsheng Li

Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search

Huanjin Yao · Jiaxing Huang · Wenhao Wu · Jingyi Zhang · Yibo Wang · Shunyu Liu · Yingjie Wang · YuXin Song · Haocheng Feng · Li Shen · Dacheng Tao

Find your Needle: Small Object Image Retrieval via Multi-Object Attention Optimization

Michael Green · Matan Levy · Issar Tzachor · Dvir Samuel · Nir Darshan · Rami Ben-Ari

Watch and Listen: Understanding Audio-Visual-Speech Moments with Multimodal LLM

Zinuo Li · Xian Zhang · Yongxin Guo · Mohammed Bennamoun · Farid Boussaid · Girish Dwivedi · Luqi Gong · Qiuhong Ke

Statistical Analysis of an Adversarial Bayesian Weak Supervision Method

Steven An

Stratify or Die: Rethinking Data Splits in Image Segmentation

Naga Venkata Sai Jitin Jami · Thomas Altstidl · Jonas Mueller · Jindong Li · Dario Zanca · Bjoern Eskofier · Heike Leutheuser

ARGenSeg: Image Segmentation with Autoregressive Image Generation Model

Xiaolong Wang · Lixiang Ru · Ziyuan Huang · Kaixiang Ji · DanDan Zheng · Jingdong Chen · Jun Zhou

Segment Anything Model Meets Semi-supervised Medical Image Segmentation: A Novel Perspective

Haifeng Zhao · Haiyang Li · Lei-Lei Ma · Dengdi Sun

Robust Egocentric Referring Video Object Segmentation via Dual-Modal Causal Intervention

Haijing Liu · Zhiyuan Song · Hefeng Wu · Tao Pu · Keze Wang · Liang Lin

OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection

Zhongyu Xia · Jishuo Li · Zhiwei Lin · Xinhao Wang · Yongtao Wang · Ming-Hsuan Yang

MomentSeeker: A Task-Oriented Benchmark For Long-Video Moment Retrieval

Huaying Yuan · Jian Ni · Zheng Liu · Yueze Wang · Junjie Zhou · Zhengyang Liang · Bo Zhao · Zhao Cao · Ji-Rong Wen · Zhicheng Dou

ReinAD: Towards Real-world Industrial Anomaly Detection with a Comprehensive Contrastive Dataset

Xu Wang · Jingyuan Zhuo · Zhiyuan You · Zhiyu Tan · Yikuan Yu · Siyu Wang · Xinyi Le

SGAR: Structural Generative Augmentation for 3D Human Motion Retrieval

Jiahang Zhang · Lilang Lin · Shuai Yang · Jiaying Liu

Beyond the Seen: Bounded Distribution Estimation for Open-Vocabulary Learning

Xiaomeng Fan · Yuchuan Mao · Zhi Gao · Yuwei Wu · Jin Chen · Yunde Jia

Towards Single-Source Domain Generalized Object Detection via Causal Visual Prompts

Chen Li · Huiying Xu · Changxin Gao · Zeyu Wang · Yun Liu · Xinzhong Zhu

Collaborative and Confidential Junction Trees for Hybrid Bayesian Networks

Roberto Gheda · Abele Mălan · Thiago Guzella · Carlo Lancia · Robert Birke · Lydia Chen

DAMamba: Vision State Space Model with Dynamic Adaptive Scan

Tanzhe Li · Caoshuo Li · Jiayi Lyu · Hongjuan Pei · Baochang Zhang · Taisong Jin · Rongrong Ji

Learning Dense Hand Contact Estimation from Imbalanced Data

Daniel Jung · Kyoung Mu Lee

VT-FSL: Bridging Vision and Text with LLMs for Few-Shot Learning

Wenhao Li · Qiangchang Wang · Xianjing Meng · Zhibin Wu · Yilong Yin

TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning

Xudong Yan · Songhe Feng

What We Miss Matters: Learning from the Overlooked in Point Cloud Transformers

Yi Wang · Jiaze Wang · Ziyu Guo · Renrui Zhang · Donghao Zhou · Guangyong Chen · Anfeng Liu · Pheng-Ann Heng

ImageNet-trained CNNs are not biased towards texture: Revisiting feature reliance through controlled suppression

Tom Burgert · Oliver Stoll · Paolo Rota · Begum Demir

Prompt-guided Disentangled Representation for Action Recognition

tianci wu · Guangming Zhu · Lu jiang · Siyuan Wang · Ning Wang · Nuoye Xiong · Liang Zhang

SPAZER: Spatial-Semantic Progressive Reasoning Agent for Zero-shot 3D Visual Grounding

Zhao Jin · Rong-Cheng Tu · Jingyi Liao · Wenhao Sun · Xiao Luo · Shunyu Liu · Dacheng Tao

PANDA: Towards Generalist Video Anomaly Detection via Agentic AI Engineer

Zhiwei Yang · Chen Gao · Mike Zheng Shou

Learning Skill-Attributes for Transferable Assessment in Video

Kumar Ashutosh · Kristen Grauman

Geometry-Aware Collaborative Multi-Solutions Optimizer for Model Fine-Tuning with Parameter Efficiency

Van-Anh Nguyen · Trung Le · Mehrtash Harandi · Ehsan Abbasnejad · Thanh-Toan Do · Dinh Phung

Epistemic Uncertainty Estimation in Regression Ensemble Models with Pairwise Epistemic Estimators

Lucas Berry · David Meger

Multilevel neural simulation-based inference

Yuga Hikida · Ayush Bharti · Niall Jeffrey · Francois-Xavier Briol

Distance-informed Neural Processes

Aishwarya Venkataramanan · Joachim Denzler

Temporal-Difference Variational Continual Learning

Luckeciano Carvalho Melo · Alessandro Abate · Yarin Gal

Optimal Adjustment Sets for Nonparametric Estimation of Weighted Controlled Direct Effect

Ruiyang Lin · Yongyi Guo · Kyra Gan

Synthetic-powered predictive inference

Meshi Bashari · Roy Maor Lotan · Yonghoon Lee · Edgar Dobriban · Yaniv Romano

Effortless, Simulation-Efficient Bayesian Inference using Tabular Foundation Models

Julius Vetter · Manuel Gloeckler · Daniel Gedon · Jakob H Macke

Solving and Learning Partial Differential Equations with Variational Q-Exponential Processes

Guangting Yu · Shiwei Lan

GOATex: Geometry & Occlusion-Aware Texturing

Hyunjin Kim · Kunho Kim · Adam Lee · Wonkwang Lee

One-Step Diffusion-Based Image Compression with Semantic Distillation

Naifu Xue · Zhaoyang Jia · Jiahao Li · Bin Li · Yuan Zhang · Yan Lu

HAODiff: Human-Aware One-Step Diffusion via Dual-Prompt Guidance

JUE GONG · Tingyu Yang · Jingkai Wang · Zheng Chen · Xing Liu · Hong Gu · Yulun Zhang · Xiaokang Yang

Zero-Shot Blind-Spot Image Denoising via Cross-Scale Non-Local Pixel Refilling

Qilong Guo · Tianjing Zhang · Zhiyuan Ma · Hui Ji

Can NeRFs "See" without Cameras?

Chaitanya Amballa · Yu-Lin Wei · Sattwik Basu · Zhijian Yang · Mehmet Ergezer · Romit Roy Choudhury

DON’T NEED RETRAINING: A Mixture of DETR and Vision Foundation Models for Cross-Domain Few-Shot Object Detection

Changhan Liu · xunzhi xiang · Zixuan Duan · Wenbin Li · Qi Fan · Yang Gao

Looking Into the Water by Unsupervised Learning of the Surface Shape

Ori Lifschitz · Tali Treibitz · Dan Rosenbaum

Autoregressive Motion Generation with Gaussian Mixture-Guided Latent Sampling

Linnan Tu · Lingwei Meng · Zongyi Li · Hefei Ling · Shijuan Huang

Toward Real-world Text Image Forgery Localization: Structured and Interpretable Data Synthesis

Zeqin Yu · Haotao Xie · Jian Zhang · Jiangqun Ni · Wenkang Su · Jiwu Huang

Language Model Behavioral Phases are Consistent Across Architecture, Training Data, and Scale

James Michaelov · Roger Levy · Benjamin Bergen

Constrained Feedback Learning for Non-Stationary Multi-Armed Bandits

Shaoang Li · Jian Li

Boosting Skeleton-based Zero-Shot Action Recognition with Training-Free Test-Time Adaptation

Jingmin Zhu · Anqi Zhu · Hossein Rahmani · Jun Liu · Mohammed Bennamoun · Qiuhong Ke

Representation-Level Counterfactual Calibration for Debiased Zero-Shot Recognition

Pei Peng · Ming-Kun Xie · Hang Hao · Tong Jin · Sheng-Jun Huang

State Entropy Regularization for Robust Reinforcement Learning

Yonatan Ashlag · Uri Koren · Mirco Mutti · Esther Derman · Pierre-Luc Bacon · Shie Mannor

A Unifying View of Linear Function Approximation in Off-Policy RL Through Matrix Splitting and Preconditioning

Zechen Wu · Amy Greenwald · Ronald Parr

Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning

Bastien Dubail · Stefan Stojanovic · Alexandre Proutiere

When Can Model-Free Reinforcement Learning be Enough for Thinking?

Josiah Hanna · Nicholas Corrado

Diff-ICMH: Harmonizing Machine and Human Vision in Image Compression with Generative Prior

Ruoyu Feng · Yunpeng Qi · Jinming Liu · Yixin Gao · Xin Li · Xin Jin · Zhibo Chen

Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era

Feng Lu · Tong Jin · Canming Ye · Xiangyuan Lan · Yunpeng Liu · Chun Yuan

Unified Algorithms for RL with Decision-Estimation Coefficients: PAC, Reward-Free, Preference-Based Learning, and Beyond

Fan Chen · Song Mei · Yu Bai

Foundation Models for Scientific Discovery: From Paradigm Enhancement to Paradigm Transition

Fan LIU · Jindong Han · Tengfei Lyu · Weijia Zhang · Zherui Yang · Lu Dai · Cancheng Liu · Hao Liu

Position: Require Frontier AI Labs To Release Small "Analog" Models

Shriyash Upadhyay · Philip Quirke · Narmeen Oozeer · Chaithanya Bandi

IndustryEQA: Pushing the Frontiers of Embodied Question Answering in Industrial Scenarios

Yifan Li · Yuhang Chen · Anh Dao · Lichi Li · Zhongyi Cai · Zhen Tan · Tianlong Chen · Yu Kong

DetectiumFire: A Comprehensive Multi-modal Dataset Bridging Vision and Language for Fire Understanding

Zixuan Liu · Siavash H. Khajavi · Guangkai Jiang

DyFlow: Dynamic Workflow Framework for Agentic Reasoning

Yanbo Wang · Zixiang Xu · Yue Huang · Xiangqi Wang · Zirui Song · Lang Gao · Chenxi Wang · Robert Tang · Yue Zhao · Arman Cohan · Xiangliang Zhang · Xiuying Chen

CF-VLM：CounterFactual Vision-Language Fine-tuning

jusheng zhang · Kaitong Cai · Yijia Fan · Jian Wang · Keze Wang

Adaptive Quantization in Generative Flow Networks for Probabilistic Sequential Prediction

Nadhir Hassen · Zhen Zhang · Johan Verjans

Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models

Zidi Xiong · Shan Chen · Zhenting Qi · Himabindu Lakkaraju

Beyond Least Squares: Uniform Approximation and the Hidden Cost of Misspecification

Davide Maran · Csaba Szepesvari

VERA: Variational Inference Framework for Jailbreaking Large Language Models

Anamika Lochab · Lu Yan · Patrick Pynadath · Xiangyu Zhang · Ruqi Zhang

Unveiling Extraneous Sampling Bias with Data Missing-Not-At-Random

Chunyuan Zheng · Haocheng Yang · Haoxuan Li · Mengyue Yang

Eagle 2.5: Boosting Long-Context Post-Training for Frontier Vision-Language Models

Guo Chen · Zhiqi Li · Shihao Wang · Jindong Jiang · Yicheng Liu · Lidong Lu · De-An Huang · Wonmin Byeon · Matthieu Le · Max Ehrlich · Tong Lu · Limin Wang · Bryan Catanzaro · Jan Kautz · Andrew Tao · Zhiding Yu · Guilin Liu

Sharp Analysis for KL-Regularized Contextual Bandits and RLHF

Heyang Zhao · Chenlu Ye · Quanquan Gu · Tong Zhang

Time-o1: Time-Series Forecasting Needs Transformed Label Alignment

Hao Wang · Licheng Pan · Zhichao Chen · Xu Chen · Qingyang Dai · Lei Wang · Haoxuan Li · Zhouchen Lin

AdvPrefix: An Objective for Nuanced LLM Jailbreaks

Sicheng Zhu · Brandon Amos · Yuandong Tian · Chuan Guo · Ivan Evtimov

Flexible Language Modeling in Continuous Space with Transformer-based Autoregressive Flows

Ruixiang Zhang · Shuangfei Zhai · Jiatao Gu · Yizhe Zhang · Huangjie Zheng · Tianrong Chen · Miguel Angel Bautista · Joshua Susskind · Navdeep Jaitly

Scalable Exploration via Ensemble++

Yingru Li · Jiawei Xu · Baoxiang Wang · Zhiquan Luo

Nemotron-Flash: Towards Latency-Optimal Hybrid Small Language Models

Yonggan Fu · Xin Dong · Shizhe Diao · Matthijs Van keirsbilck · Hanrong Ye · Wonmin Byeon · Yashaswi Karnati · Lucas Liebenwein · Maksim Khadkevich · Alexander Keller · Jan Kautz · Yingyan (Celine) Lin · Pavlo Molchanov

On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective

Ning Zhang · Henry Kenlay · Li Zhang · Mihai Cucuringu · Xiaowen Dong

Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing

Yilmazcan Ozyurt · Tunaberk Almaci · Stefan Feuerriegel · Mrinmaya Sachan

DeltaFormer: Unlock the state space of Transformer

Mingyu Xu · Tenglong Ao · Jiaao He · Jianqiao Lu · Guang Shi · Mingwu Zheng

Reinforcement Learning with Imperfect Transition Predictions: A Bellman-Jensen Approach

Chenbei Lu · Zaiwei Chen · Tongxin Li · Chenye Wu · Adam Wierman

LABridge: Text–Image Latent Alignment Framework via Mean-Conditioned OU Process

Huiyang Shao · Xin Xia · Yuxi Ren · XING WANG · Xuefeng Xiao

Understanding Parametric and Contextual Knowledge Reconciliation within Large Language Models

Jun Zhao · Yongzhuo Yang · Xiang Hu · Jingqi Tong · Yi Lu · Wei Wu · Tao Gui · Qi Zhang · Xuanjing Huang

VLForgery Face Triad: Detection, Localization and Attribution via Multimodal Large Language Models

Xinan He · Yue Zhou · Bing Fan · Bin Li · Guopu Zhu · Feng Ding

FedRAM: Federated Reweighting and Aggregation for Multi-Task Learning

Fan Wu · Xinyu Yan · Jiabei Liu · Wei Yang Bryan Lim

Correlated Low-Rank Adaptation for ConvNets

Wu Ran · Weijia Zhang · ShuYang Pang · Zhu · Jinfan Liu · JingSheng Liu · Xin Cao · Qiang Li · Yichao Yan · Chao Ma

STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis

Jiatao Gu · Tianrong Chen · David Berthelot · Huangjie Zheng · Yuyang Wang · Ruixiang Zhang · Laurent Dinh · Miguel Angel Bautista · Joshua Susskind · Shuangfei Zhai

Beyond Single-Task: Robust Multi-Task Length Generalization for LLMs

Yi Hu · Shijia Kang · Haotong Yang · Haotian Xu · Muhan Zhang

EvoBrain: Dynamic Multi-Channel EEG Graph Modeling for Time-Evolving Brain Networks

Rikuto Kotoge · Zheng Chen · Tasuku Kimura · Yasuko Matsubara · Takufumi Yanagisawa · Haruhiko Kishima · Yasushi Sakurai

Non-rectangular Robust MDPs with Normed Uncertainty Sets

Navdeep Kumar · Adarsh Gupta · Maxence Mohamed ELFATIHI · Giorgia Ramponi · Kfir Y. Levy · Shie Mannor

A Geometry-Aware Metric for Mode Collapse in Time Series Generative Models

Yassine ABBAHADDOU · Amine Aboussalah

Cost-Sensitive Freeze-thaw Bayesian Optimization for Efficient Hyperparameter Tuning

Dong Bok Lee · Aoxuan Zhang · Byungjoo Kim · Junhyeon Park · Steven Adriaensen · Juho Lee · Sung Ju Hwang · Hae Beom Lee

Video-R1: Reinforcing Video Reasoning in MLLMs

Kaituo Feng · Kaixiong Gong · Bohao Li · Zonghao Guo · Yibing Wang · Tianshuo Peng · Junfei Wu · Xiaoying Zhang · Benyou Wang · Xiangyu Yue

CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding

Yuchen Zhou · Jiamin Wu · Zichen Ren · Zhouheng Yao · Weiheng Lu · Kunyu Peng · Qihao Zheng · Chunfeng Song · Wanli Ouyang · Chao Gou

Inference-time Alignment in Continuous Space

Yige Yuan · Teng Xiao · Li Yunfan · Bingbing Xu · Shuchang Tao · Yunqi Qiu · Huawei Shen · Xueqi Cheng

TV-Rec: Time-Variant Convolutional Filter for Sequential Recommendation

Yehjin Shin · Jeongwhan Choi · Seojin Kim · Noseong Park

Smooth Quadratic Prediction Markets

Enrique Nueve · Bo Waggoner

C3PO: Optimized Large Language Model Cascades with Probabilistic Cost Constraints for Reasoning

Antonios Valkanas · Soumyasundar Pal · Pavel Rumiantsev · Yingxue Zhang · Mark Coates

Graph Alignment via Birkhoff Relaxation

Sushil Varma · Irène Waldspurger · Laurent Massoulié

UniCTokens: Boosting Personalized Understanding and Generation via Unified Concept Tokens

Ruichuan An · Sihan Yang · Renrui Zhang · zijun shen · Ming Lu · Gaole Dai · Hao Liang · Ziyu Guo · Shilin Yan · Yulin Luo · Bocheng Zou · Chaoqun Yang · Wentao Zhang

GraphMaster: Automated Graph Synthesis via LLM Agents in Data-Limited Environments

Enjun Du · Xunkai Li · Tian Jin · Zhihan Zhang · Rong-Hua Li · Guoren Wang

SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning

Wufei Ma · Yu-Cheng Chou · Qihao Liu · Xingrui Wang · Celso de Melo · Jianwen Xie · Alan Yuille

VCM: Vision Concept Modeling with Adaptive Vision Token Compression via Instruction Fine-Tuning

Run Luo · Renke Shan · Longze Chen · Ziqiang Liu · Lu Wang · Min Yang · Xiaobo Xia

Towards Resilient Safety-driven Unlearning for Diffusion Models against Downstream Fine-tuning

Boheng Li · Renjie Gu · Junjie Wang · Leyi Qi · Yiming Li · Run Wang · Zhan Qin · Tianwei Zhang

Non-Asymptotic Guarantees for Average-Reward Q-Learning with Adaptive Stepsizes

Zaiwei Chen

AI-Researcher: Autonomous Scientific Innovation

Jiabin Tang · Lianghao Xia · Zhonghang Li · Chao Huang

Not All Data are Good Labels: On the Self-supervised Labeling for Time Series Forecasting

Yuxuan Yang · Dalin Zhang · Yuxuan Liang · Hua Lu · Gang Chen · Huan Li

Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL

Joey Hong · Anca Dragan · Sergey Levine

Individual Regret in Cooperative Stochastic Multi-Armed Bandits

Idan Barnea · Tal Lancewicki · Yishay Mansour

Regret Bounds for Adversarial Contextual Bandits with General Function Approximation and Delayed Feedback

Orin Levy · Liad Erez · Alon Peled-Cohen · Yishay Mansour

On the Expressive Power of Mixture-of-Experts for Structured Complex Tasks

Mingze Wang · Weinan E

Sparc3D: Sparse Representation and Construction for High-Resolution 3D Shapes Modeling

Zhihao Li · Yufei Wang · Heliang Zheng · Yihao Luo · Bihan Wen

Visual Jenga: Discovering Object Dependencies via Counterfactual Inpainting

Anand Bhattad · Konpat Preechakul · Alexei Efros

ORIGAMISPACE: Benchmarking Multimodal LLMs in Multi-Step Spatial Reasoning with Mathematical Constraints

Rui Xu · Dakuan Lu · Zicheng Zhao · Xiaoyu Tan · Xintao Wang · Siyu Yuan · Jiangjie Chen · yinghui xu

macOSWorld: A Multilingual Interactive Benchmark for GUI Agents

Pei Yang · Hai Ci · Mike Zheng Shou

Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models

Yulei Qin · Gang Li · Zongyi Li · Zihan Xu · Yuchen Shi · Zhekai Lin · Xiao Cui · Ke Li · Xing Sun

Generalized Category Discovery under Domain Shift: A Frequency Domain Perspective

Wei Feng · Zongyuan Ge

Variational Supervised Contrastive Learning

Ziwen Wang · Jiajun Fan · Thao Nguyen · Heng Ji · Ge Liu

KeyDiff: Key Similarity-Based KV Cache Eviction for Long-Context LLM Inference in Resource-Constrained Environments

Junyoung Park · Dalton Jones · Matthew Morse · Raghavv Goel · Mingu Lee · Christopher Lott

Can MLLMs Absorb Math Reasoning Abilities from LLMs as Free Lunch?

Yijie Hu · Zihao Zhou · Kaizhu Huang · Xiaowei Huang · Qiufeng Wang

OmniSVG: A Unified Scalable Vector Graphics Generation Model

Yiying Yang · Wei Cheng · Sijin Chen · Xianfang Zeng · Fukun Yin · Jiaxu Zhang · Liao Wang · Gang Yu · Xingjun Ma · Yu-Gang Jiang

Robust SuperAlignment: Weak-to-Strong Robustness Generalization for Vision-Language Models

Junhao Dong · Cong Zhang · Xinghua Qu · Zejun MA · Piotr Koniusz · Yew Soon Ong

Balancing Gradient and Hessian Queries in Non-Convex Optimization

Deeksha Adil · Brian Bullins · Aaron Sidford · Chenyi Zhang

WebDancer: Towards Autonomous Information Seeking Agency

Jialong Wu · Baixuan Li · Runnan Fang · Wenbiao Yin · Liwen Zhang · Zhenglin Wang · Zhengwei Tao · Ding-Chu Zhang · Zekun Xi · Robert Tang · Yong Jiang · Pengjun Xie · Fei Huang · Jingren Zhou

MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem

Fan LIU · Zherui Yang · Cancheng Liu · Tianrui Song · Xiaofeng Gao · Hao Liu

Generative Pre-trained Autoregressive Diffusion Transformer

Yuan Zhang · Jiacheng Jiang · Guoqing Ma · Zhiying Lu · Bo Wang · Haoyang Huang · Jianlong Yuan · Nan Duan

Language Models (Mostly) Know When to Stop Reading

Roy Xie · Junlin Wang · Paul Rosu · Chunyuan Deng · Bolun Sun · Zihao Lin · Bhuwan Dhingra

VarFlow: Proper Scoring-Rule Diffusion Distillation via Energy Matching

Huiyang Shao · Xin Xia · Yuxi Ren · XING WANG · Xuefeng Xiao

Training-Free Bayesianization for Low-Rank Adapters of Large Language Models

Haizhou Shi · Yibin Wang · Ligong Han · Huan Zhang · Hao Wang

Rethinking Approximate Gaussian Inference in Classification

Bálint Mucsányi · Nathaël Da Costa · Philipp Hennig

Fisher meets Feynman: score-based variational inference with a product of experts

Diana Cai · Robert Gower · David Blei · Lawrence Saul

Stationary Kernels and Gaussian Processes on Lie Groups and their Homogeneous Spaces I: the compact case

Iskander Azangulov · Andrei Smolensky · Alexander Terenin · Viacheslav (Slava) Borovitskiy

Spectral Estimation with Free Decompression

Siavash Ameli · Chris van der Heide · Liam Hodgkinson · Michael Mahoney

Sparse Gaussian Processes: Structured Approximations and Power-EP Revisited

Thang Bui · Michalis Titsias

FEAT: Free energy Estimators with Adaptive Transport

Yuanqi Du · Jiajun He · Francisco Vargas · Yuanqing Wang · Carla Gomes · José Miguel Hernández-Lobato · Eric Vanden-Eijnden

Non-equilibrium Annealed Adjoint Sampler

Jaemoo Choi · Yongxin Chen · Molei Tao · Guan-Horng Liu

Fast Non-Log-Concave Sampling under Nonconvex Equality and Inequality Constraints with Landing

Kijung Jeon · Michael Muehlebach · Molei Tao

Variance-Reduced Long-Term Rehearsal Learning with Quadratic Programming Reformulation

Wen-Bo Du · Tian Qin · Tian-Zuo Wang · Zhi-Hua Zhou

Neurosymbolic Diffusion Models

Emile van Krieken · Pasquale Minervini · Edoardo Maria Ponti · Antonio Vergari

Anytime-valid, Bayes-assisted, Prediction-Powered Inference

Valentin Kilian · Stefano Cortinovis · Francois Caron

Rao-Blackwellised Reparameterisation Gradients

Kevin H. Lam · Thang Bui · George Deligiannidis · Yee Whye Teh

Uncertainty Estimation by Flexible Evidential Deep Learning

Taeseong Yoon · Heeyoung Kim

Data-Driven Performance Guarantees for Classical and Learned Optimizers

Rajiv Sambharya · Bartolomeo Stellato

Learning from A Single Markovian Trajectory: Optimality and Variance Reduction

Zhenyu Sun · Ermin Wei

Unveiling m-Sharpness Through the Structure of Stochastic Gradient Noise

Haocheng Luo · Mehrtash Harandi · Dinh Phung · Trung Le

Streaming Stochastic Submodular Maximization with On-Demand User Requests

Honglian Wang · Sijing Tu · Lutz Oettershagen · Aristides Gionis

Stochastic Momentum Methods for Non-smooth Non-Convex Finite-Sum Coupled Compositional Optimization

Xingyu Chen · Bokun Wang · Ming Yang · Qihang Lin · Tianbao Yang

Zeroth-Order Optimization Finds Flat Minima

Liang Zhang · Bingcong Li · Kiran Thekumparampil · Sewoong Oh · Michael Muehlebach · Niao He

Optimistic Online-to-Batch Conversions for Accelerated Convergence and Universality

Yu-Hu Yan · Peng Zhao · Zhi-Hua Zhou

Efficient Quadratic Corrections for Frank-Wolfe Algorithms

Jannis Halbey · Seta Rakotomandimby · Mathieu Besançon · Sébastien Designolle · Sebastian Pokutta

Multiclass Loss Geometry Matters for Generalization of Gradient Descent in Separable Classification

Matan Schliserman · Tomer Koren

Private Zeroth-Order Optimization with Public Data

Xuchen Gong · Tian Li

Solving Discrete (Semi) Unbalanced Optimal Transport with Equivalent Transformation Mechanism and KKT-Multiplier Regularization

Weiming Liu · Xinting Liao · Jun Dan · Fan Wang · Hua Yu · Junhao Dong · Shunjie Dong · Lianyong Qi · Yew Soon Ong

MTL-KD: Multi-Task Learning Via Knowledge Distillation for Generalizable Neural Vehicle Routing Solver

yuepeng zheng · Fu Luo · Zhenkun Wang · Yaoxin Wu · Yu Zhou

Large Language Models as End-to-end Combinatorial Optimization Solvers

Xia Jiang · Yaoxin Wu · Minshuo Li · Zhiguang Cao · Yingqian Zhang

Bilevel Optimization for Adversarial Learning Problems: Sharpness, Generation, and Beyond

Risheng Liu · Zhu Liu · Weihao Mao · Wei Yao · Jin Zhang

3BASiL: An Algorithmic Framework for Sparse plus Low-Rank Compression of LLMs

Mehdi Makni · Xiang Meng · Rahul Mazumder

Optimizing the Unknown: Black Box Bayesian Optimization with Energy-Based Model and Reinforcement Learning

RUIYAO MIAO · Junren Xiao · Shiya Tsang · Hui Xiong · Ying Nian Wu

Acceleration via silver step-size on Riemannian manifolds with applications to Wasserstein space

Jiyoung Park · Abhishek Roy · Jonathan W. Siegel · Anirban Bhattacharya

NPN: Non-Linear Projections of the Null-Space for Imaging Inverse Problems

Roman Jacome · Romario Gualdrón-Hurtado · León Suárez-Rodríguez · Henry Arguello

Stochastic Regret Guarantees for Online Zeroth- and First-Order Bilevel Optimization

Parvin Nazari · Bojian Hou · Davoud Ataee Tarzanagh · Li Shen · George Michailidis

Follow-the-Perturbed-Leader Nearly Achieves Best-of-Both-Worlds for the m-Set Semi-Bandit Problems

Jingxin Zhan · Yuchen Xin · Chenjie Sun · Zhihua Zhang

Fairness-Regularized Online Optimization with Switching Costs

Pengfei Li · Yuelin Han · Adam Wierman · Shaolei Ren

Purity Law for Neural Routing Problem Solvers with Enhanced Generalizability

Wenzhao Liu · Haoran Li · Congying Han · Zicheng Zhang · Anqi Li · Tiande Guo

OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling

Haoyang Liu · Jie Wang · Yuyang Cai · Xiongwei Han · Yufei Kuang · Jianye Hao

Improved Algorithms for Overlapping and Robust Clustering of Edge-Colored Hypergraphs: An LP-Based Combinatorial Approach

Changyeol Lee · Yongho Shin · Hyung-Chan An

Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems

Ni Zhang · Zhiguang Cao

Improving Generalization of Neural Combinatorial Optimization for Vehicle Routing Problems via Test-Time Projection Learning

Yuanyao Chen · Rongsheng Chen · Fu Luo · Zhenkun Wang

Hierarchical Optimization via LLM-Guided Objective Evolution for Mobility-on-Demand Systems

Yi Zhang · Yushen Long · Yun Ni · Liping Huang · Xiaohong Wang · Jun Liu

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows

Zaifeng Pan · AJJKUMAR DAHYALAL PATEL · Yipeng Shen · Zhengding Hu · Yue Guan · Wan-Lu Li · Lianhui Qin · Yida Wang · Yufei Ding

Partial Correlation Network Estimation by Semismooth Newton Methods

DongWon Kim · Sungdong Lee · Joong-Ho (Johann) Won

FlowMoE: A Scalable Pipeline Scheduling Framework for Distributed Mixture-of-Experts Training

Yunqi Gao · Bing Hu · Boloursaz Mashhadi · A-Long Jin · Yanfeng Zhang · Pei Xiao · Rahim Tafazolli · Merouane DEBBAH

Communication-Efficient Language Model Training Scales Reliably and Robustly: Scaling Laws for DiLoCo

Zachary Charles · Gabriel Teston · Lucio Dery · John Rush · Nova Fallen · Zachary Garrett · Arthur Szlam · Arthur Douillard

ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive

Xinhao Luo · Zihan Liu · Yangjie Zhou · Shihan Fang · Ziyu Huang · Yu Feng · Chen Zhang · Shixuan Sun · Zhenzhe Zheng · Jingwen Leng · Minyi Guo

A Near-Optimal Algorithm for Decentralized Convex-Concave Finite-Sum Minimax Optimization

Hongxu Chen · Ke Wei · Haishan Ye · Luo Luo

Cost-aware LLM-based Online Dataset Annotation

Eray Can Elumar · Cem Tekin · Osman Yagan

Efficient semantic uncertainty quantification in language models via diversity-steered sampling

Ji Won Park · Kyunghyun Cho

$O(\sqrt{T})$ Static Regret and Instance Dependent Constraint Violation for Constrained Online Convex Optimization

Rahul Vaze · Abhishek Sinha

Sign-In to the Lottery: Reparameterizing Sparse Training

Advait Gadhikar · Tom Jacobs · chao zhou · Rebekka Burkholz

Power Lines: Scaling laws for weight decay and batch size in LLM pre-training

Shane Bergsma · Nolan Dey · Gurpreet Gosal · Gavia Gray · Daria Soboleva · Joel Hestness

Q3R: Quadratic Reweighted Rank Regularizer for Effective Low-Rank Training

Ipsita Ghosh · Ethan Nguyen · Christian Kümmerle

Momentum-SAM: Sharpness Aware Minimization without Computational Overhead

Marlon Becker · Frederick Altrock · Benjamin Risse

FFN Fusion: Rethinking Sequential Computation in Large Language Models

Akhiad Bercovich · Mohammed Dabbah · Omri Puny · Ido Galil · Amnon Geifman · Yonatan Geifman · Izik Golan · Ehud Karpas · Itay Levy · Zach Moshe · Najeeb Nabwani · Tomer Ronen · Itamar Schen · Ido Shahaf · Oren Tropp · Ran Zilberstein · Ran El-Yaniv

Time-Embedded Algorithm Unrolling for Computational MRI

Junno Yun · Yasar Utku Alcalar · Mehmet Akcakaya

MUSTAFAR: Promoting Unstructured Sparsity for KV Cache Pruning in LLM Inference

Donghyeon Joo · Helya Hosseini · Ramyad Hadidi · Bahar Asgari

Differentiable Sparsity via $D$-Gating: Simple and Versatile Structured Penalization

Chris Kolb · Laetitia Frost · Bernd Bischl · David Rügamer

Small Batch Size Training for Language Models: When Vanilla SGD Works, and Why Gradient Accumulation is Wasteful

Martin Marek · Sanae Lotfi · Aditya Somasundaram · Andrew Wilson · Micah Goldblum

Data Efficient Adaptation in Large Language Models via Continuous Low-Rank Fine-Tuning

Xiao Han · ZIMO ZHAO · Wanyu Wang · Maolin Wang · Zitao Liu · Yi Chang · Xiangyu Zhao

Modality-Aware SAM: Sharpness-Aware-Minimization Driven Gradient Modulation for Harmonized Multimodal Learning

Hossein Rajoli Nowdeh · Jie Ji · Xiaolong Ma · Fatemeh Afghah

Neural Evolution Strategy for Black-box Pareto Set Learning

Chengyu Lu · Zhenhua Li · Xi Lin · Ji Cheng · Qingfu Zhang

Thompson Sampling in Function Spaces via Neural Operators

Rafael Oliveira · Xuesong Wang · Kian Ming Chai · Edwin Bonilla

Online Portfolio Selection with ML Predictions

Ziliang Zhang · Tianming Zhao · Albert Zomaya

Re-coding for Uncertainties: Edge-awareness Semantic Concordance for Resilient Event-RGB Segmentation

Nan Bao · Yifan Zhao · Lin Zhu · Jia Li

Variational Learning Finds Flatter Solutions at the Edge of Stability

Avrajit Ghosh · Bai Cong · Rio Yokota · Saiprasad Ravishankar · Rongrong Wang · Molei Tao · Mohammad Emtiyaz Khan · Thomas Möllenhoff

Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization

Han Wang · Chao Ning

Go to Event Page

Panel

Emergent Stories: AI Agents and New Narratives

Parag Mital · Jie Zhang · Manuel Flurin Hendry · Vanessa Rosa · Gottfried Haider

11:00 AM - 12:00 PM

Abstract: This panel explores how AI agents are reshaping contemporary storytelling across games, installations, film, and performance. From multi-agent LLM architectures that generate narratives through simulated social dynamics to environments where humans and AI construct meaning together under uncertainty, each work examines how stories emerge between actors. An interactive performance exposes the limits of computational empathy through a malfunctioning therapeutic agent, while Little Martians turns ceramic sculptures into autonomous creators releasing daily films. We will discuss how these and related projects consider storytelling as a distributed, agent-driven process that displaces the current norms of coherence, authorship and narrative control.

... more

Invited Talk

On the Science of “Alien Intelligences”: Evaluating Cognitive Capabilities in Babies, Animals, and AI

Melanie Mitchell

2:30 PM - 3:30 PM

Today’s generative AI systems—termed by some researchers as “alien intelligences”—have exceeded human performance on many benchmarks meant to test humanlike cognitive capabilities. However, these systems still struggle in unhumanlike ways on real-world tasks requiring these capabilities. This disconnect may be due in part to neglect in the AI community of well-founded experimental protocols for evaluating cognition. In this talk I will summarize several recommendations on experimental methods from developmental and comparative psychology—fields that study the “alien intelligences” of babies and non-human animals—and demonstrate the application of such methods in two case studies of cognitive abilities in LLMs: analogical reasoning and visual abstraction.

... more

Speaker Bio

Melanie Mitchell - Professor Santa Fe Institute. Mitchell's research areas include AI, cognitive science, and complex systems, with focus on conceptual abstraction and analogy-making in humans and AI systems. She authored "Complexity: A Guided Tour," which won the 2010 Phi Beta Kappa Science Book Award, and "Artificial Intelligence: A Guide for Thinking Humans," which was named one of the five best books on AI by both the New York Times and the Wall Street Journal. She received her PhD from the University of Michigan under Douglas Hofstadter, with whom she developed the Copycat cognitive architecture.

... more

Oral

Oral 4A Language Model 2

3:30 PM - 4:30 PM

3 Events in this session

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

David Chanin · James Wilken-Smith · Tomáš Dulka · Hardik Bhatnagar · Satvik Golechha · Joseph Bloom

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Zihan Qiu · Zekun Wang · Bo Zheng · Zeyu Huang · Kaiyue Wen · Songlin Yang · Rui Men · Le Yu · Fei Huang · Suozhi Huang · Dayiheng Liu · Jingren Zhou · Junyang Lin

Superposition Yields Robust Neural Scaling

Yizhou Liu · Ziming Liu · Jeff Gore

Go to Event Page

Oral

Oral 4E Algorithm 2

3:30 PM - 4:30 PM

3 Events in this session

MaxSup: Overcoming Representation Collapse in Label Smoothing

Yuxuan Zhou · Heng Li · Zhi-Qi Cheng · Xudong Yan · Yifei Dong · Mario Fritz · Margret Keuper

Advancing Expert Specialization for Better MoE

Hongcan Guo · Haolang Lu · Guoshun Nan · Bolun Chu · Jialin Zhuang · Yuan Yang · Wenhao Che · Xinye Cao · Sicong Leng · Qimei Cui · Xudong Jiang

Learning to Learn with Contrastive Meta-Objective

Shiguang Wu · Yaqing Wang · Yatao Bian · Quanming Yao

Go to Event Page

Oral

Oral 4B Generation/Simulation 2

3:30 PM - 4:30 PM

3 Events in this session

Exploring Diffusion Transformer Designs via Grafting

Keshigeyan Chandrasegaran · Michael Poli · Dan Fu · Dongjun Kim · Lea M. Hadzic · Manling Li · Agrim Gupta · Stefano Massaroli · Azalia Mirhoseini · Juan Carlos Niebles · Stefano Ermon · Fei-Fei Li

Deep Compositional Phase Diffusion for Long Motion Sequence Generation

Ho Yin Au · Jie Chen · Junkun Jiang · Jingyu Xiang

Mean Flows for One-step Generative Modeling

Zhengyang Geng · Mingyang Deng · Xingjian Bai · Zico Kolter · Kaiming He

Go to Event Page

Panel

Oral 4C Position Paper Panels

3:30 PM - 4:30 PM

2 Events in this session

Responsible AI Research & Unlearning: From Consent to Compliance to Critique

Princessa Cintaqia · Bill Marino · A. Feder Cooper

Strengthening the AI Research Ecosystem: Integrity, Critique, and Consensus

Jianghao Lin · Rylan Schaeffer · Rishi Bommasani

Go to Event Page

Oral

Oral 4D Optimization

3:30 PM - 4:30 PM

3 Events in this session

In Search of Adam’s Secret Sauce

Antonio Orvieto · Robert Gower

Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions

Zhaoxian Wu · Quan Xiao · Tayfun Gokmen · Omobayode Fagbohungbe · Tianyi Chen

Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness

Thomas Pethick · Wanyun Xie · Mete Erdogan · Kimon Antonakopoulos · Antonio Silveti-Falls · Volkan Cevher

Go to Event Page

Poster

San Diego Poster Session 4

4:30 PM - 7:30 PM

949 Events in this session

MuRating: A High Quality Data Selecting Approach to Multilingual Large Language Model Pretraining

Zhixun Chen · Ping Guo · Wenhan Han · Yifan Zhang · BINBINLIU · Haobin Lin · Fengze Liu · Yan Zhao · Bingni Zhang · Taifeng Wang · Yin Zheng · Trevor Cohn · Meng Fang

FaCT: Faithful Concept Traces for Explaining Neural Network Decisions

Amin Parchami-Araghi · Sukrut Rao · Jonas Fischer · Bernt Schiele

Advancing Interpretability of CLIP Representations with Concept Surrogate Model

Nhat Hoang-Xuan · Xiyuan Wei · Wanli Xing · Tianbao Yang · My T. Thai

Automated Detection of Visual Attribute Reliance with a Self-Reflective Agent

Christy Li · Josep Lopez Camuñas · Jake Touchet · Jacob Andreas · Agata Lapedriza · Antonio Torralba · Tamar Rott Shaham

On Logic-based Self-Explainable Graph Neural Networks

Alessio Ragno · Marc Plantevit · Céline Robardet

A is for Absorption: Studying Feature Splitting and Absorption in Sparse Autoencoders

David Chanin · James Wilken-Smith · Tomáš Dulka · Hardik Bhatnagar · Satvik Golechha · Joseph Bloom

Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry

Sai Sumedh R. Hindupur · Ekdeep S Lubana · Thomas Fel · Demba Ba

Causally Reliable Concept Bottleneck Models

Giovanni De Felice · Arianna Casanova Flores · Francesco De Santis · Silvia Santini · Johannes Schneider · Pietro Barbiero · Alberto Termine

MIX: A Multi-view Time-Frequency Interactive Explanation Framework for Time Series Classification

Viet-Hung Tran · Ngoc Phu Doan · Zichi Zhang · Tuan Pham · Phi Hung Nguyen · Xuan Hoang Nguyen · Hans Vandierendonck · Ira Assent · Thai Son Mai

Combining Cost Constrained Runtime Monitors for AI Safety

Tim Hua · James Baskerville · Henri Lemoine · Mia Hopman · Aryan Bhatt · Tyler Tracy

SHAP zero Explains Biological Sequence Models with Near-zero Marginal Cost for Future Queries

Darin Tsui · Aryan Musharaf · Yigit Efe Erginbas · Justin Kang · Amirali Aghazadeh

Robust Sampling for Active Statistical Inference

Puheng Li · Tijana Zrnic · Emmanuel Candes

Disentangled Concepts Speak Louder Than Words: Explainable Video Action Recognition

Jongseo Lee · Wooil Lee · Gyeong-Moon Park · Seong Tae Kim · Jinwoo Choi

Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lens

Samuele Bortolotti · Emanuele Marconato · Paolo Morettin · Andrea Passerini · Stefano Teso

Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions

蕾蕾温 · Liwei Zheng · Hongda Li · Lijun Sun · Zhihua Wei · Wen Shen

Reasoning Models Sometimes Output Illegible Chains of Thought

Arun Jose

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning

Julian Minder · Clément Dumas · Caden Juang · Bilal Chughtai · Neel Nanda

OVERT: A Benchmark for Over-Refusal Evaluation on Text-to-Image Models

Ziheng Cheng · Yixiao Huang · Hui Xu · Somayeh Sojoudi · Xuandong Zhao · Dawn Song · Song Mei

Is Artificial Intelligence Generated Image Detection a Solved Problem?

Ziqiang Li · Jiazhen Yan · Ziwen He · Kai Zeng · Weiwei Jiang · Lizhi Xiong · Zhangjie Fu

Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization

Bowei He · Lihao Yin · Hui-Ling Zhen · Shuqi LIU · Han Wu · Xiaokun Zhang · Mingxuan Yuan · Chen Ma

Checklists Are Better Than Reward Models For Aligning Language Models

Vijay Viswanathan · Yanchao Sun · Xiang Kong · Meng Cao · Graham Neubig · Sherry Wu

Generative Caching for Structurally Similar Prompts and Responses

Sarthak Chakraborty · Suman Nath · Xuchao Zhang · Chetan Bansal · Indranil Gupta

Efficient Multimodal Dataset Distillation via Generative Models

Zhenghao Zhao · Haoxuan Wang · Junyi Wu · Yuzhang Shang · Gaowen Liu · Yan Yan

Evaluating multiple models using labeled and unlabeled data

Divya Shanmugam · Shuvom Sadhuka · Manish Raghavan · John Guttag · Bonnie Berger · Emma Pierson

Solving Partial Differential Equations via Radon Neural Operator

Wenbin Lu · Yihan Chen · Junnan Xu · Wei Li · Junwei Zhu · Jianwei Zheng

SECODEPLT: A Unified Benchmark for Evaluating the Security Risks and Capabilities of Code GenAI

Yuzhou Nie · Zhun Wang · Yu Yang · Ruizhe Jiang · Yuheng Tang · Xander Davies · Yarin Gal · Bo Li · Wenbo Guo · Dawn Song

APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay

Akshara Prabhakar · Zuxin Liu · Ming Zhu · Jianguo Zhang · Tulika Manoj Awalgaonkar · Shiyu Wang · Zhiwei Liu · Haolin Chen · Thai Hoang · Juan Carlos Niebles · Shelby Heinecke · Weiran Yao · Huan Wang · Silvio Savarese · Caiming Xiong

EffiBench-X: A Multi-Language Benchmark for Measuring Efficiency of LLM-Generated Code

Yuhao Qing · Boyu Zhu · Mingzhe Du · Zhijiang Guo · Terry Yue Zhuo · Qianru Zhang · Jie Zhang · Heming Cui · Siu Ming Yiu · Dong HUANG · See-Kiong Ng · Anh Tuan Luu

Simple and Effective Specialized Representations for Fair Classifiers

Alberto Sinigaglia · Davide Sartor · Marina Ceccon · Gian Antonio Susto

AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference

CHE WANG · Ziqi Zhang · Yinggui Wang · Tiantong Wang · Yurong Hao · Jianbo Gao · Tao Wei · Yang Cao · Zhong Chen · Wei Yang Bryan Lim

DPA: A one-stop metric to measure bias amplification in classification datasets

Bhanu Tokas · Rahul Nair · Hannah Kerner

SafeVLA: Towards Safety Alignment of Vision-Language-Action Model via Constrained Learning

Borong Zhang · Yuhao Zhang · Jiaming Ji · Yingshan Lei · Juntao Dai · Yuanpei Chen · Yaodong Yang

Incentivizing Time-Aware Fairness in Data Sharing

Jiangwei Chen · Kieu Thao Nguyen Pham · Rachael Sim · Arun Verma · Zhaoxuan Wu · Chuan Sheng Foo · Bryan Kian Hsiang Low

Training-free Detection of AI-generated images via Cropping Robustness

Sungik Choi · Hankook Lee · Moontae Lee

The Fluorescent Veil: A Stealthy and Effective Physical Adversarial Patch Against Traffic Sign Recognition

Shuai Yuan · Xingshuo Han · Hongwei Li · Guowen Xu · Wenbo Jiang · Tao Ni · Qingchuan Zhao · Yuguang Fang

Kernel-based Equalized Odds: A Quantification of Accuracy-Fairness Trade-off in Fair Representation Learning

Yijin Ni · Xiaoming Huo

StegoZip: Enhancing Linguistic Steganography Payload in Practice with Large Language Models

Jun Jiang · Zijin Yang · Weiming Zhang · Nenghai Yu · Kejiang Chen

The Right to Red-Team: Adversarial AI Literacy as a Civic Imperative in K-12 Education

Devan Walton · Haesol Bae

Nemotron-CLIMB: Clustering-based Iterative Data Mixture Bootstrapping for Language Model Pre-training

Shizhe Diao · Yu Yang · Yonggan Fu · Xin Dong · Dan SU · Markus Kliegl · ZIJIA CHEN · Peter Belcak · Yoshi Suhara · Hongxu Yin · Mostofa Patwary · Yingyan (Celine) Lin · Jan Kautz · Pavlo Molchanov

From Specificity to Generality: Revisiting Generalizable Artifacts in Detecting Face Deepfakes

Long Ma · Zhiyuan Yan · Jin Xu · Yize Chen · Qinglang Guo · Zhen Bi · Yong Liao · Hui Lin

Obliviator Reveals the Cost of Nonlinear Guardedness in Concept Erasure

Ramin Akbari · Milad Afshari · Vishnu Boddeti

T2SMark: Balancing Robustness and Diversity in Noise-as-Watermark for Diffusion Models

Jindong Yang · Han Fang · Weiming Zhang · Nenghai Yu · Kejiang Chen

Guiding LLM Decision-Making with Fairness Reward Models

Zara Hall · Melanie Subbiah · Thomas Zollo · Kathleen McKeown · Richard Zemel

Black-Box Membership Inference Attack for LVLMs via Prior Knowledge-Calibrated Memory Probing

Jinhua Yin · Peiru Yang · Chen Yang · Huili Wang · Zhiyang Hu · Shangguang Wang · Yongfeng Huang · Tao Qi

Mitigating Sexual Content Generation via Embedding Distortion in Text-conditioned Diffusion Models

Jaesin Ahn · Heechul Jung

IR-OptSet: An Optimization-Sensitive Dataset for Advancing LLM-Based IR Optimizer

Zi Yang · Lei Qiu · FANG LYU · Ming Zhong · Zhilei Chai · Haojie Zhou · Huimin Cui · Xiaobing Feng

Data-Juicer 2.0: Cloud-Scale Adaptive Data Processing for and with Foundation Models

Daoyuan Chen · Yilun Huang · Xuchen Pan · Jiang Nana · Haibin Wang · Yilei Zhang · Ce Ge · Yushuo Chen · Wenhao Zhang · Zhijian Ma · Jun Huang · Wei Lin · Yaliang Li · Bolin Ding · Jingren Zhou

PHANTOM: A Benchmark for Hallucination Detection in Financial Long-Context QA

Lanlan Ji · Dominic Seyler · Gunkirat Kaur · Manjunath Hegde · Koustuv Dasgupta · Bing Xiang

VeriThoughts: Enabling Automated Verilog Code Generation using Reasoning and Formal Verification

Patrick Yubeaton · Andre Nakkab · Weihua Xiao · Luca Collini · Ramesh Karri · Chinmay Hegde · Siddharth Garg

Sample-Efficient Multi-Round Generative Data Augmentation for Long-Tail Instance Segmentation

Byunghyun Kim · Minyoung Bae · Jae-Gil Lee

Individually Fair Diversity Maximization

Ruien Li · Yanhao Wang

AgentBreeder: Mitigating the AI Safety Risks of Multi-Agent Scaffolds via Self-Improvement

J Rosser · Jakob Foerster

Fair Minimum Labeling: Efficient Temporal Network Activations for Reachability and Equity

Lutz Oettershagen · Othon Michail

Fair Deepfake Detectors Can Generalize

Harry Cheng · Ming-Hui Liu · Yangyang Guo · Tianyi Wang · Liqiang Nie · Mohan Kankanhalli

Some Optimizers are More Equal: Understanding the Role of Optimizers in Group Fairness

Mojtaba Kolahdouzi · Hatice Gunes · Ali Etemad

Adaptive Defense against Harmful Fine-Tuning for Large Language Models via Bayesian Data Scheduler

Zixuan Hu · Li Shen · Zhenyi Wang · Yongxian Wei · Dacheng Tao

$\mathcal{X}^2$-DFD: A framework for e$\mathcal{X}$plainable and e$\mathcal{X}$tendable Deepfake Detection

Yize Chen · Zhiyuan Yan · Guangliang Cheng · Kangran Zhao · Siwei Lyu · Baoyuan Wu

Scaling Laws For Scalable Oversight

Joshua Engels · David Baek · Subhash Kantamneni · Max Tegmark

FairImagen: Post-Processing for Bias Mitigation in Text-to-Image Models

Zihao Fu · Ryan Brown · Shun Shao · Kai Rawal · Eoin Delaney · Chris Russell

Lie Detector: Unified Backdoor Detection via Cross-Examination Framework

Xuan Wang · Siyuan Liang · Dongping Liao · Han Fang · Aishan Liu · Xiaochun Cao · Yu-liang Lu · Ee-Chien Chang · Xitong Gao

Machine Unlearning in 3D Generation: A Perspective-Coherent Acceleration Framework

Shixuan Wang · Jingwen Ye · Xinchao Wang

Perturb a Model, Not an Image: Towards Robust Privacy Protection via Anti-Personalized Diffusion Models

Tae-Young Lee · Juwon Seo · Jong Hwan Ko · Gyeong-Moon Park

Differentially Private Gomory-Hu Trees

Anders Aamand · Justin Chen · Mina Dalirrooyfard · Slobodan Mitrovic · Yuriy Nevmyvaka · Sandeep Silwal · Yinzhan Xu

Multi-order Orchestrated Curriculum Distillation for Model-Heterogeneous Federated Graph Learning

Guancheng Wan · Xu Cheng · Run Liu · Wenke Huang · Zitong Shi · Pinyi Jin · Guibin Zhang · Bo Du · Mang Ye

Private Continual Counting of Unbounded Streams

Ben Jacobsen · Kassem Fawaz

Online Locally Differentially Private Conformal Prediction via Binary Inquiries

Qiangqiang Zhang · Chenfei Gu · Xinwei Feng · Jinhan Xie · Ting Li

Distributionally Robust Feature Selection

Maitreyi Swaroop · Tamar Krishnamurti · Bryan Wilder

RLVR-World: Training World Models with Reinforcement Learning

Jialong Wu · Shaofeng Yin · Ningya Feng · Mingsheng Long

The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples

Hsiang Hsu · Pradeep Niroula · Zichang He · Ivan Brugere · Freddy Lecue · Richard Chen

CALM: Culturally Self-Aware Language Models

Lingzhi Shen · Xiaohao Cai · Yunfei Long · Imran Razzak · Guanming Chen · Shoaib Jameel

AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents

Arman Zharmagambetov · Chuan Guo · Ivan Evtimov · Maya Pavlova · Ruslan Salakhutdinov · Kamalika Chaudhuri

Semantic-KG: Using Knowledge Graphs to Construct Benchmarks for Measuring Semantic Similarity

Qiyao Wei · Edward R Morrell · Lea Goetz · Mihaela van der Schaar

Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals

Linda Zeng · Rithwik Gupta · Divij Motwani · Yi Zhang · Diji Yang

Machine Unlearning Doesn't Do What You Think: Lessons for Generative AI Policy and Research

A. Feder Cooper · Christopher Choquette-Choo · Miranda Bogen · Kevin Klyman · Matthew Jagielski · Katja Filippova · Ken Liu · Alex Chouldechova · Jamie Hayes · Yangsibo Huang · Eleni Triantafillou · Peter Kairouz · Nicole Mitchell · Niloofar Mireshghallah · Abigail Jacobs · James Grimmelmann · Vitaly Shmatikov · Christopher De Sa · I Shumailov · Andreas Terzis · Solon Barocas · Jennifer Wortman Vaughan · danah boyd · Yejin Choi · Sanmi Koyejo · Fernando Delgado · Percy Liang · Daniel Ho · Pamela Samuelson · Miles Brundage · David Bau · Seth Neel · Hanna Wallach · Amy Cyphert · Mark Lemley · Nicolas Papernot · Katherine Lee

A Generalized Binary Tree Mechanism for Private Approximation of All-Pair Shortest Distances

Zongrui Zou · Chenglin Fan · Michael Dinitz · Jingcheng Liu · Jalaj Upadhyay

Locally Optimal Private Sampling: Beyond the Global Minimax

Hrad Ghoukasian · Bonwoo Lee · Shahab Asoodeh

Continual Release Moment Estimation with Differential Privacy

Nikita Kalinin · Jalaj Upadhyay · Christoph Lampert

Convex Approximation of Two-Layer ReLU Networks for Hidden State Differential Privacy

Rob Romijnders · Antti Koskela

Practical Bayes-Optimal Membership Inference Attacks

Marcus Lassila · Johan Oestman · Khac-Hoang Ngo · Alexandre Graell i Amat

Can We Infer Confidential Properties of Training Data from LLMs?

Pengrun Huang · Chhavi Yadav · Kamalika Chaudhuri · Ruihan Wu

SPFL: Sequential updates with Parallel aggregation for Enhanced Federated Learning under Category and Domain Shifts

Haoyuan Liang · Shilei Cao · Li · Zhiyu Ye · Haohuan Fu · Juepeng Zheng

Geometric Imbalance in Semi-Supervised Node Classification

Liang Yan · Shengzhong Zhang · Bisheng Li · Menglin Yang · Chen Yang · Min Zhou · Weiyang Ding · Yutong Xie · zengfeng Huang

E2E-VGuard: Adversarial Prevention for Production LLM-based End-To-End Speech Synthesis

Zhisheng Zhang · Derui Wang · Yifan Mi · Zhiyong Wu · Jie Gao · Yuxin Cao · Kai Ye · Minhui Xue · Jie Hao

Scalable Fingerprinting of Large Language Models

Anshul Nasery · Jonathan Hayase · Creston Brooks · Peiyao Sheng · Himanshu Tyagi · Pramod Viswanath · Sewoong Oh

Abstract Rendering: Certified Rendering Under 3D Semantic Uncertainty

Chenxi Ji · Yangge Li · Xiangru Zhong · Huan Zhang · Sayan Mitra

BridgePure: Limited Protection Leakage Can Break Black-Box Data Protection

Yihan Wang · Yiwei Lu · Xiao-Shan Gao · Gautam Kamath · Yaoliang Yu

VideoGameQA-Bench: Evaluating Vision-Language Models for Video Game Quality Assurance

Mohammad Reza Taesiri · Abhijay Ghildyal · Saman Zadtootaghaj · Nabajeet Barman · Cor-Paul Bezemer

HeavyWater and SimplexWater: Distortion-free LLM Watermarks for Low-Entropy Distributions

Dor Tsur · Carol Long · Claudio Mayrink Verdun · Sajani Vithana · Hsiang Hsu · Richard Chen · haim permuter · Flavio Calmon

Blackbox Model Provenance via Palimpsestic Membership Inference

Rohith Kuditipudi · Jing Huang · Sally Zhu · Diyi Yang · Chris Potts · Percy Liang

RvLLM: LLM Runtime Verification with Domain Knowledge

Yedi Zhang · Sun Emma · Annabelle En · Jin Song Dong

DiffBreak: Is Diffusion-Based Purification Robust?

Andre Kassis · Urs Hengartner · Yaoliang Yu

AI Debate Aids Assessment of Controversial Claims

Salman Rahman · Sheriff Issaka · Ashima Suvarna · Genglin Liu · James Shiffer · Jaeyoung Lee · Md Rizwan Parvez · Hamid Palangi · Shi Feng · Nanyun Peng · Yejin Choi · Julian Michael · Liwei Jiang · Saadia Gabriel

Class conditional conformal prediction for multiple inputs by p-value aggregation

Jean-Baptiste Fermanian · Mohamed Hebiri · Joseph Salmon

Debate or Vote: Which Yields Better Decisions in Multi-Agent Large Language Models?

Hyeong Kyu Choi · Jerry Zhu · Sharon Li

Quantifying Statistical Significance of Deep Nearest Neighbor Anomaly Detection via Selective Inference

Mizuki Niihori · Shuichi Nishino · Teruyuki Katsuoka · Tomohiro Shiraishi · Kouichi Taji · Ichiro Takeuchi

LLM Unlearning via Neural Activation Redirection

William Shen · Xinchi Qiu · Meghdad Kurmanji · Alexandru-Andrei Iacob · Lorenzo Sani · Yihong Chen · Nicola Cancedda · Nicholas Lane

FALCON: An ML Framework for Fully Automated Layout-Constrained Analog Circuit Design

Asal Mehradfar · Xuzhe Zhao · Yilun Huang · Emir Ceyani · Yankai Yang · Shihao han · Hamidreza Aghasi · Salman Avestimehr

FlowRefiner: A Robust Traffic Classification Framework against Label Noise

Mingwei Zhan · Ruijie Zhao · Xianwen Deng · Zhi Xue · Qi Li · Zhuotao Liu · Guang Cheng · Ke Xu

VRAG-RL: Empower Vision-Perception-Based RAG for Visually Rich Information Understanding via Iterative Reasoning with Reinforcement Learning

Qiuchen Wang · Ruixue Ding · Yu Zeng · Zehui Chen · Lin Chen · Shihang Wang · Pengjun Xie · Fei Huang · Feng Zhao

MLZero: A Multi-Agent System for End-to-end Machine Learning Automation

Haoyang Fang · Boran Han · Nick Erickson · Xiyuan Zhang · Su Zhou · Anirudh Dagar · Jiani Zhang · Caner Turkmen · Tony Hu · Huzefa Rangwala · Ying Nian Wu · Yuyang (Bernie) Wang · George Karypis

MigGPT: Harnessing Large Language Models for Automated Migration of Out-of-Tree Linux Kernel Patches Across Versions

Pucheng Dang · Di Huang · Dong Li · Kang Chen · Yuanbo Wen · Qi Guo · Xing Hu

BeliefMapNav: 3D Voxel-Based Belief Map for Zero-Shot Object Navigation

Zibo Zhou · Yue Hu · Lingkai Zhang · Zonglin Li · Siheng Chen

IDOL: Meeting Diverse Distribution Shifts with Prior Physics for Tropical Cyclone Multi-Task Estimation

HantingYan Yan · Pan Mu · Shiqi Zhang · Yuchao Zhu · jinglin zhang · Cong Bai

SolidGeo: Measuring Multimodal Spatial Math Reasoning in Solid Geometry

Peijie Wang · Chao Yang · Zhong-Zhi Li · Fei yin · Dekang Ran · Mi Tian · Zhilong Ji · Jinfeng Bai · Cheng-lin Liu

MineAnyBuild: Benchmarking Spatial Planning for Open-world AI Agents

Ziming Wei · Bingqian Lin · Zijian Jiao · Yunshuang Nie · Liang Ma · Yuecheng Liu · Yuzheng Zhuang · Xiaodan Liang

PUO-Bench: A Panel Understanding and Operation Benchmark with A Privacy-Preserving Framework

Wei LIN · Yiwei Zhou · Junkai Zhang · Rui Shao · Zhiyuan Zhao · Junyu Gao · Antoni Chan · Xuelong Li

Machine Unlearning via Task Simplex Arithmetic

Junhao Dong · Hao Zhu · Yifei Zhang · Xinghua Qu · Yew Soon Ong · Piotr Koniusz

Fairshare Data Pricing via Data Valuation for Large Language Models

Luyang Zhang · Cathy Jiao · Beibei Li · Chenyan Xiong

CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring

Benjamin Arnav · Pablo Bernabeu-Perez · Nathan Helm-Burger · Timothy H. Kostolansky · Hannes Whittingham · Mary Phuong

TwinMarket: A Scalable Behavioral and Social Simulation for Financial Markets

Yuzhe YANG · Yifei Zhang · Minghao Wu · Kaidi Zhang · Yunmiao Zhang · Honghai Yu · Yan Hu · Benyou Wang

Transstratal Adversarial Attack: Compromising Multi-Layered Defenses in Text-to-Image Models

Chunlong Xie · Kangjie Chen · Shangwei Guo · Shudong Zhang · Tianwei Zhang · Tao Xiang

Position: Bridge the Gaps between Machine Unlearning and AI Regulation

Bill Marino · Meghdad Kurmanji · Nicholas Lane

BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editing

Jinsu Kim · Yunhun Nam · Minseon Kim · Sangpil Kim · Jongheon Jeong

Noise Injection Reveals Hidden Capabilities of Sandbagging Language Models

Cameron Tice · Philipp Kreer · Nathan Helm-Burger · Prithviraj Shahani · Fedor Ryzhenkov · Fabien Roger · Clement Neo · Jacob Haimes · Felix Hofstätter · Teun van der Weij

Graph-KV: Breaking Sequence via Injecting Structural Biases into Large Language Models

Haoyu Wang · Peihao Wang · Mufei Li · Shikun Liu · Siqi Miao · Zhangyang "Atlas" Wang · Pan Li

Fast-Slow Thinking GRPO for Large Vision-Language Model Reasoning

Wenyi Xiao · Leilei Gan

Towards Generalizable Multi-Policy Optimization with Self-Evolution for Job Scheduling

Inguk Choi · Woo-Jin Shin · Sang-Hyun Cho · Hyun-Jung Kim

Activation-Guided Consensus Merging for Large Language Models

Yuxuan Yao · Shuqi LIU · Zehua Liu · Qintong Li · Mingyang LIU · Xiongwei Han · Zhijiang Guo · Han Wu · Linqi Song

Each Complexity Deserves a Pruning Policy

Hanshi Wang · Yuhao Xu · Zekun Xu · Jin Gao · Yufan Liu · Weiming Hu · Ke Wang · Zhipeng Zhang

$\text{S}^2$Q-VDiT: Accurate Quantized Video Diffusion Transformer with Salient Data and Sparse Token Distillation

Weilun Feng · Haotong Qin · Chuanguang Yang · Xiangqi Li · Han Yang · Yuqi Li · Zhulin An · Libo Huang · Michele Magno · Yongjun Xu

Deep Compositional Phase Diffusion for Long Motion Sequence Generation

Ho Yin Au · Jie Chen · Junkun Jiang · Jingyu Xiang

Teaching Language Models to Reason with Tools

Chengpeng Li · Zhengyang Tang · Ziniu Li · Mingfeng Xue · Keqin Bao · Tian Ding · Ruoyu Sun · Benyou Wang · Xiang Wang · Junyang Lin · Dayiheng Liu

Lessons Learned: A Multi-Agent Framework for Code LLMs to Learn and Improve

Yuanzhe Liu · Ryan Deng · Tim Kaler · Xuhao Chen · Charles Leiserson · Yao Ma · Jie Chen

Online Segment Any 3D Thing as Instance Tracking

Hanshi Wang · Cai Zijian · Jin Gao · Yiwei Zhang · Weiming Hu · Ke Wang · Zhipeng Zhang

TITAN: A Trajectory-Informed Technique for Adaptive Parameter Freezing in Large-Scale VQE

Yifeng Peng · Xinyi Li · Samuel Yen-Chi Chen · Kaining Zhang · Zhiding Liang · Ying Wang · Yuxuan Du

Bridging Equivariant GNNs and Spherical CNNs for Structured Physical Domains

Colin Kohler · Purvik Patel · Nathan Vaska · Justin Goodwin · Matthew Jones · Robert Platt · Rajmonda Caceres · Robin Walters

The Catechol Benchmark: Time-series Solvent Selection Data for Few-shot Machine Learning

Toby Boyne · Juan Campos · Rebecca Langdon · Jixiang Qing · Yilin Xie · Shiqiang Zhang · Calvin Tsay · Ruth Misener · Daniel Davies · Kim Jelfs · Sarah Boyall · Thomas Dixon · Linden Schrecker · Jose Pablo Folch

MolVision: Molecular Property Prediction with Vision Language Models

Deepan Adak · Yogesh Rawat · Shruti Vyas

RoFt-Mol: Benchmarking Robust Fine-tuning with Molecular Graph Foundation Models

Shikun Liu · Deyu Zou · Nima Shoghi · Victor Fung · Kai Liu · Pan Li

All that structure matches does not glitter

Maya Martirossyan · Thomas Egg · Philipp Höllmer · George Karypis · Mark Transtrum · Adrian Roitberg · Mingjie Liu · Richard Hennig · Ellad Tadmor · Stefano Martiniani

A Dataset for Distilling Knowledge Priors from Literature for Therapeutic Design

Haydn Jones · Natalie Maus · Josh magnus Ludan · Maggie Huan · Jiaming Liang · Marcelo Der Torossian Torres · Jiatao Liang · Zachary Ives · Yoseph Barash · Cesar de la Fuente-Nunez · Jacob Gardner · Mark Yatskar

Revisiting Orbital Minimization Method for Neural Operator Decomposition

Jongha (Jon) Ryu · Samuel Zhou · Gregory Wornell

GreenHyperSpectra: A multi-source hyperspectral dataset for global vegetation trait prediction

Eya Cherif · Arthur Ouaknine · Luke Brown · Phuong Dao · Kyle Kovach · Bing Lu · Daniel Mederer · Hannes Feilhauer · Teja Kattenborn · David Rolnick

CarbonGlobe: A Global-Scale, Multi-Decade Dataset and Benchmark for Carbon Forecasting in Forest Ecosystems

Zhihao Wang · Lei Ma · George Hurtt · Xiaowei Jia · Yanhua Li · Ruohan Li · Zhili Li · Shuo Xu · Yiqun Xie

Scaling Unlocks Broader Generation and Deeper Functional Understanding of Proteins

Aadyot Bhatnagar · Sarthak Jain · Joel Beazer · Samuel Curran · Alexander Hoffnagle · Kyle Ching · Michael Martyn · Stephen Nayfach · Jeffrey Ruffolo · Ali Madani

Prior-Guided Flow Matching for Target-Aware Molecule Design with Learnable Atom Number

Jingyuan Zhou · Hao Qian · Shikui Tu · Lei Xu

Straight-Line Diffusion Model for Efficient 3D Molecular Generation

Yuyan Ni · Shikun Feng · Haohan Chi · Bowen Zheng · Huan-ang Gao · Wei-Ying Ma · Zhi-Ming Ma · Yanyan Lan

ProSpero: Active Learning for Robust Protein Design Beyond Wild-Type Neighborhoods

Michal Kmicikiewicz · Vincent Fortuin · Ewa Szczurek

Learning 3D Anisotropic Noise Distributions Improves Molecular Force Fields

Xixian Liu · Rui Jiao · ZHIYUAN LIU · Yurou Liu · Yang Liu · Ziheng Lu · Wenbing Huang · Yang Zhang · Yixin Cao

DynaPhArM: Adaptive and Physics-Constrained Modeling for Target-Drug Complexes with Drug-Specific Adaptations

Diya Zhang · Mengwei Sun · Xingdan Wang · Cheng Liang · Qiaozhen Meng · Shiqiang Ma · Fei Guo

FlashMD: long-stride, universal prediction of molecular dynamics

Filippo Bigi · Sanggyu Chong · Agustinus Kristiadi · Michele Ceriotti

Simultaneous Modeling of Protein Conformation and Dynamics via Autoregression

Yuning Shen · Lihao Wang · Huizhuo Yuan · Yan Wang · Bangji Yang · Quanquan Gu

RETRO SYNFLOW: Discrete Flow-Matching for Accurate and Diverse Single-Step Retrosynthesis

Robin Yadav · Qi Yan · Guy Wolf · Joey Bose · Renjie Liao

Enhancing Bioactivity Prediction via Spatial Emptiness Representation of Protein-ligand Complex and Union of Multiple Pockets

Zhiyuan Zhou · Yueming Yin · Yiming Yang · Yuguang Mu · Hoi-Yeung Li · Adams Wai Kin Kong

Implicit Generative Property Enhancer

Pedro O. Pinheiro · Pan Kessel · Aya Ismail · Sai Pooja Mahajan · Kyunghyun Cho · Saeed Saremi · Nataša Tagasovska

Protein Inverse Folding From Structure Feedback

Junde Xu · Zijun Gao · Xinyi Zhou · hujie · Xingyi Cheng · Le Song · Guangyong Chen · Pheng-Ann Heng · Jiezhong Qiu

Space Group Equivariant Crystal Diffusion

Rees Chang · Angela Pak · Alex Guerra · Ni Zhan · Nick Richardson · Elif Ertekin · Ryan Adams

Accurately Predicting Protein Mutational Effects via a Hierarchical Many-Body Attention Network

Dahao Xu · Jiahua Rao · Mingming Zhu · Jixian Zhang · Wei Lu · Shuangjia Zheng · Yuedong Yang

DAWP: A framework for global observation forecasting via Data Assimilation and Weather Prediction in satellite observation space

Junchao Gong · Jingyi Xu · Ben Fei · Fenghua Ling · Wenlong Zhang · Kun Chen · Wanghan Xu · Weidong Yang · Xiaokang Yang · LEI BAI

RiverMamba: A State Space Model for Global River Discharge and Flood Forecasting

Mohamad Hakam Shams Eddin · Yikui Zhang · Stefan Kollet · Jürgen Gall

RadarQA: Multi-modal Quality Analysis of Weather Radar Forecasts

Xuming He · Zhiyuan You · Junchao Gong · Couhua Liu · Xiaoyu Yue · Peiqin Zhuang · Wenlong Zhang · LEI BAI

CellVerse: Do Large Language Models Really Understand Cell Biology?

Fan Zhang · Tianyu Liu · Zhihong Zhu · Hao Wu · Haixin Wang · Donghao Zhou · Yefeng Zheng · Kun Wang · Xian Wu · Pheng-Ann Heng

PerturBench: Benchmarking Machine Learning Models for Cellular Perturbation Analysis

Yan Wu · Esther Wershof · Sebastian Schmon · Marcel Nassar · Błażej Osiński · Ridvan Eksi · Zichao Yan · Rory Stark · Kun Zhang · Thore Graepel

Generative Distribution Embeddings

Nic Fishman · Gokul Gowri · Peng Yin · Jonathan Gootenberg · Omar Abudayyeh

CPathAgent: An Agent-based Foundation Model for Interpretable High-Resolution Pathology Image Analysis Mimicking Pathologists' Diagnostic Logic

YUXUAN SUN · Yixuan Si · Chenglu Zhu · Kai Zhang · Zhongyi Shui · Bowen Ding · Tao Lin · Lin Yang

scMRDR: A scalable and flexible framework for unpaired single-cell multi-omics data integration

Jianle Sun · Chaoqi Liang · Ran Wei · Peng Zheng · LEI BAI · Wanli Ouyang · Hongliang Yan · Peng Ye

Prot2Text-V2: Protein Function Prediction with Multimodal Contrastive Alignment

Xiao Fei · Michail Chatzianastasis · Sarah Carneiro · Hadi Abdine · Lawrence Petalidis · Michalis Vazirgiannis

MedAgentBoard: Benchmarking Multi-Agent Collaboration with Conventional Methods for Diverse Medical Tasks

Yinghao Zhu · Ziyi He · Haoran Hu · Xiaochen Zheng · Xichen Zhang · Wang · Junyi Gao · Liantao Ma · Lequan Yu

Multimodal Disease Progression Modeling via Spatiotemporal Disentanglement and Multiscale Alignment

Chen Liu · Wenfang Yao · Kejing Yin · William K. Cheung · Jing Qin

MoodAngels: A Retrieval-augmented Multi-agent Framework for Psychiatry Diagnosis

Mengxi Xiao · Ben Liu · He Li · Jimin Huang · Qianqian Xie · Xiaofen Zong · Mang Ye · Min Peng

Orochi: Versatile Biomedical Image Processor

Gaole Dai · Chenghao Zhou · Yu Zhou · Rongyu Zhang · Yuan Zhang · Chengkai Hou · Tiejun Huang · Jianxu Chen · Shanghang Zhang

Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning

Yuxuan Zhou · Xien Liu · Xiao Zhang · Chen Ning · Shijin Wang · Guoping Hu · Ji Wu

Magical: Medical Lay Language Generation via Semantic Invariance and Layperson-tailored Adaptation

Weibin Liao · Tianlong Wang · Yinghao Zhu · Yasha Wang · Junyi Gao · Liantao Ma

Embracing Trustworthy Brain-Agent Collaboration as Paradigm Extension for Intelligent Assistive Technologies

Yankai Chen · Xinni Zhang · Yifei Zhang · Yangning Li · Henry Zou · Chunyu Miao · Weizhi Zhang · Steve (Xue) Liu · Philip S Yu

System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts

Xiaoqiang Wang · Suyuchen Wang · Yun Zhu · Bang Liu

Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning

Yeongbin Seo · Dongha Lee · Jaehyung Kim · Jinyoung Yeo

Neural Correlates of Serial Dependence: Synaptic Short-term Plasticity Orchestrates Repulsion and Attraction

Xiuning Zhang · Xincheng Lu · Nihong Chen · Yuanyuan Mi

Audio Flamingo 3: Advancing Audio Intelligence with Fully Open Large Audio Language Models

Sreyan Ghosh · Arushi Goel · Jaehyeon Kim · Sonal Kumar · Zhifeng Kong · Sang-gil Lee · Chao-Han Yang · Ramani Duraiswami · Dinesh Manocha · Rafael Valle · Bryan Catanzaro

Lua-LLM: Learning Unstructured-Sparsity Allocation for Large Language Models

Mingge Lu · Jingwei Sun · Junqing Lin · Zechun Zhou · Guangzhong Sun

Unveiling the Learning Mind of Language Models: A Cognitive Framework and Empirical Study

Zhengyu Hu · Jianxun Lian · Zheyuan Xiao · Seraphina Zhang · Tianfu Wang · Nicholas Jing Yuan · Xing Xie · Hui Xiong

Lifelong Safety Alignment for Language Models

Haoyu Wang · Yifei Zhao · Zeyu Qin · Chao Du · Min Lin · Xueqian Wang · Tianyu Pang

AVCD: Mitigating Hallucinations in Audio-Visual Large Language Models through Contrastive Decoding

Chaeyoung Jung · Youngjoon Jang · Joon Son Chung

Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models

Sophia Han · Howard Dai · Stephen Xia · Grant Zhang · Chen Liu · Lichang Chen · Hoang H Nguyen · Hongyuan Mei · Jiayuan Mao · R. Thomas McCoy

GRIP: A Graph-Based Reasoning Instruction Producer

Jiankang Wang · Jianjun Xu · Xiaorui Wang · Yuxin Wang · Mengting Xing · Shancheng Fang · Hongtao Xie

CoVoMix2: Advancing Zero-Shot Dialogue Generation with Fully Non-Autoregressive Flow Matching

Leying Zhang · Yao Qian · Xiaofei Wang · Manthan Thakker · Dongmei Wang · Jianwei Yu · Haibin Wu · Yuxuan Hu · Jinyu Li · Yanmin Qian · sheng zhao

L-MTP: Leap Multi-Token Prediction Beyond Adjacent Context for Large Language Models

Xiaohao Liu · Xiaobo Xia · Weixiang Zhao · Manyi Zhang · Xianzhi Yu · Xiu Su · Shuo Yang · See-Kiong Ng · Tat-Seng Chua

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

Amartya Chakraborty · Paresh Dashore · Nadia Bathaee · Anmol Jain · Anirban Das · Shi-Xiong Zhang · Sambit Sahu · Milind Naphade · Genta Winata

MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations

Wenxiang Guo · Changhao Pan · Zhiyuan Zhu · Xintong Hu · Yu Zhang · Li Tang · Rui Yang · Han Wang · Zongbao Zhang · Yuhan Wang · Yixuan Chen · Hankun Xu · Ke Xu · PengFei Fan · ZheTao Chen · Yanhao Yu · Qiange Huang · Fei Wu · Zhou Zhao

UniEdit: A Unified Knowledge Editing Benchmark for Large Language Models

Qizhou Chen · Dakan Wang · Taolin Zhang · Zaoming Yan · Chengsong You · Chengyu Wang · Xiaofeng He

HawkBench: Investigating Resilience of RAG Methods on Stratified Information-Seeking Tasks

Hongjin Qian · Zheng Liu · Chao Gao · Yankai Wang · Defu Lian · Zhicheng Dou

SwitchLingua: The First Large-Scale Multilingual and Multi-Ethnic Code-Switching Dataset

Peng Xie · Xingyuan Liu · Yequan Bie · Tsz Wai Chan · Yangqiu Song · Yang Wang · Hao CHEN · Kani Chen

Filter Like You Test: Data-Driven Data Filtering for CLIP Pretraining

Mikey Shechter · Yair Carmon

On Evaluating LLM Alignment by Evaluating LLMs as Judges

Yixin Liu · Pengfei Liu · Arman Cohan

Generalizing Experience for Language Agents with Hierarchical MetaFlows

Shengda Fan · Xin Cong · Zhong Zhang · Yuepeng Fu · Yesai Wu · Hao Wang · Xinyu Zhang · Enrui Hu · Yankai Lin

Skrull: Towards Efficient Long Context Fine-tuning through Dynamic Data Scheduling

Hongtao Xu · Wenting Shen · Yuanxin Wei · Ang Wang · Guo Runfan · Tianxing Wang · Yong Li · Mingzhen Li · Weile Jia

Multi-agent KTO: Enhancing Strategic Interactions of Large Language Model in Language Game

Rong Ye · Yongxin Zhang · yikai zhang · Haoyu Kuang · peng sun · zhongyu wei

Broken Tokens? Your Language Model can Secretly Handle Non-Canonical Tokenizations

Brian Zheng · Alisa Liu · Orevaoghene Ahia · Jonathan Hayase · Yejin Choi · Noah Smith

Program Synthesis via Test-Time Transduction

Kang-il Lee · Jahyun Koo · Seunghyun Yoon · Minbeom Kim · Hyukhun Koh · Dongryeol Lee · Kyomin Jung

DeepASA: An Object-Oriented Multi-Purpose Network for Auditory Scene Analysis

Dongheon Lee · Younghoo Kwon · Jung-Woo Choi

Edit Less, Achieve More: Dynamic Sparse Neuron Masking for Lifelong Knowledge Editing in LLMs

Jinzhe Liu · Junshu Sun · Shufan Shen · Chenxue Yang · Shuhui Wang

Chain-of-Retrieval Augmented Generation

Liang Wang · Haonan Chen · Nan Yang · Xiaolong Huang · Zhicheng Dou · Furu Wei

Correlation Dimension of Autoregressive Large Language Models

Xin Du · Kumiko Tanaka-Ishii

ConceptScope: Characterizing Dataset Bias via Disentangled Visual Concepts

Jinho Choi · Hyesu Lim · Steffen Schneider · Jaegul Choo

AutoJudge: Judge Decoding Without Manual Annotation

Roman Garipov · Fedor Velikonivtsev · Ivan Ermakov · Ruslan Svirschevski · Vage Egiazarian · Max Ryabinin

SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search

Dong Li · Xujiang Zhao · Linlin Yu · Yanchi Liu · Wei Cheng · Zhengzhang Chen · Zhong Chen · Feng Chen · Chen Zhao · Haifeng Chen

ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing

Huadai Liu · Kaicheng Luo · Jialei Wang · Wen Wang · Qian Chen · Zhou Zhao · Wei Xue

Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents

Qizheng Zhang · Michael Wornow · Kunle Olukotun

KORGym: A Dynamic Game Platform for LLM Reasoning Evaluation

Jiajun Shi · Jian Yang · Jiaheng Liu · Xingyuan Bu · Jiangjie Chen · Junting Zhou · Kaijing Ma · Zhoufutu Wen · Bingli Wang · Yancheng He · Liang Song · Hualei Zhu · Shilong Li · Xingjian Wang · Wei Zhang · Ruibin Yuan · Yifan Yao · Wenjun Yang · Yunli Wang · Siyuan Fang · Siyu Yuan · Qianyu He · Robert Tang · Yingshui Tan · Wangchunshu Zhou · ZHAO-XIANG ZHANG · Zhoujun Li · Wenhao Huang · Ge Zhang

MemSim: A Bayesian Simulator for Evaluating Memory of LLM-based Personal Assistants

Zeyu Zhang · Quanyu Dai · Luyu Chen · Zeren Jiang · Rui Li · Jieming Zhu · Xu Chen · Yi Xie · Zhenhua Dong · Ji-Rong Wen

Document Summarization with Conformal Importance Guarantees

Bruce Kuwahara · Chen-Yuan Lin · Xiao Shi Huang · Kin Kwan Leung · Jullian Yapeter · Ilya Stanevich · Felipe Perez · Jesse Cresswell

Knowledge Starts with Practice: Knowledge-Aware Exercise Generative Recommendation with Adaptive Multi-Agent Cooperation

Yangtao Zhou · Hua Chu · chen · Ziwen Wang · Jiacheng Liu · Jianan Li · Yueying Feng · Xiangming Li · Zihan Han · Qingshan Li

SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications

Jinyang Li · Xiaolong Li · Ge Qu · Per Jacobsson · Bowen Qin · Binyuan Hui · Shuzheng Si · Nan Huo · Xiaohan Xu · Yue Zhang · Ziwei Tang · Yuanshuai Li · Florensia Widjaja · Xintong Zhu · Feige Zhou · Yongfeng Huang · Yannis Papakonstantinou · Fatma Ozcan · Ma Chenhao · Reynold Cheng

PARROT: A Benchmark for Evaluating LLMs in Cross-System SQL Translation

Wei Zhou · Guoliang Li · Haoyu Wang · Yuxing Han · Xufei Wu · Fan Wu · Xuanhe Zhou

Dataset Distillation for Pre-Trained Self-Supervised Vision Models

George Cazenavette · Antonio Torralba · Vincent Sitzmann

FairDICE: Fairness-Driven Offline Multi-Objective Reinforcement Learning

Woosung Kim · Jinho Lee · Jongmin Lee · Byung-Jun Lee

Offline Actor-Critic for Average Reward MDPs

William Powell · Jeongyeol Kwon · Qiaomin Xie · Hanbaek Lyu

Uncertainty-Guided Exploration for Efficient AlphaZero Training

Scott Cheng · Meng-Yu Tsai · Ding-Yong Hong · Mahmut T Kandemir

AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning

Yang Chen · Zhuolin Yang · Zihan Liu · Chankyu Lee · Peng Xu · Mohammad Shoeybi · Bryan Catanzaro · Wei Ping

A-Mem: Agentic Memory for LLM Agents

Wujiang Xu · Zujie Liang · Kai Mei · Hang Gao · Juntao Tan · Yongfeng Zhang

Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference

Eray Erturk · Maryam Shanechi

S$^2$NN: Sub-bit Spiking Neural Networks

Wenjie Wei · Malu Zhang · Jieyuan (Eric) Zhang · Ammar Belatreche · Shuai Wang · Yimeng Shan · Hanwen Liu · Honglin Cao · Guoqing Wang · Yang Yang · Haizhou Li

Efficient Allocation of Working Memory Resource for Utility Maximization in Humans and Recurrent Neural Networks

Qingqing Yang · Hsin-Hung Li

What Moves the Eyes: Doubling Mechanistic Model Performance Using Deep Networks to Discover and Test Cognitive Hypotheses

Federico D'Agostino · Lisa Schwetlick · Matthias Bethge · Matthias Kümmerer

Hierarchical Frequency Tagging Probe (HFTP): A Unified Approach to Investigate Syntactic Structure Representations in Large Language Models and the Human Brain

Jingmin An · Yilong Song · Ruolin Yang · Nai Ding · Lingxi Lu · Yuxuan Wang · Wei Wang · Chu Zhuang · Qian Wang · Fang Fang

SynBrain: Enhancing Visual-to-fMRI Synthesis via Probabilistic Representation Learning

Weijian Mai · Jiamin Wu · Yu Zhu · Zhouheng Yao · Dongzhan Zhou · Andrew Luo · Qihao Zheng · Wanli Ouyang · Chunfeng Song

Shaping Sequence Attractor Schema in Recurrent Neural Networks

Zhikun Chu · Bo Ho · xiaolong zou · Yuanyuan Mi

Learning Dynamics of RNNs in Closed-Loop Environments

Yoav Ger · Omri Barak

Identifying multi-compartment Hodgkin-Huxley models with high-density extracellular voltage recordings

Ian Christopher Tanoh · Michael Deistler · Jakob H Macke · Scott Linderman

Slow Transition to Low-Dimensional Chaos in Heavy-Tailed Recurrent Neural Networks

Eva Xie · Stefan Mihalas · Łukasz Kuśmierz

Mind the GAP! The Challenges of Scale in Pixel-based Deep Reinforcement Learning

Ghada Sokar · Pablo Samuel Castro

ZEBRA: Towards Zero-Shot Cross-Subject Generalization for Universal Brain Visual Decoding

Haonan Wang · Jingyu Lu · Hongrui Li · Xiaomeng Li

Modelling the control of offline processing with reinforcement learning

Eleanor Spens · Neil Burgess · Tim Behrens

Decomposing motor units through elimination for real-time intention driven assistive neurotechnology

Nicholas Tacca · Bryan Schlink · Jackson Levine · Mary K. Heimann · Collin Dunlap · Sam Colachis · Philip Putnam · Matthew Zeglen · Daniel Brobston · Austin Bollinger · José Pons · Lauren Wengerd · Eric Meyers · David Friedenberg

Meta-Learning an In-Context Transformer Model of Human Higher Visual Cortex

Muquan Yu · Mu Nan · Hossein Adeli · Jacob Prince · John A. Pyles · Leila Wehbe · Maggie Henderson · Michael Tarr · Andrew Luo

In Silico Mapping of Visual Categorical Selectivity Across the Whole Brain

Ethan Hwang · Hossein Adeli · Wenxuan Guo · Andrew Luo · Nikolaus Kriegeskorte

Memory by accident: a theory of learning as a byproduct of network stabilization

Basile Confavreux · William Dorrell · Nishil Patel · Andrew Saxe

No Experts, No Problem: Avoidance Learning from Bad Demonstrations

Huy Hoang · Tien Mai · Pradeep Varakantham

IOSTOM: Offline Imitation Learning from Observations via State Transition Occupancy Matching

Quang Anh Pham · Janaka Brahmanage · Tien Mai · Akshat Kumar

Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards

Charles Arnal · Gaëtan Narozniak · Vivien Cabannes · Yunhao Tang · Julia Kempe · Remi Munos

A Temporal Difference Method for Stochastic Continuous Dynamics

Haruki Settai · Naoya Takeishi · Takehisa Yairi

Dyn-O: Building Structured World Models with Object-Centric Representations

Zizhao Wang · Kaixin Wang · Li Zhao · Peter Stone · Jiang Bian

Large Language Models Think Too Fast To Explore Effectively

Lan Pan · Hanbo Xie · Robert Wilson

BrainEC-LLM: Brain Effective Connectivity Estimation by Multiscale Mixing LLM

Wen Xiong · Junzhong Ji · Jinduo Liu

Large Language Models as Model Organisms for Human Associative Learning

Camila Kolling · Vy Vo · Mariya Toneva

AutoToM: Scaling Model-based Mental Inference via Automated Agent Modeling

Zhining Zhang · Chuanyang Jin · Mung Yao Jia · Shunchi Zhang · Tianmin Shu

Interpretable Next-token Prediction via the Generalized Induction Head

Eunji Kim · Sriya Mantena · Weiwei Yang · Chandan Singh · Sungroh Yoon · Jianfeng Gao

DAAC: Discrepancy-Aware Adaptive Contrastive Learning for Medical Time series

Yifan WANG · Hongfeng Ai · ruiqi li · Maowei Jiang · Quangao Liu · Jiahua Dong · ruiyuan kang · Alan Liang · Zihang Wang · ruikai liu · Cheng Jiang · Chenzhong Li

Brain Harmony: A Multimodal Foundation Model Unifying Morphology and Function into 1D Tokens

Zijian Dong · Ruilin Li · Joanna Chong · Niousha Dehestani · Yinghui Teng · Yi Lin · Zhizhou Li · Yichi Zhang · Yapei Xie · Leon Ooi · B.T. Yeo · Juan Helen Zhou

A Generalist Intracortical Motor Decoder

Joel Ye · Fabio Rizzoglio · Xuan Ma · Adam Smoulder · Hongwei Mao · Gary Blumenthal · William Hockeimer · Nicolas Kunigk · Dalton Moore · Patrick Marino · Raeed Chowdhury · J. Patrick Mayo · Aaron Batista · Steven Chase · Michael Boninger · Charles Greenspon · Andrew B Schwartz · Nicholas Hatsopoulos · Lee Miller · Kristofer Bouchard · Jennifer Collinger · Leila Wehbe · Robert Gaunt

PHYBench: Holistic Evaluation of Physical Perception and Reasoning in Large Language Models

Shi Qiu · Shaoyang Guo · Zhuo-Yang Song · Yunbo Sun · Zeyu Cai · Jiashen Wei · Tianyu Luo · Yixuan Yin · Zhang Haoxu · Yi Hu · Chenyang Wang · Chencheng Tang · Haoling Chang · Qi Liu · Ziheng Zhou · Tianyu Zhang · Jingtian Zhang · Zhangyi Liu · Minghao Li · Yuku Zhang · Boxuan Jing · Xianqi Yin · Yutong Ren · Zizhuo Fu · Jiaming Ji · Weike Wang · Xudong Tian · Anqi Lv · Laifu Man · Jianxiang Li · Feiyu Tao · Qihua Sun · Zhou Liang · Yushu Mu · Zhongxuan Li · Jing-Jun Zhang · Shutao Zhang · Xiaotian Li · Xingqi Xia · Jiawei Lin · Zheyu Shen · Jiahang Chen · Qiuhao Xiong · Binran Wang · Fengyuan Wang · Niziyang · Bohan Zhang · Fan Cui · shaochangkun · Qing-Hong Cao · Ming-xing Luo · Muhan Zhang · Hua Xing Zhu

Improving Energy Natural Gradient Descent through Woodbury, Momentum, and Randomization

Andrés Guzmán-Cordero · Felix Dangel · Gil Goldshlager · Marius Zeinhofer

Neural Tangent Knowledge Distillation for Optical Convolutional Networks

Jinlin Xiang · Minho Choi · Yubo Zhang · Zhihao Zhou · Arka Majumdar · Eli Shlizerman

Hierarchical Implicit Neural Emulators

Ruoxi Jiang · Xiao Zhang · Karan Jakhar · Peter Y. Lu · Pedram Hassanzadeh · Michael Maire · Rebecca Willett

UEPI: Universal Energy-Behavior-Preserving Integrators for Energy Conservative/Dissipative Differential Equations

Elena Celledoni · Brynjulf Owren · Chong Shen · Baige Xu · Takaharu Yaguchi

Predicting partially observable dynamical systems via diffusion models with a multiscale inference scheme

Rudy Morel · Francesco Ramunno · Jeff Shen · Alberto Bietti · Kyunghyun Cho · Miles Cranmer · Siavash Golkar · OLEXANDR GUGNIN · Geraud Krawezik · Tanya Marwah · Michael McCabe · Lucas Meyer · Payel Mukhopadhyay · Ruben Ohana · Liam Parker · Helen Qu · François Rozet · K.D. Leka · Francois Lanusse · David Fouhey · Shirley Ho

PDEfuncta: Spectrally-Aware Neural Representation for PDE Solution Modeling

Minju Jo · Woojin Cho · Uvini Balasuriya Mudiyanselage · Seungjun Lee · Noseong Park · Kookjin Lee

Mixture-of-Experts Operator Transformer for Large-Scale PDE Pre-Training

Hong Wang · Haiyang Xin · Jie Wang · Xuanze Yang · Fei Zha · huanshuo dong · Yan Jiang

DynaGuide: Steering Diffusion Polices with Active Dynamic Guidance

Maximilian Du · Shuran Song

Scaffolding Dexterous Manipulation with Vision-Language Models

Vincent de Bakker · Joey Hejna · Tyler Lum · Onur Celik · Aleksandar Taranovic · Denis Blessing · Gerhard Neumann · Jeannette Bohg · Dorsa Sadigh

CAML: Collaborative Auxiliary Modality Learning for Multi-Agent Systems

Rui Liu · Yu Shen · Peng Gao · Pratap Tokekar · Ming C. Lin

SDTagNet: Leveraging Text-Annotated Navigation Maps for Online HD Map Construction

Fabian Immel · Jan-Hendrik Pauls · Richard Schwarzkopf · Frank Bieder · Jonas Merkert · Christoph Stiller

KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills

Weiji Xie · Jinrui Han · Jiakun Zheng · Huanyu Li · Xinzhe Liu · Jiyuan Shi · Weinan Zhang · Chenjia Bai · Xuelong Li

Self-Improving Embodied Foundation Models

Seyed Kamyar Seyed Ghasemipour · Ayzaan Wahid · Jonathan Tompson · Pannag Sanketi · Igor Mordatch

Tree-Guided Diffusion Planner

Hyeonseong Jeon · Cheolhong Min · Jaesik Park

Raw2Drive: Reinforcement Learning with Aligned World Models for End-to-End Autonomous Driving (in CARLA v2)

Zhenjie Yang · Xiaosong Jia · Qifeng Li · Xue Yang · Maoqing Yao · Junchi Yan

TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving

Yanping Fu · Xinyuan Liu · Tianyu Li · Yike Ma · Yucheng Zhang · Feng Dai

Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning

Jiyuan Shi · Xinzhe Liu · Dewei Wang · ouyang lu · Sören Schwertfeger · Chi Zhang · Fuchun Sun · Chenjia Bai · Xuelong Li

VIKI‑R: Coordinating Embodied Multi-Agent Cooperation via Reinforcement Learning

Li Kang · Xiufeng Song · Heng Zhou · Yiran Qin · Jie Yang · Xiaohong Liu · Philip Torr · LEI BAI · Zhenfei Yin

Lost in Latent Space: An Empirical Study of Latent Diffusion Models for Physics Emulation

François Rozet · Ruben Ohana · Michael McCabe · Gilles Louppe · Francois Lanusse · Shirley Ho

A Plug-and-Play Query Synthesis Active Learning Framework for Neural PDE Solvers

Zhiyuan Wang · Jinwoo Go · Byung-Jun Yoon · Nathan Urban · Xiaoning Qian

Latent Mixture of Symmetries for Sample-Efficient Dynamic Learning

Haoran Li · CHENHAN XIAO · Muhao Guo · Yang Weng

Physics-informed machine learning with domain decomposition and global dynamics for three-dimensional intersecting flows

Leslie Hwang

Stable Port-Hamiltonian Neural Networks

Fabian J. Roth · Dominik K. Klein · Maximilian Kannapinn · Jan Peters · Oliver Weeger

EddyFormer: Accelerated Neural Simulations of Three-Dimensional Turbulence at Scale

Yiheng Du · Aditi Krishnapriyan

RIGNO: A Graph-based Framework For Robust And Accurate Operator Learning For PDEs On Arbitrary Domains

Sepehr Mousavi · Shizheng Wen · Levi Lingsch · Maximilian Herde · Bogdan Raonic · Siddhartha Mishra

From Experts to a Generalist: Toward General Whole-Body Control for Humanoid Robots

Yuxuan Wang · Ming Yang · Gang Ding · Yu Zhang · Weishuai Zeng · Xinrun Xu · Haobin Jiang · Zongqing Lu

DexGarmentLab: Dexterous Garment Manipulation Environment with Generalizable Policy

Yuran Wang · Ruihai Wu · Yue Chen · Jiarui Wang · Jiaqi Liang · Ziyu Zhu · Haoran Geng · Jitendra Malik · Pieter Abbeel · Hao Dong

DriveDPO: Policy Learning via Safety DPO For End-to-End Autonomous Driving

Shuyao Shang · Yuntao Chen · Yuqi Wang · Yingyan Li · ZHAO-XIANG ZHANG

BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models

Peiyan Li · Yixiang Chen · Hongtao Wu · Xiao Ma · Xiangnan Wu · Yan Huang · Liang Wang · Tao Kong · Tieniu Tan

World-aware Planning Narratives Enhance Large Vision-Language Model Planner

Junhao Shi · Zhaoye Fei · Siyin Wang · Qipeng Guo · Jingjing Gong · Xipeng Qiu

URDF-Anything: Constructing Articulated Objects with 3D Multimodal Language Model

Zhe Li · Xiang Bai · Jieyu Zhang · Zhuangzhe Wu · Che Xu · Ying Li · Chengkai Hou · Shanghang Zhang

Exploring the Limits of Vision-Language-Action Manipulation in Cross-task Generalization

Jiaming Zhou · Ke Ye · Jiayi Liu · Teli Ma · Zifan Wang · Ronghe QIU · Kun-Yu Lin · Zhilin Zhao · Junwei Liang

EnerVerse: Envisioning Embodied Future Space for Robotics Manipulation

Siyuan Huang · Liliang Chen · Pengfei Zhou · Shengcong Chen · Yue Liao · Zhengkai Jiang · Yue Hu · Peng Gao · Hongsheng Li · Maoqing Yao · Guanghui Ren

BadVLA: Towards Backdoor Attacks on Vision-Language-Action Models via Objective-Decoupled Optimization

Xueyang Zhou · Guiyao Tie · Guowen Zhang · Hecheng Wang · Pan Zhou · Lichao Sun

Generalizable Domain Adaptation for Sim-and-Real Policy Co-Training

Shuo Cheng · Liqian Ma · Zhenyang Chen · Ajay Mandlekar · Caelan Garrett · Danfei Xu

TraffiDent: A Dataset for Understanding the Interplay Between Traffic Dynamics and Incidents

Xiaochuan Gou · Ziyue Li · Tian Lan · Junpeng Lin · zhishuai Li · Bingyu Zhao · Chen Zhang · Di Wang · Xiangliang Zhang

Benchmarking Spatiotemporal Reasoning in LLMs and Reasoning Models: Capabilities and Challenges

Pengrui Quan · Brian Wang · Kang Yang · Liying Han · Mani Srivastava

RHYTHM: Reasoning with Hierarchical Temporal Tokenization for Human Mobility

Haoyu He · Haozheng Luo · Yan Chen · Qi Wang

Forging Time Series with Language: A Large Language Model Approach to Synthetic Data Generation

Cécile Rousseau · Tobia Boschi · Giandomenico Cornacchia · Dhaval Salwala · Alessandra Pascale · Juan Moreno

Distilled Decoding 2: One-step Sampling of Image Auto-regressive Models with Conditional Score Distillation

Enshu Liu · Qian Chen · Xuefei Ning · Shengen Yan · Guohao Dai · Zinan Lin · Yu Wang

TRACE: Grounding Time Series in Context for Multimodal Embedding and Retrieval

Jialin Chen · Ziyu Zhao · Gaukhar Nurbek · Aosong Feng · Ali Maatouk · Leandros Tassiulas · Yifeng Gao · Rex Ying

On the Universal Near Optimality of Hedge in Combinatorial Settings

Zhiyuan Fan · Arnab Maiti · Lillian Ratliff · Kevin Jamieson · Gabriele Farina

Less but More: Linear Adaptive Graph Learning Empowering Spatiotemporal Forecasting

Jiaming Ma · Binwu Wang · Guanjun Wang · Kuo Yang · Zhengyang Zhou · Pengkun Wang · Xu Wang · Yang Wang

Orthogonal Survival Learners for Estimating Heterogeneous Treatment Effects from Time-to-Event Data

Dennis Frauen · Maresa Schröder · Konstantin Hess · Stefan Feuerriegel

GST-UNet: A Neural Framework for Spatiotemporal Causal Inference with Time-Varying Confounding

Miruna Oprescu · David Park · Xihaier Luo · Shinjae Yoo · Nathan Kallus

Differentially Private Federated Low Rank Adaptation Beyond Fixed-Matrix

Ming Wen · Jiaqi Zhu · Yuedong Xu · Yipeng Zhou · DINGDING HAN

Heterogeneous Diffusion Structure Inference for Network Cascade

Siyu Huang · Abdul Basit Adeel · Yubai Yuan

Faster Generic Identification in Tree-Shaped Structural Causal Models

Yasmine Briefs · Markus Bläser

Improving Target Sound Extraction via Disentangled Codec Representations with Privileged Knowledge Distillation

Dail Kim · Joon-Hyuk Chang

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior

Penghao Wu · Shengnan Ma · Bo Wang · Jiaheng Yu · Lewei Lu · Ziwei Liu

From Euler to AI: Unifying Formulas for Mathematical Constants

Tomer Raz · Michael Shalyt · Elyasheev Leibtag · Rotem Kalisch · Shachar Weinbaum · Yaron Hadad · Ido Kaminer

MobileUse: A Hierarchical Reflection-Driven GUI Agent for Autonomous Mobile Operation

Ning Li · Xiangmou Qu · Jiamu Zhou · Jun Wang · Muning Wen · Kounianhua Du · Xingyu Lou · Qiuying Peng · Jun Wang · Weinan Zhang

DynaNav: Dynamic Feature and Layer Selection for Efficient Visual Navigation

Jiahui Wang · Changhao Chen

Self-Supervised Learning of Graph Representations for Network Intrusion Detection

Lorenzo Guerra · Thomas Chapuis · Guillaume Duc · Pavlo Mozharovskyi · Van-Tam Nguyen

Resounding Acoustic Fields with Reciprocity

Zitong Lan · Yiduo Hao · Mingmin Zhao

VLMLight: Safety-Critical Traffic Signal Control via Vision-Language Meta-Control and Dual-Branch Reasoning Architecture

Maonan Wang · Yirong Chen · Aoyu Pang · Yuxin Cai · Chung Shue Chen · Yuheng Kan · Man On Pun

Open CaptchaWorld: A Comprehensive Web-based Platform for Testing and Benchmarking Multimodal LLM Agents

Yaxin Luo · Zhaoyi Li · Jiacheng Liu · Jiacheng Cui · Xiaohan Zhao · Zhiqiang Shen

AlgoTune: Can Language Models Speed Up General-Purpose Numerical Programs?

Ori Press · Brandon Amos · Haoyu Zhao · Yikai Wu · Samuel Ainsworth · Dominik Krupke · Patrick Kidger · Touqir Sajed · Bartolomeo Stellato · Jisun Park · Nathanael Bosch · Eli Meril · Albert Steppi · Arman Zharmagambetov · Fangzhao Zhang · David Pérez-Piñeiro · Alberto Mercurio · Ni Zhan · Talor Abramovich · Kilian Lieret · Hanlin Zhang · Shirley Huang · Matthias Bethge · Ofir Press

Multivariate Time Series Anomaly Detection with Idempotent Reconstruction

Xin Sun · Heng Zhou · Chao Li

Diffusion Transformers as Open-World Spatiotemporal Foundation Models

Yuan Yuan · Chonghua Han · Jingtao Ding · Guozhen Zhang · Depeng Jin · Yong Li

Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning

Lifan Zhao · Yanyan Shen · Zhaoyang Liu · xue wang · Jiaji Deng

Adaptive Data-Borrowing for Improving Treatment Effect Estimation using External Controls

Qinwei Yang · Jingyi Li · Peng Wu

Causal Discovery over Clusters of Variables in Markovian Systems

Tara Anand · Adèle Ribeiro · Jin Tian · George Hripcsak · Elias Bareinboim

Evaluating and Learning Optimal Dynamic Treatment Regimes under Truncation by Death

Sihyung Park · Wenbin Lu · Shu Yang

Counterfactual reasoning: an analysis of in-context emergence

Moritz Miller · Bernhard Schölkopf · Siyuan Guo

Disentanglement Beyond Static vs. Dynamic: A Benchmark and Evaluation Framework for Multi-Factor Sequential Representations

Tal Barami · Nimrod Berman · Ilan Naiman · Amos H Hason · Rotem Ezra · Omri Azencot

Self-supervised Learning of Echocardiographic Video Representations via Online Cluster Distillation

Divyanshu Mishra · Mohammadreza Salehi · Pramit Saha · Olga Patey · Aris Papageorghiou · Yuki Asano · Alison Noble

CoUn: Empowering Machine Unlearning via Contrastive Learning

Yasser Khalil · Mehdi Setayesh · Hongliang Li

Learning to Specialize: Joint Gating-Expert Training for Adaptive MoEs in Decentralized Settings

Yehya Farhat · Hamza ElMokhtar Shili · Fangshuo Liao · Chen Dun · Mirian Hipolito Garcia · Guoqing Zheng · Ahmed Awadallah · Robert Sim · Dimitrios Dimitriadis · Anastasios Kyrillidis

Object-Centric Concept-Bottlenecks

David Steinmann · Wolfgang Stammer · Antonia Wüst · Kristian Kersting

Latent Space Factorization in LoRA

Shashi Kumar · Yacouba Kaloga · John Mitros · Petr Motlicek · Ina Kodrasi

CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning

Man Ho Lam · Chaozheng Wang · Jen-Tse Huang · Michael R Lyu

Incomplete Multi-view Clustering via Hierarchical Semantic Alignment and Cooperative Completion

Xiaojian Ding · Lin Zhao · Xian Li · Xiaoying Zhu

Flow Equivariant Recurrent Neural Networks

Andy Keller

Anchor-based Maximum Discrepancy for Relative Similarity Testing

Zhijian Zhou · Liuhua Peng · Xunye Tian · Feng Liu

Scaling Language-centric Omnimodal Representation Learning

Chenghao Xiao · Hou Pong (Ken) Chan · Hao Zhang · Weiwen Xu · Mahani Aljunied · Yu Rong

MaxSup: Overcoming Representation Collapse in Label Smoothing

Yuxuan Zhou · Heng Li · Zhi-Qi Cheng · Xudong Yan · Yifei Dong · Mario Fritz · Margret Keuper

Revolutionizing Graph Aggregation: From Suppression to Amplification via BoostGCN

Jiaxin Wu · Chenglong Pang · Guangxiong Chen · Jie Zhao

Learning Shared Representations from Unpaired Data

Amitai Yacobi · Nir Ben-Ari · Ronen Talmon · Uri Shaham

Scalable Signature Kernel Computations via Local Neumann Series Expansions

Matthew Tamayo-Rios · Alexander Schell · Rima Alaifari

UMU-Bench: Closing the Modality Gap in Multimodal Unlearning Evaluation

Chengye Wang · Yuyuan Li · XiaoHua Feng · Chaochao Chen · Xiaolin Zheng · Jianwei Yin

SGCD: Stain-Guided CycleDiffusion for Unsupervised Domain Adaptation of Histopathology Image Classification

Hsi-Ling Chen · Chun-Shien Lu · Pau-Choo Chung

Aggregation Hides Out-of-Distribution Generalization Failures from Spurious Correlations

Olawale Salaudeen · Haoran Zhang · Kumail Alhamoud · Sara Beery · Marzyeh Ghassemi

Learning to Learn with Contrastive Meta-Objective

Shiguang Wu · Yaqing Wang · Yatao Bian · Quanming Yao

Multi-Objective One-Shot Pruning for Large Language Models

Weiyu Chen · Hansi Yang · Yunhao Gou · Han Shi · Enliang Hu · Zhenguo Li · James Kwok

Semi-Supervised Regression with Heteroscedastic Pseudo-Labels

Xueqing Sun · Renzhen Wang · Quanziang Wang · Yichen WU · Xixi Jia · Deyu Meng

TabSTAR: A Tabular Foundation Model for Tabular Data with Text Fields

Alan Arazi · Eilam Shapira · Roi Reichart

Learning Task-Agnostic Representations through Multi-Teacher Distillation

Philippe Formont · Maxime Darrin · Banafsheh Karimian · Eric Granger · Jackie CK Cheung · Ismail Ayed · Mohammadhadi Shateri · Pablo Piantanida

Understanding Bias Terms in Neural Representations

Weixiang Zhang · Boxi Li · Shuzhao Xie · Chengwei Ren · Yuan Xue · Zhi Wang

OOD Detection with Relative Angles

Berker Demirel · Marco Fumero · Francesco Locatello

Mitra: Mixed Synthetic Priors for Enhancing Tabular Foundation Models

Xiyuan Zhang · Danielle Maddix Robinson · Junming Yin · Nick Erickson · Abdul Fatir Ansari · Boran Han · Shuai Zhang · Leman Akoglu · Christos Faloutsos · Michael Mahoney · Tony Hu · Huzefa Rangwala · George Karypis · Yuyang (Bernie) Wang

Understanding and Enhancing Mask-Based Pretraining towards Universal Representations

Mingze Dong · Leda Wang · Yuval Kluger

A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities

Han-Jia Ye · Si-Yang Liu · Wei-Lun (Harry) Chao

Hierarchical Retrieval: The Geometry and a Pretrain-Finetune Recipe

Chong You · Rajesh Jayaram · Ananda Theertha Suresh · Robin Nittka · Felix Yu · Sanjiv Kumar

T-REGS: Minimum Spanning Tree Regularization for Self-Supervised Learning

Julie Mordacq · David Loiseaux · Vicky Kalogeiton · Steve OUDOT

Aligning Compound AI Systems via System-level DPO

Xiangwen Wang · Yibo Jacky Zhang · Zhoujie Ding · Katherine Tsai · Haolun Wu · Sanmi Koyejo

Gaussian Regression-Driven Tensorized Incomplete Multi-View Clustering with Dual Manifold Regularization

Zhenhao Zhong · Zhibin Gu · Pengpeng Yang · Yaqian zhou · Ruiqiang Guo

CARE: Decoding-Time Safety Alignment via Rollback and Introspection Intervention

Xiaomeng Hu · Fei Huang · Chenhan Yuan · Junyang Lin · Tsung-Yi Ho

Neural Mutual Information Estimation with Vector Copulas

Yanzhi Chen · Zijing Ou · Adrian Weller · Michael Gutmann

Rethinking PCA Through Duality

Jan Quan · Johan Suykens · Panagiotis Patrinos

Estimating Model Performance Under Covariate Shift Without Labels

Jakub Białek · Juhani Kivimäki · Wojciech Kuberski · Nikolaos Perrakis

Online Functional Tensor Decomposition via Continual Learning for Streaming Data Completion

Xi Zhang · Yanyi Li · Yisi Luo · Qi Xie · Deyu Meng

Fréchet Geodesic Boosting

Yidong Zhou · SU I IAO · Hans-Georg Müller

AI Research Agents for Machine Learning: Search, Exploration, and Generalization in MLE-bench

Edan Toledo · Karen Hambardzumyan · Martin Josifoski · Rishi Hazra · Nicolas Baldwin · Alexis Audran-Reiss · Michael Kuchnik · Despoina Magka · Minqi Jiang · Alisia Lupidi · Andrei Lupu · Roberta Raileanu · Tatiana Shavrina · Kelvin Niu · Jean-Christophe Gagnon-Audet · Michael Shvartsman · Shagun Sodhani · Alexander Miller · Abhishek Charnalia · Derek Dunfield · Carole-Jean Wu · Pontus Lars Erik Saito Stenetorp · Nicola Cancedda · Jakob Foerster · Yoram Bachrach

Beyond Modality Collapse: Representation Blending for Multimodal Dataset Distillation

xin zhang · Ziruo Zhang · JIAWEI DU · Zuozhu Liu · Joey Tianyi Zhou

Value Diffusion Reinforcement Learning

Xiaoliang Hu · Fuyun Wang · Tong Zhang · Zhen Cui

Enhancing Deep Batch Active Learning for Regression with Imperfect Data Guided Selection

Yinjie Min · Furong Xu · Xinyao Li · Changliang Zou · Yongdao Zhou

EraseFlow: Learning Concept Erasure Policies via GFlowNet-Driven Alignment

Naga Sai Abhiram Kusumba · Maitreya Patel · Kyle Min · Changhoon Kim · Chitta Baral · 'YZ' Yezhou Yang

Gatekeeper: Improving Model Cascades Through Confidence Tuning

Stephan Rabanser · Nathalie Rauschmayr · Achin Kulshrestha · Petra Poklukar · Wittawat Jitkrittum · Sean Augenstein · Congchao Wang · Federico Tombari

Rethinking Hebbian Principle: Low-Dimensional Structural Projection for Unsupervised Learning

Shikuang Deng · Jiayuan Zhang · Yuhang Wu · Ting Chen · Shi Gu

The Flood Complex: Large-Scale Persistent Homology on Millions of Points

Florian Graf · Paolo Pellizzoni · Martin Uray · Stefan Huber · Roland Kwitt

Uniform Generalization Bounds on Data-Dependent Hypothesis Sets via PAC-Bayesian Theory on Random Sets

Benjamin Dupuis · Paul Viallard · George Deligiannidis · Umut Simsekli

Pseudo-Labeling for Kernel Ridge Regression under Covariate Shift

Kaizheng Wang

Why Playing Against Diverse and Challenging Opponents Speeds Up Coevolution: A Theoretical Analysis on Combinatorial Games

Alistair Benford · Per Kristian Lehre

Truthful Aggregation of LLMs with an Application to Online Advertising

Ermis Soumalias · Michael Curry · Sven Seuken

From Average-Iterate to Last-Iterate Convergence in Games: A Reduction and Its Applications

Yang Cai · Haipeng Luo · Chen-Yu Wei · Weiqiang Zheng

Last Iterate Convergence in Monotone Mean Field Games

Noboru Isobe · Kenshi Abe · Kaito Ariu

Thresholds for sensitive optimality and Blackwell optimality in stochastic games

Stephane Gaubert · Julien Grand-Clément · Ricardo Katz

Efficient Kernelized Learning in Polyhedral Games beyond Full Information: From Colonel Blotto to Congestion Games

Andreas Kontogiannis · Vasilis Pollatos · Gabriele Farina · Panayotis Mertikopoulos · Ioannis Panageas

Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration

Kyriakos Lotidis · Panayotis Mertikopoulos · Nicholas Bambos · Jose Blanchet

Solving Neural Min-Max Games: The Role of Architecture, Initialization & Dynamics

Deep Patel · Emmanouil-Vasileios Vlatakis-Gkaragkounis

Mechanism Design for LLM Fine-tuning with Multiple Reward Models

Haoran Sun · Yurong Chen · Siwei Wang · Chu Xu · Wei Chen · Xiaotie Deng

Lifelong Test-Time Adaptation via Online Learning in Tracked Low-Dimensional Subspace

Dexin Duan · Rui Xu · Peilin Liu · Fei Wen

Data Selection Matters: Towards Robust Instruction Tuning of Large Multimodal Models

Xu Yang · Chen Liu · Ying Wei

Conformal Prediction under Lévy-Prokhorov Distribution Shifts: Robustness to Local and Global Perturbations

Liviu Aolaritei · Julie Zhu · Oliver Wang · Michael Jordan · Youssef Marzouk

Composing Linear Layers from Irreducibles

Travis Pence · Daisuke Yamada · Vikas Singh

Adversarial Graph Fusion for Incomplete Multi-view Semi-supervised Learning with Tensorial Imputation

Zhangqi Jiang · Tingjin Luo · Xu Yang · Xinyan Liang

Entropy-Calibrated Label Distribution Learning

Yunan Lu · Bowen Xue · Xiuyi Jia · Lei Yang

MisoDICE: Multi-Agent Imitation from Mixed-Quality Demonstrations

The Viet Bui · Tien Mai · Thanh Nguyen

Asymptotically Stable Quaternion-valued Hopfield-structured Neural Network with Periodic Projection-based Supervised Learning Rules

Tianwei Wang · Xinhui Ma · Wei Pang

Bivariate Matrix-valued Linear Regression (BMLR): Finite-sample performance under Identifiability and Sparsity Assumptions

Nayel Bettache

Replicable Online pricing

Kiarash Banihashem · Mohammadhossein Bateni · Hossein Esfandiari · Samira Goudarzi · MohammadTaghi Hajiaghayi

Consistency Conditions for Differentiable Surrogate Losses

Drona Khurana · Anish Thilagar · Dhamma Kimpara · Rafael Frongillo

How Data Mixing Shapes In-Context Learning: Asymptotic Equivalence for Transformers with MLPs

Samet Demir · Zafer Dogan

Assessing the quality of denoising diffusion models in Wasserstein distance: noisy score and optimal bounds

Vahan Arsenyan · Elen Vardanyan · Arnak Dalalyan

Median Selection with Noisy and Structural Information

Chenglin Fan · Mingyu Kang

Any-stepsize Gradient Descent for Separable Data under Fenchel–Young Losses

Han Bao · Shinsaku Sakaue · Yuki Takezawa

Hybrid Re-matching for Continual Learning with Parameter-Efficient Tuning

Weicheng Wang · Guoli Jia · Xialei Liu · Liang Lin · Jufeng Yang

Online Prediction with Limited Selectivity

Licheng Liu · Mingda Qiao

Enhancing Vision-Language Model Reliability with Uncertainty-Guided Dropout Decoding

Yixiong Fang · Ziran Yang · Zhaorun Chen · Zhuokai Zhao · Jiawei Zhou

Simultaneous Swap Regret Minimization via KL-Calibration

Haipeng Luo · Spandan Senapati · Vatsal Sharan

A Geometric Analysis of PCA

Ayoub El Hanchi · Murat Erdogdu · Chris Maddison

Stabilizing LTI Systems under Partial Observability: Sample Complexity and Fundamental Limits

Ziyi Zhang · Yorie Nakahira · Guannan Qu

Sharp Matrix Empirical Bernstein Inequalities

Hongjian Wang · Aaditya Ramdas

Learning from Interval Targets

Rattana Pukdee · Ziqi Ke · Chirag Gupta

Learning-Augmented Streaming Algorithms for Correlation Clustering

Yinhao Dong · Shan Jiang · Shi Li · Pan Peng

PAC-Bayes Bounds for Multivariate Linear Regression and Linear Autoencoders

Ruixin Guo · Ruoming Jin · Xinyu Li · Yang Zhou

Heterogeneous Graph Transformers for Simultaneous Mobile Multi-Robot Task Allocation and Scheduling under Temporal Constraints

Batuhan Altundas · Shengkang Chen · Shivika Singh · Shivangi Deo · Minwoo Cho · Matthew Gombolay

Learning and Planning Multi-Agent Tasks via an MoE-based World Model

Zijie Zhao · Zhongyue Zhao · Kaixuan Xu · Yuqian Fu · Jiajun Chai · Yuanheng Zhu · Dongbin Zhao

Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form Games

Fivos Kalogiannis · Gabriele Farina

Rainbow Delay Compensation: A Multi-Agent Reinforcement Learning Framework for Mitigating Observation Delays

Songchen Fu · Siang Chen · Shaojing Zhao · Letian Bai · Hong Liang · Ta Li · Yonghong Yan

High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning

Qinyu Xu · Yuanyang Zhu · Xuefei Wu · Chunlin Chen

In-Context Fully Decentralized Cooperative Multi-Agent Reinforcement Learning

Chao Li · Bingkun BAO · Yang Gao

Bayesian Ego-graph inference for Networked Multi-Agent Reinforcement Learning

Wei Duan · Jie Lu · Junyu Xuan

Multi-Agent Reinforcement Learning with Communication-Constrained Priors

Guang Yang · Jingwen Qiao · Tianpei Yang · Yanqing Wu · Jing Huo · Xingguo Chen · Yang Gao

EconGym: A Scalable AI Testbed with Diverse Economic Tasks

Qirui Mi · Qipeng Yang · Zijun Fan · Wentian Fan · Heyang Ma · Chengdong Ma · Siyu Xia · Bo An · Jun Wang · Haifeng Zhang

Comparator-Adaptive $\Phi$-Regret: Improved Bounds, Simpler Algorithms, and Applications to Games

Soumita Hait · Ping Li · Haipeng Luo · Mengxiao Zhang

Normalization in Attention Dynamics

Nikita Karagodin · Shu Ge · Yury Polyanskiy · Philippe Rigollet

How Many Domains Suffice for Domain Generalization? A Tight Characterization via the Domain Shattering Dimension

Cynthia Dwork · Lunjia Hu · Han Shao

Nonlinear Laplacians: Tunable principal component analysis under directional prior information

Yuxin Ma · Dmitriy Kunisky

Sample-Adaptivity Tradeoff in On-Demand Sampling

Nika Haghtalab · Omar Montasser · Mingda Qiao

Low-degree evidence for computational transition of recovery rate in stochastic block model

Jingqiu Ding · Yiding Hua · Lucas Slot · David Steurer

Concentration and excess risk bounds for imbalanced classification with synthetic oversampling

Touqeer Ahmad · Mohammadreza Mousavi Kalan · François Portier · Gilles Stupfler

Stability and Oracle Inequalities for Optimal Transport Maps between General Distributions

Shubo Li · Yizhe Ding · Lingzhou Xue · Runze Li

Unlabeled Data Can Provably Enhance In-Context Learning of Transformers

Renpu Liu · Jing Yang

Is the acquisition worth the cost? Surrogate losses for Consistent Two-stage Classifiers

florence regol · Joseph Cotnareanu · Theodore Glavas · Mark Coates

VolleyBots: A Testbed for Multi-Drone Volleyball Game Combining Motion Control and Strategic Play

Zelai Xu · Ruize Zhang · Chao Yu · Huining Yuan · Xiangmin Yi · Shilong Ji · Chuqi Wang · Wenhao Tang · Feng Gao · Wenbo Ding · Xinlei Chen · Yu Wang

Subsampled Ensemble Can Improve Generalization Tail Exponentially

Huajie Qian · Donghao Ying · Henry Lam · Wotao Yin

Factorio Learning Environment

Jack Hopkins · Mart Bakler · Akbir Khan

Prompt Tuning Decision Transformers with Structured and Scalable Bandits

Finn Rietz · Oleg Smirnov · Sara Karimi · Lele Cao

Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning

Jiayu Wang · Yifei Ming · Zixuan Ke · Caiming Xiong · Shafiq Joty · Aws Albarghouthi · Frederic Sala

1000 Layer Networks for Self-Supervised RL: Scaling Depth Can Enable New Goal-Reaching Capabilities

Kevin Wang · Ishaan Javali · Michał Bortkiewicz · Tomasz Trzcinski · Benjamin Eysenbach

Hadamax Encoding: Elevating Performance in Model-Free Atari

Jacob Eeuwe Kooi · Zhao Yang · Vincent Francois-Lavet

Robust Regression of General ReLUs with Queries

Ilias Diakonikolas · Daniel Kane · Mingchen Ma

The $\varphi$ Curve: The Shape of Generalization through the Lens of Norm-based Capacity Control

Yichen Wang · Yudong Chen · Lorenzo Rosasco · Fanghui Liu

Last-Iterate Convergence of Smooth Regret Matching$^+$ Variants in Learning Nash Equilibria

Linjian Meng · Youzhi Zhang · Zhenxing Ge · Tianyu Ding · Shangdong Yang · Zheng Xu · Wenbin Li · Yang Gao

Globally Optimal Policy Gradient Algorithms for Reinforcement Learning with PID Control Policies

Vipul Sharma · Wesley Suttle · S Sivaranjani

Learning Juntas under Markov Random Fields

Gautam Chandrasekaran · Adam Klivans

Error Forcing in Recurrent Neural Networks

A Sağtekin · Colin Bredenberg · Cristina Savin

Bridging Distributional and Risk-sensitive Reinforcement Learning with Provable Regret Bounds

Hao Liang · Zhiquan Luo

No-Regret Thompson Sampling for Finite-Horizon Markov Decision Processes with Gaussian Processes

Jasmine Bayrooti · Sattar Vakili · Amanda Prorok · Carl Henrik Ek

Finite Sample Analysis of Linear Temporal Difference Learning with Arbitrary Features

Zixuan Xie · Xinyu Liu · Rohan Chandra · Shangtong Zhang

Global Convergence for Average Reward Constrained MDPs with Primal-Dual Actor Critic Algorithm

Yang Xu · Swetha Ganesh · Washim Mondal · Qinbo Bai · Vaneet Aggarwal

Sample Complexity of Distributionally Robust Average-Reward Reinforcement Learning

Zijun Chen · Shengbo Wang · Nian Si

The Structural Complexity of Matrix-Vector Multiplication

Emile Anand · Jan van den Brand · Rose McCarty

Pairwise Calibrated Rewards for Pluralistic Alignment

Daniel Halpern · Evi Micha · Ariel Procaccia · Itai Shapira

Structure-Aware Spectral Sparsification via Uniform Edge Sampling

Kaiwen He · Petros Drineas · Rajiv Khanna

Closed-Form Training Dynamics Reveal Learned Features and Linear Structure in Word2Vec-like Models

Dhruva Karkada · James Simon · Yasaman Bahri · Michael Deweese

Hadamard Test is Sufficient for Efficient Quantum Gradient Estimation with Lie Algebraic Symmetries

Mohsen Heidari · Masih Mozakka · Wojciech Szpankowski

Asymptotics of SGD in Sequence-Single Index Models and Single-Layer Attention Networks

Luca Arnaboldi · Bruno Loureiro · Ludovic Stephan · Florent Krzakala · Lenka Zdeborová

Foundations of Top-$k$ Decoding for Language Models

Georgy Noarov · Soham Mallick · Tao Wang · Sunay Joshi · Yan Sun · Yangxinyu Xie · Mengxin Yu · Edgar Dobriban

Neural Collapse under Gradient Flow on Shallow ReLU Networks for Orthogonally Separable Data

Hancheng Min · Zhihui Zhu · Rene Vidal

Simple and Optimal Sublinear Algorithms for Mean Estimation

Beatrice Bertolotti · Matteo Russo · Chris Schwiegelshohn · Sudarshan Shyam

Stochastic Shortest Path with Sparse Adversarial Costs

Emmeran Johnson · Alberto Rumi · Ciara Pike-Burke · Patrick Rebeschini

Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options

Joongkyu Lee · Seouh-won Yi · Min-hwan Oh

Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning

Jifeng Hu · Sili Huang · Zhejian Yang · Shengchao Hu · Li Shen · Hechang Chen · Lichao Sun · Yi Chang · Dacheng Tao

On the Global Optimality of Policy Gradient Methods in General Utility Reinforcement Learning

Anas Barakat · Souradip Chakraborty · Peihong Yu · Pratap Tokekar · Amrit Singh Bedi

Distances for Markov chains from sample streams

Sergio Calo · Anders Jonsson · Gergely Neu · Ludovic Schwartz · Javier Segovia-Aguas

Optimal Single-Policy Sample Complexity and Transient Coverage for Average-Reward Offline RL

Matthew Zurek · Guy Zamir · Yudong Chen

An Improved Algorithm for Adversarial Linear Contextual Bandits via Reduction

Tim van Erven · Jack Mayo · Julia Olkhovskaya · Chen-Yu Wei

Beyond Average Value Function in Precision Medicine: Maximum Probability-Driven Reinforcement Learning for Survival Analysis

Jianqi Feng · Chengchun Shi · Zhenke Wu · Xiaodong Yan · Wei Zhao

Linear Mixture Distributionally Robust Markov Decision Processes

Zhishuai Liu · Pan Xu

On the Entropy Calibration of Language Models

Steven Cao · Gregory Valiant · Percy Liang

Estimation of Stochastic Optimal Transport Maps

Sloan Nietert · Ziv Goldfeld

Distance Adaptive Beam Search for Provably Accurate Graph-Based Nearest Neighbor Search

Yousef Al-Jazzazi · Haya Diwan · Jinrui Gou · Cameron Musco · Christopher Musco · Torsten Suel

On Extending Direct Preference Optimization to Accommodate Ties

Jinghong Chen · Guangyu Yang · Weizhe Lin · Jingbiao Mei · Chenxu Lyu · Bill Byrne

Dynamic Bundling with Large Language Models for Zero-Shot Inference on Text-Attributed Graphs

Yusheng Zhao · Qixin Zhang · Xiao Luo · Weizhi Zhang · Zhiping Xiao · Wei Ju · Philip S Yu · Ming Zhang

DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning

Sitong Wu · Haoru Tan · Jingyao Li · Shaofeng Zhang · Xiaojuan Qi · Bei Yu · Jiaya Jia

AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks

Fali Wang · Hui Liu · Zhenwei Dai · Jingying Zeng · Zhiwei Zhang · Zongyu Wu · Chen Luo · Zhen Li · Xianfeng Tang · Qi He · Suhang Wang

Universal Cross-Tokenizer Distillation via Approximate Likelihood Matching

Benjamin Minixhofer · Ivan Vulić · Edoardo Maria Ponti

SpectraLDS: Provable Distillation for Linear Dynamical Systems

Devan Shah · Shlomo Fortgang · Sofiia Druchyna · Elad Hazan

Convex Potential Mirror Langevin Algorithm for Efficient Sampling of Energy-Based Models

Zitao Yang · Amin Ullah · Shuai Li · Fuxin Li · Jun Li

Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data

Shuli Zhang · Hao Zhou · Jiaqi Zheng · Guibin Jiang · Cheng Bing · Wei Lin · Guihai Chen

Learning to Solve Complex Problems via Dataset Decomposition

Wanru Zhao · Lucas Page-Caccia · Zhengyan Shi · Minseon Kim · Weijia Xu · Alessandro Sordoni

Whitened Score Diffusion: A Structured Prior for Imaging Inverse Problems

Jeffrey Alido · Tongyu Li · Yu Sun · Lei Tian

Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks

Shakir Yousefi · Andreas Plesner · Till Aczel · Roger Wattenhofer

HPSERec: A Hierarchical Partitioning and Stepwise Enhancement Framework for Long-tailed Sequential Recommendation

Xiaolong Xu · Xudong Zhao · Haolong Xiang · Xuyun Zhang · Wei Shen · Hongsheng Hu · Lianyong Qi

Layer as Puzzle Pieces: Compressing Large Language Models through Layer Concatenation

Fei Wang · Li Shen · Liang Ding · Chao Xue · Ye Liu · Changxing Ding

PoLAR: Polar-Decomposed Low-Rank Adapter Representation

Kai Lion · Liang Zhang · Bingcong Li · Niao He

ModHiFi: Identifying High Fidelity predictive components for Model Modification

Dhruva Kashyap · Chaitanya Murti · Pranav K Nayak · Tanay Narshana · Chiranjib Bhattacharyya

FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts

Heming Zou · Yunliang Zang · Wutong Xu · Yao Zhu · Xiangyang Ji

A Partition Cover Approach to Tokenization

Jia Peng Lim · Shawn Tan · XianJun, Davin Choo · Hady Lauw

Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP Tasks

Wentao Deng · Jiahuan Pei · Zhiwei Xu · Zhaochun Ren · Zhumin Chen · Pengjie Ren

Positional Fragility in LLMs: How Offset Effects Reshape Our Understanding of Memorization Risks

Yixuan Xu · Antoine Bosselut · Imanol Schlag

Fira: Can We Achieve Full-rank Training of LLMs Under Low-rank Constraint?

Xi Chen · Kaituo Feng · Changsheng Li · Xunhao Lai · Xiangyu Yue · Ye Yuan · Guoren Wang

Distributional Autoencoders Know the Score

Andrej Leban

NeuroGenPoisoning: Neuron-Guided Attacks on Retrieval-Augmented Generation of LLM via Genetic Optimization of External Knowledge

Hanyu Zhu · Lance Fiondella · Jiawei Yuan · Kai Zeng · Long Jiao

The ML.ENERGY Benchmark: Toward Automated Inference Energy Measurement and Optimization

Jae-Won Chung · Jeff J. Ma · Ruofan Wu · Jiachen Liu · Oh Jun Kweon · Yuxuan Xia · Zhiyu Wu · Mosharaf Chowdhury

Transformers Learn Faster with Semantic Focus

Parikshit Ram · Kenneth Clarkson · Tim Klinger · Shashanka Ubaru · Alexander Gray

Attention (as Discrete-Time Markov) Chains

Yotam Erel · Olaf Dünkel · Rishabh Dabral · Vladislav Golyanik · Christian Theobalt · Amit Bermano

Attention Sinks: A 'Catch, Tag, Release' Mechanism for Embeddings

Stephen Zhang · Mustafa Khan · Vardan Papyan

Multi-head Temporal Latent Attention

Keqi Deng · Phil Woodland

Linear Transformers Implicitly Discover Unified Numerical Algorithms

Patrick Lutz · Aditya Gangrade · Hadi Daneshmand · Venkatesh Saligrama

Two Heads are Better than One: Simulating Large Transformers with Small Ones

Hantao Yu · Josh Alman

Efficient Low Rank Attention for Long-Context Inference in Large Language Models

Li Tenghui · Guoxu Zhou · Xuyang Zhao · Yuning Qiu · Qibin Zhao

Recurrent Self-Attention Dynamics: An Energy-Agnostic Perspective from Jacobians

Akiyoshi Tomihari · Ryo Karakida

GSPN-2: Efficient Parallel Sequence Modeling

Hongjun Wang · yitong jiang · Collin McCarthy · David Wehr · Hanrong Ye · Xinhao Li · Ka Chun Cheung · Wonmin Byeon · Jinwei Gu · Ke Chen · Kai Han · Hongxu Yin · Pavlo Molchanov · Jan Kautz · Sifei Liu

Titans: Learning to Memorize at Test Time

Ali Behrouz · Peilin Zhong · Vahab Mirrokni

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression

Chenlong Deng · Zhisong Zhang · Kelong Mao · Shuaiyi Li · Tianqing Fang · Hongming Zhang · Haitao Mi · Dong Yu · Zhicheng Dou

Mind the Quote: Enabling Quotation-Aware Dialogue in LLMs via Plug-and-Play Modules

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

Enforcing convex constraints in Graph Neural Networks

Ahmed Rashwan · Keith Briggs · Chris Budd · Lisa Kreusser

Reinforcement Learning Teachers of Test Time Scaling

Edoardo Cetin · Tianyu Zhao · Yujin Tang

Training Language Models to Reason Efficiently

Daman Arora · Andrea Zanette

Exploring Diffusion Transformer Designs via Grafting

Nabla-R2D3: Effective and Efficient 3D Diffusion Alignment with 2D Rewards

Qingming LIU · Zhen Liu · Dinghuai Zhang · Kui Jia

Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding

Xiangyu Wen · Min Li · Junhua Huang · Jianyuan Zhong · Zhijian Xu · Zeju Li · Yongxiang Huang · Mingxuan Yuan · Qiang Xu

Fourier Token Merging: Understanding and Capitalizing Frequency Domain for Efficient Image Generation

Jiesong Liu · Xipeng Shen

Remasking Discrete Diffusion Models with Inference-Time Scaling

Guanghan Wang · Yair Schiff · Subham Sahoo · Volodymyr Kuleshov

Beyond Oracle: Verifier-Supervision for Instruction Hierarchy in Reasoning and Instruction-Tuned LLMs

Sian-Yao Huang · Li-Hsien Chang · Che-Yu Lin · Cheng-Lin Yang

Preference Optimization by Estimating the Ratio of the Data Distribution

Yeongmin Kim · HeeSun Bae · Byeonghu Na · Il-chul Moon

Transformer Copilot: Learning from The Mistake Log in LLM Fine-tuning

Jiaru Zou · Yikun Ban · Zihao Li · Yunzhe Qi · Ruizhong Qiu · Ling Yang · Jingrui He

Deep Taxonomic Networks for Unsupervised Hierarchical Prototype Discovery

Zekun Wang · Ethan Haarer · Tianyi Zhu · Zhiyi Dai · Christopher MacLellan

Sample and Map from a Single Convex Potential: Generation using Conjugate Moment Measures

Nina Vesseron · Louis Bethune · Marco Cuturi

Measuring and Guiding Monosemanticity

Ruben Härle · Felix Friedrich · Manuel Brack · Björn Deiseroth · Stephan Waeldchen · Patrick Schramowski · Kristian Kersting

Riemannian Consistency Model

Chaoran Cheng · Yusong Wang · Yuxin Chen · Xiangxin Zhou · Nanning Zheng · Ge Liu

BioCG: Constrained Generative Modeling for Biochemical Interaction Prediction

Amitay Sicherman · Kira Radinsky

Linearly Constrained Diffusion Implicit Models

Vivek Jayaram · Ira Kemelmacher-Shlizerman · Steve Seitz · John Thickstun

Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking

Heli Ben-Hamu · Itai Gat · Daniel Severo · Niklas S Nolte · Brian Karrer

Neural MJD: Neural Non-Stationary Merton Jump Diffusion for Time Series Prediction

Yuanpei Gao · Qi Yan · Yan Leng · Renjie Liao

MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization

Chenglong Wang · Yang Gan · Hang Zhou · Chi Hu · Yongyu Mu · Kai Song · MuRun Yang · Bei Li · Chunliang Zhang · Tongran Liu · JingBo Zhu · Zhengtao Yu · Tong Xiao

NSNQuant: A Double Normalization Approach for Calibration-Free Low-Bit Vector Quantization of KV Cache

Donghyun Son · Euntae Choi · Sungjoo Yoo

HOI-Dyn: Learning Interaction Dynamics for Human-Object Motion Diffusion

Lin Wu · Zhixiang Chen · Jianglin Lan

Simple and Efficient Heterogeneous Temporal Graph Neural Network

Yili Wang · Tairan Huang · Changlong He · Qiutong Li · Jianliang Gao

Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification

Xiaobao Wang · Ruoxiao Sun · Yujun Zhang · Bingdao Feng · Dongxiao He · Luzhi Wang · Di Jin

OCN: Effectively Utilizing Higher-Order Common Neighbors for Better Link Prediction

Juntong Wang · Xiyuan Wang · Muhan Zhang

Adjusted Count Quantification Learning on Graphs

Clemens Damke · Eyke Hüllermeier

Towards Pre-trained Graph Condensation via Optimal Transport

Yeyu Yan · Shuai Zheng · Wenjun Hui · Xiangkai Zhu · Chen Dong · Zhenfeng Zhu · Yao Zhao · Kunlun He

How Particle System Theory Enhances Hypergraph Message Passing

Yixuan Ma · Kai Yi · Pietro Lió · Shi Jin · Yuguang Wang

Architectural and Inferential Inductive Biases for Exchangeable Sequence Modeling

Daksh Mittal · Leon Li · Thomson Yen · C. Guetta · Hongseok Namkoong

HumanoidGen: Data Generation for Bimanual Dexterous Manipulation via LLM Reasoning

Zhi Jing · Siyuan Yang · Jicong Ao · Ting Xiao · Yu-Gang Jiang · Chenjia Bai

Let LRMs Break Free from Overthinking via Self-Braking Tuning

Haoran Zhao · Yuchen Yan · Yongliang Shen · Haolei Xu · Wenqi Zhang · Kaitao Song · Jian Shao · Weiming Lu · Jun Xiao · Yueting Zhuang

Topology-aware Graph Diffusion Model with Persistent Homology

Joonhyuk Park · Donghyun Lee · Yujee Song · Guorong Wu · Won Hwa Kim

Chain-of-Model Learning for Language Model

Xiaohua Wang · Kaitao Song · Xu Tan · Huiqiang Jiang · Chengruidong Zhang · Yongliang Shen · Cen Lu · Zihao Li · Zifan Song · Caihua Shan · Yansen Wang · Kan Ren · Xiaoqing Zheng · Tao Qin · Yuqing Yang · Dongsheng Li · Lili Qiu

Learning to Insert for Constructive Neural Vehicle Routing Solver

Fu Luo · Xi Lin · Mengyuan Zhong · Fei Liu · Zhenkun Wang · Jianyong Sun · Qingfu Zhang

Compositional Monte Carlo Tree Diffusion for Extendable Planning

Jaesik Yoon · Hyeonseo Cho · Sungjin Ahn

Neptune-X: Active X-to-Maritime Generation for Universal Maritime Object Detection

Yu Guo · Shengfeng He · Yuxu Lu · Haonan An · Yihang Tao · Huilin Zhu · Jingxian Liu · Yuguang Fang

MF-LLM: Simulating Population Decision Dynamics via a Mean-Field Large Language Model Framework

Qirui Mi · Mengyue Yang · Xiangning Yu · Zhiyu Zhao · Cheng Deng · Bo An · Haifeng Zhang · Xu Chen · Jun Wang

What's Producible May Not Be Reachable: Measuring the Steerability of Generative Models

Keyon Vafa · Sarah Bentley · Jon Kleinberg · Sendhil Mullainathan

Discrete Spatial Diffusion: Intensity-Preserving Diffusion Modeling

Javier E. Santos · Agnese Marcato · Roman Colman · NIcholas Lubbers · Yen Ting Lin

Superposition Yields Robust Neural Scaling

Yizhou Liu · Ziming Liu · Jeff Gore

Next Semantic Scale Prediction via Hierarchical Diffusion Language Models

Cai Zhou · Chenyu Wang · Dinghuai Zhang · Shangyuan Tong · Yifei Wang · Stephen Bates · Tommi Jaakkola

MURKA: Multi-Reward Reinforcement Learning with Knowledge Alignment for Optimization Tasks

WANTONG XIE · Yi-Xiang Hu · Jieyang Xu · Feng Wu · Xiangyang Li

GMV: A Unified and Efficient Graph Multi-View Learning Framework

Qipeng zhu · Jie Chen · Jian Pu · Junping Zhang

Diffusion-Based Hierarchical Graph Neural Networks for Simulating Nonlinear Solid Mechanics

Tobias Würth · Niklas Freymuth · Gerhard Neumann · Luise Kärger

Learning Individual Behavior in Agent-Based Models with Graph Diffusion Networks

Francesco Cozzi · Marco Pangallo · Alan Perotti · André Panisson · Corrado Monti

L2DGCN: Learnable Enhancement and Label Selection Dynamic Graph Convolutional Networks for Mitigating Degree Bias

jingxiao zhang · Shifei Ding · Jian Zhang · Lili Guo · Xuan Li

Generalizable Insights for Graph Transformers in Theory and Practice

Timo Stoll · Luis Müller · Christopher Morris

You Only Spectralize Once: Taking a Spectral Detour to Accelerate Graph Neural Network

Yi Li · Zhichun Guo · Guanpeng Li · Bingzhe Li

On topological descriptors for graph products

Mattie Ji · Amauri Souza · Vikas Garg

Axial Neural Networks for Dimension-Free Foundation Models

Hyunsu Kim · Jonggeon Park · Joan Bruna · Hongseok Yang · Juho Lee

Relieving the Over-Aggregating Effect in Graph Transformers

Junshu Sun · Wanxing Chang · Chenxue Yang · Qingming Huang · Shuhui Wang

A CLT for Polynomial GNNs on Community-Based Graphs

Luciano Vinas · Arash Amini

Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks

Ryien Hosseini · Filippo Simini · Venkatram Vishwanath · Rebecca Willett · Henry Hoffmann

HyperMixup: Hypergraph-Augmented with Higher-order Information Mixup

Kaixuan Yao · Zhuo Li · Jianqing Liang · Jiye Liang · Ming Li · Feilong Cao

Mixture of Scope Experts at Test: Generalizing Deeper Graph Neural Networks with Shallow Variants

Gangda Deng · Hongkuan Zhou · Rajgopal Kannan · Viktor Prasanna

Graph-Theoretic Insights into Bayesian Personalized Ranking for Recommendation

Kai Zheng · Jianxin Wang · Jinhui Xu

TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction

Zhongyi Yu · Jianqiu Wu · Zhenghao Wu · Shuhan Zhong · Weifeng Su · Chul-Ho Lee · Weipeng Zhuo

Failure by Interference: Language Models Make Balanced Parentheses Errors When Faulty Mechanisms Overshadow Sound Ones

Daking Rai · Samuel Miller · Kevin Moran · Ziyu Yao

Scalable Valuation of Human Feedback through Provably Robust Model Alignment

Masahiro Fujisawa · Masaki Adachi · Michael A Osborne

StyleGuard: Preventing Text-to-Image-Model-based Style Mimicry Attacks by Style Perturbations

Yanjie Li · Wenxuan Zhang · Xinqi Lyu · Yihao LIU · Bin Xiao

SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification

Zhenglin Lai · Mengyao Liao · Bingzhe Wu · Dong Xu · Zebin Zhao · Zhihang Yuan · Chao Fan · Jianqiang Li

SilentStriker: Toward Stealthy Bit-Flip Attacks on Large Language Models

HAOTIAN XU · Qingsong Peng · Jie Shi · Huadi Zheng · YU LI · Cheng Zhuo

CoreGuard: Safeguarding Foundational Capabilities of LLMs Against Model Stealing in Edge Deployment

Qinfeng Li · Tianyue Luo · Xuhong Zhang · Yangfan Xie · Zhiqiang Shen · Lijun Zhang · Yier Jin · Hao Peng · Xinkui Zhao · XianWei Zhu · Jianwei Yin

L$^2$M: Mutual Information Scaling Law for Long-Context Language Modeling

Zhuo Chen · Oriol Comas · Zhuotao Jin · Di Luo · Marin Soljacic

Learning with Restricted Boltzmann Machines: Asymptotics of AMP and GD in High Dimensions

Yizhou Xu · Florent Krzakala · Lenka Zdeborová

Neural Collapse in Cumulative Link Models for Ordinal Regression: An Analysis with Unconstrained Feature Model

Chuang Ma · Tomoyuki Obuchi · Toshiyuki Tanaka

Knee-Deep in C-RASP: A Transformer Depth Hierarchy

Andy J Yang · Michaël Cadilhac · David Chiang

MAP Estimation with Denoisers: Convergence Rates and Guarantees

Scott Pesme · Giacomo Meanti · Michael Arbel · Julien Mairal

Vocabulary In-Context Learning in Transformers: Benefits of Positional Encoding

Qian Ma · Ruoxiang Xu · Yongqiang Cai

Consistency of Physics-Informed Neural Networks for Second-Order Elliptic Equations

Yuqian Cheng · Zhuo Chen · Qian Lin

The Cost of Robustness: Tighter Bounds on Parameter Complexity for Robust Memorization in ReLU Nets

Yujun Kim · Chaewon Moon · Chulhee Yun

Structured Linear CDEs: Maximally Expressive and Parallel-in-Time Sequence Models

Benjamin Walker · Lingyi Yang · Nicola Muca Cirone · Cristopher Salvi · Terry Lyons

When Models Don’t Collapse: On the Consistency of Iterative MLE

Daniel Barzilai · Ohad Shamir

Just One Layer Norm Guarantees Stable Extrapolation

Juliusz Ziomek · George Whittle · Michael A Osborne

Neural Networks Generalize on Low Complexity Data

Sourav Chatterjee · Timothy Sudijono

A Geometrical Analysis of Kernel Ridge Regression and its Applications

Georgios Gavrilopoulos · Guillaume Lecué · Zong Shang

AdaptDel: Adaptable Deletion Rate Randomized Smoothing for Certified Robustness

Zhuoqun Huang · Neil Marchant · Olga Ohrimenko · Benjamin Rubinstein

SeCon-RAG: A Two-Stage Semantic Filtering and Conflict-Free Framework for Trustworthy RAG

Xiaonan Si · Meilin Zhu · Simeng Qin · Lijia Yu · Lijun Zhang · Shuaitong Liu · Xinfeng Li · Ranjie Duan · Yang Liu · Xiaojun Jia

On the Robustness of Verbal Confidence of LLMs in Adversarial Attacks

Stephen Obadinma · Xiaodan Zhu

Frame Context Packing and Drift Prevention in Next-Frame-Prediction Video Diffusion Models

Lvmin Zhang · Shengqu Cai · Muyang Li · Gordon Wetzstein · Maneesh Agrawala

Generating and Checking DNN Verification Proofs

Hai Duong · ThanhVu Nguyen · Matthew Dwyer

DepthVanish: Optimizing Adversarial Interval Structures for Stereo-Depth-Invisible Patches

Yun Xing · Yue Cao · Nhat Chung · Jie Zhang · Ivor Tsang · Ming-Ming Cheng · Yang Liu · Lei Ma · Qing Guo

On Feasible Rewards in Multi-Agent Inverse Reinforcement Learning

Till Freihaut · Giorgia Ramponi

Cost-Aware Contrastive Routing for LLMs

Reza Shirkavand · Shangqian Gao · Peiran Yu · Heng Huang

RAPTR: Radar-based 3D Pose Estimation using Transformer

Sorachi Kato · Ryoma Yataka · Pu Wang · Pedro Miraldo · Takuya Fujihashi · Petros Boufounos

Diversity-Aware Policy Optimization for Large Language Model Reasoning

Jian Yao · Ran Cheng · Xingyu Wu · Jibin Wu · KC Tan

AdaMSS: Adaptive Multi-Subspace Approach for Parameter-Efficient Fine-Tuning

Jingjing Zheng · Wanglong Lu · Yiming Dong · Chaojie Ji · Yankai Cao · Zhouchen Lin

PIVNO: Particle Image Velocimetry Neural Operator

Xu Jie · Xuesong Zhang · Jing Jiang · Qinghua Cui

Memory Decoder: A Pretrained, Plug-and-Play Memory for Large Language Models

Jiaqi Cao · Jiarui Wang · Rubin Wei · Qipeng Guo · Kai Chen · Bowen Zhou · Zhouhan Lin

Complexity Scaling Laws for Neural Models using Combinatorial Optimization

Lowell Weissman · Michael Krumdick · A. Abbott

SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning

Jiaqi Chen · Bang Zhang · Ruotian Ma · Peisong Wang · Xiaodan Liang · Zhaopeng Tu · Xiaolong Li · Kwan-Yee K. Wong

DartQuant: Efficient Rotational Distribution Calibration for LLM Quantization

YUANTIAN SHAO · Yuanteng Chen · Peisong Wang · Jianlin Yu · Jing Lin · yiwu yao · Zhihui Wei · Jian Cheng

ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning

Jingyang Yi · Jiazheng Wang · Sida Li

MindForge: Empowering Embodied Agents with Theory of Mind for Lifelong Cultural Learning

Mircea Lică · Ojas Shirekar · Baptiste Colle · Chirag Raman

QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks

Qian Chen · Linxin Yang · Akang Wang · Xiaodong Luo · Yin Zhang

REP: Resource-Efficient Prompting for Rehearsal-Free Continual Learning

Sungho Jeon · Xinyue Ma · Kwang In Kim · Myeongjae Jeon

FUDOKI: Discrete Flow-based Unified Understanding and Generation via Kinetic-Optimal Velocities

Jin Wang · Yao Lai · Aoxue Li · Shifeng Zhang · Jiacheng Sun · Ning Kang · Chengyue Wu · Zhenguo Li · Ping Luo

Context-Aware Hierarchical Learning: A Two-Step Paradigm towards Safer LLMs

Tengyun Ma · Damon Yao · Daojing He · Shihao Peng · YU LI · Shaohui Liu · Zhuotao Tian

Scaling Law with Learning Rate Annealing

Howe Tissue · Venus Wang · Lu Wang

Adaptive Gradient Masking for Balancing ID and MLLM-based Representations in Recommendation

Yidong Wu · Siyuan Chen · Binrui Wu · Fan Li · Jiechao Gao

Feature-Based Instance Neighbor Discovery: Advanced Stable Test-Time Adaptation in Dynamic World

Qinting Jiang · Chuyang Ye · Dongyan Wei · Bingli Wang · Yuan Xue · Jingyan Jiang · Zhi Wang

ARIA: Training Language Agents with Intention-driven Reward Aggregation

Ruihan Yang · yikai zhang · Aili Chen · Xintao Wang · Jiangjie Chen · Siyu Yuan · Deqing Yang · Yanghua Xiao

Revitalizing SVD for Global Covariance Pooling: Halley’s Method to Overcome Over-Flattening

Jiawei Gu · Ziyue Qiao · Xinming Li · Zechao Li

Robust Hallucination Detection in LLMs via Adaptive Token Selection

Mengjia Niu · Hamed Haddadi · Guansong Pang

Estimation and Inference in Distributional Reinforcement Learning

Liangyu Zhang · Yang Peng · Jiadong Liang · Wenhao Yang · Zhihua Zhang

Reasoning Gym: Reasoning Environments for Reinforcement Learning with Verifiable Rewards

Zafir Stojanovski · Oliver Stanley · Joe Sharratt · Richard Jones · Abdulhakeem Adefioye · Jean Kaddour · Andreas Köpf

Graph Neural Network Based Action Ranking for Planning

Rajesh Mangannavar · Stefan Lee · Alan Fern · Prasad Tadepalli

ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning

Timo Kaufmann · Yannick Metz · Daniel Keim · Eyke Hüllermeier

CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision

Awni Altabaa · Omar Montasser · John Lafferty

Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs

Yifan Zhou · Sachin Grover · Mohamed El Mistiri · Kamalesh Kalirathinam · Pratyush Kerhalkar · Swaroop Mishra · Neelesh Kumar · Sanket Gaurav · Oya Aran · Heni Ben Amor

Improving Reward Models with Proximal Policy Exploration for Preference-Based Reinforcement Learning

Yiwen Zhu · Jinyi Liu · Pengjie Gu · Yifu Yuan · Zhenxing Ge · Wenya Wei · Zhou Fang · Yujing Hu · Bo An

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models

Yiran Guo · Lijie Xu · Jie Liu · DAN YE · Shuang Qiu

OpenS2V-Nexus: A Detailed Benchmark and Million-Scale Dataset for Subject-to-Video Generation

Shenghai Yuan · Xianyi He · Yufan Deng · Yang Ye · Jinfa Huang · lin bin · Chongyang Ma · Jiebo Luo · Li Yuan

MultiHuman-Testbench: Benchmarking Image Generation for Multiple Humans

Shubhankar Borse · Seokeon Choi · Sunghyun Park · Jeongho Kim · Shreya Kadambi · Risheek Garrepalli · Sungrack Yun · Durga Malladi · Fatih Porikli

Normal-Abnormal Guided Generalist Anomaly Detection

Yuexin Wang · Xiaolei Wang · Yizheng Gong · Jimin XIAO

FALQON: Accelerating LoRA Fine-tuning with Low-Bit Floating-Point Arithmetic

Kanghyun Choi · Hyeyoon Lee · Sunjong Park · Dain Kwon · Jinho Lee

Accurate and Efficient Low-Rank Model Merging in Core Space

Aniello Panariello · Daniel Marczak · Simone Magistri · Angelo Porrello · Bartłomiej Twardowski · Andrew Bagdanov · SIMONE CALDERARA · Joost van de Weijer

Continuous Thought Machines

Luke Darlow · Ciaran Regan · Sebastian Risi · Jeffrey Seely · Llion Jones

HiMoLE: Towards OOD-Robust LoRA via Hierarchical Mixture of Experts

Yinuo Jiang · Yan Xiaodong · Keyan Ding · Deng Zhao · Lei Liang · Qiang Zhang · Huajun Chen

How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation

Xin Lu · Yanyan Zhao · Si Wei · Shijin Wang · Bing Qin · Ting Liu

LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits

Duy Nguyen · Archiki Prasad · Elias Stengel-Eskin · Mohit Bansal

Preserving Task-Relevant Information Under Linear Concept Removal

Floris Holstege · Shauli Ravfogel · Bram Wouters

GoalLadder: Incremental Goal Discovery with Vision-Language Models

Alexey Zakharov · Shimon Whiteson

EvaLearn: Quantifying the Learning Capability and Efficiency of LLMs via Sequential Problem Solving

Shihan Dou · Ming Zhang · Chenhao Huang · Jiayi Chen · Feng Chen · Shichun Liu · Yan Liu · Chenxiao Liu · CHENG ZHONG · Zongzhang Zhang · Tao Gui · Chao Xin · Wei Chengzhi · Lin Yan · Qi Zhang · Xuanjing Huang

Federated Dialogue-Semantic Diffusion for Emotion Recognition under Incomplete Modalities

Xihang Qiu · Jiarong Cheng · Yuhao Fang · Wanpeng Zhang · Yao Lu · Ye Zhang · Chun Li

Constrained Best Arm Identification

Tyron Lardy · Christina Katsimerou · Wouter Koolen

WHAT MAKES MATH PROBLEMS HARD FOR REINFORCEMENT LEARNING: A CASE STUDY

Ali Shehper · Anibal Medina-Mardones · Lucas Fagan · Bartłomiej Lewandowski · Angus Gruen · Yang Qiu · Piotr Kucharski · Zhenghan Wang · Sergei Gukov

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

Yuxiang Wei · Olivier Duchenne · Jade Copet · Quentin Carbonneaux · LINGMING ZHANG · Daniel Fried · Gabriel Synnaeve · Rishabh Singh · Sida Wang

GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning

Haolong Yan · Yeqing Shen · Xin Huang · Jia Wang · Kaijun Tan · Zhixuan Liang · Hongxin Li · Zheng Ge · Osamu Yoshie · Si Li · Xiangyu Zhang · Daxin Jiang

Contextual Integrity in LLMs via Reasoning and Reinforcement Learning

Guangchen (Eric) Lan · Huseyin A. Inan · Sahar Abdelnabi · Janardhan Kulkarni · Lukas Wutschitz · Reza Shokri · Christopher Brinton · Robert Sim

Martian World Model: Controllable Video Synthesis with Physically Accurate 3D Reconstructions

Longfei Li · Zhiwen Fan · Wenyan Cong · Xinhang Liu · Yuyang Yin · Matt Foutter · Panwang Pan · Chenyu You · Yue Wang · Zhangyang "Atlas" Wang · Yao Zhao · Marco Pavone · Yunchao Wei

ImgEdit: A Unified Image Editing Dataset and Benchmark

Yang Ye · Xianyi He · Zongjian Li · lin bin · Shenghai Yuan · Zhiyuan Yan · Bohan Hou · Li Yuan

BlurDM: A Blur Diffusion Model for Image Deblurring

Jin-Ting He · Fu-Jen Tsai · Yan-Tsung Peng · Min-Hung Chen · Chia-Wen Lin · Yen-Yu Lin

Let Them Talk: Audio-Driven Multi-Person Conversational Video Generation

Zhe Kong · Feng Gao · Yong Zhang · Zhuoliang Kang · Xiaoming Wei · Xunliang Cai · Guanying Chen · Wenhan Luo

FlexVAR: Flexible Visual Autoregressive Modeling without Residual Prediction

Siyu Jiao · Gengwei Zhang · Yinlong Qian · Jiancheng Huang · Yao Zhao · Humphrey Shi · Lin Ma · Yunchao Wei · Zequn Jie

Deno-IF: Unsupervised Noisy Visible and Infrared Image Fusion Method

Han Xu · Yuyang Li · Yunfei Deng · Jiayi Ma · Guangcan Liu

Fast constrained sampling in pre-trained diffusion models

Alexandros Graikos · Nebojsa Jojic · Dimitris Samaras

NEP: Autoregressive Image Editing via Next Editing Token Prediction

Huimin Wu · Xiaojian (Shawn) Ma · Haozhe Zhao · Yanpeng Zhao · Qing Li

Switchable Token-Specific Codebook Quantization For Face Image Compression

Yongbo Wang · Haonan Wang · Guodong Mu · Ruixin Zhang · Jiaqi Chen · Jingyun Zhang · Jun Wang · Yuan Xie · zhizhong zhang · Shouhong Ding

SPRO: Improving Image Generation via Self-Play

Ritika Jha · Aanisha Bhattacharyya · Yaman Singla · Rajiv Ratn Shah · Changyou Chen · Balaji Krishnamurthy

FlashMo: Geometric Interpolants and Frequency-Aware Sparsity for Scalable Efficient Motion Generation

Zeyu Zhang · Yiran Wang · Danning Li · Dong Gong · Ian Reid · Richard Hartley

UMAMI: Unifying Masked Autoregressive Models and Deterministic Rendering for View Synthesis

Thanh-Tung Le · Tuan Pham · Tung Nguyen · Deying Kong · Xiaohui Xie · Stephan Mandt

Dynamic Shadow Unveils Invisible Semantics for Video Outpainting

Ruilin Li · Hang Yu · Jiayan Qiu

FLOWING: Implicit Neural Flows for Structure-Preserving Morphing

Arthur Bizzi · Matias Grynberg Portnoy · Vitor Pereira Matias · Daniel Perazzo · João Paulo Silva do Monte Lima · Luiz Velho · Nuno Gonçalves · João Pereira · Guilherme Schardong · Tiago Novello

VideoMAR: Autoregressive Video Generation with Continuous Tokens

Hu Yu · Biao Gong · Hangjie Yuan · DanDan Zheng · Weilong Chai · Jingdong Chen · Kecheng Zheng · Feng Zhao

Kernel Density Steering: Inference-Time Scaling via Mode Seeking for Image Restoration

Yuyang Hu · Kangfu Mei · Mojtaba Ardakani · Ulugbek Kamilov · Peyman Milanfar · Mauricio Delbracio

AutoEdit: Automatic Hyperparameter Tuning for Image Editing

Chau Pham · Quan Dao · Mahesh Bhosale · Yunjie Tian · Dimitris Metaxas · DAVID DOERMANN

Force Prompting: Video Generation Models Can Learn And Generalize Physics-based Control Signals

Nate Gillman · Charles Herrmann · Michael Freeman · Daksh Aggarwal · Evan Luo · Deqing Sun · Chen Sun

LoRAShop: Training-Free Multi-Concept Image Generation and Editing with Rectified Flow Transformers

Yusuf Dalva · Hidir Yesiltepe · Pinar Yanardag

Scaling Diffusion Transformers Efficiently via $\mu$P

Chenyu Zheng · Xinyu Zhang · Rongzhen Wang · Wei Huang · Zhi Tian · Weilin Huang · Jun Zhu · Chongxuan LI

Temporal In‑Context Fine‑Tuning for Versatile Control of Video Diffusion Models

Kinam Kim · Junha Hyung · Jaegul Choo

Overcoming Challenges of Long-Horizon Prediction in Driving World Models

Arian Mousakhan · Sudhanshu Mittal · Silvio Galesso · Karim Farid · Thomas Brox

Ambient Diffusion Omni: Training Good Models with Bad Data

Giannis Daras · Adrian Rodriguez-Munoz · Adam Klivans · Antonio Torralba · Constantinos Daskalakis

A Minimalistic Unified Framework for Incremental Learning across Image Restoration Tasks

Xiaoxuan Gong · Jie Ma

UltraHR-100K: Enhancing UHR Image Synthesis with A Large-Scale High-Quality Dataset

Chen Zhao · En Ci · Yunzhe Xu · Tiehan Fan · Shanyan Guan · Yanhao Ge · Jian Yang · Ying Tai

Foundation Cures Personalization: Improving Personalized Models’ Prompt Consistency via Hidden Foundation Knowledge

Yiyang Cai · Zhengkai Jiang · Yulong Liu · Chunyang Jiang · Wei Xue · Yike Guo · Wenhan Luo

ASDSV: Multimodal Generation Made Efficient with Approximate Speculative Diffusion and Speculative Verification

Kaijun Zhou · Xingyu Yan · Xingda Wei · Xijun Li · Jinyu Gu

Chain-of-Zoom: Extreme Super-Resolution via Scale Autoregression and Preference Alignment

Bryan Sangwoo Kim · Jeongsol Kim · Jong Chul Ye

Re-ttention: Ultra Sparse Visual Generation via Attention Statistical Reshape

Ruichen Chen · Keith Mills · Liyao Jiang · Chao Gao · Di Niu

Learning World Models for Interactive Video Generation

Taiye Chen · Xun Hu · Zihan Ding · Chi Jin

From Programs to Poses: Factored Real-World Scene Generation via Learned Program Libraries

Joy Hsu · Emily Jin · Jiajun Wu · Niloy Mitra

From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging

Tao Liu · Dafeng Zhang · Gengchen Li · Shizhuo Liu · yongqi song · Senmao Li · Shiqi Yang · Boqian Li · Kai Wang · Yaxing Wang

SparseDiT: Token Sparsification for Efficient Diffusion Transformer

Shuning Chang · Pichao WANG · Jiasheng Tang · Fan Wang · Yi Yang

Balanced Conic Rectified Flow

Kim Shin seong · Mingi Kwon · Jaeseok Jeong · Youngjung Uh

SplitFlow: Flow Decomposition for Inversion-Free Text-to-Image Editing

Sung-Hoon Yoon · Minghan Li · Gaspard Beaudouin · Congcong Wen · Muhammad Rafay Azhar · Mengyu Wang

Where and How to Perturb: On the Design of Perturbation Guidance in Diffusion and Flow Models

Donghoon Ahn · Jiwon Kang · Sanghyun Lee · Minjae Kim · Wooseok Jang · Jaewon Min · Sangwu Lee · Sayak Paul · Seungryong Kim

NFIG: Multi-Scale Autoregressive Image Generation via Frequency Ordering

Zhihao Huang · Xi Qiu · Yukuo Ma · Yifu Zhou · Junjie Chen · Hongyuan Zhang · Chi Zhang · Xuelong Li

Mitigating Occlusions in Virtual Try-On via A Simple-Yet-Effective Mask-Free Framework

Chenghu Du · Shengwu Xiong · junyin Wang · Yi Rong · Shili Xiong

Align Your Flow: Scaling Continuous-Time Flow Map Distillation

Amirmojtaba Sabour · Sanja Fidler · Karsten Kreis

Consistent Story Generation: Unlocking the Potential of Zigzag Sampling

Mingxiao Li · Mang Ning · Marie-Francine Moens

WorldWeaver: Generating Long-Horizon Video Worlds via Rich Perception

Zhiheng Liu · Xueqing Deng · Shoufa Chen · Angtian Wang · Qiushan Guo · Mingfei Han · Zeyue Xue · Mengzhao Chen · Ping Luo · Linjie Yang

Locality in Image Diffusion Models Emerges from Data Statistics

Artem Lukoianov · Chenyang Yuan · Justin Solomon · Vincent Sitzmann

Hierarchical Fine-grained Preference Optimization for Physically Plausible Video Generation

Harold Haodong Chen · Haojian Huang · Qifeng Chen · Harry Yang · Ser Nam Lim

Semantic and Visual Crop-Guided Diffusion Models for Heterogeneous Tissue Synthesis in Histopathology

Saghir Alfasly · Wataru Uegami · MD ENAMUL HOQ · Ghazal Alabtah · Hamid Tizhoosh

Bifrost-1: Bridging Multimodal LLMs and Diffusion Models with Patch-level CLIP Latents

Han Lin · Jaemin Cho · Amir Zadeh · Chuan Li · Mohit Bansal

Spik-NeRF: Spiking Neural Networks for Neural Radiance Fields

Gang Wan · Qinlong Lan · Zihan Li · Huimin Wang · Wu Yitian · wang zhen · Wanhua Li · Yufei Guo

ProDyG: Progressive Dynamic Scene Reconstruction via Gaussian Splatting from Monocular Videos

Shi Chen · Erik Sandström · Sandro Lombardi · Siyuan Li · Martin R. Oswald

VGGT-SLAM: Dense RGB SLAM Optimized on the SL(4) Manifold

Dominic Maggio · Hyungtae Lim · Luca Carlone

SyncHuman: Synchronizing 2D and 3D Generative Models for Single-view Human Reconstruction

Wenyue Chen · Peng Li · Wangguandong Zheng · Chengfeng Zhao · Mengfei Li · Yaolong Zhu · Zhiyang Dou · Ronggang Wang · Yuan Liu

FHGS: Feature-Homogenized Gaussian Splatting

qigeng duan · Benyun ZHAO · Mingqiao Han · Yijun Huang · Ben Chen

SIU3R: Simultaneous Scene Understanding and 3D Reconstruction Beyond Feature Alignment

QiXu · Dongxu Wei · Lingzhe Zhao · Wenpu Li · Zhangchi Huang · Shunping Ji · Peidong Liu

DGH: Dynamic Gaussian Hair

Junying Wang · Yuanlu Xu · Edith Tretschk · Ziyan Wang · Anastasia Ianina · Aljaz Bozic · Ulrich Neumann · Tony Tung

TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixels

Jiahao Lu · Weitao Xiong · Jiacheng Deng · Peng Li · Tianyu Huang · Zhiyang Dou · Cheng Lin · Sai-Kit Yeung · Yuan Liu

EF-3DGS: Event-Aided Free-Trajectory 3D Gaussian Splatting

Bohao Liao · Wei Zhai · Zengyu Wan · Zhixin Cheng · Wenfei Yang · Yang Cao · Tianzhu Zhang · Zheng-Jun Zha

Eve3D: Elevating Vision Models for Enhanced 3D Surface Reconstruction via Gaussian Splatting

Jiawei Zhang · Youmin Zhang · Fabio Tosi · Meiying Gu · Jiahe Li · Xiaohan Yu · Jin Zheng · Xiao Bai · Matteo Poggi

Unifying Appearance Codes and Bilateral Grids for Driving Scene Gaussian Splatting

Nan Wang · Lixing Xiao · Yuantao Chen · Weiqing Xiao · Pierre Merriaux · Lei Lei · Ziyang Yan · Saining Zhang · Shaocong Xu · chongjie Ye · Bohan Li · Zhaoxi Chen · Tianfan Xue · Hao Zhao

Feed-Forward Bullet-Time Reconstruction of Dynamic Scenes from Monocular Videos

hanxue liang · Jiawei Ren · Ashkan Mirzaei · Antonio Torralba · Ziwei Liu · Igor Gilitschenski · Sanja Fidler · Cengiz Oztireli · Huan Ling · Zan Gojcic · Jiahui Huang

Enhancing 3D Reconstruction for Dynamic Scenes

Jisang Han · Honggyu An · Jaewoo Jung · Takuya Narihira · Junyoung Seo · Kazumi Fukuda · Chaehyun Kim · Sunghwan Hong · Yuki Mitsufuji · Seungryong Kim

KaRF: Weakly-Supervised Kolmogorov-Arnold Networks-based Radiance Fields for Local Color Editing

Wudi Chen · Zhiyuan Zha · Shigang Wang · Bihan Wen · Xin Yuan · Jiantao Zhou · zipei fan · Gang Yan · Ce Zhu

Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos

Junyi Wu · Jiachen Tao · Haoxuan Wang · Gaowen Liu · Ramana Kompella · Yan Yan

BecomingLit: Relightable Gaussian Avatars with Hybrid Neural Shading

Jonathan Schmidt · Simon Giebenhain · Matthias Niessner

Rectified Point Flow: Generic Point Cloud Pose Estimation

Tao Sun · Liyuan Zhu · Shengyu Huang · Shuran Song · Iro Armeni

LinPrim: Linear Primitives for Differentiable Volumetric Rendering

Nicolas von Lützow · Matthias Niessner

PLANA3R: Zero-shot Metric Planar 3D Reconstruction via Feed-forward Planar Splatting

Changkun Liu · Bin Tan · Zeran Ke · Shangzhan Zhang · Jiachen Liu · Ming Qian · Nan Xue · Yujun Shen · Tristan Braud

Unified 2D-3D Discrete Priors for Noise-Robust and Calibration-Free Multiview 3D Human Pose Estimation

Geng Chen · Pengfei Ren · Xufeng Jian · Haifeng Sun · Menghao Zhang · Qi Qi · Zirui Zhuang · Jing Wang · Jianxin Liao · Jingyu Wang

GeGS-PCR: Fast and Robust Color 3D Point Cloud Registration with Two-Stage Geometric-3DGS Fusion

Jiayi Tian · Haiduo Huang · Tian Xia · Wenzhe zhao · Pengju Ren

MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning

Jinkun Hao · Naifu Liang · Zhen Luo · Xudong XU · Weipeng Zhong · Ran Yi · Yichen Jin · Zhaoyang Lyu · Feng Zheng · Lizhuang Ma · Jiangmiao Pang

NopeRoomGS: Indoor 3D Gaussian Splatting Optimization without Camera Pose Input

Wenbo Li · Yan Xu · Mingde Yao · Fengjie Liang · Jiankai Sun · Menglu Wang · Guofeng Zhang · Linjiang Huang · Hongsheng Li

Evaluating Robustness of Monocular Depth Estimation with Procedural Scene Perturbations

Jack Nugent · Siyang Wu · Zeyu Ma · Beining Han · Meenal Parakh · Abhishek Joshi · Lingjie Mei · Alexander Raistrick · Xinyuan Li · Jia Deng

DC4GS: Directional Consistency-Driven Adaptive Density Control for 3D Gaussian Splatting

Moonsoo Jeong · Dongbeen Kim · Minseong Kim · Sungkil Lee

Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation

Jiyuan Wang · Chunyu Lin · cheng guan · Lang Nie · Jing He · Haodong Li · Kang Liao · Yao Zhao

Cycle-Sync: Robust Global Camera Pose Estimation through Enhanced Cycle-Consistent Synchronization

Shaohan Li · Yunpeng Shi · Gilad Lerman

Holistic Large-Scale Scene Reconstruction via Mixed Gaussian Splatting

Chuandong Liu · Huijiao Wang · Lei YU · Gui-Song Xia

ZPressor: Bottleneck-Aware Compression for Scalable Feed-Forward 3DGS

Weijie Wang · Donny Y. Chen · Zeyu Zhang · Duochao Shi · Akide Liu · Bohan Zhuang

Novel View Synthesis from A Few Glimpses via Test-Time Natural Video Completion

Yan Xu · Yixing Wang · Stella X. Yu

SeePhys: Does Seeing Help Thinking? – Benchmarking Vision-Based Physics Reasoning

Kun Xiang · Heng Li · Terry Jingchen Zhang · Yinya Huang · Zirong Liu · Peixin Qu · Jixi He · Jiaqi Chen · Yu-Jie Yuan · Jianhua Han · Hang Xu · Hanhui Li · Mrinmaya Sachan · Xiaodan Liang

From Objects to Anywhere: A Holistic Benchmark for Multi-level Visual Grounding in 3D Scenes

Tianxu Wang · Zhuofan Zhang · Ziyu Zhu · Yue Fan · Jing Xiong · Pengxiang Li · Xiaojian (Shawn) Ma · Qing Li

Hyperphantasia: A Benchmark for Evaluating the Mental Visualization Capabilities of Multimodal LLMs

Mohammad Shahab Sepehri · Berk Tinaz · Zalan Fabian · Mahdi Soltanolkotabi

Fire360: A Benchmark for Robust Perception and Episodic Memory in Degraded 360° Firefighting Video

Aditi Tiwari · Farzaneh Masoud · Dac Nguyen · Jill Kraft · Heng Ji · Klara Nahrstedt

CrypticBio: A Large Multimodal Dataset for Visually Confusing Species

Georgiana Manolache · Gerard Schouten · Joaquin Vanschoren

EgoExoBench: A Benchmark for First- and Third-person View Video Understanding in MLLMs

Yuping He · Yifei Huang · Guo Chen · Baoqi Pei · Jilan Xu · Tong Lu · Jiangmiao Pang

MONITRS: Multimodal Observations of Natural Incidents Through Remote Sensing

Shreelekha Revankar · Utkarsh Mall · Cheng Perng Phoo · Kavita Bala · Bharath Hariharan

MME-VideoOCR: Evaluating OCR-Based Capabilities of Multimodal LLMs in Video Scenarios

Yang Shi · Huanqian Wang · Xie · Huanyao Zhang · Lijie Zhao · yifan zhang · Xinfeng Li · Chaoyou Fu · Zhuoer Wen · Wenting Liu · Zhuoran Zhang · Xinlong Chen · Bohan Zeng · Sihan Yang · Yushuo Guan · Zhang Zhang · Liang Wang · Haoxuan Li · Zhouchen Lin · Yuanxing Zhang · Pengfei Wan · Haotian Wang · Wenjing Yang

IndEgo: A Dataset of Industrial Scenarios and Collaborative Work for Egocentric Assistants

Vivek Chavan · Yasmina Imgrund · Tung Dao · Sanwantri Bai · Bosong Wang · Ze Lu · Oliver Heimann · Jörg Krüger

Impromptu VLA: Open Weights and Open Data for Driving Vision-Language-Action Models

Haohan Chi · Huan-ang Gao · Ziming Liu · Jianing Liu · Chenyu Liu · Jinwei Li · Kaisen Yang · Yangcheng Yu · Zeda Wang · Wenyi Li · Leichen Wang · Xingtao HU · HAO SUN · Hang Zhao · Hao Zhao

InfoChartQA: A Benchmark for Multimodal Question Answering on Infographic Charts

Tianchi Xie · Minzhi Lin · Mengchen Liu · Yilin Ye · Changjian Chen · Shixia Liu

Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models

Jun Ling · Yao Qi · Tao Huang · Shibo Zhou · Yanqin Huang · Jiang Yang · Ziqi Song · Ying Zhou · Yang Yang · Hengtao Shen · Peng Wang

Recurrent Attention-based Token Selection for Efficient Streaming Video-LLMs

Evangelos Dorovatas · Soroush Seifi · Gunshi Gupta · Rahaf Aljundi

VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Set

Shufan Shen · Junshu Sun · Qingming Huang · Shuhui Wang

Eyes Wide Open: Ego Proactive Video-LLM for Streaming Video

Xueyang Yu · Cheng Shi · Yang Wang · Sibei Yang

Generate, but Verify: Reducing Hallucination in Vision-Language Models with Retrospective Resampling

Tsung-Han (Patrick) Wu · Heekyung Lee · Jiaxin Ge · Joseph Gonzalez · Trevor Darrell · David Chan

Gaze Beyond the Frame: Forecasting Egocentric 3D Visual Span

Heeseung Yun · Joonil Na · Jaeyeon Kim · Calvin Murdock · Gunhee Kim

Adaptive Re-calibration Learning for Balanced Multimodal Intention Recognition

Qu Yang · Xiyang Li · Fu Lin · Mang Ye

Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models

Xiaoyu Zhan · Wenxuan Huang · Hao Sun · Xinyu Fu · Changfeng Ma · Shaosheng Cao · Bohan Jia · Shaohui Lin · Zhenfei Yin · LEI BAI · Wanli Ouyang · Yuanqi Li · Jie Guo · Yanwen Guo

Self-alignment of Large Video Language Models with Refined Regularized Preference Optimization

Pritam Sarkar · Ali Etemad

Amplifying Prominent Representations in Multimodal Learning via Variational Dirichlet Process

Tsai Hor Chan · Feng Wu · Yihang Chen · Guosheng Yin · Lequan Yu

RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability

Jonggwon Park · Byungmu Yoon · Soobum Kim · Kyoyun Choi

Image Token Matters: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing

Weixing Wang · Zifeng Ding · Jindong Gu · RUI CAO · Christoph Meinel · Gerard de Melo · Haojin Yang

Partition-Then-Adapt: Combating Prediction Bias for Reliable Multi-Modal Test-Time Adaptation

Guowei Wang · Fan Lyu · Changxing Ding

Prioritizing Perception-Guided Self-Supervision: A New Paradigm for Causal Modeling in End-to-End Autonomous Driving

Yi Huang · Zhan Qu · Lihui Jiang · Bingbing Liu · Hongbo Zhang

Advancing Compositional Awareness in CLIP with Efficient Fine-Tuning

Amit Peleg · Naman Deep Singh · Matthias Hein

Elastic ViTs from Pretrained Models without Retraining

Walter Simoncini · Michael Dorkenwald · Tijmen Blankevoort · Cees Snoek · Yuki Asano

RoboRefer: Towards Spatial Referring with Reasoning in Vision-Language Models for Robotics

Enshen Zhou · Jingkun An · Cheng Chi · Yi Han · Shanyu Rong · Chi Zhang · Pengwei Wang · Zhongyuan Wang · Tiejun Huang · Lu Sheng · Shanghang Zhang

ROVER: Recursive Reasoning Over Videos with Vision-Language Models for Embodied Tasks

Philip Schroeder · Ondrej Biza · Thomas Weng · Hongyin Luo · Jim Glass

UniViT: Unifying Image and Video Understanding in One Vision Encoder

feilong tang · xiangan · Haolin Yang · Yin Xie · Kaicheng Yang · Ming Hu · Zheng Cheng · Xingyu Zhou · Zimin Ran · Imran Razzak · Ziyong Feng · Behzad Bozorgtabar · Jiankang Deng · Zongyuan Ge

LongVPO: From Anchored Cues to Self-Reasoning for Long-Form Video Preference Optimization

Zhenpeng Huang · Jiaqi Li · zihan jia · Xinhao Li · Desen Meng · Lingxue Song · Xi Chen · Liang Li · Limin Wang

Learning Source-Free Domain Adaptation for Visible-Infrared Person Re-Identification

Yongxiang Li · Yanglin Feng · Yuan Sun · Dezhong Peng · Xi Peng · Peng Hu

Fully Spiking Neural Networks for Unified Frame-Event Object Tracking

Jingjun Yang · Liangwei Fan · Jinpu Zhang · Xiangkai Lian · Hui Shen · Dewen Hu

Towards Reliable and Holistic Visual In-Context Learning Prompt Selection

Wenxiao Wu · Jing-Hao Xue · Chengming Xu · Chen Liu · Xinwei Sun · Changxin Gao · Nong Sang · Yanwei Fu

VIBE: Annotation-Free Video-to-Text Information Bottleneck Evaluation for TL;DR

Shenghui Chen · Po-han Li · Sandeep Chinchali · Ufuk Topcu

Why 1 + 1 < 1 in Visual Token Pruning: Beyond Naive Integration via Multi-Objective Balanced Covering

Yangfu Li · Hongjian Zhan · Tianyi Chen · Qi Liu · Yu-Jie Xiong · Yue Lu

Retrv-R1: A Reasoning-Driven MLLM Framework for Universal and Efficient Multimodal Retrieval

Lanyun Zhu · Deyi Ji · Tianrun Chen · Haiyang Wu · Shiqi Wang

PC-Net: Weakly Supervised Compositional Moment Retrieval via Proposal-Centric Network

Mingyao Zhou · Hao Sun · Wei Xie · Ming Dong · Chengji Wang · Mang Ye

Vision Function Layer in Multimodal LLMs

Cheng Shi · Yizhou Yu · Sibei Yang

Deep Video Discovery: Agentic Search with Tool Use for Long-form Video Understanding

Xiaoyi Zhang · Zhaoyang Jia · Zongyu Guo · Jiahao Li · Bin Li · Houqiang Li · Yan Lu

Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors

Duo Zheng · shijia Huang · Yanyang Li · Liwei Wang

Empower Words: DualGround for Structured Phrase and Sentence-Level Temporal Grounding

Minseok Kang · Minhyeok Lee · Minjung Kim · Donghyeong Kim · Sangyoun Lee

Towards Physics-informed Spatial Intelligence with Human Priors: An Autonomous Driving Pilot Study

Guanlin (Frank) Wu · Boyan Su · Yang Zhao · Pu Wang · Yichen Lin · Hao Frank Yang

3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model

Wenbo Hu · Yining Hong · Yanjun Wang · Leison Gao · Zibu Wei · Xingcheng Yao · Nanyun Peng · Yonatan Bitton · Idan Szpektor · Kai-Wei Chang

Backpropagation-Free Test-Time Adaptation via Probabilistic Gaussian Alignment

Youjia Zhang · Youngeun Kim · Young-Geun Choi · Hongyeob Kim · Huiling Liu · Sungeun Hong

PrefixKV: Adaptive Prefix KV Cache is What Vision Instruction-Following Models Need for Efficient Generation

Ao Wang · Hui Chen · Jianchao Tan · Kefeng Zhang · Xunliang Cai · Zijia Lin · Jungong Han · guiguang ding

Mitigating Hallucination Through Theory-Consistent Symmetric Multimodal Preference Optimization

Wenqi Liu · Xuemeng Song · Jiaxi Li · Yinwei Wei · Na Zheng · Jianhua Yin · Liqiang Nie

Rare Text Semantics Were Always There in Your Diffusion Transformer

seil kang · Woojung Han · Dayun Ju · Seong Jae Hwang

OmniResponse: Online Multimodal Conversational Response Generation in Dyadic Interactions

Cheng Luo · Jianghui Wang · Bing Li · Siyang Song · Bernard Ghanem

STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization

Diqi He · Xuehao Gao · Hao Li · Junwei Han · Dingwen Zhang

Towards 3D Objectness Learning in an Open World

Taichi Liu · Zhenyu Wang · Ruofeng Liu · Guang Wang · Desheng Zhang

Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought

ZIhui Cheng · Qiguang Chen · Xiao Xu · Jiaqi Wang · Weiyun Wang · Hao Fei · Yidong Wang · Alex Jinpeng Wang · Zhi Chen · Wanxiang Che · Libo Qin

Reinforcing Spatial Reasoning in Vision-Language Models with Interwoven Thinking and Visual Drawing

Junfei Wu · Jian Guan · Kaituo Feng · Qiang Liu · Shu Wu · Liang Wang · Wei Wu · Tieniu Tan

Spatially-aware Weights Tokenization for NeRF-Language Models

Andrea Amaduzzi · Pierluigi Zama Ramirez · Giuseppe Lisanti · Samuele Salti · Luigi Di Stefano

Dynamic Masking and Auxiliary Hash Learning for Enhanced Cross-Modal Retrieval

Shuang Zhang · Yue Wu · Lei Shi · Yingxue Zhang · Feifei Kou · Huilong Jin · Pengfei Zhang · Meiyu Liang · Mingying Xu

COS3D: Collaborative Open-Vocabulary 3D Segmentation

Runsong Zhu · Ka-Hei Hui · Zhengzhe Liu · Qianyi Wu · Weiliang Tang · Shi Qiu · Pheng-Ann Heng · Chi-Wing Fu

InstructSAM: A Training-free Framework for Instruction-Oriented Remote Sensing Object Recognition

Yijie Zheng · Weijie Wu · Qingyun Li · Xuehui Wang · Xu Zhou · Aiai Ren · Jun Shen · Long Zhao · Guoqing Li · Xue Yang

Right for the Right Reasons: Avoiding Reasoning Shortcuts via Prototypical Neurosymbolic AI

Luca Andolfi · Eleonora Giunchiglia

Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns

Menghao Zhang · Huazheng Wang · Pengfei Ren · Kangheng Lin · Qi Qi · Haifeng Sun · Zirui Zhuang · Lei Zhang · Jianxin Liao · Jingyu Wang

Towards Reliable Identification of Diffusion-based Image Manipulations

Alex Costanzino · Woody Bayliss · Juil Sock · Marc Gorriz Blanch · Danijela Horak · Ivan Laptev · Philip Torr · Fabio Pizzati

DevFD : Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces

Tianshuo Zhang · Li Gao · Siran Peng · Xiangyu Zhu · Zhen Lei

Unbiased Prototype Consistency Learning for Multi-Modal and Multi-Task Object Re-Identification

Zhongao Zhou · Bin Yang · Wenke Huang · Jun Chen · Mang Ye

Unlabeled Data Improves Fine-Grained Image Zero-shot Classification with Multimodal LLMs

Yunqi Hong · Sohyun An · Andrew Bai · Neil Lin · Cho-Jui Hsieh

Mamba Only Glances Once (MOGO): A Lightweight Framework for Efficient Video Action Detection

Yunqing Liu · Nan Zhang · Fangjun Wang · Kengo Murata · Takuma Yamamoto · Osafumi Nakayama · Genta Suzuki · Zhiming Tan

Model Editing for Vision Transformers

Xinyi Huang · Kangfei Zhao · Long-Kai Huang

DSRF: A Dynamic and Scalable Reasoning Framework for Solving RPMs

Chengtai Li · Yuting He · Jianfeng Ren · Ruibin Bai · Yitian Zhao · Xudong Jiang

Guard Me If You Know Me: Protecting Specific Face-Identity from Deepfakes

Kaiqing Lin · Zhiyuan Yan · Ke-Yue Zhang · Li Hao · Yue Zhou · Yuzhen Lin · Weixiang Li · Taiping Yao · Shouhong Ding · Bin Li

EA3D: Online Open-World 3D Object Extraction from Streaming Videos

Xiaoyu Zhou · Jingqi Wang · Yuang Jia · Yongtao Wang · Deqing Sun · Ming-Hsuan Yang

Accident Anticipation via Temporal Occurrence Prediction

Tianhao Zhao · Yiyang Zou · Zihao Mao · Peilun Xiao · Yulin Huang · Hongda Yang · Yuxuan Li · Tracy Li · Guobin Wu · Yutian Lin

Object-centric binding in Contrastive Language-Image Pretraining

Rim Assouel · Pietro Astolfi · Florian Bordes · Michal Drozdzal · Adriana Romero-Soriano

Looking Beyond the Known: Towards a Data Discovery Guided Open-World Object Detection

Anay Majee · Amitesh Gangrade · Rishabh Iyer

Denoising Trajectory Biases for Zero-Shot AI-Generated Image Detection

Yachao Liang · Min Yu · Gang Li · Jianguo Jiang · Fuqiang Du · Jingyuan Li · Lanchi Xie · Zhen Xu · Weiqing Huang

mmWalk: Towards Multi-modal Multi-view Walking Assistance

Kedi Ying · Ruiping Liu · Chongyan Chen · Mingzhe Tao · Hao Shi · Kailun Yang · Jiaming Zhang · Rainer Stiefelhagen

Reasoning Beyond Points: A Visual Introspective Approach for Few-Shot 3D Segmentation

Changshuo Wang · Shuting He · Xiang Fang · Zhijian Hu · JIA-HONG HUANG · Yixian Shen · Prayag Tiwari

SAM-R1: Leveraging SAM for Reward Feedback in Multimodal Segmentation via Reinforcement Learning

Jiaqi Huang · Zunnan Xu · Jun Zhou · Ting Liu · Yicheng Xiao · Mingwen Ou · Bowen Ji · Xiu Li · Kehong Yuan

SegGraph: Leveraging Graphs of SAM Segments for Few-Shot 3D Part Segmentation

Yueyang Hu · Haiyong Jiang · Haoxuan Song · Jun Xiao · Hao Pan

LoMix: Learnable Weighted Multi-Scale Logits Mixing for Medical Image Segmentation

Md Mostafijur Rahman · Radu Marculescu

Inference with correlated priors using sisters cells

Sina Tootoonian · Andreas Schaefer

YOLOv12: Attention-Centric Real-Time Object Detectors

Yunjie Tian · Qixiang Ye · DAVID DOERMANN

Handling Label Noise via Instance-Level Difficulty Modeling and Dynamic Optimization

Kuan Zhang · Chengliang Chai · Jingzhe Xu · Chi Zhang · Han Han · Ye Yuan · Guoren Wang · Lei Cao

Vocabulary-Guided Gait Recognition

Panjian Huang · Saihui Hou · Chunshui Cao · Xu Liu · Yongzhen Huang

LT-Soups: Bridging Head and Tail Classes via Subsampled Model Soups

Masih Aminbeidokhti · Subhankar Roy · Eric Granger · Elisa Ricci · Marco Pedersoli

Doodle to Detect: A Goofy but Powerful Approach to Skeleton-based Hand Gesture Recognition

Sang Han · Seonho Lee · Hyeok Nam · Jae Hyeon Park · Min Hee Cha · Min Geol Kim · Hyunse Lee · Sangyeon Ahn · Moonju Chae · Sung In Cho

FastDINOv2: Frequency Based Curriculum Learning Improves Robustness and Training Speed

Jiaqi Zhang · Juntuo Wang · Zhixin Sun · John Zou · Randall Balestriero

FlareX: A Physics-Informed Dataset for Lens Flare Removal via 2D Synthesis and 3D Rendering

Lishen Qu · Zhihao Liu · Jinshan Pan · Shihao Zhou · Jinglei Shi · Duosheng Chen · Jufeng Yang

GPLQ: A General, Practical, and Lightning QAT Method for Vision Transformers

Guang Liang · Xinyao Liu · Jianxin Wu

Lattice Boltzmann Model for Learning Real-World Pixel Dynamicity

Guangze Zheng · Shijie Lin · Haobo Zuo · Si Si · Ming-Shan Wang · Changhong Fu · Jia Pan

Zero-shot Denoising via Neural Compression: Theoretical and algorithmic framework

Ali Zafari · Xi Chen · Shirin Jalali

Latent Chain-of-Thought for Visual Reasoning

Guohao Sun · Hang Hua · Jian Wang · Jiebo Luo · Sohail Dianat · MAJID RABBANI · Raghuveer Rao · Zhiqiang Tao

Bridging the gap to real-world language-grounded visual concept learning

whie jung · Semin Kim · Junee Kim · Seunghoon Hong

Quantum Visual Fields with Neural Amplitude Encoding

Shuteng Wang · Christian Theobalt · Vladislav Golyanik

PMQ-VE: Progressive Multi-Frame Quantization for Video Enhancement

ZhanFeng Feng · Long Peng · Xin Di · Yong Guo · Wenbo Li · Yulun Zhang · Renjing Pei · Yang Wang · Yang Cao · Zheng-Jun Zha

DualFocus: Depth from Focus with Spatio-Focal Dual Variational Constraints

Sungmin Woo · Sangyoun Lee

Learning Differential Pyramid Representation for Tone Mapping

Qirui Yang · Yinbo Li · Yihao Liu · Peng-Tao Jiang · Fangpu Zhang · cheng qihua · Huanjing Yue · Jingyu Yang

RigAnyFace: Scaling Neural Facial Mesh Auto-Rigging with Unlabeled Data

Wenchao Ma · Dario Kneubuehler · Maurice Chu · Ian Sachs · Haomiao Jiang · Sharon Huang

FlexEvent: Towards Flexible Event-Frame Object Detection at Varying Operational Frequencies

Dongyue Lu · Lingdong Kong · Gim Hee Lee · Camille Simon Chane · Wei Tsang Ooi

FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Driving

Shuang Zeng · Xinyuan Chang · Mengwei Xie · Xinran Liu · Yifan Bai · Zheng Pan · Mu Xu · Xing Wei

LoRATv2: Enabling Low-Cost Temporal Modeling in One-Stream Trackers

Liting Lin · Heng Fan · Zhipeng Zhang · Yuqing Huang · Yaowei Wang · Yong Xu · Haibin Ling

Rethinking Scale-Aware Temporal Encoding for Event-based Object Detection

Lin Zhu · Tengyu Long · Xiao Wang · Lizhi Wang · Hua Huang

Learning to Condition: A Neural Heuristic for Scalable MPE Inference

Brij Malhotra · Shivvrat Arya · Tahrima Rahman · Vibhav Gogate

NeuSymEA: Neuro-symbolic Entity Alignment via Variational Inference

Shengyuan Chen · Zheng Yuan · Qinggang Zhang · Wen Hua · Jiannong Cao · Xiao Huang

Stochastic Process Learning via Operator Flow Matching

Yaozhong Shi · Zachary Ross · Domniki Asimaki · Kamyar Azizzadenesheli

Spectral Convolutional Conditional Neural Process

Peiman Mohseni · Nick Duffield

Generator-Mediated Bandits: Thompson Sampling for GenAI-Powered Adaptive Interventions

Marc Brooks · Gabriel Durham · Kihyuk Hong · Ambuj Tewari

Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data

Yunhao Tang · Sid Wang · Lovish Madaan · Remi Munos

PoE-World: Compositional World Modeling with Products of Programmatic Experts

Top Piriyakulkij · Yichao Liang · Hao Tang · Adrian Weller · Marta Kryven · Kevin Ellis

Improving LLM General Preference Alignment via Optimistic Online Mirror Descent

Yuheng Zhang · Dian Yu · Tao Ge · Linfeng Song · Zhichen Zeng · Haitao Mi · Nan Jiang · Dong Yu

KL-Regularized RLHF with Multiple Reference Models: Exact Solutions and Sample Complexity

Gholamali Aminian · Amir R. Asadi · Idan Shenfeld · Youssef Mroueh

MedChain: Bridging the Gap Between LLM Agents and Clinical Practice with Interactive Sequence

Jie Liu · Wenxuan Wang · Zizhan Ma · Guolin Huang · Yihang SU · Kao-Jung Chang · Haoliang Li · Linlin Shen · Michael R Lyu · Wenting Chen

RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering

Rongyang Zhang · Yuqing Huang · Chengqiang Lu · Qimeng Wang · Yan Gao · YIWU · Yao Hu · Yin Xu · Wei Wang · Hao Wang · Enhong Chen

A Technical Report on “Erasing the Invisible”: The 2024 NeurIPS Competition on Stress Testing Image Watermarks

Mucong Ding · Bang An · Tahseen Rabbani · Chenghao Deng · Anirudh Satheesh · Souradip Chakraborty · Mehrdad Saberi · Yuxin Wen · Kyle Sang · Aakriti Agrawal · Xuandong Zhao · Mo Zhou · Mary-Anne Hartley · Lei Li · Yu-Xiang Wang · Vishal Patel · Soheil Feizi · Tom Goldstein · Furong Huang

SuperGPQA: Scaling LLM Evaluation across 285 Graduate Disciplines

Xeron Du · Yifan Yao · Kaijing Ma · Bingli Wang · Tianyu Zheng · Zhu · Minghao Liu · Yiming Liang · Xiaolong Jin · Zhenlin Wei · Chujie Zheng · Kaixin Deng · Shuyue Guo · Shian Jia · Sichao Jiang · Yiyan Liao · Rui Li · Qinrui Li · Sirun Li · Yizhi Li · Yunwen Li · Dehua Ma · Yuansheng Ni · Haoran Que · Qiyao Wang · Zhoufutu Wen · Siwei Wu · Tianshun Xing · 明许 · Zhenzhu Yang · Noah Wang · Junting Zhou · yuelin bai · Xingyuan Bu · chenglin cai · Liang Chen · Yifan Chen · Cheng Chengtuo · Tianhao Cheng · Keyi Ding · Siming Huang · HUANG YUN · Yaoru Li · Yizhe Li · Zhaoqun Li · Tianhao Liang · Chengdong Lin · Hongquan Lin · Yinghao Ma · Zhongyuan Peng · Zifan Peng · Qige Qi · Shi Qiu · Xingwei Qu · Shanghaoran Quan · Yizhou Tan · Zili Wang · 王晨清 · Hao Wang · Yiya Wang · Yubo Wang · Jiajun Xu · Kexin Yang · Ruibin Yuan · Yuanhao Yue · Tianyang Zhan · Chun Zhang · Jinyang Zhang · Xiyue Zhang · Owen Zhang · Yue Zhang · Yongchi Zhao · Xiangyu Zheng · ChenghuaZhong · Yang Gao · Zhoujun Li · Dayiheng Liu · Qian Liu · Tianyu Liu · Shiwen Ni · Junran Peng · Yujia Qin · Wenbo Su · Guoyin Wang · Shi Wang · Jian Yang · Min Yang · Meng Cao · Xiang Yue · ZHAO-XIANG ZHANG · Wangchunshu Zhou · Jiaheng Liu · Qunshu Lin · Wenhao Huang · Ge Zhang

NeurIPS should lead scientific consensus on AI policy

Rishi Bommasani

Position: Machine Learning Conferences Should Establish a "Refutations and Critiques" Track

Rylan Schaeffer · Joshua Kazdan · Yegor Denisov-Blanch · Brando Miranda · Matthias Gerstgrasser · Susan Zhang · Andreas Haupt · Isha Gupta · Elyas Obbad · Jesse Dodge · Jessica Forde · Francesco Orabona · Sanmi Koyejo · David Donoho

Policy learning “without” overlap: Pessimism and generalized empirical Bernstein’s inequality

Ying Jin · Zhimei Ren · Zhuoran Yang · Zhaoran Wang

Implicit-ARAP: Efficient Handle-Guided Neural Field Deformation via Local Patch Meshing

Daniele Baieri · Filippo Maggioli · Emanuele Rodolà · Simone Melzi · Zorah Laehner

Towards Syn-to-Real IQA: A Novel Perspective on Reshaping Synthetic Data Distributions

Aobo Li · Jinjian Wu · Yongxu Liu · Leida Li · Weisheng Dong

UltraLED: Learning to See Everything in Ultra-High Dynamic Range Scenes

Yuang Meng · Xin Jin · Lina Lei · Chun-Le Guo · Chongyi Li

Multi-Task Vehicle Routing Solver via Mixture of Specialized Experts under State-Decomposable MDP

Yuxin Pan · Zhiguang Cao · Chengyang GU · Liu Liu · Peilin Zhao · Yize Chen · Fangzhen Lin

Coarse-to-Fine 3D Part Assembly via Semantic Super-Parts and Symmetry-Aware Pose Estimation

Xinyi Zhang · Bingyang Wei · Ruixuan Yu · Jian Sun

Revisiting Generative Infrared and Visible Image Fusion Based on Human Cognitive Laws

Lin Guo · Xiaoqing Luo · Wei Xie · Zhancheng Zhang · Hui Li · Rui Wang · Zhenhua Feng · Xiaoning Song

Plasticity as the Mirror of Empowerment

David Abel · Michael Bowling · Andre Barreto · Will Dabney · Shi Dong · Steven Hansen · Anna Harutyunyan · Khimya Khetarpal · Clare Lyle · Razvan Pascanu · Georgios Piliouras · Doina Precup · Jonathan Richens · Mark Rowland · Tom Schaul · Satinder Singh

Bernstein–von Mises for Adaptively Collected Data

Kevin Du · Yash Nair · Lucas Janson

Sequential Monte Carlo for Policy Optimization in Continuous POMDPs

Hany Abdulsamad · Sahel Mohammad Iqbal · Simo Sarkka

Imitation Beyond Expectation Using Pluralistic Stochastic Dominance

Ali Farajzadeh · Danyal Saeed · Syed M Abbas · Rushit Shah · Aadirupa Saha · Brian Ziebart

MMCSBench: A Fine-Grained Benchmark for Large Vision-Language Models in Camouflage Scenes

Jin Zhang · Ruiheng Zhang · Zhe Cao · Kaizheng Chen

RBench-V: A Primary Assessment for Visual Reasoning Models with Multimodal Outputs

Meng-Hao Guo · Xuanyu Chu · Qianrui Yang · Zhe-Han Mo · Yiqing Shen · Pei-lin Li · Xinjie Lin · Jinnian Zhang · Xin-Sheng Chen · Yi Zhang · Kiyohiro Nakayama · Zhengyang Geng · Houwen Peng · Han Hu · Shi-min Hu

Gated Attention for Large Language Models: Non-linearity, Sparsity, and Attention-Sink-Free

Zihan Qiu · Zekun Wang · Bo Zheng · Zeyu Huang · Kaiyue Wen · Songlin Yang · Rui Men · Le Yu · Fei Huang · Suozhi Huang · Dayiheng Liu · Jingren Zhou · Junyang Lin

FlexOLMo: Open Language Models for Flexible Data Use

Weijia Shi · Akshita Bhagia · Kevin Farhat · Niklas Muennighoff · Jacob Morrison · Evan Walsh · Dustin Schwenk · Shayne Longpre · Jake Poznanski · Allyson Ettinger · Daogao Liu · Margaret Li · Mike Lewis · Scott Yih · Dirk Groeneveld · Luca Soldaini · Kyle Lo · Noah Smith · Luke Zettlemoyer · Pang Wei Koh · Hanna Hajishirzi · Ali Farhadi · Sewon Min

Scalable Best-of-N Selection for Large Language Models via Self-Certainty

Zhewei Kang · Xuandong Zhao · Dawn Song

ReCon: Region-Controllable Data Augmentation with Rectification and Alignment for Object Detection

Haowei Zhu · Tianxiang Pan · Rui Qin · Jun-Hai Yong · Bin Wang

A Signed Graph Approach to Understanding and Mitigating Oversmoothing

Jiaqi Wang · Xinyi Wu · James Cheng · Yifei Wang

Exploring the Translation Mechanism of Large Language Models

Hongbin Zhang · Kehai Chen · Xuefeng Bai · Xiucheng Li · Yang Xiang · Min Zhang

Theoretical Insights into In-context Learning with Unlabeled Data

Yingcong Li · Xiangyu Chang · Muti Kara · Xiaofeng Liu · Amit Roy-Chowdhury · Samet Oymak

RFMPose: Generative Category-level Object Pose Estimation via Riemannian Flow Matching

Wenzhe Ouyang · Qi Ye · Jinghua Wang · Zenglin Xu · Jiming Chen

Safety Pretraining: Toward the Next Generation of Safe AI

Pratyush Maini · Sachin Goyal · Dylan Sam · Alexander Robey · Yash Savani · Yiding Jiang · Andy Zou · Matt Fredrikson · Zachary Lipton · Zico Kolter

Self-Guided Hierarchical Exploration for Generalist Foundation Model Web Agents

Qianlan Yang · XJ Wang · Danielle Perszyk · Yu-Xiong Wang

PUATE: Efficient ATE Estimation from Treated (Positive) and Unlabeled Units

Masahiro Kato · Fumiaki Kozai · RYO INOKUCHI

Achieving $\tilde{\mathcal{O}}(1/N)$ Optimality Gap in Restless Bandits through Gaussian Approximation

Chen YAN · Weina Wang · Lei Ying

SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning

Yang Liu · Ming Ma · Xiaomin Yu · Pengxiang Ding · Han Zhao · Mingyang Sun · Siteng Huang · Donglin Wang

Emergent Temporal Correspondences from Video Diffusion Transformers

Jisu Nam · Soowon Son · Dahyun Chung · Jiyoung Kim · Siyoon Jin · Junhwa Hur · Seungryong Kim

DynaAct: Large Language Model Reasoning with Dynamic Action Spaces

Xueliang Zhao · Wei Wu · Jian Guan · Qintong Li · Lingpeng Kong

Safe RLHF-V: Safe Reinforcement Learning from Multi-modal Human Feedback

Jiaming Ji · Xinyu Chen · Rui Pan · Han Zhu · Jiahao Li · Donghai Hong · Boyuan Chen · Jiayi Zhou · Kaile Wang · Juntao Dai · Chi-Min Chan · Sirui Han · Yike Guo · Yaodong Yang

T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT

Dongzhi JIANG · Ziyu Guo · Renrui Zhang · ZHUOFAN ZONG · Hao Li · Le Zhuo · Shilin Yan · Pheng-Ann Heng · Hongsheng Li

Uncoupled and Convergent Learning in Monotone Games under Bandit Feedback

Jing Dong · Baoxiang Wang · Yaoliang Yu

LMFusion: Adapting Pretrained Language Models for Multimodal Generation

Weijia Shi · Xiaochuang Han · Chunting Zhou · Weixin Liang · Victoria Lin · Luke Zettlemoyer · LILI YU

Noise Consistency Training: A Native Approach for One-step Generator in Learning Additional Controls

Yihong Luo · Shuchen Xue · Tianyang Hu · Jing Tang

OmniGen-AR: AutoRegressive Any-to-Image Generation

Junke Wang · Xun Wang · Qiushan Guo · Peize Sun · Weilin Huang · Zuxuan Wu · Yu-Gang Jiang

Understanding Softmax Attention Layers:\\ Exact Mean-Field Analysis on a Toy Problem

Elvis Dohmatob

Improving Generative Behavior Cloning via Self-Guidance and Adaptive Chunking

Junhyuk So · Chiwoong Lee · Shinyoung Lee · Jungseul Ok · Eunhyeok Park

HumanCrafter: Synergizing Generalizable Human Reconstruction and Semantic 3D Segmentation

Panwang Pan · Tingting Shen · Chenxin Li · Yunlong Lin · Kairun Wen · Jingjing Zhao · Yixuan Yuan

GAM-Agent: Game-Theoretic and Uncertainty-Aware Collaboration for Complex Visual Reasoning

jusheng zhang · Yijia Fan · Wenjun Lin · Ruiqi Chen · Haoyi Jiang · Wenhao Chai · Jian Wang · Keze Wang

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis

Hoang Pham · The Anh Ta · Tom Jacobs · Rebekka Burkholz · Long Tran-Thanh

Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning

Chen Qian · Dongrui Liu · Haochen Wen · Zhen Bai · Yong Liu · Jing Shao

R2R: Efficiently Navigating Divergent Reasoning Paths with Small-Large Model Token Routing

Tianyu Fu · Yi Ge · Yichen You · Enshu Liu · Zhihang Yuan · Guohao Dai · Shengen Yan · Huazhong Yang · Yu Wang

ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding

Muye Huang · Lingling Zhang · Jie Ma · Han Lai · Fangzhi Xu · Yifei Li · Wenjun Wu · Yaqiang Wu · Jun Liu

Personalized Image Editing in Text-to-Image Diffusion Models via Collaborative Direct Preference Optimization

Connor Dunlop · Matthew Zheng · Kavana Venkatesh · Pinar Yanardag

PolyPose: Deformable 2D/3D Registration via Polyrigid Transformations

Vivek Gopalakrishnan · Neel Dey · Polina Golland

Fundamental Limitations in Pointwise Defences of LLM Finetuning APIs

Xander Davies · Eric Winsor · Alexandra Souly · Tomek Korbak · Robert Kirk · Christian Schroeder de Witt · Yarin Gal

Antidistillation Sampling

Yash Savani · Asher Trockman · Zhili Feng · Yixuan Xu · Avi Schwarzschild · Alexander Robey · Marc Finzi · Zico Kolter

ChemOrch: Empowering LLMs with Chemical Intelligence via Groundbreaking Synthetic Instructions

Yue Huang · Zhengzhe Jiang · Xiaonan Luo · Kehan Guo · Haomin Zhuang · Yujun Zhou · Zhengqing Yuan · Xiaoqi Sun · Jules Schleinitz · Yanbo Wang · Shuhao Zhang · Mihir Surve · Nitesh Chawla · Olaf Wiest · Xiangliang Zhang

Information-Computation Tradeoffs for Noiseless Linear Regression with Oblivious Contamination

Ilias Diakonikolas · Chao Gao · Daniel Kane · John Lafferty · Ankit Pensia

MAT-Agent: Adaptive Multi-Agent Training Optimization

jusheng zhang · Kaitong Cai · Yijia Fan · Ningyuan Liu · Keze Wang

UFT: Unifying Supervised and Reinforcement Fine-Tuning

Mingyang Liu · Gabriele Farina · Asuman Ozdaglar

Wide-Horizon Thinking and Simulation-Based Evaluation for Real-World LLM Planning with Multifaceted Constraints

Dongjie Yang · Chengqiang Lu · Qimeng Wang · Xinbei Ma · Yan Gao · Yao Hu · Hai Zhao

VaporTok: RL-Driven Adaptive Video Tokenizer with Prior & Task Awareness

Minghao Yang · Zechen Bai · Jing Lin · Haoqian Wang · Alex Jinpeng Wang

Quadratic Coreset Selection: Certifying and Reconciling Sequence and Token Mining for Efficient Instruction Tuning

Ziliang Chen · Yongsen Zheng · Zhao-Rong Lai · Zhanfu Yang · Cuixi Li · Yang Liu · Liang Lin

Online Experimental Design With Estimation-Regret Trade-off Under Network Interference

Zhiheng Zhang · Zichen Wang

Geometric Logit Decoupling for Energy-Based Graph Out-of-distribution Detection

Min Wang · Hao Yang · Qing Cheng · Jincai Huang

WKV-sharing embraced random shuffle RWKV high-order modeling for pan-sharpening

man zhou · Xuanhua He · Danfeng Hong · Bo Huang

Information-Theoretic Reward Decomposition for Generalizable RLHF

Liyuan Mao · Haoran Xu · Amy Zhang · Weinan Zhang · Chenjia Bai

Radial Attention: $\mathcal O(n \log n)$ Sparse Attention for Long Video Generation

XINGYANG LI · Muyang Li · Tianle Cai · Haocheng Xi · Shuo Yang · Yujun Lin · Lvmin Zhang · Songlin Yang · Jinbo Hu · Kelly Peng · Maneesh Agrawala · Ion Stoica · Kurt Keutzer · Song Han

ZeroPatcher: Training-free Sampler for Video Inpainting and Editing

Shaoshu Yang · Yingya Zhang · Ran He

Advancing Expert Specialization for Better MoE

Hongcan Guo · Haolang Lu · Guoshun Nan · Bolun Chu · Jialin Zhuang · Yuan Yang · Wenhao Che · Xinye Cao · Sicong Leng · Qimei Cui · Xudong Jiang

Contribution of task-irrelevant stimuli to drift of neural representations

Farhad Pashakhanloo

Optimizing Anytime Reasoning via Budget Relative Policy Optimization

Penghui Qi · Zichen Liu · Tianyu Pang · Chao Du · Wee Sun Lee · Min Lin

Value-Guided Search for Efficient Chain-of-Thought Reasoning

Kaiwen Wang · Jin Zhou · Jonathan Chang · Zhaolin Gao · Nathan Kallus · Kianté Brantley · Wen Sun

Uncertainty-aware Preference Alignment for Diffusion Policies

Runqing Miao · Sheng Xu · Runyi Zhao · Wai Kin (Victor) Chan · Guiliang Liu

Dynamic Siamese Expansion Framework for Improving Robustness in Online Continual Learning

Fei Ye · Yulong Zhao · Qihe Liu · Junlin Chen · Adrian G. Bors · Jingling sun · Rongyao Hu · shijie zhou

Learning Expandable and Adaptable Representations for Continual Learning

Ruilong Yu · Mingyan Liu · Fei Ye · Adrian G. Bors · Rongyao Hu · Jingling sun · shijie zhou

Learning Multi-Source and Robust Representations for Continual Learning

Fei Ye · Yongcheng Zhong · Qihe Liu · Adrian G. Bors · Jingling sun · Rongyao Hu · shijie zhou

Unifying Symbolic Music Arrangement: Track-Aware Reconstruction and Structured Tokenization

Longshen Ou · Jingwei Zhao · Ziyu Wang · Gus Xia · Qihao Liang · Torin Hopkins · Ye Wang

Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning

Shenzhi Wang · Le Yu · Chang Gao · Chujie Zheng · Shixuan Liu · Rui Lu · Kai Dang · Xiong-Hui Chen · Jianxin Yang · Zhenru Zhang · Yuqiong Liu · An Yang · Andrew Zhao · Yang Yue · Shiji Song · Bowen Yu · Gao Huang · Junyang Lin

Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning

Minheng Ni · Zhengyuan Yang · Linjie Li · Chung-Ching Lin · Kevin Lin · Wangmeng Zuo · Lijuan Wang

Moment- and Power-Spectrum-Based Gaussianity Regularization for Text-to-Image Models

Jisung Hwang · Jaihoon Kim · Minhyuk Sung

Regional Explanations: Bridging Local and Global Variable Importance

Salim I. Amoukou · Nicolas Brunel

Mean Flows for One-step Generative Modeling

Zhengyang Geng · Mingyang Deng · Xingjian Bai · Zico Kolter · Kaiming He

EquiTabPFN: A Target-Permutation Equivariant Prior Fitted Network

Michael Arbel · David Salinas · Frank Hutter

Reward-Instruct: A Reward-Centric Approach to Fast Photo-Realistic Image Generation

Yihong Luo · Tianyang Hu · Weijian Luo · Kenji Kawaguchi · Jing Tang

LaX: Boosting Low-Rank Training of Foundation Models via Latent Crossing

Ruijie (Ray) Zhang · Ziyue (Alvin) Liu · Zhengyang Wang · Zheng Zhang

Domain-RAG: Retrieval-Guided Compositional Image Generation for Cross-Domain Few-Shot Object Detection

Yu Li · Xingyu Qiu · Yuqian Fu · Jie Chen · Tianwen Qian · Xu Zheng · Danda Pani Paudel · Yanwei Fu · Xuanjing Huang · Luc V Gool · Yu-Gang Jiang

One for All: Universal Topological Primitive Transfer for Graph Structure Learning

Yide Qiu · Tong Zhang · Xing Cai · Hui Yan · Zhen Cui

CSGO: Content-Style Composition in Text-to-Image Generation

Peng Xing · Haofan Wang · Yanpeng Sun · wangqixun · Baixu · Hao Ai · Jen-Yuan Huang · Zechao Li

Orient Anything V2: Unifying Orientation and Rotation Understanding

Zehan Wang · Ziang Zhang · Jiayang Xu · Jialei Wang · Tianyu Pang · Chao Du · Hengshuang Zhao · Zhou Zhao

Integrating Drug Substructures and Longitudinal Electronic Health Records for Personalized Drug Recommendation

Wenjie Du · Xuqiang Li · Jinke Feng · Shuai Zhang · Wen Zhang · Yang Wang

Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

Xun Huang · Zhengqi Li · Guande He · Mingyuan Zhou · Eli Shechtman

Plug-and-Play Context Feature Reuse for Efficient Masked Generation

Xuejie Liu · Anji Liu · Guy Van den Broeck · Yitao Liang

CoLT: The conditional localization test for assessing the accuracy of neural posterior estimates

Tianyu Chen · Vansh Bansal · James Scott

Amortized Variational Transdimensional Inference

Laurence Davies · Daniel MacKinlay · Rafael Oliveira · Scott SIsson

Functional Complexity-adaptive Temporal Tensor Decomposition

Panqi Chen · Lei Cheng · Jianlong Li · Weichang Li · Weiqing Liu · Jiang Bian · Shikai Fang

Score-Based Diffusion Modeling for Nonparametric Empirical Bayes in Heteroscedastic Gaussian Mixtures

Gongyu Chen · Ying Cui

Squared families are useful conjugate priors

Russell Tsuchida · Jiawei Liu · Cheng Soon Ong · Dino Sejdinovic

Efficient Bayesian Experiment Design with Equivariant Networks

Conor Igoe · Tejus Gupta · Jeff Schneider

Model-Informed Flows for Bayesian Inference

Joohwan Ko · Justin Domke

Turbocharging Gaussian Process Inference with Approximate Sketch-and-Project

Pratik Rathore · Zachary Frangella · Sachin Garg · Shaghayegh Fazliani · Michal Derezinski · Madeleine Udell

Zero-Shot Performance Prediction for Probabilistic Scaling Laws

Viktoria Schram · Markus Hiller · Daniel Beck · Trevor Cohn

Robust and Computation-Aware Gaussian Processes

Marshal Sinaga · Julien Martinelli · Samuel Kaski

Least squares variational inference

Yvann Le Fay · Nicolas Chopin · Simon Barthelmé

Informed Correctors for Discrete Diffusion Models

Yixiu Zhao · Jiaxin Shi · Feng Chen · Shaul Druckmann · Lester Mackey · Scott Linderman

Rethinking Losses for Diffusion Bridge Samplers

Sebastian Sanokowski · Lukas Gruber · Christoph Bartmann · Sepp Hochreiter · Sebastian Lehner

From stability of Langevin diffusion to convergence of proximal MCMC for non-log-concave sampling

Marien Renaud · Valentin De Bortoli · Arthur Leclaire · Nicolas Papadakis

Omni-R1: Reinforcement Learning for Omnimodal Reasoning via Two-System Collaboration

Hao Zhong · Muzhi Zhu · Zongze Du · Zheng Huang · Canyu Zhao · Mingyu Liu · Wen Wang · Hao Chen · Chunhua Shen

AutoOpt: A Dataset and a Unified Framework for Automating Optimization Problem Solving

Ankur Sinha · Shobhit Arora · Dhaval Pujara

Hephaestus: Mixture Generative Modeling with Energy Guidance for Large-scale QoS Degradation

Nguyen Do · Bach Ngo · Youval Kashuv · Canh Pham · Hanghang Tong · My T. Thai

A Learning-Augmented Dynamic Programming Approach for Orienteering Problem with Time Windows

Guansheng Peng · Lining Xing · Fuyan Ma · Aldy Gunawan · Guopeng Song · Pieter Vansteenwegen

ALE-Bench: A Benchmark for Long-Horizon Objective-Driven Algorithm Engineering

Yuki Imajuku · Kohki Horie · Yoichi Iwata · Kensho Aoki · Naohiro Takahashi · Takuya Akiba

Learning with Statistical Equality Constraints

Aneesh Barthakur · Luiz Chamon

Stochastic Optimization in Semi-Discrete Optimal Transport: Convergence Analysis and Minimax Rate

Ferdinand Genans · Antoine Godichon-Baggioni · François-Xavier Vialard · Olivier Wintenberger

Quasi-Self-Concordant Optimization with $\ell_{\infty}$ Lewis Weights

Alina Ene · Ta Duy Nguyen · Adrian Vladu

Analog In-memory Training on General Non-ideal Resistive Elements: The Impact of Response Functions

Zhaoxian Wu · Quan Xiao · Tayfun Gokmen · Omobayode Fagbohungbe · Tianyi Chen

Convergence of Clipped SGD on Convex $(L_0,L_1)$-Smooth Functions

Ofir Gaash · Kfir Y. Levy · Yair Carmon

MGUP: A Momentum-Gradient Alignment Update Policy for Stochastic Optimization

Da Chang · Ganzhao Yuan

On the Sample Complexity of Differentially Private Policy Optimization

Yi He · Xingyu Zhou

Deep Legendre Transform

Aleksey Minabutdinov · Patrick Cheridito

Enhancing Zero-Shot Black-Box Optimization via Pretrained Models with Efficient Population Modeling, Interaction, and Stable Gradient Approximation

Muqi Han · Xiaobin Li · Kai Wu · Xiaoyu Zhang · Handing Wang

A Single-Loop Gradient Algorithm for Pessimistic Bilevel Optimization via Smooth Approximation

Qichao Cao · Shangzhi Zeng · Jin Zhang

Finding Low-Rank Matrix Weights in DNNs via Riemannian Optimization: RAdaGrad and RAdamW

Fengmiao Bian · Jinyang ZHENG · Ziyun Liu · Jianzhou Luo · Jian-Feng CAI

Hamiltonian Descent Algorithms for Optimization: Accelerated Rates via Randomized Integration Time

Qiang Fu · Andre Wibisono

An Adaptive Algorithm for Bilevel Optimization on Riemannian Manifolds

Xu Shi · Rufeng Xiao · Rujun Jiang

Escaping saddle points without Lipschitz smoothness: the power of nonlinear preconditioning

Alexander Bodard · Panagiotis Patrinos

FlowerTune: A Cross-Domain Benchmark for Federated Fine-Tuning of Large Language Models

Yan Gao · Massimo R. Scamarcia · Javier Fernandez-Marques · Mohammad Naseri · Chong Ng · Dimitris Stripelis · Zexi Li · Tao Shen · Jiamu Bai · Daoyuan Chen · Zikai Zhang · Rui Hu · InSeo Song · KangYoon Lee · Hong Jia · Ting Dang · Junyan Wang · Zheyuan Liu · Daniel J. Beutel · Lingjuan Lyu · Nicholas Lane

FLiP: Towards Comprehensive and Reliable Evaluation of Federated Prompt Learning

Dongping Liao · Xitong Gao · Cheng-Zhong Xu

PubSub-VFL: Towards Efficient Two-Party Split Learning in Heterogeneous Environments via Publisher/Subscriber Architecture

Yi Liu · Yang Liu · Leqian Zheng · Jue Hong · Junjie Shi · Qingyou Yang · Ye Wu · Cong Wang

Unextractable Protocol Models: Collaborative Training and Inference without Weight Materialization

Alexander Long · Chamin Hewa Koneputugodage · Thalaiyasingam Ajanthan · Yan Zuo · Gil Avraham · Violetta Shevchenko · Hadi Mohaghegh Dolatabadi · Sameera Ramasinghe

Bi-Directional Communication-Efficient Stochastic FL via Remote Source Generation

Maximilian Egger · Rawad Bitar · Antonia Wachter-Zeh · Nir Weinberger · Deniz Gunduz

FORLA: Federated Object-centric Representation Learning with Slot Attention

Guiqiu Liao · Matjaz Jogan · Eric Eaton · Daniel Hashimoto

HyGen: Efficient LLM Serving via Elastic Online-Offline Request Co-location

Ting Sun · Penghan Wang · Fan Lai

Tight analyses of first-order methods with error feedback

Daniel Berg Thomsen · Adrien Taylor · Aymeric Dieuleveut

Streaming Federated Learning with Markovian Data

Khiem HUYNH · Malcolm Egan · Giovanni Neglia · Jean-Marie Gorce

QuestBench: Can LLMs ask the right question to acquire information in reasoning tasks?

Belinda Li · Been Kim · Zi Wang

A Single-Loop First-Order Algorithm for Linearly Constrained Bilevel Optimization

Wei Shen · Jiawei Zhang · Minhui Huang · Cong Shen

Learning-Augmented Online Bidding in Stochastic Settings

Spyros Angelopoulos · Bertrand Simon

Revisiting Follow-the-Perturbed-Leader with Unbounded Perturbations in Bandit Problems

Jongyeong Lee · Junya Honda · Shinji Ito · Min-hwan Oh

ESCORT: Efficient Stein-variational and Sliced Consistency-Optimized Temporal Belief Representation for POMDPs

Yunuo Zhang · Baiting Luo · Ayan Mukhopadhyay · Gabor Karsai · Abhishek Dubey

Solver-Free Decision-Focused Learning for Linear Optimization Problems

Senne Berden · Ali Mahmutoğulları · Dimos Tsouros · Tias Guns

CAMO: Convergence-Aware Multi-Fidelity Bayesian Optimization

WEI XING · Zhenjie Lu · Akeel Shah

Convergence Rates of Constrained Expected Improvement

Haowei Wang · Jingyi Wang · Zhongxiang Dai · Nai-Yuan Chiang · Szu Hui Ng · Cosmin Petra

Transformer Key-Value Memories Are Nearly as Interpretable as Sparse Autoencoders

Mengyu Ye · Jun Suzuki · Tatsuro Inaba · Tatsuki Kuribayashi

Correcting misinterpretations of additive models

Benedict Clark · Rick Wilming · Hjalmar Schulz · Rustam Zhumagambetov · Danny Panknin · Stefan Haufe

Stop the Nonconsensual Use of Nude Images in Research

Princessa Cintaqia · Arshia Arya · Elissa Redmiles · Deepak Kumar · Allison McDonald · Lucy Qin

AutoRedTeamer: Autonomous Red Teaming with Lifelong Attack Integration

Andy Zhou · Kevin Wu · Francesco Pinto · Zhaorun Chen · Yi Zeng · Yu Yang · Shuang Yang · Sanmi Koyejo · James Zou · Bo Li

Valid Inference with Imperfect Synthetic Data

Yewon Byun · Shantanu Gupta · Zachary Lipton · Rachel Childers · Bryan Wilder

LARGO: Latent Adversarial Reflection through Gradient Optimization for Jailbreaking LLMs

Ran Li · Hao Wang · Chengzhi Mao

Deep Value Benchmark: Measuring Whether Models Generalize Deep values or Shallow Preferences

Joshua Ashkinaze · Hua Shen · Saipranav Avula · Eric Gilbert · Ceren Budak

Can DPO Learn Diverse Human Values? A Theoretical Scaling Law

Shawn Im · Sharon Li

CodeGEMM: A Codebook-Centric Approach to Efficient GEMM in Quantized LLMs

Gunho Park · Jeongin Bae · Byeongwook Kim · Baeseong Park · Jiwon Ryu · Hoseung Kim · Se Jung Kwon · Dongsoo Lee

Generalized Gradient Norm Clipping & Non-Euclidean $(L_0,L_1)$-Smoothness

Thomas Pethick · Wanyun Xie · Mete Erdogan · Kimon Antonakopoulos · Antonio Silveti-Falls · Volkan Cevher

BIPNN: Learning to Solve Binary Integer Programming via Hypergraph Neural Networks

Sen Bai · Chunqi Yang · Xin Bai · Xin Zhang · Zhengang Jiang

Attribution-Driven Adaptive Token Pruning for Transformers

YAOYAO YAN · Hui Yu · Weizhi Xu

In Search of Adam’s Secret Sauce

Antonio Orvieto · Robert Gower

LoTA-QAF: Lossless Ternary Adaptation for Quantization-Aware Fine-Tuning

Junyu Chen · Junzhuo Li · Zhen Peng · Wenjie Wang · Yuxiang Ren · Long Shi · Xuming Hu

Bayesian Optimization with Preference Exploration using a Monotonic Neural Network Ensemble

Hanyang Wang · Juergen Branke · Matthias Poloczek

Covering Multiple Objectives with a Small Set of Solutions Using Bayesian Optimization

Natalie Maus · Kyurae Kim · Yimeng Zeng · Haydn Jones · Fangping Wan · Marcelo Der Torossian Torres · Cesar de la Fuente-Nunez · Jacob Gardner

Robust Satisficing Gaussian Process Bandits Under Adversarial Attacks

Artun Saday · Yaşar Cahit Yıldırım · Cem Tekin

Go to Event Page

Creative AI Session 4

Marcelo Coelho · Luba Elliott · Priya Prakash · Yingtao Tian

4:30 PM - 7:30 PM

23 Events in this session

An Inference Zoo for Real-Time Media Arts: Avendish as a Bridge Between AI and Creative Environments

Jean-Michaël Celerier

Artificial "Authentic" Intelligence: Can AI Systems Embody and Evolve Cultural Heritage? A Case Study of "Cyber Subin" and Thai Traditional Dance

Pat Pataranutaporn · Chayapatr Archiwaranguprok · Phoomparin Mano · Piyaporn Bhongse-tong · Patricia Maes · Pichet Klunchun

"Artificial Spectator" Developing AI Audiences for Watching AI-Generated Films: A Speculative Exploration on the Future of Media and AI

Pat Pataranutaporn · Chayapatr Archiwaranguprok · Manaswi Mishra · Patricia Maes

Between Reality and AI Hallucinations: Reimagining the Sacred Soundscape of Ming Rituals

Ziwei Chi · Wen Liang

BioArtlas: Computational Clustering of Multi-Dimensional Complexity in Bioart

Joonhyung Bae

Blankscope: Real-time Bridging of Human Perception with AI Imagination

Chiun Lee · Qingyun Liu · Krystal Montgomery

Craving Checkpoint: An Interactive Fridge Lock for Mindful Eating

Xiaoman Yang · Jinyue Wang · Zijie Zhou · Ziang Liu

Creative Synthesis of Kinematic Mechanisms

Jiong Lin · Jialong Ning · Judah Goldfeder · Hod Lipson

From Movement Memories to Robotic Dialogue: A Language-Mediated Pipeline for Somatic Machine Translation

Pinyao Liu · Keon Ju M. Lee · Paul Liang

Green Topics, Deep Roots: Energy-Aware Topic Modelling of Multilingual Nigerian Lyrics

Sakinat Folorunso · Tosin Akerele · Francisca Oladipo · Giwa Rukayat

"Jutters''

Selina Khan · Gonçalo Marcelino · Meike Driessen

Little Martians: From Desert Clay to Generative Agents

Gene Kogan · Vanessa Rosa

MCP2OSC: Parametric Control by Natural Language

Yuan-Yi Fan

Opt-In Art: Learning Art Styles Only from Few Examples

Hui Ren · Joanna Materzynska · Rohit Gandikota · Giannis Daras · David Bau · Antonio Torralba

Pocket Ink - Heaven’s mandate: a hyper-individualized tangible card game platform in the Age of AI

Quincy Kuang · Lucy Yuqing Li · Lingdong Huang · Hiroshi Ishii

Roulettective: Repurposing a Vintage Slide Projector into an AI-Driven Physical Detective Game

Yuhan Wang · Jianuo Xuan

Scene-Aware Urban Design: A Human–AI Recommendation Framework Using Co-Occurrence Embeddings and Vision-Language Models

Rodrigo Gallardo · Alexander Htet Kyaw · Oz Fishman

SPICE: A Synergistic, Precise, Iterative, and Customizable Image Editing Workflow

Kenan Tang · Yanhong Li · Yao Qin

Superradiance

Memo Akten · Katie Hofstadter

The Glitching Therapist: Performing the Limits of AI Empathy

Manuel Flurin Hendry · Meredith Thomas · Paulina Zybinska · Linus Jacobson · Piotr Mirowski

TinyTim: a family of language models for divergent generation

Christopher Agostino

(Un)Natural Language

Peijing Mou

Writing in Symbiosis: Mapping Human Creative Agency in the AI Era

Vivan Doshi · Mengyuan Li

Go to Event Page

Panel

Objects of AI

4:30 PM - 5:30 PM

This panel explores how generative and embodied AI are transforming design into a materially intelligent practice. Through projects spanning olfactory storytelling, edible architecture, autonomous instruments, and robotic co-fabrication, the discussion investigates how intelligence manifests through physical form, sensory interaction, and situated behavior. Bringing together researchers from architecture, robotics, music, and computational design, the panel examines how physical AI systems reconfigure the relationship between cognition and materiality, suggesting new paradigms for co-creation and human experience in an embodied, multisensory design ecology.

Panelists: Selina Khan Alexander Htet Kyaw Cyrus Clarke Masatoshi Hamanaka Ethan Chang

... more

Social

Value Chain from Research to ROI

Vinutha Magal Shreenath · Frincy Clement · Naimeesha murthy · Suparna Pawar

7:00 PM - 9:00 PM

We aim to understand: How can research be ready to accelerate into products/applied solutions? What kind of environments, processes & catalysts are needed to establish pathways from research to larger ecosystems consisting of products & businesses? We will have a panel discussion on these topics followed by a hands-on group activity where attendees will ideate sector-specific product applications from their own research. The event is structured to help researchers articulate their research’s broader potential, emphasizing ecosystem thinking and practical steps needed to scale research impact.

... more

Social

NeuroEd: Artificial Intelligence and the Future of Learning

Saket Ganti · Rodean Morshidi · Arnav GPT · BT · Schakra

7:00 PM - 9:00 PM

NeuroEd: Artificial Intelligence and the Future of Learning explores how educational technology and AI are transforming teaching and learning. The social invites participants to discuss AI-driven tools that personalize education, accelerate learning, and enhance educational outcomes. Attendees will connect across disciplines, AI, EdTech, ethics, and beyond, to share ideas, talk about implications, and imagine a future where technology empowers educators and learners alike.

... more

Social

When Errors Dream: Exploring Collective Creativity through AI Hallucination

Tiange Wang · Asuka Kondo · Isabella James · Ryo Tada · I-yang Huang

7:00 PM - 9:00 PM

When Errors Dream reframes AI hallucination as creative material. In a two-hour open-space jam in festival style, attendees rotate through small groups to generate surprising AI outputs—text, image, or sound—and transform them into collaborative artworks and interactive experiences using digital and analog media. No prior skills are required; emphasis is on the joy of making with machines, not polish. Designed to be drop-in friendly, the format scales to 150–200 participants through science-fair-style stations and quick exquisite-corpse creation cycles, fostering inclusive networking through shared play rather than one-directional talks.

... more

Social

Evaluating Agentic Systems: Bridging Research Benchmarks and Real-World Impact

Tatia Tsmindashvili · Raphael Kalandadze

7:00 PM - 9:00 PM

Agentic AI systems - LLM-driven agents capable of autonomous planning, tool use, and multi-step task execution - are rapidly advancing, yet methods for evaluating them remain underdeveloped. Traditional metrics for static or single-turn tasks fail to capture the complexity of open-ended, long-horizon interactions where goals evolve and behaviors emerge dynamically. This social aims to bridge research and industry perspectives on designing frameworks, simulation environments, and metrics that assess reliability, alignment, and safety in autonomous agents. Through lightning talks, panel discussions, and networking, the event fosters an interactive exchange on how to meaningfully evaluate and benchmark the next generation of agentic AI systems.

... more