NeurIPS 2023 Schedule

Filter Events

SUN 10 DEC

7 a.m.

Registration Desk

(ends 4:00 PM)

9 a.m.

Expo Talk Panel:

Open-source Quantization with Advanced Data Formats

(ends 9:50 AM)

Expo Demonstration:

Transforming the Cost of Transformer Inference with Positron AI

(ends 3:00 PM)

Expo Demonstration:

Real-time Portrait Video Relighting with AI-Generated HDRI maps on Mobile

(ends 3:00 PM)

Expo Demonstration:

EXAONE Universe: Toward Mindful Language Modeling for Insights and Inspiration

(ends 3:00 PM)

Expo Demonstration:

Fast and Accurate Inference of LLaMA2-Chat 7B on a Smartphone via Quantization Aware Training and Speculative Decoding with Knowledge Distillation

(ends 3:00 PM)

Expo Demonstration:

Enhanced Segmentation for Video Conferencing with On-device Learning (ODL)

(ends 3:00 PM)

Expo Demonstration:

Fast visual content generation with Stable Diffusion on mobile devices

(ends 3:00 PM)

Expo Demonstration:

Cutting-Edge AI Approaches for IT Diagnosis

(duration 1.5 hr)

Expo Demonstration:

FlowPilot: An LLM-Powered System for Enterprise Data Integration

(duration 1.5 hr)

Expo Demonstration:

The BAM Laboratory - Empowering AI Builders with User-Centric Tooling

(duration 1.5 hr)

Expo Demonstration:

Optimizing LLMs for Code: Fine-tuning Techniques & Architectures

(ends 3:00 PM)

Expo Demonstration:

Deep Dive into LLM Agents: From Structure to Task Automation at Scale

(ends 3:00 PM)

10 a.m.

Expo Talk Panel:

The Kitchen and the Lab: Bringing reproducibility and traceability to Bloomberg’s ML practices

(ends 10:50 AM)

Expo Talk Panel:

Optimizing and Reasoning about LLM Inference: from First Principles to SOTA Techniques

(ends 10:50 AM)

Expo Talk Panel:

On-device Personal Voice for Accessibility

(ends 10:50 AM)

10:30 a.m.

Expo Demonstration:

Log Diagnosis powered via Large Language Model for ITOps

(duration 1.5 hr)

Expo Demonstration:

Industrial demonstration of popular backbones for Time Series Foundation Models

(duration 1.5 hr)

Expo Demonstration:

IBM Intelligent Remediation for ITOps Incidents powered by Generative AI

(duration 1.5 hr)

11 a.m.

Expo Talk Panel:

Artificial Intelligence & Machine Learning Across the Entire Drug Development Pipeline

(ends 11:50 AM)

Expo Talk Panel:

Understanding the Effectiveness of Large Language Models in Code Translation

(ends 11:50 AM)

Expo Talk Panel:

Graph Learning Meets Artificial Intelligence

(ends 11:50 AM)

Expo Talk Panel:

Conversational Recommendations: Present and Future

(ends 11:50 AM)

noon

Expo Demonstration:

Cutting-Edge AI Approaches for IT Diagnosis

(duration 1.5 hr)

Expo Demonstration:

FlowPilot: An LLM-Powered System for Enterprise Data Integration

(duration 1.5 hr)

Expo Demonstration:

The BAM Laboratory - Empowering AI Builders with User-Centric Tooling

(duration 1.5 hr)

Expo Talk Panel:

Resonator: Music Space

(ends 12:50 PM)

Expo Talk Panel:

Tabular Representation Learning for Dataset Discovery over Data Lakes

(ends 12:50 PM)

Expo Talk Panel:

Knowledge Base For Everyone

(ends 12:50 PM)

Expo Workshop:

Building using Llama 2

(ends 2:00 PM)

Expo Workshop:

AutoGluon 1.0: AutoML at Your Fingertips

(ends 2:00 PM)

Expo Workshop:

Efficient AI Experimentation with Ax

(ends 2:00 PM)

Expo Workshop:

Knowledge-enhanced AI for Industry Verticals

(ends 2:00 PM)

1 p.m.

Break

Expo Talk Panel:

MACHINE LEARNING AND OPTIMIZATION FOR AUTOMATED TRADING AT HRT

(ends 1:50 PM)

Expo Talk Panel:

Large Language Models for Artificial Expert Intelligence

(ends 1:50 PM)

Expo Talk Panel:

Reinforcement Learning: Trends, Applications, and Challenges

(ends 1:50 PM)

1:30 p.m.

Expo Demonstration:

Log Diagnosis powered via Large Language Model for ITOps

(duration 1.5 hr)

Expo Demonstration:

Industrial demonstration of popular backbones for Time Series Foundation Models

(duration 1.5 hr)

Expo Demonstration:

IBM Intelligent Remediation for ITOps Incidents powered by Generative AI

(duration 1.5 hr)

2 p.m.

Expo Talk Panel:

Using AI to Improve Control Design Workflows

(ends 2:50 PM)

Expo Talk Panel:

AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

(ends 2:50 PM)

Expo Talk Panel:

The Future is Here: A Deep Dive into Autonomous Agents

(ends 2:50 PM)

Expo Workshop:

MARBLE 2: The Second workshop on Machine Learning and Artificial Intelligence for Biologics Engineering

(ends 4:00 PM)

Expo Workshop:

Communication without language barriers: recent advances in translation foundation models

(ends 4:00 PM)

Expo Workshop:

Production-ready Reinforcement Learning Active Training

(ends 4:00 PM)

Expo Workshop:

Sony’s Media Content Restoration and Editing with Deep Generative Models and Beyond.

(ends 4:00 PM)

2:30 p.m.

Break

3 p.m.

Expo Talk Panel:

Empirical rigor in ML as a massively parallelizable challenge

(ends 3:50 PM)

Expo Talk Panel:

From Theory to Practice: Incorporating ML Models into Safety-Critical Systems

(ends 3:50 PM)

Expo Talk Panel:

Augmenting PromptOPS with Partner Products: A Comprehensive Framework for Input-Output Guardrails in Large Language Models

(ends 3:50 PM)

Expo Demonstration:

Better Model Development? Make Data the Star of the Show

(ends 4:00 PM)

4 p.m.

Expo Talk Panel:

Smaller models can pack a punch in the era of Large Language Models

(ends 4:50 PM)

MON 11 DEC

5:30 a.m.

Registration Desk

(ends 4:00 PM)

6 a.m.

Workshop:

Women in ML

(ends 1:30 PM)

6:15 a.m.

Workshop:

Black in AI

(ends 1:30 PM)

Workshop:

New in ML

(ends 1:30 PM)

Workshop:

Latinx in AI

(ends 1:30 PM)

6:30 a.m.

Workshop:

North Africans in ML

(ends 1:30 PM)

Workshop:

Muslims in ML

(ends 1:30 PM)

7 a.m.

Workshop:

Indigenous in AI/ML

(ends 1:15 PM)

7:15 a.m.

Break

7:30 a.m.

Workshop:

Queer in AI

(ends 1:30 PM)

7:45 a.m.

Tutorial:

Governance & Accountability for ML: Existing Tools, Ongoing Efforts, & Future Directions

(ends 10:15 AM)

Tutorial:

How to Work With Real Humans in Human-AI Systems

(ends 10:15 AM)

Tutorial:

Language Models Meet World Models

(ends 10:15 AM)

Tutorial:

Recent and Upcoming Developments in Randomized Numerical Linear Algebra for ML

(ends 10:15 AM)

Tutorial:

Contributing to an Efficient and Democratized Large Model Era

(ends 10:15 AM)

Tutorial:

Latent Diffusion Models: Is the Generative AI Revolution Happening in Latent Space?

(ends 10:15 AM)

Tutorial:

Data Contribution Estimation for Machine Learning

(ends 10:15 AM)

9 a.m.

Workshop:

Global South AI

(ends 12:00 PM)

10 a.m.

Education Outreach:

Education Outreach

(ends 11:40 AM)

10:15 a.m.

Lunch (On Your Own)

10:45 a.m.

Mentorship:

Science Communication for AI Researchers - A Quick Introduction

(ends 2:00 PM)

11:45 a.m.

Tutorial:

Machine Learning for Theorem Proving

(ends 2:15 PM)

Tutorial:

Application Development using Large Language Models

(ends 2:15 PM)

Tutorial:

Data-Centric AI for reliable and responsible AI: from theory to practice

(ends 2:15 PM)

Tutorial:

Do You Prefer Learning with Preferences?

(ends 2:15 PM)

Tutorial:

Modeling and Exploiting Data Heterogeneity under Distribution Shifts

(ends 2:15 PM)

Tutorial:

Reconsidering Overfitting in the Age of Overparameterized Models

(ends 2:15 PM)

Tutorial:

What can we do about NeurIPS Reviewer #2?Challenges, Solutions, Experiments and Open Problemsin Peer Review

(ends 2:15 PM)

1:30 p.m.

Affinity Poster Session:

Joint Poster Session

(ends 2:30 PM)

2 p.m.

Break

3 p.m.

Opening Remarks:

Remarks

(ends 3:25 PM)

3:25 p.m.

Invited Talk:

NextGenAI: The Delusion of Scaling and the Future of Generative AI

Björn Ommer

(ends 4:15 PM)

4:15 p.m.

Reception:

Welcome Reception

(ends 6:30 PM)

4:30 p.m.

Creative AI Performances 1 [4:30-6:00]

Chairs: Jean Oh · Isabelle Guyon

s 4:30-6:00

[4:30] Voice Scroll

[4:30] The WHOOPS! Gallery: An Intersection of AI, Creativity, and the Unusual

[4:30] Kiss/Crash

[4:30] Emergent Rhythm — Real-time AI Generative DJ Set

[4:30] Fusion: Landscape and Beyond

[4:30] Entanglement

(ends 6:00 PM)

TUE 12 DEC

5:30 a.m.

Registration Desk

(ends 4:00 PM)

6:30 a.m.

Invited Talk:

The Many Faces of Responsible AI

Lora Aroyo

(ends 7:20 AM)

7:15 a.m.

Break

8 a.m.

Oral 1A RL [8:00-8:45]

Orals 8:00-8:45

[8:00] Ordering-based Conditions for Global Convergence of Policy Gradient Methods

[8:15] When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning

[8:30] Online RL in Linearly $q^\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore

(ends 8:45 AM)

Oral 1B Datasets & Benchmarks [8:00-8:45]

Orals 8:00-8:45

[8:00] LeanDojo: Theorem Proving with Retrieval-Augmented Language Models

[8:15] OpenAssistant Conversations - Democratizing Large Language Model Alignment

[8:30] DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

(ends 8:45 AM)

Oral 1C Tractable models [8:00-8:45]

Orals 8:00-8:45

[8:00] How to Turn Your Knowledge Graph Embeddings into Generative Models

[8:15] Exact Bayesian Inference on Discrete Models via Probability Generating Functions: A Probabilistic Programming Approach

[8:30] Characteristic Circuits

(ends 8:45 AM)

Oral 1D DL Theory [8:00-8:45]

Orals 8:00-8:45

[8:00] Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization

[8:15] Abide by the law and follow the flow: conservation laws for gradient flows

[8:30] A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning

(ends 8:45 AM)

8:45 a.m.

Poster Session 1 [8:45-10:45]

Posters 8:45-10:45

PIXIU: A Comprehensive Benchmark, Instruction Dataset and Large Language Model for Finance

FETV: A Benchmark for Fine-Grained Evaluation of Open-Domain Text-to-Video Generation

Wyze Rule: Federated Rule Dataset for Rule Recommendation Benchmarking

ChessGPT: Bridging Policy Learning and Language Modeling

EMBERSim: A Large-Scale Databank for Boosting Similarity Search in Malware Analysis

AllSim: Simulating and Benchmarking Resource Allocation Policies in Multi-User Systems

Disentangled Wasserstein Autoencoder for T-Cell Receptor Engineering

Fragment-based Pretraining and Finetuning on Molecular Graphs

Pre-Training Protein Encoder via Siamese Sequence-Structure Diffusion Trajectory Prediction

AbDiffuser: full-atom generation of in-vitro functioning antibodies

Predicting mutational effects on protein-protein binding via a side-chain diffusion probabilistic model

Density of States Prediction of Crystalline Materials via Prompt-guided Multi-Modal Transformer

Smooth, exact rotational symmetrization for deep learning on point clouds

AirDelhi: Fine-Grained Spatio-Temporal Particulate Matter Dataset From Delhi For ML based Modeling

SubseasonalClimateUSA: A Dataset for Subseasonal Forecasting and Benchmarking

OceanBench: The Sea Surface Height Edition

M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark

ClimateSet: A Large-Scale Climate Model Dataset for Machine Learning

HA-ViD: A Human Assembly Video Dataset for Comprehensive Assembly Knowledge Understanding

DVSOD: RGB-D Video Salient Object Detection

Hierarchical Open-vocabulary Universal Image Segmentation

FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models

Query-based Temporal Fusion with Explicit Motion for 3D Object Detection

Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning

Zero-shot Visual Relation Detection via Composite Visual Cues from Large Language Models

VisIT-Bench: A Dynamic Benchmark for Evaluating Instruction-Following Vision-and-Language Models

PrObeD: Proactive Object Detection Wrapper

DreamSparse: Escaping from Plato’s Cave with 2D Diffusion Model Given Sparse Views

Generalizable One-shot 3D Neural Head Avatar

Video-Mined Task Graphs for Keystep Recognition in Instructional Videos

SANFlow: Semantic-Aware Normalizing Flow for Anomaly Detection

Deep Optimal Transport: A Practical Algorithm for Photo-realistic Image Restoration

Deep Non-line-of-sight Imaging from Under-scanning Measurements

ProBio: A Protocol-guided Multimodal Dataset for Molecular Biology Lab

Rewrite Caption Semantics: Bridging Semantic Gaps for Language-Supervised Semantic Segmentation

What’s Left? Concept Grounding with Logic-Enhanced Foundation Models

Species196: A One-Million Semi-supervised Dataset for Fine-grained Species Recognition

Fine-Grained Cross-View Geo-Localization Using a Correlation-Aware Homography Estimator

Leave No Stone Unturned: Mine Extra Knowledge for Imbalanced Facial Expression Recognition

Knowledge Diffusion for Distillation

GenS: Generalizable Neural Surface Reconstruction from Multi-View Images

Diffusion-SS3D: Diffusion Model for Semi-supervised 3D Object Detection

ConRad: Image Constrained Radiance Fields for 3D Generation from a Single Image

StoryBench: A Multifaceted Benchmark for Continuous Story Visualization

3D Indoor Instance Segmentation in an Open-World

Dense and Aligned Captions (DAC) Promote Compositional Reasoning in VL Models

CityRefer: Geography-aware 3D Visual Grounding Dataset on City-scale Point Cloud Data

Subject-driven Text-to-Image Generation via Apprenticeship Learning

Topological RANSAC for instance verification and retrieval without fine-tuning

Michelangelo: Conditional 3D Shape Generation based on Shape-Image-Text Aligned Latent Representation

LoCoOp: Few-Shot Out-of-Distribution Detection via Prompt Learning

RenderMe-360: A Large Digital Asset Library and Benchmarks Towards High-fidelity Head Avatars

Aligning Gradient and Hessian for Neural Signed Distance Function

CP-SLAM: Collaborative Neural Point-based SLAM System

STXD: Structural and Temporal Cross-Modal Distillation for Multi-View 3D Object Detection

FaceComposer: A Unified Model for Versatile Facial Content Creation

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization

T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation

A Multi-modal Global Instance Tracking Benchmark (MGIT): Better Locating Target in Complex Spatio-temporal and Causal Relationship

XAGen: 3D Expressive Human Avatars Generation

Mr. HiSum: A Large-scale Dataset for Video Highlight Detection and Summarization

Learning to Parameterize Visual Attributes for Open-set Fine-grained Retrieval

SMPLer-X: Scaling Up Expressive Human Pose and Shape Estimation

Online Map Vectorization for Autonomous Driving: A Rasterization Perspective

Are These the Same Apple? Comparing Images Based on Object Intrinsics

StEik: Stabilizing the Optimization of Neural Signed Distance Functions and Finer Shape Representation

LayoutPrompter: Awaken the Design Ability of Large Language Models

JourneyDB: A Benchmark for Generative Image Understanding

Kiki or Bouba? Sound Symbolism in Vision-and-Language Models

Global Structure-Aware Diffusion Process for Low-light Image Enhancement

A High-Resolution Dataset for Instance Detection with Multi-View Object Capture

Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text

Dual Mean-Teacher: An Unbiased Semi-Supervised Framework for Audio-Visual Source Localization

OpenIllumination: A Multi-Illumination Dataset for Inverse Rendering Evaluation on Real Objects

Glance and Focus: Memory Prompting for Multi-Event Video Question Answering

AND: Adversarial Neural Degradation for Learning Blind Image Super-Resolution

PackQViT: Faster Sub-8-bit Vision Transformers via Full and Packed Quantization on the Mobile

ReContrast: Domain-Specific Anomaly Detection via Contrastive Reconstruction

NurViD: A Large Expert-Level Video Database for Nursing Procedure Activity Understanding

Emergent Correspondence from Image Diffusion

OpenMask3D: Open-Vocabulary 3D Instance Segmentation

LeanDojo: Theorem Proving with Retrieval-Augmented Language Models

WordScape: a Pipeline to extract multilingual, visually rich Documents with Layout Annotations from Web Crawl Data

UUKG: Unified Urban Knowledge Graph Dataset for Urban Spatiotemporal Prediction

HubRouter: Learning Global Routing via Hub Generation and Pin-hub Connection

ALGO: Synthesizing Algorithmic Programs with Generated Oracle Verifiers

The Cambridge Law Corpus: A Corpus for Legal AI Research

Metis: Understanding and Enhancing In-Network Regular Expressions

HyenaDNA: Long-Range Genomic Sequence Modeling at Single Nucleotide Resolution

ProteinGym: Large-Scale Benchmarks for Protein Fitness Prediction and Design

StressID: a Multimodal Dataset for Stress Identification

VTaC: A Benchmark Dataset of Ventricular Tachycardia Alarms from ICU Monitors

Differentiable sorting for censored time-to-event data.

Coupled Reconstruction of Cortical Surfaces by Diffeomorphic Mesh Deformation

Reliable Off-Policy Learning for Dosage Combinations

rPPG-Toolbox: Deep Remote PPG Toolbox

EHRXQA: A Multi-Modal Question Answering Dataset for Electronic Health Records with Chest X-ray Images

Unsupervised Polychromatic Neural Representation for CT Metal Artifact Reduction

RaLEs: a Benchmark for Radiology Language Evaluations

Aligning Synthetic Medical Images with Clinical Knowledge using Human Feedback

Thrust: Adaptively Propels Large Language Models with External Knowledge

How Far Can Camels Go? Exploring the State of Instruction Tuning on Open Resources

OpenAssistant Conversations - Democratizing Large Language Model Alignment

DIN-SQL: Decomposed In-Context Learning of Text-to-SQL with Self-Correction

Towards Efficient Pre-Trained Language Model via Feature Correlation Distillation

MoCa: Measuring Human-Language Model Alignment on Causal and Moral Judgment Tasks

PopSign ASL v1.0: An Isolated American Sign Language Dataset Collected via Smartphones

Rethinking the Role of Token Retrieval in Multi-Vector Retrieval

Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena

Deductive Verification of Chain-of-Thought Reasoning

CLadder: Assessing Causal Reasoning in Language Models

SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents

LegalBench: A Collaboratively Built Benchmark for Measuring Legal Reasoning in Large Language Models

Mathematical Capabilities of ChatGPT

SituatedGen: Incorporating Geographical and Temporal Contexts into Generative Commonsense Reasoning

Binarized Neural Machine Translation

Don’t Stop Pretraining? Make Prompt-based Fine-tuning Powerful Learner

Unified Segment-to-Segment Framework for Simultaneous Sequence Generation

Faith and Fate: Limits of Transformers on Compositionality

Diplomat: A Dialogue Dataset for Situated PragMATic Reasoning

ToolQA: A Dataset for LLM Question Answering with External Tools

Bayesian target optimisation for high-precision holographic optogenetics

Human-in-the-Loop Optimization for Deep Stimulus Encoding in Visual Prostheses

Multimodal Deep Learning Model Unveils Behavioral Dynamics of V1 Activity in Freely Moving Mice

Taking the neural sampling code very seriously: A data-driven approach for evaluating generative models of the visual system

Are Vision Transformers More Data Hungry Than Newborn Visual Systems?

Dis-inhibitory neuronal circuits can control the sign of synaptic plasticity

Learning better with Dale’s Law: A Spectral Perspective

Estimating Noise Correlations Across Continuous Conditions With Wishart Processes

Data-Driven Network Neuroscience: On Data Collection and Benchmark

Sequential Memory with Temporal Predictive Coding

Extraction and Recovery of Spatio-Temporal Structure in Latent Dynamics Alignment with Diffusion Models

CORNN: Convex optimization of recurrent neural networks for rapid inference of neural dynamics

Plug-and-Play Stability for Intracortical Brain-Computer Interfaces: A One-Year Demonstration of Seamless Brain-to-Text Communication

Bounded rationality in structured density estimation

SwiFT: Swin 4D fMRI Transformer

Uncovering motifs of concurrent signaling across multiple neuronal populations

Long Sequence Hopfield Memory

Slow and Weak Attractor Computation Embedded in Fast and Strong E-I Balanced Neural Dynamics

Learning Topology-Agnostic EEG Representations with Geometry-Aware Modeling

Scalable Transformer for PDE Surrogate Modeling

Online PCA in Converging Self-consistent Field Equations

Geometry-Informed Neural Operator for Large-Scale 3D PDEs

SUPA: A Lightweight Diagnostic Simulator for Machine Learning in Particle Physics

Towards Foundation Models for Scientific Machine Learning: Characterizing Scaling and Transfer Behavior

Equivariant flow matching

Equivariant Neural Simulators for Stochastic Spatiotemporal Dynamics

Turbulence in Focus: Benchmarking Scaling Behavior of 3D Volumetric Super-Resolution with BLASTNet 2.0 Data

BubbleML: A Multiphase Multiphysics Dataset and Benchmarks for Machine Learning

SoundCam: A Dataset for Finding Humans Using Room Acoustics

ANTN: Bridging Autoregressive Neural Networks and Tensor Networks for Quantum Many-Body Simulation

Newton–Cotes Graph Neural Networks: On the Time Evolution of Dynamic Systems

Learning Efficient Surrogate Dynamic Models with Graph Spline Networks

Operator Learning with Neural Fields: Tackling PDEs on General Geometries

Domain Agnostic Fourier Neural Operators

Classical Simulation of Quantum Circuits: Parallel Environments and Benchmark

SheetCopilot: Bringing Software Productivity to the Next Level through Large Language Models

Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping

What Truly Matters in Trajectory Prediction for Autonomous Driving?

Hierarchical Adaptive Value Estimation for Multi-modal Visual Reinforcement Learning

Grounded Decoding: Guiding Text Generation with Grounded Models for Embodied Agents

ScenarioNet: Open-Source Platform for Large-Scale Traffic Scenario Simulation and Modeling

Model-Based Control with Sparse Neural Dynamics

Amazon-M2: A Multilingual Multi-locale Shopping Session Dataset for Recommendation and Text Generation

MEMTO: Memory-guided Transformer for Multivariate Time Series Anomaly Detection

LargeST: A Benchmark Dataset for Large-Scale Traffic Forecasting

CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion

AbdomenAtlas-8K: Annotating 8,000 CT Volumes for Multi-Organ Segmentation in Three Weeks

Why Does Sharpness-Aware Minimization Generalize Better Than SGD?

Fantastic Weights and How to Find Them: Where to Prune in Dynamic Sparse Training

Augmentation-Free Dense Contrastive Knowledge Distillation for Efficient Semantic Segmentation

Alternating Updates for Efficient Transformers

Training Chain-of-Thought via Latent-Variable Inference

Module-wise Adaptive Distillation for Multimodality Foundation Models

CAP: Correlation-Aware Pruning for Highly-Accurate Sparse Vision Models

Reconciling Competing Sampling Strategies of Network Embedding

Triangulation Residual Loss for Data-efficient 3D Pose Estimation

SEENN: Towards Temporal Spiking Early Exit Neural Networks

Towards Unbounded Machine Unlearning

Deep Contract Design via Discontinuous Networks

H2O: Heavy-Hitter Oracle for Efficient Generative Inference of Large Language Models

On Sparse Modern Hopfield Model

Training-free Diffusion Model Adaptation for Variable-Sized Text-to-Image Synthesis

Primal-Attention: Self-attention through Asymmetric Kernel SVD in Primal Representation

Validated Image Caption Rating Dataset

One-Pass Distribution Sketch for Measuring Data Heterogeneity in Federated Learning

RD-Suite: A Benchmark for Ranking Distillation

Investigating how ReLU-networks encode symmetries

GNeSF: Generalizable Neural Semantic Fields

GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image

Improving multimodal datasets with image captioning

DiffInfinite: Large Mask-Image Synthesis via Parallel Random Patch Diffusion in Histopathology

Continuous-Time Functional Diffusion Processes

DreamWaltz: Make a Scene with Complex 3D Animatable Avatars

Rethinking Conditional Diffusion Sampling with Progressive Guidance

Add and Thin: Diffusion for Temporal Point Processes

Improving Diffusion-Based Image Synthesis with Context Prediction

Diffusion-Based Adversarial Sample Generation for Improved Stealthiness and Controllability

Beta Diffusion

Precision-Recall Divergence Optimization for Generative Modeling with GANs and Normalizing Flows

Concept Algebra for (Score-Based) Text-Controlled Generative Models

On the Generalization Properties of Diffusion Models

Arbitrarily Scalable Environment Generators via Neural Cellular Automata

UniPC: A Unified Predictor-Corrector Framework for Fast Sampling of Diffusion Models

Temporal Dynamic Quantization for Diffusion Models

Language Quantized AutoEncoders: Towards Unsupervised Text-Image Alignment

Joint Prompt Optimization of Stacked LLMs using Variational Inference

Expanding Small-Scale Datasets with Guided Imagination

Inserting Anybody in Diffusion Models via Celeb Basis

Customizable Image Synthesis with Multiple Subjects

Uni-ControlNet: All-in-One Control to Text-to-Image Diffusion Models

GlyphControl: Glyph Conditional Control for Visual Text Generation

Score-based Data Assimilation

Diffusion Probabilistic Models for Structured Node Classification

Censored Sampling of Diffusion Models Using 3 Minutes of Human Feedback

Semi-Implicit Denoising Diffusion Models (SIDDMs)

Reinforcement-Enhanced Autoregressive Feature Transformation: Gradient-steered Search in Continuous Space for Postfix Expressions

Modelling Cellular Perturbations with the Sparse Additive Mechanism Shift Variational Autoencoder

Constructing Non-isotropic Gaussian Diffusion Model Using Isotropic Gaussian Diffusion Model for Image Editing

Synthcity: a benchmark framework for diverse use cases of tabular synthetic data

Euler-Lagrange Analysis of Generative Adversarial Networks

Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics

Efficient Learning of Linear Graph Neural Networks via Node Subsampling

A Comprehensive Study on Text-attributed Graphs: Benchmarking and Rethinking

Characterizing Graph Datasets for Node Classification: Homophily-Heterophily Dichotomy and Beyond

CAT-Walk: Inductive Hypergraph Learning via Set Walks

TpuGraphs: A Performance Prediction Dataset on Large Tensor Computational Graphs

A Theory of Link Prediction via Relational Weisfeiler-Leman on Knowledge Graphs

Temporal Graph Benchmark for Machine Learning on Temporal Graphs

Fine-grained Expressivity of Graph Neural Networks

Approximately Equivariant Graph Networks

TopoSRL: Topology preserving self-supervised Simplicial Representation Learning

Lovász Principle for Unsupervised Graph Representation Learning

Demystifying Oversmoothing in Attention-Based Graph Neural Networks

Adversarial Training for Graph Neural Networks: Pitfalls, Solutions, and New Directions

WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding

Are GATs Out of Balance?

PRODIGY: Enabling In-context Learning Over Graphs

GSLB: The Graph Structure Learning Benchmark

ASIF: Coupled Data Turns Unimodal Models to Multimodal without Training

Kissing to Find a Match: Efficient Low-Rank Permutation Representation

Aging with GRACE: Lifelong Model Editing with Discrete Key-Value Adaptors

Analyzing Vision Transformers for Image Classification in Class Embedding Space

Topology-Aware Uncertainty for Image Segmentation

Learning Adaptive Tensorial Density Fields for Clean Cryo-ET Reconstruction

Task-aware Distributed Source Coding under Dynamic Bandwidth

An Inverse Scaling Law for CLIP Training

Online learning of long-range dependencies

Generalizable Lightweight Proxy for Robust NAS against Diverse Perturbations

Improving Adversarial Robustness via Information Bottleneck Distillation

Revisiting Adversarial Training for ImageNet: Architectures, Training and Generalization across Threat Models

Cola: A Benchmark for Compositional Text-to-image Retrieval

Holistic Transfer: Towards Non-Disruptive Fine-Tuning with Partial Target Data

Towards Last-layer Retraining for Group Robustness with Fewer Annotations

Don’t blame Dataset Shift! Shortcut Learning due to Gradients and Cross Entropy

Blurred-Dilated Method for Adversarial Attacks

RoboDepth: Robust Out-of-Distribution Depth Estimation under Corruptions

Asymmetric Certified Robustness via Feature-Convex Neural Networks

AdaptSSR: Pre-training User Model with Augmentation-Adaptive Self-Supervised Ranking

HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception

Implicit Contrastive Representation Learning with Guided Stop-gradient

[Re] Masked Autoencoders Are Small Scale Vision Learners: A Reproduction Under Resource Constraints

Reverse Engineering Self-Supervised Learning

Feature Dropout: Revisiting the Role of Augmentations in Contrastive Learning

Towards In-context Scene Understanding

Slimmed Asymmetrical Contrastive Learning and Cross Distillation for Lightweight Model Training

SSL4EO-L: Datasets and Foundation Models for Landsat Imagery

Taming Local Effects in Graph-based Spatiotemporal Forecasting

Stabilized Neural Differential Equations for Learning Dynamics with Explicit Constraints

Automatic Integration for Spatiotemporal Neural Point Processes

Transformers learn through gradual rank increase

On the Power of SVD in the Stochastic Block Model

Swap Agnostic Learning, or Characterizing Omniprediction via Multicalibration

Precise asymptotic generalization for multiclass classification with overparameterized linear models

Polynomially Over-Parameterized Convolutional Neural Networks Contain Structured Strong Winning Lottery Tickets

Implicit Bias of Gradient Descent for Logistic Regression at the Edge of Stability

Theoretical Analysis of the Inductive Biases in Deep Convolutional Networks

Training shallow ReLU networks on noisy data using hinge loss: when do we overfit and is it benign?

Provable Guarantees for Nonlinear Feature Learning in Three-Layer Neural Networks

The Crucial Role of Normalization in Sharpness-Aware Minimization

Adversarial Examples Exist in Two-Layer ReLU Networks for Low Dimensional Linear Subspaces

Abide by the law and follow the flow: conservation laws for gradient flows

Statistical Guarantees for Variational Autoencoders using PAC-Bayesian Theory

On skip connections and normalisation layers in deep optimisation

Provable Guarantees for Neural Networks via Gradient Feature Learning

Small Transformers Compute Universal Metric Embeddings

Learning DAGs from Data with Few Root Causes

Partial Counterfactual Identification of Continuous Outcomes with a Curvature Sensitivity Model

Directed Cyclic Graph for Causal Discovery from Multivariate Functional Data

CLIP-OGD: An Experimental Design for Adaptive Neyman Allocation in Sequential Experiments

Cause-Effect Inference in Location-Scale Noise Models: Maximum Likelihood vs. Independence Testing

Analysis of Variance of Multiple Causal Networks

Intervention Generalization: A View from Factor Graph Models

Conditional independence testing under misspecified inductive biases

DataPerf: Benchmarks for Data-Centric AI Development

PRIOR: Personalized Prior for Reactivating the Information Overlooked in Federated Learning.

Markovian Sliced Wasserstein Distances: Beyond Independent Projections

Interaction Measures, Partition Lattices and Kernel Tests for High-Order Interactions

Koopman Kernel Regression

Towards a Unified Analysis of Kernel-based Methods Under Covariate Shift

Sharp Spectral Rates for Koopman Operator Learning

Kernel Stein Discrepancy thinning: a theoretical perspective of pathologies and a practical fix with regularization

Improved Best-of-Both-Worlds Guarantees for Multi-Armed Bandits: FTRL with General Regularizers and Multiple Optimal Arms

Intensity Profile Projection: A Framework for Continuous-Time Representation Learning for Dynamic Networks

Embedding Space Interpolation Beyond Mini-Batch, Beyond Pairs and Beyond Examples

SNEkhorn: Dimension Reduction with Symmetric Entropic Affinities

MAViL: Masked Audio-Video Learners

Differentiable Neuro-Symbolic Reasoning on Large-Scale Knowledge Graphs

Cross-modal Prompts: Adapting Large Pre-trained Models for Audio-Visual Downstream Tasks

Invariant Anomaly Detection under Distribution Shifts: A Causal Perspective

DynaDojo: An Extensible Platform for Benchmarking Scaling in Dynamical System Identification

When Does Confidence-Based Cascade Deferral Suffice?

Learning Curves for Deep Structured Gaussian Feature Models

Scalarization for Multi-Task and Multi-Domain Learning at Scale

What a MESS: Multi-Domain Evaluation of Zero-Shot Semantic Segmentation

Optimal testing using combined test statistics across independent studies

Order Matters in the Presence of Dataset Imbalance for Multilingual Learning

Language Semantic Graph Guided Data-Efficient Learning

To Stay or Not to Stay in the Pre-train Basin: Insights on Ensembling in Transfer Learning

FedL2P: Federated Learning to Personalize

Adaptive Test-Time Personalization for Federated Learning

Mixed Samples as Probes for Unsupervised Model Selection in Domain Adaptation

ForkMerge: Mitigating Negative Transfer in Auxiliary-Task Learning

Zero-Shot Anomaly Detection via Batch Normalization

Efficient Policy Adaptation with Contrastive Prompt Ensemble for Embodied Agents

FlatMatch: Bridging Labeled Data and Unlabeled Data with Cross-Sharpness for Semi-Supervised Learning

Orthogonal Non-negative Tensor Factorization based Multi-view Clustering

SwapPrompt: Test-Time Prompt Adaptation for Vision-Language Models

Large sample spectral analysis of graph-based multi-manifold clustering

Multi-Swap k-Means++

Semi-Supervised Domain Generalization with Known and Unknown Classes

Harnessing Hard Mixed Samples with Decoupled Regularizer

Binary Classification with Confidence Difference

Path following algorithms for $\ell_2$-regularized $M$-estimation with approximation guarantee

Robust Distributed Learning: Tight Error Bounds and Breakdown Point under Data Heterogeneity

Neural Fields with Hard Constraints of Arbitrary Differential Order

On the Convergence to a Global Solution of Shuffling-Type Gradient Algorithms

Projection-Free Methods for Stochastic Simple Bilevel Optimization with Convex Lower-level Problem

Zeroth-Order Methods for Nondifferentiable, Nonconvex, and Hierarchical Federated Optimization

Non-Convex Bilevel Optimization with Time-Varying Objective Functions

Distributionally Robust Linear Quadratic Control

Connected Superlevel Set in (Deep) Reinforcement Learning and its Application to Minimax Theorems

Similarity, Compression and Local Steps: Three Pillars of Efficient Communications for Distributed Variational Inequalities

Boosting with Tempered Exponential Measures

Computational Guarantees for Doubly Entropic Wasserstein Barycenters

A Unified Discretization Framework for Differential Equation Approach with Lyapunov Arguments for Convex Optimization

Optimizing over trained GNNs via symmetry breaking

Advancing Bayesian Optimization via Learning Correlated Latent Space

Differentiable Sampling of Categorical Distributions Using the CatLog-Derivative Trick

DoWG Unleashed: An Efficient Universal Parameter-Free Gradient Descent Method

GloptiNets: Scalable Non-Convex Optimization with Certificates

Globally solving the Gromov-Wasserstein problem for point clouds in low dimensional Euclidean spaces

Decentralized Matrix Sensing: Statistical Guarantees and Fast Convergence

Learning to Search Feasible and Infeasible Regions of Routing Problems with Flexible Neural k-Opt

Robust Learning for Smoothed Online Convex Optimization with Feedback Delay

Exponentially Convergent Algorithms for Supervised Matrix Factorization

Rigorous Runtime Analysis of MOEA/D for Solving Multi-Objective Minimum Weight Base Problems

(S)GD over Diagonal Linear Networks: Implicit bias, Large Stepsizes and Edge of Stability

Stable Nonconvex-Nonconcave Training via Linear Interpolation

Oracle Complexity of Single-Loop Switching Subgradient Methods for Non-Smooth Weakly Convex Functional Constrained Optimization

LogSpecT: Feasible Graph Learning Model from Stationary Signals with Recovery Guarantees

Weitzman's Rule for Pandora's Box with Correlations

A Unified Approach for Maximizing Continuous DR-submodular Functions

Gradient Descent with Linearly Correlated Noise: Theory and Applications to Differential Privacy

Optimal Extragradient-Based Algorithms for Stochastic Variational Inequalities with Separable Structure

A Guide Through the Zoo of Biased SGD

Failure-Aware Gaussian Process Optimization with Regret Bounds

Framework and Benchmarks for Combinatorial and Mixed-variable Bayesian Optimization

Accelerated Zeroth-order Method for Non-Smooth Stochastic Convex Optimization Problem with Infinite Variance

Bayesian Optimization with Cost-varying Variable Subsets

Self-Correcting Bayesian Optimization through Bayesian Active Learning

How to Turn Your Knowledge Graph Embeddings into Generative Models

Moment Matching Denoising Gibbs Sampling

L-C2ST: Local Diagnostics for Posterior Approximations in Simulation-Based Inference

Model and Feature Diversity for Bayesian Neural Networks in Mutual Learning

Exact Bayesian Inference on Discrete Models via Probability Generating Functions: A Probabilistic Programming Approach

Hierarchical Semi-Implicit Variational Inference with Application to Diffusion Model Acceleration

Quantification of Uncertainty with Adversarial Models

Collapsed Inference for Bayesian Deep Learning

Function Space Bayesian Pseudocoreset for Bayesian Neural Networks

Efficient Bayesian Learning Curve Extrapolation using Prior-Data Fitted Networks

Energy-Based Sliced Wasserstein Distance

On the Identifiability and Interpretability of Gaussian Process Models

Probabilistic Exponential Integrators

Approximate inference of marginals using the IBIA framework

Characteristic Circuits

Discriminative Calibration: Check Bayesian Computation from Simulations and Flexible Classifier

Learning Rate Free Sampling in Constrained Domains

Fast Conditional Mixing of MCMC Algorithms for Non-log-concave Distributions

Provable benefits of annealing for estimating normalizing constants: Importance Sampling, Noise-Contrastive Estimation, and beyond

Structure Learning with Adaptive Random Neighborhood Informed MCMC

Joint Bayesian Inference of Graphical Structure and Parameters with a Single Generative Flow Network

Amortized Reparametrization: Efficient and Scalable Variational Inference for Latent SDEs

KuaiSim: A Comprehensive Simulator for Recommender Systems

Behavior Alignment via Reward Function Optimization

Online Nonstochastic Model-Free Reinforcement Learning

Supervised Pretraining Can Learn In-Context Reinforcement Learning

Learning World Models with Identifiable Factorization

Facing Off World Model Backbones: RNNs, Transformers, and S4

Imitation Learning from Imperfection: Theoretical Justifications and Algorithms

Policy Optimization for Continuous Reinforcement Learning

Finite-Time Analysis of Whittle Index based Q-Learning for Restless Multi-Armed Bandits with Neural Network Function Approximation

Offline Reinforcement Learning with Differential Privacy

SustainGym: Reinforcement Learning Environments for Sustainable Energy Systems

When Demonstrations meet Generative World Models: A Maximum Likelihood Framework for Offline Inverse Reinforcement Learning

Model-Free Active Exploration in Reinforcement Learning

Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals

Probabilistic Inference in Reinforcement Learning Done Right

Learning Generalizable Agents via Saliency-guided Features Decorrelation

Accelerating Exploration with Unlabeled Prior Data

Improved Communication Efficiency in Federated Natural Policy Gradient via ADMM-based Gradient Updates

Provably Efficient Offline Reinforcement Learning in Regular Decision Processes

Accountability in Offline Reinforcement Learning: Explaining Decisions with a Corpus of Examples

Offline Multi-Agent Reinforcement Learning with Implicit Global-to-Local Value Regularization

Train Once, Get a Family: State-Adaptive Balances for Offline-to-Online Reinforcement Learning

Refining Diffusion Planner for Reliable Behavior Synthesis by Automatic Detection of Infeasible Plans

Offline Imitation Learning with Variational Counterfactual Reasoning

ODE-based Recurrent Model-free Reinforcement Learning for POMDPs

Reinforcement Learning with Fast and Forgetful Memory

COOM: A Game Benchmark for Continual Reinforcement Learning

LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learning

Guide Your Agent with Adaptive Multimodal Rewards

Contrastive Modules with Temporal Attention for Multi-Task Reinforcement Learning

Dynamics Generalisation in Reinforcement Learning via Adaptive Context-Aware Policies

LightZero: A Unified Benchmark for Monte Carlo Tree Search in General Sequential Decision Scenarios

On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $\epsilon$-Greedy Exploration

Rewarded soups: towards Pareto-optimal alignment by interpolating weights fine-tuned on diverse rewards

Learning from Visual Observation via Offline Pretrained State-to-Go Transformer

Learning from Active Human Involvement through Proxy Value Propagation

Policy Optimization in a Noisy Neighborhood: On Return Landscapes in Continuous Control

MIMEx: Intrinsic Rewards from Masked Input Modeling

Interpretable Reward Redistribution in Reinforcement Learning: A Causal Approach

Kernelized Reinforcement Learning with Order Optimal Regret Bounds

Ordering-based Conditions for Global Convergence of Policy Gradient Methods

The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning

Learning Shared Safety Constraints from Multi-task Demonstrations

Conservative Offline Policy Adaptation in Multi-Agent Games

Policy Space Diversity for Non-Transitive Games

IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL

Information Design in Multi-Agent Reinforcement Learning

DIFFER:Decomposing Individual Reward for Fair Experience Replay in Multi-Agent Reinforcement Learning

Diverse Conventions for Human-AI Collaboration

How to Fine-tune the Model: Unified Model Shift and Model Bias Policy Optimization

Egocentric Planning for Scalable Embodied Task Achievement

Optimistic Exploration in Reinforcement Learning Using Symbolic Model Estimates

On the Planning Abilities of Large Language Models - A Critical Investigation

Percentile Criterion Optimization in Offline Reinforcement Learning

Risk-Averse Model Uncertainty for Distributionally Robust Safe Reinforcement Learning

Train Hard, Fight Easy: Robust Meta Reinforcement Learning

A Path to Simpler Models Starts With Noise

State2Explanation: Concept-Based Explanations to Benefit Agent Learning and User Understanding

Disentangling Cognitive Diagnosis with Limited Exercise Labels

Interpretability at Scale: Identifying Causal Mechanisms in Alpaca

Renku: a platform for sustainable data science

REASONER: An Explainable Recommendation Dataset with Comprehensive Labeling Ground Truths

OpenDataVal: a Unified Benchmark for Data Valuation

SmoothHess: ReLU Network Feature Interactions via Stein's Lemma

Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance

Towards a fuller understanding of neurons with Clustered Compositional Explanations

GLIME: General, Stable and Local LIME Explanation

StateMask: Explaining Deep Reinforcement Learning through State Mask

Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models

Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models

SynMob: Creating High-Fidelity Synthetic GPS Trajectory Dataset for Urban Mobility Analysis

Fair Streaming Principal Component Analysis: Statistical and Algorithmic Viewpoint

Face Reconstruction from Facial Templates by Learning Latent Space of a Generator Network

Participatory Personalization in Classification

Stable Bias: Evaluating Societal Representations in Diffusion Models

Causal Context Connects Counterfactual Fairness to Robust Prediction and Group Fairness

Variational Imbalanced Regression: Fair Uncertainty Quantification via Probabilistic Smoothing

Gaussian Differential Privacy on Riemannian Manifolds

Better Private Linear Regression Through Better Private Feature Selection

Bounding the Invertibility of Privacy-preserving Instance Encoding using Fisher Information

Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks

The Target-Charging Technique for Privacy Analysis across Interactive Computations

Differentially Private Image Classification by Learning Priors from Random Processes

Optimal privacy guarantees for a relaxed threat model: Addressing sub-optimal adversaries in differentially private machine learning

Scaling Up Differentially Private LASSO Regularized Logistic Regression via Faster Frank-Wolfe Iterations

Differentially Private Approximate Near Neighbor Counting in High Dimensions

Model Sparsity Can Simplify Machine Unlearning

Anonymous Learning via Look-Alike Clustering: A Precise Analysis of Model Generalization

Penguin: Parallel-Packed Homomorphic Encryption for Fast Graph Convolutional Network Inference

LinGCN: Structural Linearized Graph Convolutional Network for Homomorphically Encrypted Inference

On Differentially Private Sampling from Gaussian and Product Distributions

Tree-Rings Watermarks: Invisible Fingerprints for Diffusion Images

DecodingTrust: A Comprehensive Assessment of Trustworthiness in GPT Models

TRIAGE: Characterizing and auditing training data for improved regression

ParaFuzz: An Interpretability-Driven Technique for Detecting Poisoned Samples in NLP

RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks

ProPILE: Probing Privacy Leakage in Large Language Models

Where Did I Come From? Origin Attribution of AI-Generated Images

Stability Guarantees for Feature Attributions with Multiplicative Smoothing

Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Features

Black-box Backdoor Defense via Zero-shot Image Purification

UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation

TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery

What Distributions are Robust to Indiscriminate Poisoning Attacks for Linear Learners?

Punctuation-level Attack: Single-shot and Single Punctuation Can Fool Text Models

Selective Sampling and Imitation Learning via Online Regression

Contextual Bandits and Imitation Learning with Preference-Based Active Queries

Learning Domain-Aware Detection Head with Prompt Tuning

SoTTA: Robust Test-Time Adaptation on Noisy Data Streams

Subspace Identification for Multi-Source Domain Adaptation

A Fast and Accurate Estimator for Large Scale Linear Model via Data Averaging

Global Identifiability of $\ell_1$-based Dictionary Learning via Matrix Volume Optimization

Mode Connectivity in Auction Design

Persuading Farsighted Receivers in MDPs: the Power of Honesty

Logarithmic-Regret Quantum Learning Algorithms for Zero-Sum Games

Is Learning in Games Good for the Learners?

Fair Allocation of Indivisible Chores: Beyond Additive Costs

The Equivalence of Dynamic and Strategic Stability under Regularized Learning in Games

Supply-Side Equilibria in Recommender Systems

Efficient Subgame Refinement for Extensive-form Games

Data Market Design through Deep Learning

On the Interplay between Social Welfare and Tractability of Equilibria

List and Certificate Complexities in Replicable Learning

Near-Optimal Bounds for Learning Gaussian Halfspaces with Random Classification Noise

Learning Mixtures of Gaussians Using the DDPM Objective

Can semi-supervised learning use all the data effectively? A lower bound perspective

Recovering Unbalanced Communities in the Stochastic Block Model with Application to Clustering with a Faulty Oracle

Feature Adaptation for Sparse Linear Regression

Bottleneck Structure in Learned Features: Low-Dimension vs Regularity Tradeoff

Agnostically Learning Single-Index Models using Omnipredictors

A unified framework for information-theoretic generalization bounds

Unified Lower Bounds for Interactive High-dimensional Estimation under Information Constraints

Bayesian Learning of Optimal Policies in Markov Decision Processes with Countably Infinite State-Space

Regularization properties of adversarially-trained linear regression

A Unifying Perspective on Multi-Calibration: Game Dynamics for Multi-Objective Learning

A Theory of Unsupervised Translation Motivated by Understanding Animal Communication

Generalization in the Face of Adaptivity: A Bayesian Perspective

A U-turn on Double Descent: Rethinking Parameter Counting in Statistical Learning

Smoothed Analysis of Sequential Probability Assignment

A Batch-to-Online Transformation under Random-Order Model

Adversarial Attacks on Online Learning to Rank with Click Feedback

No-Regret Learning with Unbounded Losses: The Case of Logarithmic Pooling

High-dimensional Contextual Bandit Problem without Sparsity

Online Convex Optimization with Unbounded Memory

Fast Asymptotically Optimal Algorithms for Non-Parametric Stochastic Bandits

Practical Contextual Bandits with Feedback Graphs

On the Minimax Regret for Online Learning with Feedback Graphs

Dynamic Pricing and Learning with Bayesian Persuasion

Multi-task Representation Learning for Pure Exploration in Bilinear Bandits

Stochastic Multi-armed Bandits: Optimal Trade-off among Optimality, Consistency, and Tail Risk

Practical Sharpness-Aware Minimization Cannot Converge All the Way to Optima

Tight Risk Bounds for Gradient Descent on Separable Data

The probability flow ODE is provably fast

Matrix Compression via Randomized Low Rank and Low Precision Factorization

Optimistic Active Exploration of Dynamical Systems

When is Agnostic Reinforcement Learning Statistically Tractable?

Online RL in Linearly $q^\pi$-Realizable MDPs Is as Easy as in Linear MDPs If You Learn What to Ignore

Optimal Convergence Rate for Exact Policy Mirror Descent in Discounted Markov Decision Processes

Eliciting User Preferences for Personalized Multi-Objective Decision Making through Comparative Feedback

Provably (More) Sample-Efficient Offline RL with Options

Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch

The Curious Price of Distributional Robustness in Reinforcement Learning with a Generative Model

Evaluating Self-Supervised Learning for Molecular Graph Embeddings

End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics

Near Optimal Reconstruction of Spherical Harmonic Expansions

Distribution-Free Statistical Dispersion Control for Societal Applications

AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs

BoardgameQA: A Dataset for Natural Language Reasoning with Contradictory Information

Provably Efficient Algorithm for Nonstationary Low-Rank MDPs

Locality-Aware Generalizable Implicit Neural Representation

DiffSketcher: Text Guided Vector Sketch Synthesis through Latent Diffusion Models

Understanding and Mitigating Copying in Diffusion Models

On the Sublinear Regret of GP-UCB

Maximum State Entropy Exploration using Predecessor and Successor Representations

Sharpness Minimization Algorithms Do Not Only Minimize Sharpness To Achieve Better Generalization

Revisit Weakly-Supervised Audio-Visual Video Parsing from the Language Perspective

ResShift: Efficient Diffusion Model for Image Super-resolution by Residual Shifting

May the Force be with You: Unified Force-Centric Pre-Training for 3D Molecular Conformations

A Performance-Driven Benchmark for Feature Selection in Tabular Deep Learning

PLANNER: Generating Diversified Paragraph via Latent Language Diffusion Model

TFLEX: Temporal Feature-Logic Embedding Framework for Complex Reasoning over Temporal Knowledge Graph

The Best of Both Worlds in Network Population Games: Reaching Consensus and Convergence to Equilibrium

The Double-Edged Sword of Implicit Bias: Generalization vs. Robustness in ReLU Networks

Alpha-divergence Variational Inference Meets Importance Weighted Auto-Encoders: Methodology and Asymptotics

Data-Informed Geometric Space Selection

Degraded Polygons Raise Fundamental Questions of Neural Network Perception

Language Model Alignment with Elastic Reset

DISCS: A Benchmark for Discrete Sampling

Should We Learn Most Likely Functions or Parameters?

Certification of Distributional Individual Fairness

Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models

Norm-based Generalization Bounds for Sparse Neural Networks

Exploring Why Object Recognition Performance Degrades Across Income Levels and Geographies with Factor Annotations

Estimating Causal Effects Identifiable from a Combination of Observations and Experiments

Cheaply Estimating Inference Efficiency Metrics for Autoregressive Transformer Models

MCUFormer: Deploying Vision Tranformers on Microcontrollers with Limited Memory

Reproducibility Study of ”CartoonX: Cartoon Explanations of Image Classifiers”

Reproducibility study of 'Proto2Proto: Can you recognise the car, the way I do?'

Mitigating Source Bias for Fairer Weak Supervision

Waymax: An Accelerated, Data-Driven Simulator for Large-Scale Autonomous Driving Research

Robust Data Pruning under Label Noise via Maximizing Re-labeling Accuracy

[Re] Hierarchical Shrinkage: Improving the Accuracy and Interpretability of Tree-Based Methods

Monte Carlo Tree Search with Boltzmann Exploration

[Re] VAE Approximation Error: ELBO and Exponential Families

NeuroEvoBench: Benchmarking Evolutionary Optimizers for Deep Learning Applications

Holistic Evaluation of Text-to-Image Models

HT-Step: Aligning Instructional Articles with How-To Videos

(ends 10:45 AM)

10:45 a.m.

Lunch (On Your Own)

12:15 p.m.

Invited Talk:

Coherence statistics, self-generated experience and why young humans are much smarter than current AI.

Linda Smith

(ends 1:05 PM)

1:05 p.m.

Creative AI Session 1 [1:05-1:40]

Chairs: Jean Oh · Isabelle Guyon

s 1:05-1:40

[1:05] Kiss/Crash

[1:05] Blabrecs: An AI-Based Game of Nonsense Word Creation

[1:05] Androgynous and Mixed Race Human Face

[1:05] Voice Scroll

[1:05] The WHOOPS! Gallery: An Intersection of AI, Creativity, and the Unusual

[1:05] Visions of Resilience: Augmented Diversity

[1:05] salad bowl

[1:05] AI Applications to Illustrate Native American Arts: Birdsongs: Using Transfer Learning to Augment Image Generation Models

[1:05] Visualising AI

[1:05] Creating playful comics together with AI

(ends 1:40 PM)

Test Of Time:

Test of Time Award Talk:Distributed Representations of Words and Phrases and their Compositionality

(ends 1:25 PM)

1:20 p.m.

Coffee Only

1:40 p.m.

Oral 2A Efficient Learning [1:40-2:40]

Orals 1:40-2:40

[1:40] Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture

[1:55] QLoRA: Efficient Finetuning of Quantized LLMs

[2:10] Scaling Data-Constrained Language Models

[2:25] Bridging Discrete and Backpropagation: Straight-Through and Beyond

(ends 2:40 PM)

Oral 2B Objects/ Neuroscience/Vision [1:40-2:40]

Orals 1:40-2:40

[1:40] Rotating Features for Object Discovery

[1:55] Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment

[2:10] Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

[2:25] Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity

(ends 2:40 PM)

Oral 2C Causality [1:40-2:40]

Orals 1:40-2:40

[1:40] Learning Linear Causal Representations from Interventions under General Nonlinear Mixing

[1:55] A Measure-Theoretic Axiomatisation of Causality

[2:10] Conformal Meta-learners for Predictive Inference of Individual Treatment Effects

[2:25] Causal normalizing flows: from theory to practice

(ends 2:40 PM)

Oral 2D Privacy [1:40-2:40]

Orals 1:40-2:40

[1:40] Nearly Tight Bounds For Differentially Private Multiway Cut

[1:55] Privacy Auditing with One (1) Training Run

[2:10] Private Everlasting Prediction

[2:25] User-Level Differential Privacy With Few Examples Per User

(ends 2:40 PM)

2:45 p.m.

Break

3:15 p.m.

Poster Session 2 [3:15-5:15]

Posters 3:15-5:15

A Deep Instance Generative Framework for MILP Solvers Under Limited Data Availability

Unsupervised Protein-Ligand Binding Energy Prediction via Neural Euler's Rotation Equation

AI for Interpretable Chemistry: Predicting Radical Mechanistic Pathways via Contrastive Learning

Accelerating Molecular Graph Neural Networks via Knowledge Distillation

TensorNet: Cartesian Tensor Representations for Efficient Learning of Molecular Potentials

LinkerNet: Fragment Poses and Linker Co-Design with 3D Equivariant Diffusion

GeoTMI: Predicting Quantum Chemical Property with Easy-to-Obtain Geometry via Positional Denoising

Implicit Transfer Operator Learning: Multiple Time-Resolution Models for Molecular Dynamics

De novo Drug Design using Reinforcement Learning with Multiple GPT Agents

Semantic segmentation of sparse irregular point clouds for leaf/wood discrimination

Debias Coarsely, Sample Conditionally: Statistical Downscaling through Optimal Transport and Probabilistic Diffusion Models

StreamNet: Memory-Efficient Streaming Tiny Deep Learning Inference on the Microcontroller

Adaptive Contextual Perception: How To Generalize To New Backgrounds and Ambiguous Objects

3D-Aware Visual Question Answering about Parts, Poses and Occlusions

Mip-Grid: Anti-aliased Grid Representations for Neural Radiance Fields

MG-ViT: A Multi-Granularity Method for Compact and Efficient Vision Transformers

CRoSS: Diffusion Model Makes Controllable, Robust and Secure Image Steganography

Lookup Table meets Local Laplacian Filter: Pyramid Reconstruction Network for Tone Mapping

SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs

PAPR: Proximity Attention Point Rendering

Unsupervised Optical Flow Estimation with Dynamic Timing Representation for Spike Camera

Structure from Duplicates: Neural Inverse Graphics from a Pile of Objects

Convolutions Die Hard: Open-Vocabulary Segmentation with Single Frozen Convolutional CLIP

Label-efficient Segmentation via Affinity Propagation

DAC-DETR: Divide the Attention Layers and Conquer

Mitigating the Effect of Incidental Correlations on Part-based Learning

Generative Category-level Object Pose Estimation via Diffusion Models

Tuning Multi-mode Token-level Prompt Alignment across Modalities

Discovering Intrinsic Spatial-Temporal Logic Rules to Explain Human Actions

M$^{2}$SODAI: Multi-Modal Maritime Object Detection Dataset With RGB and Hyperspectral Image Sensors

CamoPatch: An Evolutionary Strategy for Generating Camoflauged Adversarial Patches

Decorate3D: Text-Driven High-Quality Texture Generation for Mesh Decoration in the Wild

DDF-HO: Hand-Held Object Reconstruction via Conditional Directed Distance Field

Align Your Prompts: Test-Time Prompting with Distribution Alignment for Zero-Shot Generalization

Compressed Video Prompt Tuning

ReTR: Modeling Rendering Via Transformer for Generalizable Neural Surface Reconstruction

Saving 100x Storage: Prototype Replay for Reconstructing Training Sample Distribution in Class-Incremental Semantic Segmentation

Masked Image Residual Learning for Scaling Deeper Vision Transformers

LuminAIRe: Illumination-Aware Conditional Image Repainting for Lighting-Realistic Generation

Segment Anything in 3D with NeRFs

Real-World Image Super-Resolution as Multi-Task Learning

VPGTrans: Transfer Visual Prompt Generator across LLMs

What Do Deep Saliency Models Learn about Visual Attention?

Mask Propagation for Efficient Video Semantic Segmentation

Stanford-ORB: A Real-World 3D Object Inverse Rendering Benchmark

CommonScenes: Generating Commonsense 3D Indoor Scenes with Scene Graph Diffusion

Towards Label-free Scene Understanding by Vision Foundation Models

Real3D-AD: A Dataset of Point Cloud Anomaly Detection

Tame a Wild Camera: In-the-Wild Monocular Camera Calibration

MixFormerV2: Efficient Fully Transformer Tracking

TMT-VIS: Taxonomy-aware Multi-dataset Joint Training for Video Instance Segmentation

Learning Neural Implicit through Volume Rendering with Attentive Depth Fusion Priors

Towards A Richer 2D Understanding of Hands at Scale

HotBEV: Hardware-oriented Transformer-based Multi-View 3D Detector for BEV Perception

QuantSR: Accurate Low-bit Quantization for Efficient Image Super-Resolution

ViSt3D: Video Stylization with 3D CNN

IDEA: An Invariant Perspective for Efficient Domain Adaptive Image Retrieval

Uni3DETR: Unified 3D Detection Transformer

Training on Foveated Images Improves Robustness to Adversarial Attacks

Volume Feature Rendering for Fast Neural Radiance Field Reconstruction

Multi-body SE(3) Equivariance for Unsupervised Rigid Segmentation and Motion Estimation

From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces

DFRD: Data-Free Robustness Distillation for Heterogeneous Federated Learning

SALSA VERDE: a machine learning attack on LWE with sparse small secrets

GeoPhy: Differentiable Phylogenetic Inference via Geometric Gradients of Tree Topologies

ProteinNPT: Improving Protein Property Prediction and Design with Non-Parametric Transformers

PoET: A generative model of protein families as sequences-of-sequences

Neural Frailty Machine: Beyond proportional hazard assumption in neural survival regressions

Med-UniC: Unifying Cross-Lingual Medical Vision-Language Pre-Training by Diminishing Bias

AVIS: Autonomous Visual Information Seeking with Large Language Model Agent

The Goldilocks of Pragmatic Understanding: Fine-Tuning Strategy Matters for Implicature Resolution by LLMs

Composing Parameter-Efficient Modules with Arithmetic Operation

HyTrel: Hypergraph-enhanced Tabular Data Representation Learning

Parameterizing Context: Unleashing the Power of Parameter-Efficient Fine-Tuning and In-Context Tuning for Continual Table Semantic Parsing

Augmenting Language Models with Long-Term Memory

CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Society

Large language models transition from integrating across position-yoked, exponential windows to structure-yoked, power-law windows

Large Language Models for Automated Data Science: Introducing CAAFE for Context-Aware Automated Feature Engineering

Is Your Code Generated by ChatGPT Really Correct? Rigorous Evaluation of Large Language Models for Code Generation

Birth of a Transformer: A Memory Viewpoint

Fine-Grained Human Feedback Gives Better Rewards for Language Model Training

AR-Diffusion: Auto-Regressive Diffusion Model for Text Generation

Preference-grounded Token-level Guidance for Language Model Fine-tuning

From Cloze to Comprehension: Retrofitting Pre-trained Masked Language Models to Pre-trained Machine Reader

Grammar Prompting for Domain-Specific Language Generation with Large Language Models

Intrinsic Dimension Estimation for Robust Detection of AI-Generated Texts

ComSL: A Composite Speech-Language Model for End-to-End Speech-to-Text Translation

Incomplete Multimodality-Diffused Emotion Recognition

Self-Evaluation Guided Beam Search for Reasoning

ASL Citizen: A Community-Sourced Dataset for Advancing Isolated Sign Language Recognition

DOSE: Diffusion Dropout with Adaptive Prior for Speech Enhancement

Gaussian Partial Information Decomposition: Bias Correction and Application to High-dimensional Data

Exploring Loss Functions for Time-based Training Strategy in Spiking Neural Networks

Scaling laws for language encoding models in fMRI

Computing a human-like reaction time metric from stable recurrent vision models

Explaining V1 Properties with a Biologically Constrained Deep Learning Architecture

Energy Guided Diffusion for Generating Neurally Exciting Images

AMAG: Additive, Multiplicative and Adaptive Graph Neural Network For Forecasting Neuron Activity

Strong and Precise Modulation of Human Percepts via Robustified ANNs

Convolution Monge Mapping Normalization for learning on sleep data

Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity

A normative theory of social conflict

Neural Data Transformer 2: Multi-context Pretraining for Neural Spiking Activity

Large Language Models are Visual Reasoning Coordinators

Neural Circuits for Fast Poisson Compressed Sensing in the Olfactory Bulb

Hierarchical VAEs provide a normative account of motion processing in the primate brain

Beyond Geometry: Comparing the Temporal Structure of Computation in Neural Circuits with Dynamical Similarity Analysis

Joint processing of linguistic properties in brains and language models

Spike-driven Transformer

Self-Supervised Learning of Representations for Space Generates Multi-Modular Grid Cells

DeWave: Discrete Encoding of EEG Waves for EEG to Text Translation

Training neural operators to preserve invariant measures of chaotic attractors

MMGP: a Mesh Morphing Gaussian Process-based machine learning method for regression of physical problems under nonparametrized geometrical variability

Solving Inverse Physics Problems with Score Matching

PETAL: Physics Emulation Through Averaged Linearizations for Solving Inverse Problems

Transformer-based Planning for Symbolic Regression

Unifying Predictions of Deterministic and Stochastic Physics in Mesh-reduced Space with Sequential Flow Generative Model

Representation Equivalent Neural Operators: a Framework for Alias-free Operator Learning

Find What You Want: Learning Demand-conditioned Object Attribute Space for Demand-driven Navigation

Online POMDP Planning with Anytime Deterministic Guarantees

Information Maximizing Curriculum: A Curriculum-Based Approach for Learning Versatile Skills

Accelerating Motion Planning via Optimal Transport

Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?

POMDP Planning for Object Search in Partially Unknown Environment

FGPrompt: Fine-grained Goal Prompting for Image-goal Navigation

Adaptive Normalization for Non-stationary Time Series Forecasting: A Temporal Slice Perspective

Deciphering Spatio-Temporal Graph Forecasting: A Causal Lens and Treatment

Koopa: Learning Non-stationary Time Series Dynamics with Koopman Predictors

Diversify Your Vision Datasets with Automatic Diffusion-based Augmentation

HyP-NeRF: Learning Improved NeRF Priors using a HyperNetwork

Meet in the Middle: A New Pre-training Paradigm

Lightweight Vision Transformer with Bidirectional Interaction

Memory-Efficient Fine-Tuning of Compressed Large Language Models via sub-4-bit Integer Quantization

Tanh Works Better with Asymmetry

A General Framework for Equivariant Neural Networks on Reductive Lie Groups

Clustering the Sketch: Dynamic Compression for Embedding Tables

Systematic Visual Reasoning through Object-Centric Relational Abstraction

Learning Sample Difficulty from Pre-trained Models for Reliable Prediction

Bridging Discrete and Backpropagation: Straight-Through and Beyond

Module-wise Training of Neural Networks via the Minimizing Movement Scheme

You Only Condense Once: Two Rules for Pruning Condensed Datasets

Sharpness-Aware Minimization Leads to Low-Rank Features

AlpacaFarm: A Simulation Framework for Methods that Learn from Human Feedback

Monarch Mixer: A Simple Sub-Quadratic GEMM-Based Architecture

Probabilistic Weight Fixing: Large-scale training of neural network weight uncertainties for quantisation.

ScaleLong: Towards More Stable Training of Diffusion Model via Scaling Network Long Skip Connection

A Data-Free Approach to Mitigate Catastrophic Forgetting in Federated Class Incremental Learning for Vision Tasks

Inconsistency, Instability, and Generalization Gap of Deep Neural Network Training

Towards Anytime Classification in Early-Exit Architectures by Enforcing Conditional Monotonicity

Accurate Interpolation for Scattered Data through Hierarchical Residual Refinement

Geometric Transformer with Interatomic Positional Encoding

Random-Access Infinite Context Length for Transformers

Designing Robust Transformers using Robust Kernel Density Estimation

Schema-learning and rebinding as mechanisms of in-context learning and emergence

Polyhedron Attention Module: Learning Adaptive-order Interactions

Coneheads: Hierarchy Aware Attention

The Quantization Model of Neural Scaling

Pruning vs Quantization: Which is Better?

QLoRA: Efficient Finetuning of Quantized LLMs

How a Student becomes a Teacher: learning and forgetting through Spectral methods

DatasetDM: Synthesizing Data with Perception Annotations Using Diffusion Models

TextDiffuser: Diffusion Models as Text Painters

A Unified Framework for U-Net Design and Analysis

Energy Discrepancies: A Score-Independent Loss for Energy-Based Models

Learning Space-Time Continuous Latent Neural PDEs from Partially Observed States

Addressing Negative Transfer in Diffusion Models

Scenario Diffusion: Controllable Driving Scenario Generation With Diffusion

PTQD: Accurate Post-Training Quantization for Diffusion Models

Generative Modeling through the Semi-dual Formulation of Unbalanced Optimal Transport

Learning Energy-based Model via Dual-MCMC Teaching

In-Context Learning Unlocked for Diffusion Models

Energy-Based Models for Anomaly Detection: A Manifold Diffusion Recovery Approach

Dynamic Prompt Learning: Addressing Cross-Attention Leakage for Text-Based Image Editing

Diffusion Model for Graph Inverse Problems: Towards Effective Source Localization on Complex Networks

DPM-Solver-v3: Improved Diffusion ODE Solver with Empirical Model Statistics

AmadeusGPT: a natural language interface for interactive animal behavioral analysis

Optimal Transport-Guided Conditional Score-Based Diffusion Model

Direct Diffusion Bridge using Data Consistency for Inverse Problems

DPOK: Reinforcement Learning for Fine-tuning Text-to-Image Diffusion Models

Complexity Matters: Rethinking the Latent Space for Generative Modeling

Im-Promptu: In-Context Composition from Image Prompts

Gaussian Mixture Solvers for Diffusion Models

Score-based Generative Modeling through Stochastic Evolution Equations in Hilbert Spaces

Projection Regret: Reducing Background Bias for Novelty Detection via Diffusion Models

Score-based Source Separation with Applications to Digital Communication Signals

Recommender Systems with Generative Retrieval

Exposing flaws of generative model evaluation metrics and their unfair treatment of diffusion models

Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedback

Towards Efficient Image Compression Without Autoregressive Models

Idempotent Learned Image Compression with Right-Inverse

Bootstrapping Vision-Language Learning with Decoupled Language Pre-training

TopP&R: Robust Support Estimation Approach for Evaluating Fidelity and Diversity in Generative Models

MultiFusion: Fusing Pre-Trained Models for Multi-Lingual, Multi-Modal Image Generation

HeadSculpt: Crafting 3D Head Avatars with Text

Training Energy-Based Normalizing Flow with Score-Matching Objectives

Linguistic Binding in Diffusion Models: Enhancing Attribute Correspondence through Attention Map Alignment

VideoComposer: Compositional Video Synthesis with Motion Controllability

Three Iterations of (d − 1)-WL Test Distinguish Non Isometric Clouds of d-dimensional Points

Graph Contrastive Learning with Stable and Scalable Spectral Encoding

Reversible and irreversible bracket-based dynamics for deep graph neural networks

No Change, No Gain: Empowering Graph Neural Networks with Expected Model Change Maximization for Active Learning

Implicit Convolutional Kernels for Steerable CNNs

Learning Large Graph Property Prediction via Graph Segment Training

Laplacian Canonization: A Minimalist Approach to Sign and Basis Invariant Spectral Embedding

Re-Think and Re-Design Graph Neural Networks in Spaces of Continuous Graph Diffusion Functionals

Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs

Recurrent Temporal Revision Graph Networks

Live Graph Lab: Towards Open, Dynamic and Real Transaction Graphs with NFT

V-InFoR: A Robust Graph Neural Networks Explainer for Structurally Corrupted Graphs

Modeling Dynamics over Meshes with Gauge Equivariant Nonlinear Message Passing

LD2: Scalable Heterophilous Graph Neural Network with Decoupled Embeddings

Rethinking Semi-Supervised Imbalanced Node Classification from Bias-Variance Decomposition

Universal Prompt Tuning for Graph Neural Networks

MeGraph: Capturing Long-Range Interactions by Alternating Local and Hierarchical Aggregation on Multi-Scaled Graph Hierarchy

MuSe-GNN: Learning Unified Gene Representation From Multimodal Biological Graph Data

Learning Unseen Modality Interaction

CAPro: Webly Supervised Learning with Cross-modality Aligned Prototypes

Rotating Features for Object Discovery

CoLLAT: On Adding Fine-grained Audio Understanding to Language Models using Token-Level Locked-Language Tuning

Topological Obstructions and How to Avoid Them

Convolutional State Space Models for Long-Range Spatiotemporal Modeling

Evolving Connectivity for Recurrent Spiking Neural Networks

Robust Learning with Progressive Data Expansion Against Spurious Correlation

Video Dynamics Prior: An Internal Learning Approach for Robust Video Enhancements

A Theory of Transfer-Based Black-Box Attacks: Explanation and Implications

Fantastic Robustness Measures: The Secrets of Robust Generalization

Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models

The Adversarial Consistency of Surrogate Risks for Binary Classification

On the Connection between Pre-training Data Diversity and Fine-tuning Robustness

(Almost) Provable Error Bounds Under Distribution Shift via Disagreement Discrepancy

Hierarchical Randomized Smoothing

Characterizing the Optimal $0-1$ Loss for Multi-class Classification with a Test-time Attacker

Optimal Transport Model Distributional Robustness

Effective Targeted Attacks for Adversarial Self-Supervised Learning

Learning Invariant Representations with a Nonparametric Nadaraya-Watson Head

Cross-Scale MAE: A Tale of Multiscale Exploitation in Remote Sensing

Identifiable Contrastive Learning with Automatic Feature Importance Discovery

Test-time Training for Matching-based Video Object Segmentation

Self-supervised Object-Centric Learning for Videos

No Representation Rules Them All in Category Discovery

To Repeat or Not To Repeat: Insights from Scaling LLM under Token-Crisis

Understanding Contrastive Learning via Distributionally Robust Optimization

Pretraining task diversity and the emergence of non-Bayesian in-context learning for regression

Scale-teaching: Robust Multi-scale Training for Time Series Classification with Noisy Labels

Change point detection and inference in multivariate non-parametric models under mixing conditions

Pairwise Causality Guided Transformers for Event Sequences

Additive Decoders for Latent Variables Identification and Cartesian-Product Extrapolation

Globally injective and bijective neural operators

What Makes Data Suitable for a Locally Connected Neural Network? A Necessary and Sufficient Condition Based on Quantum Entanglement.

Provable Advantage of Curriculum Learning on Parity Targets with Mixed Inputs

The Exact Sample Complexity Gain from Invariances for Kernel Regression

Reliable learning in challenging environments

Representational Strengths and Limitations of Transformers

A General Theory of Correct, Incorrect, and Extrinsic Equivariance

Convergence of mean-field Langevin dynamics: time-space discretization, stochastic gradient, and variance reduction

Scaling Data-Constrained Language Models

Phase diagram of early training dynamics in deep neural networks: effect of the learning rate, depth, and width

Learning threshold neurons via edge of stability

On student-teacher deviations in distillation: does it pay to disobey?

Estimating Propensity for Causality-based Recommendation without Exposure Data

Causal discovery from observational and interventional data across multiple environments

Global Optimality in Bivariate Gradient-based DAG Learning

A Cross-Moment Approach for Causal Effect Estimation

Conformal Meta-learners for Predictive Inference of Individual Treatment Effects

Causal normalizing flows: from theory to practice

A Measure-Theoretic Axiomatisation of Causality

Comparing Causal Frameworks: Potential Outcomes, Structural Models, Graphs, and Abstractions

Passive learning of active causal strategies in agents and language models

Reusable Slotwise Mechanisms

Inner Product-based Neural Network Similarity

Loss Decoupling for Task-Agnostic Continual Learning

Beyond probability partitions: Calibrating neural networks with semantic aware grouping

Conformalized matrix completion

Neuro-symbolic Learning Yielding Logical Constraints

Time-uniform confidence bands for the CDF under nonstationarity

Flow: Per-instance Personalized Federated Learning

Neural approximation of Wasserstein distance via a universal architecture for symmetric and factorwise group invariant functions

Diffusion Representation for Asymmetric Kernels via Magnetic Transform

Deep learning with kernels through RKHM and the Perron-Frobenius operator

Learning Functional Transduction

Fast Approximation of Similarity Graphs with Kernel Density Estimation

Gradient-Free Kernel Stein Discrepancy

Balancing Risk and Reward: A Batched-Bandit Strategy for Automated Phased Release

Universal Online Learning with Gradient Variations: A Multi-layer Online Ensemble Approach

Active Bipartite Ranking

No-Regret Online Prediction with Strategic Experts

PERFOGRAPH: A Numerical Aware Program Graph Representation for Performance Optimization and Program Analysis

Object-centric Learning with Cyclic Walks between Parts and Whole

Stable Vectorization of Multiparameter Persistent Homology using Signed Barcodes as Measures

DisDiff: Unsupervised Disentanglement of Diffusion Probabilistic Models

GUST: Combinatorial Generalization by Unsupervised Grouping with Neuronal Coherence

Learning Interpretable Low-dimensional Representation via Physical Symmetry

SaVeNet: A Scalable Vector Network for Enhanced Molecular Representation Learning

Noether Embedding: Efficient Learning of Temporal Regularities

Selectivity Drives Productivity: Efficient Dataset Pruning for Enhanced Transfer Learning

Improved Frequency Estimation Algorithms with and without Predictions

Adaptive Topological Feature via Persistent Homology: Filtration Learning for Point Clouds

Foundation Model is Efficient Multimodal Multitask Model Selector

FeCAM: Exploiting the Heterogeneity of Class Distributions in Exemplar-Free Continual Learning

Few-Shot Class-Incremental Learning via Training-Free Prototype Calibration

When Visual Prompt Tuning Meets Source-Free Domain Adaptive Semantic Segmentation

Revisiting Scalarization in Multi-Task Learning: A Theoretical Perspective

Retaining Beneficial Information from Detrimental Data for Neural Network Repair

A Theory of Multimodal Learning

Revisit the Power of Vanilla Knowledge Distillation: from Small Scale to Large Scale

One-for-All: Bridge the Gap Between Heterogeneous Architectures in Knowledge Distillation

ExPT: Synthetic Pretraining for Few-Shot Experimental Design

Neural Priming for Sample-Efficient Adaptation

Evolving Standardization for Continual Domain Generalization over Temporal Drift

Hierarchical Decomposition of Prompt-Based Continual Learning: Rethinking Obscured Sub-optimality

Spuriosity Didn’t Kill the Classifier: Using Invariant Predictions to Harness Spurious Features

Constant Approximation for Individual Preference Stable Clustering

Self-Adaptive Motion Tracking against On-body Displacement of Flexible Sensors

Differentiable Random Partition Models

Generalized Semi-Supervised Learning via Self-Supervised Feature Adaptation

Hierarchical clustering with dot products recovers hidden tree structure

Multi-Object Representation Learning via Feature Connectivity and Object-Centric Regularization

Partial Label Learning with Dissimilarity Propagation guided Candidate Label Shrinkage

A Riemannian Exponential Augmented Lagrangian Method for Computing the Projection Robust Wasserstein Distance

Convex and Non-convex Optimization Under Generalized Smoothness

Federated Learning with Manifold Regularization and Normalized Update Reaggregation

Bilevel Coreset Selection in Continual Learning: A New Formulation and Algorithm

Exact Verification of ReLU Neural Control Barrier Functions

Neural Lyapunov Control for Discrete-Time Systems

Revisiting Implicit Differentiation for Learning Problems in Optimal Control

ReHLine: Regularized Composite ReLU-ReHU Loss Minimization with Linear Computation and Linear Convergence

Dynamic Non-monotone Submodular Maximization

Energy-Efficient Scheduling with Predictions

Adjustable Robust Reinforcement Learning for Online 3D Bin Packing

BQ-NCO: Bisimulation Quotienting for Efficient Neural Combinatorial Optimization

A Combinatorial Algorithm for Approximating the Optimal Transport in the Parallel and MPC Settings

One-step differentiation of iterative algorithms

Rethinking Gauss-Newton for learning over-parameterized models

Many-body Approximation for Non-negative Tensors

A Computationally Efficient Sparsified Online Newton Method

Unbiased Compression Saves Communication in Distributed Optimization: When and How Much?

Optimal Time Complexities of Parallel Stochastic Optimization Methods Under a Fixed Computation Model

Navigating Data Heterogeneity in Federated Learning: A Semi-Supervised Federated Object Detection

A Unified Solution for Privacy and Communication Efficiency in Vertical Federated Learning

Finding Local Minima Efficiently in Decentralized Optimization

Momentum Provably Improves Error Feedback!

Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction

Learning the Efficient Frontier

Efficient Meta Neural Heuristic for Multi-Objective Combinatorial Optimization

Direction-oriented Multi-objective Learning: Simple and Provable Stochastic Algorithms

Hypervolume Maximization: A Geometric View of Pareto Set Learning

Universal Gradient Descent Ascent Method for Nonconvex-Nonconcave Minimax Optimization

Recovering Simultaneously Structured Data via Non-Convex Iteratively Reweighted Least Squares

Outlier-Robust Gromov-Wasserstein for Graph Data

Two-Stage Predict+Optimize for MILPs with Unknown Parameters in Constraints

DELTA: Diverse Client Sampling for Fasting Federated Learning

A Finite-Particle Convergence Rate for Stein Variational Gradient Descent

Optimization and Bayes: A Trade-off for Overparameterized Neural Networks

Unexpected Improvements to Expected Improvement for Bayesian Optimization

Information Maximization Perspective of Orthogonal Matching Pursuit with Applications to Explainable AI

Bayesian Metric Learning for Uncertainty Quantification in Image Retrieval

Adaptive Uncertainty Estimation via High-Dimensional Testing on Latent Representations

Towards Accelerated Model Training via Bayesian Data Selection

Sparse Deep Learning for Time Series Data: Theory and Applications

Undirected Probabilistic Model for Tensor Decomposition

On Convergence of Polynomial Approximations to the Gaussian Mixture Entropy

Bayesian Learning via Q-Exponential Process

Self-Consistent Velocity Matching of Probability Flows

Beyond Normal: On the Evaluation of Mutual Information Estimators

The Behavior and Convergence of Local Bayesian Optimization

Pointwise uncertainty quantification for sparse variational Gaussian process regression with a Brownian motion prior

Survival Permanental Processes for Survival Analysis with Time-Varying Covariates

Fast Projected Newton-like Method for Precision Matrix Estimation under Total Positivity

Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification

Unbiased learning of deep generative models with structured discrete representations

Learning Large-Scale MTP$_2$ Gaussian Graphical Models via Bridge-Block Decomposition

Langevin Quasi-Monte Carlo

Sampling from Structured Log-Concave Distributions via a Soft-Threshold Dikin Walk

Differentiable and Stable Long-Range Tracking of Multiple Posterior Modes

Distributionally Robust Skeleton Learning of Discrete Bayesian Networks

Fast Scalable and Accurate Discovery of DAGs Using the Best Order Score Search and Grow Shrink Trees

NAS-X: Neural Adaptive Smoothing via Twisting

Towards Understanding the Dynamics of Gaussian-Stein Variational Gradient Descent

Compression with Bayesian Implicit Neural Representations

Variational Inference with Gaussian Score Matching

Imitation Learning from Vague Feedback

Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control

Efficient Potential-based Exploration in Reinforcement Learning using Inverse Dynamic Bisimulation Metric

Structured State Space Models for In-Context Reinforcement Learning

Effectively Learning Initiation Sets in Hierarchical Reinforcement Learning

Finite-Time Analysis of Single-Timescale Actor-Critic

Robust Knowledge Transfer in Tiered Reinforcement Learning

No-Regret Online Reinforcement Learning with Adversarial Losses and Transitions

General Munchausen Reinforcement Learning with Tsallis Kullback-Leibler Divergence

Accelerating Monte Carlo Tree Search with Probability Tree State Abstraction

Multi-Modal Inverse Constrained Reinforcement Learning from a Mixture of Demonstrations

An Efficient End-to-End Training Approach for Zero-Shot Human-AI Coordination

Mutual Information Regularized Offline Reinforcement Learning

Uncertainty-Aware Instance Reweighting for Off-Policy Learning

Efficient Diffusion Policies For Offline Reinforcement Learning

Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets

A Simple Solution for Offline Imitation from Observations and Examples with Possibly Incomplete Trajectories

Adversarial Model for Offline Reinforcement Learning

Conservative State Value Estimation for Offline Reinforcement Learning

Counterfactual Conservative Q Learning for Offline Multi-agent Reinforcement Learning

Budgeting Counterfactual for Offline RL

Explore to Generalize in Zero-Shot RL

Regularity as Intrinsic Reward for Free Play

Pre-training Contextualized World Models with In-the-wild Videos for Reinforcement Learning

Accelerating Reinforcement Learning with Value-Conditional State Entropy Exploration

Synthetic Experience Replay

Resetting the Optimizer in Deep RL: An Empirical Study

Learning to Discover Skills through Guidance

Weakly Coupled Deep Q-Networks

Two Heads are Better Than One: A Simple Exploration Framework for Efficient Multi-Agent Reinforcement Learning

Efficient Adversarial Attacks on Online Multi-agent Reinforcement Learning

Automatic Grouping for Efficient Cooperative Multi-Agent Reinforcement Learning

Dual Self-Awareness Value Decomposition Framework without Individual Global Max for Cooperative MARL

Iteratively Learn Diverse Strategies with State Distance Information

Dynamic Regret of Adversarial Linear Mixture MDPs

Reference-Based POMDPs

Instructing Goal-Conditioned Reinforcement Learning Agents with Temporal Logic Objectives

Diffused Task-Agnostic Milestone Planner

Leveraging Pre-trained Large Language Models to Construct and Utilize World Models for Model-based Task Planning

An Alternative to Variance: Gini Deviation for Risk-averse Policy Gradient

Fast Bellman Updates for Wasserstein Distributionally Robust MDPs

Exploring and Interacting with the Set of Good Sparse Generalized Additive Models

Post Hoc Explanations of Language Models Can Improve Language Models

When Does Optimizing a Proper Loss Yield Calibration?

In-Context Impersonation Reveals Large Language Models' Strengths and Biases

HiBug: On Human-Interpretable Model Debug

OKRidge: Scalable Optimal k-Sparse Ridge Regression

The Grand Illusion: The Myth of Software Portability and Implications for ML Progress.

Explaining Predictive Uncertainty with Information Theoretic Shapley Values

Towards Automated Circuit Discovery for Mechanistic Interpretability

Gaussian Process Probes (GPP) for Uncertainty-Aware Probing

Learning to Receive Help: Intervention-Aware Concept Embedding Models

Counterfactual Memorization in Neural Language Models

The Contextual Lasso: Sparse Linear Models via Deep Neural Networks

On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspective

Neural Sculpting: Uncovering hierarchically modular task structure in neural networks through pruning and network analysis

On the Relationship Between Relevance and Conflict in Online Social Link Recommendations

Uncovering and Quantifying Social Biases in Code Generation

Language Model Tokenizers Introduce Unfairness Between Languages

Fairness Aware Counterfactuals for Subgroups

Long-Term Fairness with Unknown Dynamics

Should I Stop or Should I Go: Early Stopping with Heterogeneous Populations

Bias in Evaluation Processes: An Optimization-Based Model

Adapting Fairness Interventions to Missing Values

Differentially Private Statistical Inference through $\beta$-Divergence One Posterior Sampling

UltraRE: Enhancing RecEraser for Recommendation Unlearning via Error Decomposition

Gaussian Membership Inference Privacy

Exact Optimality of Communication-Privacy-Utility Tradeoffs in Distributed Mean Estimation

Privacy Auditing with One (1) Training Run

k-Median Clustering via Metric Embedding: Towards Better Initialization with Differential Privacy

Certified Minimax Unlearning with Generalization Rates and Deletion Capacity

Bounding training data reconstruction in DP-SGD

DP-Mix: Mixup-based Data Augmentation for Differentially Private Learning

On Computing Pairwise Statistics with Local Differential Privacy

DP-HyPO: An Adaptive Private Framework for Hyperparameter Optimization

Breaking the Communication-Privacy-Accuracy Tradeoff with $f$-Differential Privacy

User-Level Differential Privacy With Few Examples Per User

Counting Distinct Elements in the Turnstile Model with Differential Privacy under Continual Observation

LANCE: Stress-testing Visual Models by Generating Language-guided Counterfactual Images

Causes and Effects of Unanticipated Numerical Deviations in Neural Network Inference Frameworks

Boosting Adversarial Transferability by Achieving Flat Local Maxima

On the Powerfulness of Textual Outlier Exposure for Visual OoD Detection

On the Importance of Feature Separability in Predicting Out-Of-Distribution Error

Towards Stable Backdoor Purification through Feature Shift Tuning

Causal Fairness for Outcome Control

On the Exploitability of Instruction Tuning

Django: Detecting Trojans in Object Detection Models via Gaussian Focus Calibration

A Unified Detection Framework for Inference-Stage Backdoor Defenses

Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

Out-of-distribution Detection Learning with Unreliable Out-of-distribution Sources

Counterfactually Comparing Abstaining Classifiers

Defending against Data-Free Model Extraction by Distributionally Robust Defensive Training

Private Everlasting Prediction

On the Convergence of Encoder-only Shallow Transformers

A Competitive Algorithm for Agnostic Active Learning

FIRAL: An Active Learning Algorithm for Multinomial Logistic Regression

Make the U in UDA Matter: Invariant Consistency Learning for Unsupervised Domain Adaptation

Incentives in Federated Learning: Equilibria, Dynamics, and Mechanisms for Welfare Maximization

On the Convergence of No-Regret Learning Dynamics in Time-Varying Games

Refined Mechanism Design for Approximately Structured Priors via Active Regression

Bicriteria Multidimensional Mechanism Design with Side Information

Combinatorial Group Testing with Selfish Agents

On the Last-iterate Convergence in Time-varying Zero-sum Games: Extra Gradient Succeeds where Optimism Fails

Exploiting hidden structures in non-convex games for convergence to Nash equilibrium

Uncoupled and Convergent Learning in Two-Player Zero-Sum Markov Games with Bandit Feedback

No-Regret Learning in Dynamic Competition with Reference Effects Under Logit Demand

Block-Coordinate Methods and Restarting for Solving Extensive-Form Games

Strategic Data Sharing between Competitors

Strategic Classification under Unknown Personalized Manipulation

Statistical Analysis of Quantum State Learning Process in Quantum Neural Networks

Generalized equivalences between subsampling and ridge regularization

Analyzing Generalization of Neural Networks through Loss Path Kernels

Adversarially Robust Learning with Uncertain Perturbation Sets

PAC Learning Linear Thresholds from Label Proportions

Optimal Excess Risk Bounds for Empirical Risk Minimization on $p$-Norm Linear Regression

Learning via Wasserstein-Based High Probability Generalisation Bounds

Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent

Robust Second-Order Nonconvex Optimization and Its Application to Low Rank Matrix Sensing

Towards Data-Algorithm Dependent Generalization: a Case Study on Overparameterized Linear Regression

On the Variance, Admissibility, and Stability of Empirical Risk Minimization

On Proper Learnability between Average- and Worst-case Robustness

New Bounds for Hyperparameter Tuning of Regression Problems Across Instances

How many samples are needed to leverage smoothness?

The Pick-to-Learn Algorithm: Empowering Compression for Tight Generalization Bounds and Improved Post-training Performance

Fine-Grained Theoretical Analysis of Federated Zeroth-Order Optimization

A Sublinear-Time Spectral Clustering Oracle with Improved Preprocessing Time

Hypothesis Selection with Memory Constraints

Replicable Clustering

Closing the Computational-Statistical Gap in Best Arm Identification for Combinatorial Semi-bandits

Statistical and Computational Trade-off in Multi-Agent Multi-Armed Bandits

Efficient Online Clustering with Moving Costs

Double Auctions with Two-sided Bandit Feedback

Noise-Adaptive Thompson Sampling for Linear Contextual Bandits

An Improved Relaxation for Oracle-Efficient Adversarial Contextual Bandits

Quantifying the Cost of Learning in Queueing Systems

Multi-Agent Learning with Heterogeneous Linear Contextual Bandits

Online Clustering of Bandits with Misspecified User Models

Nearest Neighbour with Bandit Feedback

Incentivized Communication for Federated Bandits

Cascading Contextual Assortment Bandits

Adaptive Selective Sampling for Online Prediction with Experts

Robust Lipschitz Bandits to Adversarial Corruptions

Improving the Knowledge Gradient Algorithm

Likelihood Ratio Confidence Sets for Sequential Decision Making

Optimal cross-learning for contextual bandits with unknown context distributions

Non-Asymptotic Analysis of a UCB-based Top Two Algorithm

Online Ad Procurement in Non-stationary Autobidding Worlds

Data-Dependent Bounds for Online Portfolio Selection Without Lipschitzness and Smoothness

Riemannian Projection-free Online Learning

Greedy Pruning with Group Lasso Provably Generalizes for Matrix Sensing

AGD: an Auto-switchable Optimizer using Stepwise Gradient Difference for Preconditioning Matrix

Nearly Tight Bounds For Differentially Private Multiway Cut

Communication-Efficient Federated Bilevel Optimization with Global and Local Lower Level Problems

Embracing the chaos: analysis and diagnosis of numerical instability in variational flows

Attention as Implicit Structural Inference

Improved Bayesian Regret Bounds for Thompson Sampling in Reinforcement Learning

Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration

Replicability in Reinforcement Learning

Online Pricing for Multi-User Multi-Item Markets

A Theoretical Analysis of Optimistic Proximal Policy Optimization in Linear Markov Decision Processes

Decision-Aware Actor-Critic with Function Approximation and Theoretical Guarantees

A Reduction-based Framework for Sequential Decision Making with Delayed Feedback

Importance Weighted Actor-Critic for Optimal Conservative Offline Reinforcement Learning

Data-driven Optimal Filtering for Linear Systems with Unknown Noise Covariances

Model-Free Reinforcement Learning with the Decision-Estimation Coefficient

Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models

Enhancing User Intent Capture in Session-Based Recommendation with Attribute Patterns

Large Language Models Are Latent Variable Models: Explaining and Finding Good Demonstrations for In-Context Learning

Common Ground in Cooperative Communication

A Spectral Theory of Neural Prediction and Alignment

Language Models are Weak Learners

Any-to-Any Generation via Composable Diffusion

Group Robust Classification Without Any Group Information

Structured Federated Learning through Clustered Additive Modeling

Robustness Guarantees for Adversarially Trained Neural Networks

What is the Inductive Bias of Flatness Regularization? A Study of Deep Matrix Factorization Models

A Diffusion-Model of Joint Interactive Navigation

Cal-DETR: Calibrated Detection Transformer

Improving Graph Matching with Positional Reconstruction Encoder-Decoder Network

Mitigating Over-smoothing in Transformers via Regularized Nonlocal Functionals

Collaborative Score Distillation for Consistent Visual Editing

A State Representation for Diminishing Rewards

SAMoSSA: Multivariate Singular Spectrum Analysis with Stochastic Autoregressive Noise

Zero-shot causal learning

Unsupervised Behavior Extraction via Random Intent Priors

Enhancing CLIP with CLIP: Exploring Pseudolabeling for Limited-Label Prompt Tuning

Posthoc privacy guarantees for collaborative inference with modified Propose-Test-Release

MosaicBERT: A Bidirectional Encoder Optimized for Fast Pretraining

Learning and Collusion in Multi-unit Auctions

Train 'n Trade: Foundations of Parameter Markets

Finite Population Regression Adjustment and Non-asymptotic Guarantees for Treatment Effect Estimation

Accelerated On-Device Forward Neural Network Training with Module-Wise Descending Asynchronism

PUe: Biased Positive-Unlabeled Learning Enhancement by Causal Inference

FLSL: Feature-level Self-supervised Learning

Convex-Concave Zero-Sum Markov Stackelberg Games

High Precision Causal Model Evaluation with Conditional Randomization

Single-Stage Visual Query Localization in Egocentric Videos

Removing Hidden Confounding in Recommendation: A Unified Multi-Task Learning Approach

Dynamic Sparsity Is Channel-Level Sparsity Learner

Adversarially Robust Distributed Count Tracking via Partial Differential Privacy

Beyond Invariance: Test-Time Label-Shift Adaptation for Addressing "Spurious" Correlations

Near-Optimal $k$-Clustering in the Sliding Window Model

Banana: Banach Fixed-Point Network for Pointcloud Segmentation with Inter-Part Equivariance

Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evaluations

Symmetry-Informed Geometric Representation for Molecules, Proteins, and Crystalline Materials

Exploring the Optimal Choice for Generative Processes in Diffusion Models: Ordinary vs Stochastic Differential Equations

Subclass-Dominant Label Noise: A Counterexample for the Success of Early Stopping

MADLAD-400: A Multilingual And Document-Level Large Audited Dataset

(ends 5:15 PM)

5 p.m.

WED 13 DEC

5:30 a.m.

Registration Desk

(ends 4:00 PM)

6:30 a.m.

Invited Talk:

Sketching: core tools, learning-augmentation, and adaptive robustness

Jelani Nelson

(ends 7:20 AM)

7:15 a.m.

Break

8 a.m.

Oral 3A Neuro [8:00-8:45]

Orals 8:00-8:45

[8:00] Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models

[8:15] Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity

[8:30] Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language

(ends 8:45 AM)

Oral 3B NLP/Tools [8:00-8:45]

Orals 8:00-8:45

[8:00] ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

[8:15] Toolformer: Language Models Can Teach Themselves to Use Tools

[8:30] Learning Transformer Programs

(ends 8:45 AM)

Oral 3C Diffusion Models [8:00-8:45]

Orals 8:00-8:45

[8:00] Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation

[8:15] Entropic Neural Optimal Transport via Diffusion Processes

[8:30] DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models

(ends 8:45 AM)

8:45 a.m.

Poster Session 3 [8:45-10:45]

Posters 8:45-10:45

Neural Modulation for Flash Memory: An Unsupervised Learning Framework for Improved Reliability

CoDrug: Conformal Drug Property Prediction with Density Estimation under Covariate Shift

Stochastic Optimal Control for Collective Variable Free Sampling of Molecular Transition Paths

Towards Symmetry-Aware Generation of Periodic Materials

Equivariant Neural Operator Learning with Graphon Convolution

FABind: Fast and Accurate Protein-Ligand Binding

Timewarp: Transferable Acceleration of Molecular Dynamics by Learning Time-Coarsened Dynamics

Transfer learning for atomistic simulations using GNNs and kernel mean embeddings

Learning Fine-grained View-Invariant Representations from Unpaired Ego-Exo Videos via Temporal Alignment

OpenShape: Scaling Up 3D Shape Representation Towards Open-World Understanding

Transition-constant Normalization for Image Enhancement

Prototype-based Aleatoric Uncertainty Quantification for Cross-modal Retrieval

DAW: Exploring the Better Weighting Function for Semi-supervised Semantic Segmentation

PromptIR: Prompting for All-in-One Image Restoration

Weakly Supervised 3D Open-vocabulary Segmentation

Opening the Vocabulary of Egocentric Actions

Assessor360: Multi-sequence Network for Blind Omnidirectional Image Quality Assessment

Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation

SceneScape: Text-Driven Consistent Scene Generation

Unified 3D Segmenter As Prototypical Classifiers

Reading Relevant Feature from Global Representation Memory for Visual Object Tracking

KD-Zero: Evolving Knowledge Distiller for Any Teacher-Student Pairs

Learning Mask-aware CLIP Representations for Zero-Shot Segmentation

Exploring Question Decomposition for Zero-Shot VQA

ChatGPT-Powered Hierarchical Comparisons for Image Classification

ImageBrush: Learning Visual In-Context Instructions for Exemplar-Based Image Manipulation

DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data

Exploiting Contextual Objects and Relations for 3D Visual Grounding

Bitstream-Corrupted Video Recovery: A Novel Benchmark Dataset and Method

Neural-Logic Human-Object Interaction Detection

Vocabulary-free Image Classification

Synthetic-to-Real Pose Estimation with Geometric Reconstruction

Low-shot Object Learning with Mutual Exclusivity Bias

ZoomTrack: Target-aware Non-uniform Resizing for Efficient Visual Tracking

Type-to-Track: Retrieve Any Object via Prompt-based Tracking

Learning Dense Flow Field for Highly-accurate Cross-view Camera Localization

EgoDistill: Egocentric Head Motion Distillation for Efficient Video Understanding

AttrSeg: Open-Vocabulary Semantic Segmentation via Attribute Decomposition-Aggregation

SOC: Semantic-Assisted Object Cluster for Referring Video Object Segmentation

FineMoGen: Fine-Grained Spatio-Temporal Motion Generation and Editing

Jigsaw: Learning to Assemble Multiple Fractured Objects

SLIBO-Net: Floorplan Reconstruction via Slicing Box Representation with Local Geometry Regularization

PaintSeg: Painting Pixels for Training-free Segmentation

An Efficient Dataset Condensation Plugin and Its Application to Continual Learning

Boundary Guided Learning-Free Semantic Control with Diffusion Models

Lossy Image Compression with Conditional Diffusion Models

Robustifying Generalizable Implicit Shape Networks with a Tunable Non-Parametric Model

Navigating the Pitfalls of Active Learning Evaluation: A Systematic Framework for Meaningful Performance Assessment

How2comm: Communication-Efficient and Collaboration-Pragmatic Multi-Agent Perception

CoDA: Collaborative Novel Box Discovery and Cross-modal Alignment for Open-vocabulary 3D Object Detection

Fairness Continual Learning Approach to Semantic Scene Understanding in Open-World Environments

HEDNet: A Hierarchical Encoder-Decoder Network for 3D Object Detection in Point Clouds

Weakly-Supervised Concealed Object Segmentation with SAM-based Pseudo Labeling and Multi-scale Feature Grouping

NU-MCC: Multiview Compressive Coding with Neighborhood Decoder and Repulsive UDF

4D Panoptic Scene Graph Generation

Echoes Beyond Points: Unleashing the Power of Raw Radar Data in Multi-modality Fusion

GeoCLIP: Clip-Inspired Alignment between Locations and Images for Effective Worldwide Geo-localization

Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation

Towards Generic Semi-Supervised Framework for Volumetric Medical Image Segmentation

SNAP: Self-Supervised Neural Maps for Visual Positioning and Semantic Understanding

Improving neural network representations using human similarity judgments

Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives

Jaccard Metric Losses: Optimizing the Jaccard Index with Soft Labels

Template-free Articulated Neural Point Clouds for Reposable View Synthesis

NeuralGF: Unsupervised Point Normal Estimation by Learning Neural Gradient Function

Circuit as Set of Points

Importance-aware Co-teaching for Offline Model-based Optimization

Machine learning detects terminal singularities

DSR: Dynamical Surface Representation as Implicit Neural Networks for Protein

Brant: Foundation Model for Intracranial Neural Signal

An Iterative Self-Learning Framework for Medical Domain Generalization

ResoNet: Noise-Trained Physics-Informed MRI Off-Resonance Correction

REFINE: A Fine-Grained Medication Recommendation System Using Deep Learning and Personalized Drug Interaction Modeling

HyPoradise: An Open Baseline for Generative Speech Recognition with Large Language Models

NuTrea: Neural Tree Search for Context-guided Multi-hop KGQA

ToolkenGPT: Augmenting Frozen Language Models with Massive Tools via Tool Embeddings

AUDIT: Audio Editing by Following Instructions with Latent Diffusion Models

Fine-grained Late-interaction Multi-modal Retrieval for Retrieval Augmented Visual Question Answering

LLM-Pruner: On the Structural Pruning of Large Language Models

Make Pre-trained Model Reversible: From Parameter to Memory Efficient Fine-Tuning

Disentangling Voice and Content with Self-Supervision for Speaker Recognition

Learning Descriptive Image Captioning via Semipermeable Maximum Likelihood Estimation

Conditional Adapters: Parameter-efficient Transfer Learning with Fast Inference

Chameleon: Plug-and-Play Compositional Reasoning with Large Language Models

Evaluating and Inducing Personality in Pre-trained Language Models

RRHF: Rank Responses to Align Language Models with Human Feedback

Language Models can Solve Computer Tasks

Debiased and Denoised Entity Recognition from Distant Supervision

Propagating Knowledge Updates to LMs Through Distillation

On the Pareto Front of Multilingual Neural Machine Translation

Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

Aligning Language Models with Human Preferences via a Bayesian Approach

DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translation

LIMA: Less Is More for Alignment

Toolformer: Language Models Can Teach Themselves to Use Tools

Can Language Models Teach? Teacher Explanations Improve Student Performance via Personalization

Information Geometry of the Retinal Representation Manifold

Spiking PointNet: Spiking Neural Networks for Point Clouds

Brain Diffusion for Visual Exploration: Cortical Discovery using Large Scale Generative Models

Learning Time-Invariant Representations for Individual Neurons from Population Dynamics

Brain-like Flexible Visual Inference by Harnessing Feedback Feedforward Alignment

Trial matching: capturing variability with data-constrained spiking neural networks

A Recurrent Neural Circuit Mechanism of Temporal-scaling Equivariant Representation

Meta-learning families of plasticity rules in recurrent spiking networks using simulation-based inference

Training biologically plausible recurrent neural networks on cognitive tasks with long-term dependencies

Human spatiotemporal pattern learning as probabilistic program synthesis

A Dual-Stream Neural Network Explains the Functional Segregation of Dorsal and Ventral Visual Pathways in Human Brains

Cinematic Mindscapes: High-quality Video Reconstruction from Brain Activity

Addressing the speed-accuracy simulation trade-off for adaptive spiking neurons

Convolutional Neural Operators for robust and accurate learning of PDEs

QuACK: Accelerating Gradient-Based Quantum Optimization with Koopman Operator Learning

Randomized Sparse Neural Galerkin Schemes for Solving Evolution Equations with Deep Networks

PICProp: Physics-Informed Confidence Propagation for Uncertainty Quantification

Entropy-dissipation Informed Neural Network for McKean-Vlasov Type PDEs

Variational Monte Carlo on a Budget — Fine-tuning pre-trained Neural Wavefunctions

SE(3) Equivariant Augmented Coupling Flows

PDE-Refiner: Achieving Accurate Long Rollouts with Neural PDE Solvers

EmbodiedGPT: Vision-Language Pre-Training via Embodied Chain of Thought

Where2Explore: Few-shot Affordance Learning for Unseen Novel Categories of Articulated Objects

3D-IntPhys: Towards More Generalized 3D-grounded Visual Intuitive Physics under Challenging Scenes

Data Quality in Imitation Learning

DiffuseBot: Breeding Soft Robots With Physics-Augmented Generative Diffusion Models

Conformal Prediction for Time Series with Modern Hopfield Networks

OneNet: Enhancing Time Series Forecasting Models under Concept Drift by Online Ensembling

On the Constrained Time-Series Generation Problem

On the Trade-off of Intra-/Inter-class Diversity for Supervised Pre-training

Data-Centric Learning from Unlabeled Graphs with Diffusion Model

Skill-it! A data-driven skills framework for understanding and training language models

Generating Images with Multimodal Language Models

Window-Based Distribution Shift Detection for Deep Neural Networks

Implicit Bias of Gradient Descent for Two-layer ReLU and Leaky ReLU Networks on Nearly-orthogonal Data

Neural Functional Transformers

NAR-Former V2: Rethinking Transformer for Universal Neural Network Representation Learning

Enhancing Minority Classes by Mixing: An Adaptative Optimal Transport Approach for Long-tailed Classification

High dimensional, tabular deep learning with an auxiliary knowledge graph

ASPEN: Breaking Operator Barriers for Efficient Parallelization of Deep Neural Networks

MeCo: Zero-Shot NAS with One Data and Single Forward Pass via Minimum Eigenvalue of Correlation

Speculative Decoding with Big Little Decoder

SUBP: Soft Uniform Block Pruning for 1$\times$N Sparse CNNs Multithreading Acceleration

Laughing Hyena Distillery: Extracting Compact Recurrences From Convolutions

StableFDG: Style and Attention Based Learning for Federated Domain Generalization

SLaM: Student-Label Mixing for Distillation with Unlabeled Examples

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures

Accelerated Training via Incrementally Growing Neural Networks using Variance Transfer and Learning Rate Adaptation

ResMem: Learn what you can and memorize the rest

Tree-Based Diffusion Schrödinger Bridge with Applications to Wasserstein Barycenters

Efficient Low-rank Backpropagation for Vision Transformer Adaptation

Improving Few-Shot Generalization by Exploring and Exploiting Auxiliary Data

Training Transformers with 4-bit Integers

Critical Initialization of Wide and Deep Neural Networks using Partial Jacobians: General Theory and Applications

Energy Transformer

Transformers are uninterpretable with myopic methods: a case study with bounded Dyck grammars

Attentive Transfer Entropy to Exploit Transient Emergence of Coupling Effect

Blockwise Parallel Transformers for Large Context Models

Transformers learn to implement preconditioned gradient descent for in-context learning

The Impact of Positional Encoding on Length Generalization in Transformers

Hierarchically Gated Recurrent Neural Network for Sequence Modeling

Causal Interpretation of Self-Attention in Pre-Trained Transformers

Scissorhands: Exploiting the Persistence of Importance Hypothesis for LLM KV Cache Compression at Test Time

IDRNet: Intervention-Driven Relation Network for Semantic Segmentation

Frequency Domain-Based Dataset Distillation

Score-based Generative Models with Lévy Processes

Hyperbolic VAE via Latent Gaussian Distributions

Distributional Learning of Variational AutoEncoder: Application to Synthetic Data Generation

Unifying GANs and Score-Based Diffusion as Generative Particle Models

Formulating Discrete Probability Flow Through Optimal Transport

Intriguing Properties of Quantization at Scale

SEGA: Instructing Text-to-Image Models using Semantic Guidance

StyleDrop: Text-to-Image Synthesis of Any Style

Squeeze, Recover and Relabel: Dataset Condensation at ImageNet Scale From A New Perspective

Learning Visual Prior via Generative Pre-Training

Latent Diffusion for Language Generation

Lexinvariant Language Models

Mix-of-Show: Decentralized Low-Rank Adaptation for Multi-Concept Customization of Diffusion Models

Understanding Diffusion Objectives as the ELBO with Simple Data Augmentation

SyncDiffusion: Coherent Montage via Synchronized Joint Diffusions

Grassmann Manifold Flows for Stable Shape Generation

ViCA-NeRF: View-Consistency-Aware 3D Editing of Neural Radiance Fields

FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models

Token-Scaled Logit Distillation for Ternary Weight Generative Language Models

Generative Neural Fields by Mixtures of Neural Implicit Functions

CSLP-AE: A Contrastive Split-Latent Permutation Autoencoder Framework for Zero-Shot Electroencephalography Signal Conversion

Curvature Filtrations for Graph Generative Model Evaluation

Aligning Optimization Trajectories with Diffusion Models for Constrained Design Generation

MEGABYTE: Predicting Million-byte Sequences with Multiscale Transformers

Isometric Quotient Variational Auto-Encoders for Structure-Preserving Representation Learning

StyleGAN knows Normal, Depth, Albedo, and More

Debiasing Pretrained Generative Models by Uniformly Sampling Semantic Attributes

Diffusion Models and Semi-Supervised Learners Benefit Mutually with Few Labels

Extracting Reward Functions from Diffusion Models

Entropic Neural Optimal Transport via Diffusion Processes

An Information-Theoretic Evaluation of Generative Models in Learning Multi-modal Distributions

Functional Renyi Differential Privacy for Generative Modeling

Augmentation-Aware Self-Supervision for Data-Efficient GAN Training

Efficient Training of Energy-Based Models Using Jarzynski Equality

Flow Factorized Representation Learning

PreDiff: Precipitation Nowcasting with Latent Diffusion Models

ImageReward: Learning and Evaluating Human Preferences for Text-to-Image Generation

Scaling Riemannian Diffusion Models

SlotDiffusion: Object-Centric Generative Modeling with Diffusion Models

PrimDiffusion: Volumetric Primitives Diffusion for 3D Human Generation

Semantic Image Synthesis with Unconditional Generator

GlucoSynth: Generating Differentially-Private Synthetic Glucose Traces

OpenGSL: A Comprehensive Benchmark for Graph Structure Learning

On the Ability of Graph Neural Networks to Model Interactions Between Vertices

Sheaf Hypergraph Networks

Neural Graph Generation from Graph Statistics

MAG-GNN: Reinforcement Learning Boosted Graph Neural Network

Latent Field Discovery in Interacting Dynamical Systems with Neural Fields

A Metadata-Driven Approach to Understand Graph Neural Networks

Towards Label Position Bias in Graph Neural Networks

Is Distance Matrix Enough for Geometric Deep Learning?

What functions can Graph Neural Networks compute on random graphs? The role of Positional Encoding

A graphon-signal analysis of graph neural networks

Generalised f-Mean Aggregation for Graph Neural Networks

Does Invariant Graph Learning via Environment Augmentation Learn Invariance?

Geometric Algebra Transformer

Layer-Neighbor Sampling --- Defusing Neighborhood Explosion in GNNs

Zero-One Laws of Graph Neural Networks

How Re-sampling Helps for Long-Tail Learning?

Intra-Modal Proxy Learning for Zero-Shot Visual Categorization with CLIP

VoxDet: Voxel Learning for Novel Instance Detection

Feature-Learning Networks Are Consistent Across Widths At Realistic Scales

Diffused Redundancy in Pre-trained Representations

Neural Latent Geometry Search: Product Manifold Inference via Gromov-Hausdorff-Informed Bayesian Optimization

Connecting Multi-modal Contrastive Representations

Quantifying & Modeling Multimodal Interactions: An Information Decomposition Framework

What Knowledge Gets Distilled in Knowledge Distillation?

Efficient Beam Tree Recursion

Balancing memorization and generalization in RNNs for high performance brain-machine Interfaces

Bifurcations and loss jumps in RNN training

Cognitive Steering in Deep Neural Networks via Long-Range Modulatory Feedback Connections

Hardware Resilience Properties of Text-Guided Image Classifiers

Effective Robustness against Natural Distribution Shifts for Models with Different Training Data

Are aligned neural networks adversarially aligned?

HQA-Attack: Toward High Quality Black-Box Hard-Label Adversarial Attack on Text

Transferable Adversarial Robustness for Categorical Data via Universal Robust Embeddings

GradOrth: A Simple yet Efficient Out-of-Distribution Detection with Orthogonal Projection of Gradients

Robust low-rank training via approximate orthonormal constraints

Provably Bounding Neural Network Preimages

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

Red Teaming Deep Neural Networks with Feature Synthesis Tools

Testing the General Deductive Reasoning Capacity of Large Language Models Using OOD Examples

Understanding and Improving Ensemble Adversarial Defense

Robust Contrastive Language-Image Pretraining against Data Poisoning and Backdoor Attacks

Normalization-Equivariant Neural Networks with Application to Image Denoising

Certified Robustness via Dynamic Margin Maximization and Improved Lipschitz Regularization

IPMix: Label-Preserving Data Augmentation Method for Training Robust Classifiers

Neural Image Compression: Generalization, Robustness, and Spectral Biases

CSOT: Curriculum and Structure-Aware Optimal Transport for Learning with Noisy Labels

Adversarial Examples Might be Avoidable: The Role of Data Concentration in Adversarial Robustness

Task-Robust Pre-Training for Worst-Case Downstream Adaptation

Eliminating Catastrophic Overfitting Via Abnormal Adversarial Examples Regularization

Wasserstein distributional robustness of neural networks

Simplicity Bias in 1-Hidden Layer Neural Networks

On the Adversarial Robustness of Out-of-distribution Generalization Models

STREAMER: Streaming Representation Learning and Event Segmentation in a Hierarchical Manner

CADet: Fully Self-Supervised Out-Of-Distribution Detection With Contrastive Learning

Mitigating the Popularity Bias of Graph Collaborative Filtering: A Dimensional Collapse Perspective

Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models

Three Towers: Flexible Contrastive Learning with Pretrained Image Models

Better Correlation and Robustness: A Distribution-Balanced Self-Supervised Learning Framework for Automatic Dialogue Evaluation

Evolutionary Neural Architecture Search for Transformer in Knowledge Tracing

Modulated Neural ODEs

Why Did This Model Forecast This Future? Information-Theoretic Saliency for Counterfactual Explanations of Probabilistic Regression Models

The Transient Nature of Emergent In-Context Learning in Transformers

Prompt-augmented Temporal Point Process for Streaming Event Sequence

Hardness of Low Rank Approximation of Entrywise Transformed Matrix Products

Training Fully Connected Neural Networks is $\exists\mathbb{R}$-Complete

Minimum norm interpolation by perceptra: Explicit regularization and implicit bias

From Tempered to Benign Overfitting in ReLU Neural Networks

Implicit Bias of (Stochastic) Gradient Descent for Rank-1 Linear Neural Network

Learning in the Presence of Low-dimensional Structure: A Spiked Random Matrix Perspective

Penalising the biases in norm regularisation enforces sparsity

Towards a Unified Framework of Contrastive Learning for Disentangled Representations

On the spectral bias of two-layer linear networks

Don’t just prune by magnitude! Your mask topology is a secret weapon

The Shaped Transformer: Attention Models in the Infinite Depth-and-Width Limit

Should Under-parameterized Student Networks Copy or Average Teacher Weights?

Gradient-Based Feature Learning under Structured Data

Minimum Description Length and Generalization Guarantees for Representation Learning

Partial Multi-Label Learning with Probabilistic Graphical Disambiguation

Causal Component Analysis

iSCAN: Identifying Causal Mechanism Shifts among Nonlinear Additive Noise Models

Approximate Allocation Matching for Structural Causal Bandits with Unobserved Confounders

Assumption violations in causal discovery and the robustness of score matching

Fair Adaptive Experiments

Invariant Learning via Probability of Sufficient and Necessary Causes

Detecting hidden confounding in observational data using multiple environments

Disambiguated Attention Embedding for Multi-Instance Partial-Label Learning

Construction of Hierarchical Neural Architecture Search Spaces based on Context-free Grammars

Harnessing the power of choices in decision tree learning

R-divergence for Estimating Model-oriented Distribution Discrepancy

On the Asymptotic Learning Curves of Kernel Ridge Regression under Power-law Decay

Variational Weighting for Kernel Density Ratios

Kernel Quadrature with Randomly Pivoted Cholesky

MMD-Fuse: Learning and Combining Kernels for Two-Sample Testing Without Data Splitting

Efficient Test-Time Adaptation for Super-Resolution with Second-Order Degradation and Reconstruction

ALIM: Adjusting Label Importance Mechanism for Noisy Partial Label Learning

Stability-penalty-adaptive follow-the-regularized-leader: Sparsity, game-dependency, and best-of-both-worlds

Diffusion-Based Probabilistic Uncertainty Estimation for Active Domain Adaptation

Multitask Learning with No Regret: from Improved Confidence Bounds to Active Learning

Towards Free Data Selection with General-Purpose Models

Alternation makes the adversary weaker in two-player games

Experimental Designs for Heteroskedastic Variance

Scaling MLPs: A Tale of Inductive Bias

Leveraging sparse and shared feature activations for disentangled representation learning

Dynamic Tensor Decomposition via Neural Diffusion-Reaction Processes

Disentanglement via Latent Quantization

Truly Scale-Equivariant Deep Nets with Fourier Layers

Robust Concept Erasure via Kernelized Rate-Distortion Maximization

Scale Alone Does not Improve Mechanistic Interpretability in Vision Models

A Heat Diffusion Perspective on Geodesic Preserving Dimensionality Reduction

How to Scale Your EMA

AiluRus: A Scalable ViT Framework for Dense Prediction

SOAR: Improved Indexing for Approximate Nearest Neighbor Search

Estimating Koopman operators with sketching to provably learn large scale dynamical systems

SHOT: Suppressing the Hessian along the Optimization Trajectory for Gradient-Based Meta-Learning

A Simple Yet Effective Strategy to Robustify the Meta Learning Paradigm

Federated Conditional Stochastic Optimization

Mnemosyne: Learning to Train Transformers with Transformers

A Unified Approach to Domain Incremental Learning with Memory: Theory and Algorithm

Joint Data-Task Generation for Auxiliary Learning

CODA: Generalizing to Open and Unseen Domains with Compaction and Disambiguation

Understanding Few-Shot Learning: Measuring Task Relatedness and Adaptation Difficulty via Attributes

Overcoming Recency Bias of Normalization Statistics in Continual Learning: Balance and Adaptation

Guiding The Last Layer in Federated Learning with Pre-Trained Models

Transfer Learning with Affine Model Transformation

Generalizing Importance Weighting to A Universal Solver for Distribution Shift Problems

Learning Large-scale Neural Fields via Context Pruned Meta-Learning

Switching Temporary Teachers for Semi-Supervised Semantic Segmentation

Fast and Simple Spectral Clustering in Theory and Practice

S-CLIP: Semi-supervised Vision-Language Learning using Few Specialist Captions

On the Exploration of Local Significant Differences For Two-Sample Test

Optimization of Inter-group criteria for clustering with minimum size constraints

A Unified Approach to Count-Based Weakly Supervised Learning

Fast Rank-1 Lattice Targeted Sampling for Black-box Optimization

Block Coordinate Plug-and-Play Methods for Blind Inverse Problems

On the Overlooked Structure of Stochastic Gradients

Coordinating Distributed Example Orders for Provably Accelerated Training

Debiasing Conditional Stochastic Optimization

Achieving $\mathcal{O}(\epsilon^{-1.5})$ Complexity in Hessian/Jacobian-free Stochastic Bilevel Optimization

SLM: A Smoothed First-Order Lagrangian Method for Structured Constrained Nonconvex Optimization

Online Performative Gradient Descent for Learning Nash Equilibria in Decision-Dependent Games

Trajectory Alignment: Understanding the Edge of Stability Phenomenon via Bifurcation Theory

Structured Neural-PI Control with End-to-End Stability and Output Tracking Guarantees

Optimization or Architecture: How to Hack Kalman Filtering

Convergence Analysis of Sequential Federated Learning on Heterogeneous Data

First Order Methods with Markovian Noise: from Acceleration to Variational Inequalities

On the Generalization Error of Stochastic Mirror Descent for Quadratically-Bounded Losses: an Improved Analysis

Core-sets for Fair and Diverse Data Summarization

Simple, Scalable and Effective Clustering via One-Dimensional Projections

Discrete-Smoothness in Online Algorithms with Predictions

T2T: From Distribution Learning in Training to Gradient Search in Testing for Combinatorial Optimization

DIFUSCO: Graph-based Diffusion Solvers for Combinatorial Optimization

Sketchy: Memory-efficient Adaptive Regularization with Frequent Directions

Block Low-Rank Preconditioner with Shared Basis for Stochastic Optimization

KAKURENBO: Adaptively Hiding Samples in Deep Neural Network Training

H-nobs: Achieving Certified Fairness and Robustness in Distributed Learning on Heterogeneous Datasets

H3T: Efficient Integration of Memory Optimization and Parallelism for Large-scale Transformer Training

Distributed Personalized Empirical Risk Minimization

Delayed Algorithms for Distributed Stochastic Weakly Convex Optimization

EvoFed: Leveraging Evolutionary Strategies for Communication-Efficient Federated Learning

Beyond Exponential Graph: Communication-Efficient Topologies for Decentralized Learning via Finite-time Convergence

Birder: Communication-Efficient 1-bit Adaptive Optimizer for Practical Distributed DNN Training

DropCompute: simple and more robust distributed synchronous training via compute variance reduction

Byzantine-Tolerant Methods for Distributed Variational Inequalities

One Less Reason for Filter Pruning: Gaining Free Adversarial Robustness with Structured Grouped Kernel Pruning

TaskMet: Task-driven Metric Learning for Model Learning

Neural Multi-Objective Combinatorial Optimization with Diversity Enhancement

Ensemble-based Deep Reinforcement Learning for Vehicle Routing Problems under Distribution Shift

Federated Multi-Objective Learning

Geometric Analysis of Matrix Sensing over Graphs

On Single-Index Models beyond Gaussian Data

Imbalanced Mixed Linear Regression

Advice Querying under Budget Constraint for Online Algorithms

Provably Fast Finite Particle Variants of SVGD via Virtual Particle Stochastic Approximation

Quantum speedups for stochastic optimization

Stochastic Approximation Approaches to Group Distributionally Robust Optimization

“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization

Utilitarian Algorithm Configuration

An Optimal Structured Zeroth-order Algorithm for Non-smooth Optimization

Calibration by Distribution Matching: Trainable Kernel Calibration Metrics

Flow Matching for Scalable Simulation-Based Inference

Squared Neural Families: A New Class of Tractable Density Models

Bayes beats Cross Validation: Efficient and Accurate Ridge Regression via Expectation Maximization

Streaming Factor Trajectory Learning for Temporal Tensor Decomposition

Pseudo-Likelihood Inference

Tanimoto Random Features for Scalable Molecular Machine Learning

Variational Gaussian processes for linear inverse problems

Conditional Matrix Flows for Gaussian Graphical Models

Faster Relative Entropy Coding with Greedy Rejection Coding

On the Statistical Consistency of Risk-Sensitive Bayesian Decision-Making

Goal-Conditioned Predictive Coding for Offline Reinforcement Learning

Residual Q-Learning: Offline and Online Policy Customization without Value

Fractal Landscapes in Policy Optimization

Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach

Sequential Preference Ranking for Efficient Reinforcement Learning from Human Feedback

Model-free Posterior Sampling via Learning Rate Randomization

f-Policy Gradients: A General Framework for Goal-Conditioned RL using f-Divergences

RoboCLIP: One Demonstration is Enough to Learn Robot Policies

Task-aware world model learning with meta weighting via bi-level optimization

Constraint-Conditioned Policy Optimization for Versatile Safe Reinforcement Learning

Prediction and Control in Continual Reinforcement Learning

Hybrid Policy Optimization from Imperfect Demonstrations

Reduced Policy Optimization for Continuous Control with Hard Constraints

Future-Dependent Value-Based Off-Policy Evaluation in POMDPs

Direct Preference-based Policy Optimization without Reward Modeling

Sample Efficient Reinforcement Learning in Mixed Systems through Augmented Samples and Its Applications to Queueing Networks

Cal-QL: Calibrated Offline RL Pre-Training for Efficient Online Fine-Tuning

Optimal Treatment Allocation for Efficient Policy Evaluation in Sequential Decision Making

Off-Policy Evaluation for Human Feedback

CORL: Research-oriented Deep Offline Reinforcement Learning Library

Latent exploration for Reinforcement Learning

Generative Modelling of Stochastic Actions with Arbitrary Constraints in Reinforcement Learning

Goal-conditioned Offline Planning from Curious Exploration

Conditional Mutual Information for Disentangled Representations in Reinforcement Learning

State Regularized Policy Optimization on Data with Dynamics Shift

Domain Adaptive Imitation Learning with Visual Observation

RePo: Resilient Model-Based Reinforcement Learning by Regularizing Posterior Predictability

Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks via Subtask Decomposition

A Long $N$-step Surrogate Stage Reward for Deep Reinforcement Learning

State Sequences Prediction via Fourier Transform for Representation Learning

Video Prediction Models as Rewards for Reinforcement Learning

$\texttt{TACO}$: Temporal Latent Action-Driven Contrastive Loss for Visual Reinforcement Learning

For SALE: State-Action Representation Learning for Deep Reinforcement Learning

Provably Robust Temporal Difference Learning for Heavy-Tailed Rewards

Large Language Models can Implement Policy Iteration

Sample Complexity of Goal-Conditioned Hierarchical Reinforcement Learning

Efficient Model-Free Exploration in Low-Rank MDPs

Convergence of Actor-Critic with Multi-Layer Neural Networks

Learning Multi-agent Behaviors from Distributed and Streaming Demonstrations

Zero-sum Polymatrix Markov Games: Equilibrium Collapse and Efficient Computation of Nash Equilibria

RiskQ: Risk-sensitive Multi-Agent Reinforcement Learning Value Factorization

Robust Multi-Agent Reinforcement Learning via Adversarial Regularization: Theoretical Foundation and Stable Algorithms

AlberDICE: Addressing Out-Of-Distribution Joint Actions in Offline Multi-Agent RL via Alternating Stationary Distribution Correction Estimation

Blocked Collaborative Bandits: Online Collaborative Filtering with Per-Item Budget Constraints

Mutual-Information Regularized Multi-Agent Policy Iteration

Selectively Sharing Experiences Improves Multi-Agent Reinforcement Learning

Multi-Step Generalized Policy Improvement by Leveraging Approximate Models

Information-guided Planning: An Online Approach for Partially Observable Problems

Optimize Planning Heuristics to Rank, not to Estimate Cost-to-Goal

Describe, Explain, Plan and Select: Interactive Planning with LLMs Enables Open-World Multi-Task Agents

PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change

On Dynamic Programming Decompositions of Static Risk Measures in Markov Decision Processes

Trade-off Between Efficiency and Consistency for Removal-based Explanations

A Privacy-Friendly Approach to Data Valuation

Statistically Valid Variable Importance Assessment through Conditional Permutations

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

Feature Learning for Interpretable, Performant Decision Trees

Learning Transformer Programs

Visual Explanations of Image-Text Representations via Multi-Modal Information Bottleneck Attribution

VeriX: Towards Verified Explainability of Deep Neural Networks

GRAND-SLAMIN’ Interpretable Additive Modeling with Structural Constraints

Emergent and Predictable Memorization in Large Language Models

ATMAN: Understanding Transformer Predictions Through Memory Efficient Attention Manipulation

Interpretable Graph Networks Formulate Universal Algebra Conjectures

Fairly Recommending with Social Attributes: A Flexible and Controllable Optimization Approach

Label-Only Model Inversion Attacks via Knowledge Transfer

Perturbation Towards Easy Samples Improves Targeted Adversarial Transferability

Chasing Fairness Under Distribution Shift: A Model Weight Perturbation Approach

Auditing Fairness by Betting

Mitigating Test-Time Bias for Fair Image Retrieval

Counterfactually Fair Representation

Evaluating the Moral Beliefs Encoded in LLMs

Label Robust and Differentially Private Linear Regression: Computational and Statistical Efficiency

Training Private Models That Know What They Don’t Know

An Optimal and Scalable Matrix Mechanism for Noisy Marginals under Convex Loss Functions

Practical Differentially Private Hyperparameter Tuning with Subsampling

A Smooth Binary Mechanism for Efficient Private Continual Observation

Mobilizing Personalized Federated Learning in Infrastructure-Less and Heterogeneous Environments via Random Walk Stochastic ADMM

Decision Tree for Locally Private Estimation with Public Data

On the Complexity of Differentially Private Best-Arm Identification with Fixed Confidence

Adaptive Data Analysis in a Balanced Adversarial Model

Handling Data Heterogeneity via Architectural Design for Federated Visual Recognition

Joint Attribute and Model Generalization Learning for Privacy-Preserving Action Recognition

Improving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners

Initialization Matters: Privacy-Utility Analysis of Overparameterized Neural Networks

Smooth Flipping Probability for Differential Private Sign Random Projection Methods

Faster approximate subgraph counts with privacy

Unbounded Differentially Private Quantile and Maximum Estimation

DiffAttack: Evasion Attacks Against Diffusion-Based Adversarial Purification

RADAR: Robust AI-Text Detection via Adversarial Learning

Learning to Augment Distributions for Out-of-distribution Detection

Rethinking the Backward Propagation for Adversarial Transferability

Bucks for Buckets (B4B): Active Defenses Against Stealing Encoders

Honesty Is the Best Policy: Defining and Mitigating AI Deception

CBD: A Certified Backdoor Detector Based on Local Dominant Probability

Domain Watermark: Effective and Harmless Dataset Copyright Protection is Closed at Hand

CS-Isolate: Extracting Hard Confident Examples by Content and Style Isolation

Human-Aligned Calibration for AI-Assisted Decision Making

Improvements on Uncertainty Quantification for Node Classification via Distance Based Regularization

Temporal Robustness against Data poisoning

D4Explainer: In-distribution Explanations of Graph Neural Network via Discrete Denoising Diffusion

Private estimation algorithms for stochastic block models and mixture models

Active Learning-Based Species Range Estimation

On the Stability-Plasticity Dilemma in Continual Meta-Learning: Theory and Algorithm

Online Label Shift: Optimal Dynamic Regret meets Practical Algorithms

Adversarial Self-Training Improves Robustness and Generalization for Gradual Domain Adaptation

On Transfer of Adversarial Robustness from Pretraining to Downstream Tasks

Multiply Robust Federated Estimation of Targeted Average Treatment Effects

Faster Query Times for Fully Dynamic $k$-Center Clustering with Outliers

Strategic Distribution Shift of Interacting Agents via Coupled Gradient Flows

Towards Characterizing the First-order Query Complexity of Learning (Approximate) Nash Equilibria in Zero-sum Matrix Games

SHAP-IQ: Unified Approximation of any-order Shapley Interactions

A One-Size-Fits-All Approach to Improving Randomness in Paper Assignment

Payoff-based Learning with Matrix Multiplicative Weights in Quantum Games

Explainable and Efficient Randomized Voting Rules

$\varepsilon$-fractional core stability in Hedonic Games.

Improved Bayes Risk Can Yield Reduced Social Welfare Under Competition

Neural Oscillators are Universal

Contrastive Moments: Unsupervised Halfspace Learning in Polynomial Time

Toward Better PAC-Bayes Bounds for Uniformly Stable Algorithms

Universality laws for Gaussian mixtures in generalized linear models

Adaptive Principal Component Regression with Applications to Panel Data

Learning Exponential Families from Truncated Samples

A Spectral Algorithm for List-Decodable Covariance Estimation in Relative Frobenius Norm

Two-Stage Learning to Defer with Multiple Experts

$L_2$-Uniform Stability of Randomized Learning Algorithms: Sharper Generalization Bounds and Confidence Boosting

Minimax-Optimal Location Estimation

Approximation-Generalization Trade-offs under (Approximate) Group Equivariance

Distribution Learnability and Robustness

Robust covariance estimation with missing values and cell-wise contamination

Demographic Parity Constrained Minimax Optimal Regression under Linear Model

Time-Independent Information-Theoretic Generalization Bounds for SGLD

On quantum backpropagation, information reuse, and cheating measurement collapse

The Gain from Ordering in Online Learning

Perceptual adjustment queries and an inverted measurement paradigm for low-rank metric learning

First- and Second-Order Bounds for Adversarial Linear Contextual Bandits

Finite-Time Logarithmic Bayes Regret Upper Bounds

Bandit Task Assignment with Unknown Processing Time

Online Learning under Adversarial Nonlinear Constraints

Decentralized Randomly Distributed Multi-agent Multi-armed Bandit with Heterogeneous Rewards

On Robust Streaming for Learning with Experts: Algorithms and Lower Bounds

Cascading Bandits: Optimizing Recommendation Frequency in Delayed Feedback Environments

Nash Regret Guarantees for Linear Bandits

Efficient Batched Algorithm for Contextual Linear Bandits with Large Action Space via Soft Elimination

Trading-off price for data quality to achieve fair online allocation

Context-lumpable stochastic bandits

When Can We Track Significant Preference Shifts in Dueling Bandits?

Asymptotically Optimal Quantile Pure Exploration for Infinite-Armed Bandits

Faster Margin Maximization Rates for Generic Optimization Methods

Zero-Regret Performative Prediction Under Inequality Constraints

Towards Optimal Effective Resistance Estimation

On the Implicit Bias of Linear Equivariant Steerable Networks

Streaming PCA for Markovian Data

Near-Linear Time Algorithm for the Chamfer Distance

First Order Stochastic Optimization with Oblivious Noise

On Slicing Optimality for Mutual Information

Policy Gradient for Rectangular Robust Markov Decision Processes

Performance Bounds for Policy-Based Average Reward Reinforcement Learning Algorithms

Restless Bandits with Average Reward: Breaking the Uniform Global Attractor Assumption

Scalable Primal-Dual Actor-Critic Method for Safe Multi-Agent RL with General Utilities

Reward-agnostic Fine-tuning: Provable Statistical Benefits of Hybrid Reinforcement Learning

Bi-Level Offline Policy Optimization with Limited Exploration

Multi-Player Zero-Sum Markov Games with Networked Separable Interactions

Responsible AI (RAI) Games and Ensembles

Fast Optimal Locally Private Mean Estimation via Random Projections

Unlocking Feature Visualization for Deep Network with MAgnitude Constrained Optimization

Deep Stochastic Processes via Functional Markov Transition Operators

Optimal Rates for Bandit Nonstochastic Control

An Information Theory Perspective on Variance-Invariance-Covariance Regularization

Architecture Matters: Uncovering Implicit Mechanisms in Graph Contrastive Learning

Combining Behaviors with the Successor Features Keyboard

Proportional Response: Contextual Bandits for Simple and Cumulative Regret Minimization

Geometric Neural Diffusion Processes

VanillaNet: the Power of Minimalism in Deep Learning

Neural Processes with Stability

Does Visual Pretraining Help End-to-End Reasoning?

Episodic Multi-Task Learning with Heterogeneous Neural Processes

Ecosystem-level Analysis of Deployed Machine Learning Reveals Homogeneous Outcomes

Networks are Slacking Off: Understanding Generalization Problem in Image Deraining

Reward Imputation with Sketching for Contextual Batched Bandits

Optimal Transport for Treatment Effect Estimation

Crystal Structure Prediction by Joint Equivariant Diffusion

DesCo: Learning Object Recognition with Rich Language Descriptions

MGDD: A Meta Generator for Fast Dataset Distillation

LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation

Consistent Diffusion Models: Mitigating Sampling Drift by Learning to be Consistent

Recaptured Raw Screen Image and Video Demoiréing via Channel and Spatial Modulations

Adaptive Privacy Composition for Accuracy-first Mechanisms

Fast Attention Requires Bounded Entries

Understanding the Limitations of Deep Models for Molecular property prediction: Insights and Solutions

Alignment with human representations supports robust few-shot learning

Optimal Preconditioning and Fisher Adaptive Langevin Sampling

A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation

C-Disentanglement: Discovering Causally-Independent Generative Factors under an Inductive Bias of Confounder

Controlling Text-to-Image Diffusion by Orthogonal Finetuning

Reward Scale Robustness for Proximal Policy Optimization via DreamerV3 Tricks

Non-stationary Experimental Design under Linear Trends

Anytime-Competitive Reinforcement Learning with Policy Prior

Corruption-Robust Offline Reinforcement Learning with General Function Approximation

Human-like Few-Shot Learning via Bayesian Reasoning over Natural Language

Graph Mixture of Experts: Learning on Large-Scale Graphs with Explicit Diversity Modeling

Goal Driven Discovery of Distributional Differences via Language Descriptions

Compositional Generalization from First Principles

Randomized and Deterministic Maximin-share Approximations for Fractionally Subadditive Valuations

Protein Design with Guided Discrete Diffusion

SegRefiner: Towards Model-Agnostic Segmentation Refinement with Discrete Diffusion Process

Sub-optimality of the Naive Mean Field approximation for proportional high-dimensional Linear Regression

Fairness-guided Few-shot Prompting for Large Language Models

(ends 10:45 AM)

Creative AI Session 2 [8:45-12:15]

Chairs: Jean Oh · Isabelle Guyon

s 8:45-12:15

[8:45] Kiss/Crash

[8:45] Blabrecs: An AI-Based Game of Nonsense Word Creation

[8:45] Androgynous and Mixed Race Human Face

[8:45] Voice Scroll

[8:45] The WHOOPS! Gallery: An Intersection of AI, Creativity, and the Unusual

[8:45] Visions of Resilience: Augmented Diversity

[8:45] salad bowl

[8:45] Creating playful comics together with AI

[8:45] AI Applications to Illustrate Native American Arts: Birdsongs: Using Transfer Learning to Augment Image Generation Models

[8:45] Visualising AI

(ends 12:15 PM)

10:45 a.m.

Lunch (On Your Own)

12:15 p.m.

Invited Talk:

Beyond Scaling Panel

Alexander Rush · Aakanksha Chowdhery · Angela Fan · Percy Liang · Jie Tang

(ends 1:15 PM)

1:15 p.m.

Coffee Only

1:30 p.m.

Oral 4A Optimization [1:30-2:30]

Orals 1:30-2:30

[1:30] A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization

[1:45] Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models

[2:00] Generalizing Nonlinear ICA Beyond Structural Sparsity

[2:15] Fine-Tuning Language Models with Just Forward Passes

(ends 2:30 PM)

Oral 4B Datasets & Benchmarks [1:30-2:30]

Orals 1:30-2:30

[1:30] Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean

[1:45] ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation

[2:00] Quilt-1M: One Million Image-Text Pairs for Histopathology

[2:15] BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks

(ends 2:30 PM)

Oral 4C COT/reasoning [1:30-2:30]

Orals 1:30-2:30

[1:30] Why think step by step? Reasoning emerges from the locality of experience

[1:45] Tree of Thoughts: Deliberate Problem Solving with Large Language Models

[2:00] Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

[2:15] Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective

(ends 2:30 PM)

2:15 p.m.

Break

3 p.m.

Poster Session 4 [3:00-5:00]

Posters 3:00-5:00

Predicting a Protein's Stability under a Million Mutations

Full-Atom Protein Pocket Design via Iterative Refinement

3D molecule generation by denoising voxel grids

Injecting Multimodal Information into Rigid Protein Docking via Bi-level Optimization

AVIDa-hIL6: A Large-Scale VHH Dataset Produced from an Immunized Alpaca for Predicting Antigen-Antibody Interactions

Mesogeos: A multi-purpose dataset for data-driven wildfire modeling in the Mediterranean

ClimSim: A large multi-scale dataset for hybrid physics-ML climate emulation

A Hierarchical Spatial Transformer for Massive Point Samples in Continuous Space

Differentiable Registration of Images and LiDAR Point Clouds with VoxelPoint-to-Pixel Matching

PanoGen: Text-Conditioned Panoramic Environment Generation for Vision-and-Language Navigation

3D-LLM: Injecting the 3D World into Large Language Models

PolyDiffuse: Polygonal Shape Reconstruction via Guided Set Diffusion Models

Context-PIPs: Persistent Independent Particles Demands Spatial Context Features

Hierarchical Integration Diffusion Model for Realistic Image Deblurring

Unsupervised Image Denoising with Score Function

SmooSeg: Smoothness Prior for Unsupervised Semantic Segmentation

Decompose Novel into Known: Part Concept Learning For 3D Novel Class Discovery

LMC: Large Model Collaboration with Cross-assessment for Training-Free Open-Set Object Recognition

Equivariant Single View Pose Prediction Via Induced and Restriction Representations

Towards Efficient and Accurate Winograd Convolution via Full Quantization

GMSF: Global Matching Scene Flow

Text Promptable Surgical Instrument Segmentation with Vision-Language Models

Non-Rigid Shape Registration via Deep Functional Maps Prior

Understanding the Latent Space of Diffusion Models through the Lens of Riemannian Geometry

A Partially-Supervised Reinforcement Learning Framework for Visual Active Search

Rank-DETR for High Quality Object Detection

VisionLLM: Large Language Model is also an Open-Ended Decoder for Vision-Centric Tasks

DiViNeT: 3D Reconstruction from Disparate Views using Neural Template Regularization

PanoGRF: Generalizable Spherical Radiance Fields for Wide-baseline Panoramas

Chatting Makes Perfect: Chat-based Image Retrieval

PyNeRF: Pyramidal Neural Radiance Fields

Depth-discriminative Metric Learning for Monocular 3D Object Detection

Inner-Outer Aware Reconstruction Model for Monocular 3D Scene Reconstruction

Diversifying Spatial-Temporal Perception for Video Domain Generalization

Segment Everything Everywhere All at Once

Hierarchical Vector Quantized Transformer for Multi-class Unsupervised Anomaly Detection

UP-NeRF: Unconstrained Pose Prior-Free Neural Radiance Field

Detection Based Part-level Articulated Object Reconstruction from Single RGBD Image

Towards Robust and Expressive Whole-body Human Pose and Shape Estimation

PUCA: Patch-Unshuffle and Channel Attention for Enhanced Self-Supervised Image Denoising

ReMaX: Relaxing for Better Training on Efficient Panoptic Segmentation

Improving CLIP Training with Language Rewrites

MomentDiff: Generative Video Moment Retrieval from Random to Real

$p$-Poisson surface reconstruction in curl-free flow from point clouds

ClusterFomer: Clustering As A Universal Visual Learner

Symbol-LLM: Leverage Language Models for Symbolic System in Visual Human Activity Reasoning

Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes

BiMatting: Efficient Video Matting via Binarization

Dataset Diffusion: Diffusion-based Synthetic Data Generation for Pixel-Level Semantic Segmentation

RayDF: Neural Ray-surface Distance Fields with Multi-view Consistency

Self-Supervised Visual Acoustic Matching

CoDet: Co-occurrence Guided Region-Word Alignment for Open-Vocabulary Object Detection

Structural Pruning for Diffusion Models

Enhancing Motion Deblurring in High-Speed Scenes with Spike Streams

FlowCam: Training Generalizable 3D Radiance Fields without Camera Poses via Pixel-Aligned Scene Flow

LayoutGPT: Compositional Visual Planning and Generation with Large Language Models

Towards Distribution-Agnostic Generalized Category Discovery

Look Ma, No Hands! Agent-Environment Factorization of Egocentric Videos

Active Reasoning in an Open-World Environment

Quilt-1M: One Million Image-Text Pairs for Histopathology

L-CAD: Language-based Colorization with Any-level Descriptions using Diffusion Priors

A case for reframing automated medical image classification as segmentation

A Unified Conditional Framework for Diffusion-based Image Restoration

3D Copy-Paste: Physically Plausible Object Insertion for Monocular 3D Detection

Binary Radiance Fields

Continuous Parametric Optical Flow

Puzzlefusion: Unleashing the Power of Diffusion Models for Spatial Puzzle Solving

Towards Higher Ranks via Adversarial Weight Pruning

Hyperbolic Space with Hierarchical Margin Boosts Fine-Grained Learning from Coarse Labels

FourierHandFlow: Neural 4D Hand Representation Using Fourier Query Flow

DiffUTE: Universal Text Editing Diffusion Model

SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation

LightSpeed: Light and Fast Neural Light Fields on Mobile Devices

Deep Patch Visual Odometry

Self-Chained Image-Language Model for Video Localization and Question Answering

Scale-Space Hypernetworks for Efficient Biomedical Image Analysis

DropPos: Pre-Training Vision Transformers by Reconstructing Dropped Positions

Segment Anything in High Quality

Chanakya: Learning Runtime Decisions for Adaptive Real-Time Perception

ATTA: Anomaly-aware Test-Time Adaptation for Out-of-Distribution Detection in Segmentation

Contrastive Lift: 3D Object Instance Segmentation by Slow-Fast Contrastive Fusion

DiffKendall: A Novel Approach for Few-Shot Learning with Differentiable Kendall's Rank Correlation

What You See is What You Read? Improving Text-Image Alignment Evaluation

MarioGPT: Open-Ended Text2Level Generation through Large Language Models

Boosting Learning for LDPC Codes to Improve the Error-Floor Performance

ANPL: Towards Natural Programming with Interactive Decomposition

CELLE-2: Translating Proteins to Pictures and Back with a Bidirectional Text-to-Image Transformer

DynGFN: Towards Bayesian Inference of Gene Regulatory Networks with GFlowNets

ARTree: A Deep Autoregressive Model for Phylogenetic Inference

BIOT: Biosignal Transformer for Cross-data Learning in the Wild

Towards Semi-Structured Automatic ICD Coding via Tree-based Contrastive Learning

Risk-Averse Active Sensing for Timely Outcome Prediction under Cost Pressure

Spatio-Angular Convolutions for Super-resolution in Diffusion MRI

SpecTr: Fast Speculative Decoding via Optimal Transport

SatLM: Satisfiability-Aided Language Models Using Declarative Prompting

Can Language Models Solve Graph Problems in Natural Language?

Localized Symbolic Knowledge Distillation for Visual Commonsense Models

SwiftSage: A Generative Agent with Fast and Slow Thinking for Complex Interactive Tasks

Guiding Large Language Models via Directional Stimulus Prompting

Language Models Can Improve Event Prediction by Few-Shot Abductive Reasoning

UNSSOR: Unsupervised Neural Speech Separation by Leveraging Over-determined Training Mixtures

Tree of Thoughts: Deliberate Problem Solving with Large Language Models

EMMA-X: An EM-like Multilingual Pre-training Algorithm for Cross-lingual Representation Learning

Language Models Meet World Models: Embodied Experiences Enhance Language Models

RECKONING: Reasoning through Dynamic Knowledge Encoding

Paxion: Patching Action Knowledge in Video-Language Foundation Models

Paraphrasing evades detectors of AI-generated text, but retrieval is an effective defense

MotionGPT: Human Motion as a Foreign Language

Learning to Tokenize for Generative Retrieval

Inference-Time Intervention: Eliciting Truthful Answers from a Language Model

On-the-Fly Adapting Code Summarization on Trainable Cost-Effective Language Models

Repetition In Repetition Out: Towards Understanding Neural Text Degeneration from the Data Perspective

Interactive Multi-fidelity Learning for Cost-effective Adaptation of Language Model with Sparse Human Supervision

Correlative Information Maximization: A Biologically Plausible Approach to Supervised Deep Neural Networks without Weight Symmetry

Low Tensor Rank Learning of Neural Dynamics

Enhancing Adaptive History Reserving by Spiking Convolutional Block Attention Module in Recurrent Neural Networks

Cognitive Model Discovery via Disentangled RNNs

Explainable Brain Age Prediction using coVariance Neural Networks

Temporal Conditioning Spiking Latent Variable Models of the Neural Response to Natural Visual Scenes

Performance-optimized deep neural networks are evolving into worse models of inferotemporal visual cortex

Contrast, Attend and Diffuse to Decode High-Resolution Images from Brain Activities

Expressive probabilistic sampling in recurrent neural networks

Brain encoding models based on multimodal transformers can transfer across language and vision

Separable Physics-Informed Neural Networks

SyncTREE: Fast Timing Analysis for Integrated Circuit Design through a Physics-informed Tree-based Graph Neural Network

Hypernetwork-based Meta-Learning for Low-Rank Physics-Informed Neural Networks

Conformal Prediction for Uncertainty-Aware Planning with Diffusion Dynamics Model

Real-Time Motion Prediction via Heterogeneous Polyline Transformer with Relative Pose Encoding

Asynchrony-Robust Collaborative Perception via Bird's Eye View Flow

Learning Environment-Aware Affordance for 3D Articulated Object Manipulation under Occlusions

Time Series as Images: Vision Transformer for Irregularly Sampled Time Series

Drift doesn't Matter: Dynamic Decomposition with Diffusion Reconstruction for Unstable Multivariate Time Series Anomaly Detection

Back-Modality: Leveraging Modal Transformation for Data Augmentation

Sparse Parameterization for Epitomic Dataset Distillation

Collaborative Learning via Prediction Consensus

Train Faster, Perform Better: Modular Adaptive Training in Over-Parameterized Models

NeuroGF: A Neural Representation for Fast Geodesic Distance and Path Queries

The geometry of hidden representations of large transformer models

VCC: Scaling Transformers to 128K Tokens or More by Prioritizing Important Tokens

TART: A plug-and-play Transformer module for task-agnostic reasoning

Sparse Modular Activation for Efficient Sequence Modeling

Distributed Inference and Fine-tuning of Large Language Models Over The Internet

An Inductive Bias for Tabular Deep Learning

Understanding Neural Network Binarization with Forward and Backward Proximal Quantizers

MathNAS: If Blocks Have a Role in Mathematical Architecture Design

ZipLM: Inference-Aware Structured Pruning of Language Models

Fine-Tuning Language Models with Just Forward Passes

Learning Layer-wise Equivariances Automatically using Gradients

Reusing Pretrained Models by Multi-linear Operators for Efficient Training

Enhancing Sharpness-Aware Optimization Through Variance Suppression

BayesTune: Bayesian Sparse Deep Model Fine-tuning

NCDL: A Framework for Deep Learning on non-Cartesian Lattices

CoLA: Exploiting Compositional Structure for Automatic and Efficient Numerical Linear Algebra

Bypass Exponential Time Preprocessing: Fast Neural Network Training via Weight-Data Correlation Preprocessing

Model-enhanced Vector Index

Max-Margin Token Selection in Attention Mechanism

The emergence of clusters in self-attention dynamics

On Separate Normalization in Self-supervised Transformers

Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

Fast Attention Over Long Sequences With Dynamic Sparse Flash Attention

Exposing Attention Glitches with Flip-Flop Language Modeling

Encoding Human Behavior in Information Design through Deep Learning

GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction

Lie Point Symmetry and Physics-Informed Networks

Empowering Convolutional Neural Nets with MetaSin Activation

Multiplication-Free Transformer Training via Piecewise Affine Operations

Learning to Reason and Memorize with Self-Notes

REx: Data-Free Residual Quantization Error Expansion

Joint Training of Deep Ensembles Fails Due to Learner Collusion

A-NeSI: A Scalable Approximate Method for Probabilistic Neurosymbolic Inference

Diff-Instruct: A Universal Approach for Transferring Knowledge From Pre-trained Diffusion Models

Large Language Models of Code Fail at Completing Code with Potential Bugs

On Calibrating Diffusion Probabilistic Models

Is This Loss Informative? Faster Text-to-Image Customization by Tracking Objective Dynamics

Why think step by step? Reasoning emerges from the locality of experience

Textually Pretrained Speech Language Models

Tree Variational Autoencoders

Towards Test-Time Refusals via Concept Negation

Counterfactual Generation with Identifiability Guarantees

Contrastive Sampling Chains in Diffusion Models

GLOBER: Coherent Non-autoregressive Video Generation via GLOBal Guided Video DecodER

Likelihood-Based Diffusion Language Models

From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion

SEEDS: Exponential SDE Solvers for Fast High-Quality Sampling from Diffusion Models

Hard Prompts Made Easy: Gradient-Based Discrete Optimization for Prompt Tuning and Discovery

Diffusion Hyperfeatures: Searching Through Time and Space for Semantic Correspondence

Conditional Score Guidance for Text-Driven Image-to-Image Translation

Regularizing Neural Networks with Meta-Learning Generative Models

Structured Neural Networks for Density Estimation and Causal Inference

Parallel Sampling of Diffusion Models

DYffusion: A Dynamics-informed Diffusion Model for Spatiotemporal Forecasting

Normalizing flow neural networks by JKO scheme

NICE: NoIse-modulated Consistency rEgularization for Data-Efficient GANs

Mirror Diffusion Models for Constrained and Watermarked Generation

Context-guided Embedding Adaptation for Effective Topic Modeling in Low-Resource Regimes

Autodecoding Latent 3D Diffusion Models

Towards Consistent Video Editing with Text-to-Image Diffusion Models

Exploring Diverse In-Context Configurations for Image Captioning

Distance-Restricted Folklore Weisfeiler-Leman GNNs with Provable Cycle Counting Power

Joint Learning of Label and Environment Causal Independence for Graph Out-of-Distribution Generalization

Structure-free Graph Condensation: From Large-scale Graphs to Condensed Graph-free Data

Spectral Invariant Learning for Dynamic Graphs under Distribution Shifts

Simple and Asymmetric Graph Contrastive Learning without Augmentations

Graph of Circuits with GNN for Exploring the Optimal Design Space

Self-supervised Graph Neural Networks via Low-Rank Decomposition

Unsupervised Graph Neural Architecture Search with Disentangled Self-Supervision

Efficiently incorporating quintuple interactions into geometric deep learning force fields

Towards Self-Interpretable Graph-Level Anomaly Detection

SGFormer: Simplifying and Empowering Transformers for Large-Graph Representations

Public Opinion Field Effect Fusion in Representation Learning for Trending Topics Diffusion

Learning Rule-Induced Subgraph Representations for Inductive Relation Prediction

Extending the Design Space of Graph Neural Networks by Rethinking Folklore Weisfeiler-Lehman

A*Net: A Scalable Path-based Reasoning Approach for Knowledge Graphs

Does Graph Distillation See Like Vision Dataset Counterpart?

Provable Training for Graph Contrastive Learning

Graph Convolutional Kernel Machine versus Graph Convolutional Networks

Probabilistic Invariant Learning with Randomized Linear Classifiers

An Empirical Study Towards Prompt-Tuning for Graph Contrastive Pre-Training in Recommendations

Multi-task Graph Neural Architecture Search with Task-aware Collaboration and Curriculum

Expressive Sign Equivariant Networks for Spectral Geometric Learning

Category-Extensible Out-of-Distribution Detection via Hierarchical Context Descriptions

Accessing Higher Dimensions for Unsupervised Word Translation

Test-Time Distribution Normalization for Contrastively Learned Visual-language Models

Feature Selection in the Contrastive Analysis Setting

Learning-to-Rank Meets Language: Boosting Language-Driven Ordering Alignment for Ordinal Classification

LICO: Explainable Models with Language-Image COnsistency

Efficient Equivariant Transfer Learning from Pretrained Models

Evaluating Neuron Interpretation Methods of NLP Models

Riemannian Residual Neural Networks

Deep Recurrent Optimal Stopping

Distributionally Robust Ensemble of Lottery Tickets Towards Calibrated Sparse Network Training

Adversarial Robustness through Random Weight Sampling

Improving Adversarial Transferability via Intermediate-level Perturbation Decay

Topological Parallax: A Geometric Specification for Deep Perception Models

Improving Robustness with Adaptive Weight Decay

Which Models have Perceptually-Aligned Gradients? An Explanation via Off-Manifold Robustness

RDumb: A simple approach that questions our progress in continual test-time adaptation

Characterizing Out-of-Distribution Error via Optimal Transport

Fast Trainable Projection for Robust Fine-tuning

Optimal Parameter and Neuron Pruning for Out-of-Distribution Detection

NEO-KD: Knowledge-Distillation-Based Adversarial Training for Robust Multi-Exit Neural Networks

Unlocking Deterministic Robustness Certification on ImageNet

Towards Evaluating Transfer-based Attacks Systematically, Practically, and Fairly

Batchnorm Allows Unsupervised Radial Attacks

TrojLLM: A Black-box Trojan Prompt Attack on Large Language Models

On the Role of Randomization in Adversarially Robust Classification

Enhancing Adversarial Robustness via Score-Based Optimization

RevColV2: Exploring Disentangled Representations in Masked Image Modeling

Uncovering the Hidden Dynamics of Video Self-supervised Learning under Distribution Shifts

Relax, it doesn’t matter how you get there: A new self-supervised approach for multi-timescale behavior analysis

Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder

Keypoint-Augmented Self-Supervised Learning for Medical Image Segmentation with Limited Annotation

Deep Insights into Noisy Pseudo Labeling on Graph Data

UP-DP: Unsupervised Prompt Learning for Data Pre-Selection with Vision-Language Models

Factorized Contrastive Learning: Going Beyond Multi-view Redundancy

Finding Order in Chaos: A Novel Data Augmentation Method for Time Series in Contrastive Learning

Block-State Transformers

Perceptual Kalman Filters: Online State Estimation under a Perfect Perceptual-Quality Constraint

FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective

Smoothing the Landscape Boosts the Signal for SGD: Optimal Sample Complexity for Learning Single Index Models

Neural Injective Functions for Multisets, Measures and Graphs via a Finite Witness Theorem

Functional Equivalence and Path Connectivity of Reducible Hyperbolic Tangent Networks

Connecting Pre-trained Language Model and Downstream Task via Properties of Representation

Does a sparse ReLU network training problem always admit an optimum ?

Training Neural Networks is NP-Hard in Fixed Dimension

Pareto Frontiers in Deep Feature Learning: Data, Compute, Width, and Luck

Path Regularization: A Convexity and Sparsity Inducing Regularization for Parallel ReLU Networks

Beyond NTK with Vanilla Gradient Descent: A Mean-Field Analysis of Neural Networks with Polynomial Width, Samples, and Time

Nearly Optimal VC-Dimension and Pseudo-Dimension Bounds for Deep Neural Network Derivatives

Fixing the NTK: From Neural Network Linearizations to Exact Convex Programs

Trust Your $\nabla$: Gradient-based Intervention Targeting for Causal Discovery

Causal Imitability Under Context-Specific Independence Relations

Nonparametric Identifiability of Causal Representations from Unknown Interventions

Learning Nonparametric Latent Causal Graphs with Unknown Interventions

Identification of Nonlinear Latent Hierarchical Models

Finding Counterfactually Optimal Action Sequences in Continuous State Spaces

Double and Single Descent in Causal Inference with an Application to High-Dimensional Synthetic Control

Causal Discovery in Semi-Stationary Time Series

Data Augmentations for Improved (Large) Language Model Generalization

Generalizing Nonlinear ICA Beyond Structural Sparsity

Rehearsal Learning for Avoiding Undesired Future

Solving Linear Inverse Problems Provably via Posterior Sampling with Latent Diffusion Models

AdANNS: A Framework for Adaptive Semantic Search

Horospherical Decision Boundaries for Large Margin Classification in Hyperbolic Space

Sequential Predictive Two-Sample and Independence Testing

Gacs-Korner Common Information Variational Autoencoder

BanditPAM++: Faster $k$-medoids Clustering

Multinomial Logistic Regression: Asymptotic Normality on Null Covariates in High-Dimensions

CosNet: A Generalized Spectral Kernel Network

On kernel-based statistical learning theory in the mean field limit

An Efficient Doubly-Robust Test for the Kernel Treatment Effect

Maximum Average Randomly Sampled: A Scale Free and Non-parametric Algorithm for Stochastic Bandits

No-regret Algorithms for Fair Resource Allocation

Smoothed Online Learning for Prediction in Piecewise Affine Systems

Online Inventory Problems: Beyond the i.i.d. Setting with Online Convex Optimization

Anytime Model Selection in Linear Bandits

Transportability for Bandits with Data from Different Environments

CS4ML: A general framework for active learning with arbitrary data based on Christoffel functions

Adapting to Continuous Covariate Shift via Online Density Ratio Estimation

Exact Representation of Sparse Networks with Symmetric Nonnegative Embeddings

DAMEX: Dataset-aware Mixture-of-Experts for visual understanding of mixture-of-datasets

Rank-N-Contrast: Learning Continuous Representations for Regression

A Graph-Theoretic Framework for Understanding Open-World Semi-Supervised Learning

Temporally Disentangled Representation Learning under Unknown Nonstationarity

Sequential Subset Matching for Dataset Distillation

DeepPCR: Parallelizing Sequential Operations in Neural Networks

Tight Bounds for Volumetric Spanners and Applications

On the Size and Approximation Error of Distilled Datasets

Unbalanced Low-rank Optimal Transport Solvers

Integration-free Training for Spatio-temporal Multimodal Covariate Deep Kernel Point Processes

Time Series Kernels based on Nonlinear Vector AutoRegressive Delay Embeddings

Estimating Riemannian Metric with Noise-Contaminated Intrinsic Distance

Anchor Data Augmentation

A Unified Generalization Analysis of Re-Weighting and Logit-Adjustment for Imbalanced Learning

Meta-AdaM: An Meta-Learned Adaptive Optimizer with Momentum for Few-Shot Learning

Your representations are in the network: composable and parallel adaptation for large scale models

The s-value: evaluating stability with respect to distributional shifts

4M: Massively Multimodal Masked Modeling

Parameter and Computation Efficient Transfer Learning for Vision-Language Pre-trained Models

Revisiting Logistic-softmax Likelihood in Bayesian Meta-Learning for Few-Shot Classification

Efficient Adaptation of Large Vision Transformer via Adapter Re-Composing

Federated Learning via Meta-Variational Dropout

RanPAC: Random Projections and Pre-trained Models for Continual Learning

GraphAdapter: Tuning Vision-Language Models With Dual Knowledge Graph

Meta-Learning with Neural Bandit Scheduler

Fully Dynamic $k$-Clustering in $\tilde O(k)$ Update Time

Promises and Pitfalls of Threshold-based Auto-labeling

Class-Distribution-Aware Pseudo-Labeling for Semi-Supervised Multi-Label Learning

Beyond Myopia: Learning from Positive and Unlabeled Data through Holistic Predictive Trends

Exact recovery and Bregman hard clustering of node-attributed Stochastic Block Model

Federated Spectral Clustering via Secure Similarity Reconstruction

Characterizing the Impacts of Semi-supervised Learning for Weak Supervision

Optimistic Meta-Gradients

Contextual Stochastic Bilevel Optimization

SimFBO: Towards Simple, Flexible and Communication-efficient Federated Bilevel Learning

Making Scalable Meta Learning Practical

Last-Iterate Convergent Policy Gradient Primal-Dual Methods for Constrained MDPs

Convergence analysis of ODE models for accelerated first-order methods via positive semidefinite kernels

A Robust Exact Algorithm for the Euclidean Bipartite Matching Problem

Bayesian Optimisation of Functions on Graphs

Variational Annealing on Graphs for Combinatorial Optimization

Bounce: Reliable High-Dimensional Bayesian Optimization for Combinatorial and Mixed Spaces

Necessary and Sufficient Conditions for Optimal Decision Trees using Dynamic Programming

DeepACO: Neural-enhanced Ant Systems for Combinatorial Optimization

Convergent Bregman Plug-and-Play Image Restoration for Poisson Inverse Problems

Structured Semidefinite Programming for Recovering Structured Preconditioners

Local Convergence of Gradient Methods for Min-Max Games: Partial Curvature Generically Suffices

Bringing regularized optimal transport to lightspeed: a splitting method adapted for GPUs

Adaptive SGD with Polyak stepsize and Line-search: Robust Convergence and Variance Reduction

Revisiting Area Convexity: Faster Box-Simplex Games and Spectrahedral Generalizations

A Variational Perspective on High-Resolution ODEs

Correlation Aware Sparsified Mean Estimation Using Random Projection

Federated Learning with Client Subsampling, Data Heterogeneity, and Unbounded Smoothness: A New Algorithm and Lower Bounds

Large-Scale Distributed Learning via Private On-Device LSH

$\textbf{A}^2\textbf{CiD}^2$: Accelerating Asynchronous Communication in Decentralized Deep Learning

Solving a Class of Non-Convex Minimax Optimization in Federated Learning

Winner-Take-All Column Row Sampling for Memory Efficient Adaptation of Language Model

Efficient Activation Function Optimization through Surrogate Modeling

Neural Combinatorial Optimization with Heavy Decoder: Toward Large Scale Generalization

ReSync: Riemannian Subgradient-based Robust Rotation Synchronization

A Single-Loop Accelerated Extra-Gradient Difference Algorithm with Improved Complexity Bounds for Constrained Minimax Optimization

Convergence of Alternating Gradient Descent for Matrix Factorization

Aiming towards the minimizers: fast convergence of SGD for overparametrized problems

A Unified Framework for Rank-based Loss Minimization

Projection-Free Methods for Solving Nonconvex-Concave Saddle Point Problems

Distributionally Robust Bayesian Optimization with $\varphi$-divergences

Predict-then-Calibrate: A New Perspective of Robust Contextual LP

Efficient Uncertainty Quantification and Reduction for Over-Parameterized Neural Networks

Fast Exact Leverage Score Sampling from Khatri-Rao Products with Applications to Tensor Decomposition

A Dynamical System View of Langevin-Based Non-Convex Sampling

Approximate Heavy Tails in Offline (Multi-Pass) Stochastic Gradient Descent

Batch Bayesian Optimization For Replicable Experimental Design

Variance-Reduced Gradient Estimation via Noise-Reuse in Online Evolution Strategies

Quantum Bayesian Optimization

Riemannian Laplace approximations for Bayesian neural networks

Generalized Bayesian Inference for Scientific Simulators via Amortized Cost Estimation

Neural Sampling in Hierarchical Exponential-family Energy-based Models

Learning Robust Statistics for Simulation-based Inference under Model Misspecification

Effective Bayesian Heteroscedastic Regression with Deep Neural Networks

Posterior Contraction Rates for Matérn Gaussian Processes on Riemannian Manifolds

Leveraging Locality and Robustness to Achieve Massively Scalable Gaussian Process Regression

Implicit Manifold Gaussian Process Regression

The Rank-Reduced Kalman Filter: Approximate Dynamical-Low-Rank Filtering In High Dimensions

Deep Gaussian Markov Random Fields for Graph-Structured Dynamical Systems

Entropy-based Training Methods for Scalable Neural Implicit Samplers

Stochastic Approximation Algorithms for Systems of Interacting Particles

Greedy Poisson Rejection Sampling

A Bayesian Take on Gaussian Process Networks

The Memory-Perturbation Equation: Understanding Model's Sensitivity to Data

On the Convergence of Black-Box Variational Inference

A Heavy-Tailed Algebra for Probabilistic Programming

Implicit Variational Inference for High-Dimensional Posteriors

Latent SDEs on Homogeneous Spaces

Learning non-Markovian Decision-Making from State-only Sequences

Natural Language Instruction-following with Task-related Language Development and Translation

Learning Dynamic Attribute-factored World Models for Efficient Multi-object Reinforcement Learning

Offline Reinforcement Learning for Mixture-of-Expert Dialogue Management

BEDD: The MineRL BASALT Evaluation and Demonstrations Dataset for Training and Benchmarking Agents that Solve Fuzzy Tasks

MoVie: Visual Model-Based Policy Adaptation for View Generalization

Posterior Sampling with Delayed Feedback for Reinforcement Learning with Linear Function Approximation

Learning to Modulate pre-trained Models in RL

Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning

A Definition of Continual Reinforcement Learning

Inverse Reinforcement Learning with the Average Reward Criterion

HIQL: Offline Goal-Conditioned RL with Latent States as Actions

Counterfactual-Augmented Importance Sampling for Semi-Offline Policy Evaluation

Elastic Decision Transformer

Context Shift Reduction for Offline Meta-Reinforcement Learning

STEVE-1: A Generative Model for Text-to-Behavior in Minecraft

Constrained Policy Optimization with Explicit Behavior Density For Offline Reinforcement Learning

Regularized Behavior Cloning for Blocking the Leakage of Past Action Information

Sample-Efficient and Safe Deep Reinforcement Learning via Reset Deep Ensemble Agents

Thought Cloning: Learning to Think while Acting by Imitating Human Thinking

PLASTIC: Improving Input and Label Plasticity for Sample Efficient Reinforcement Learning

A Unified Algorithm Framework for Unsupervised Discovery of Skills based on Determinantal Point Process

Discovering Hierarchical Achievements in Reinforcement Learning via Contrastive Learning

STORM: Efficient Stochastic Transformer based World Models for Reinforcement Learning

Cross-Episodic Curriculum for Transformer Agents

Large Language Models Are Semi-Parametric Reinforcement Learning Agents

Compositional Foundation Models for Hierarchical Planning

Action Inference by Maximising Evidence: Zero-Shot Imitation from Observation with World Models

Double Gumbel Q-Learning

TD Convergence: An Optimization Perspective

Mixed-Initiative Multiagent Apprenticeship Learning for Human Training of Robot Teams

Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning

Multi-Agent First Order Constrained Optimization in Policy Space

On Imitation in Mean-field Games

Learning Adversarial Low-rank Markov Decision Processes with Unknown Transition and Full-information Feedback

Hybrid Search for Efficient Planning with Completeness Guarantees

Autonomous Capability Assessment of Sequential Decision-Making Systems in Stochastic Settings

Large Language Models as Commonsense Knowledge for Large-Scale Task Planning

EDGI: Equivariant Diffusion for Planning with Embodied Agents

Evaluating Cognitive Maps and Planning in Large Language Models with CogEval

GraphMP: Graph Neural Network-based Motion Planning with Efficient Graph Search

Compositional Policy Learning in Stochastic Control Systems with Formal Guarantees

Safe Exploration in Reinforcement Learning: A Generalized Formulation and Algorithms

Mass-Producing Failures of Multimodal Systems with Language Models

A Bayesian Approach To Analysing Training Data Attribution In Deep Learning

The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importance

On the Robustness of Removal-Based Feature Attributions

Concept Distillation: Leveraging Human-Centered Explanations for Model Improvement

Explain Any Concept: Segment Anything Meets Concept-Based Explanation

LEACE: Perfect linear concept erasure in closed form

Language Models Don't Always Say What They Think: Unfaithful Explanations in Chain-of-Thought Prompting

This Looks Like Those: Illuminating Prototypical Concepts Using Multiple Visualizations

Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learning

Auditing for Human Expertise

Aleatoric and Epistemic Discrimination: Fundamental Limits of Fairness Interventions

Fair Canonical Correlation Analysis

Estimating and Controlling for Equalized Odds via Sensitive Attribute Predictors

Cookie Consent Has Disparate Impact on Estimation Accuracy

Group Fairness in Peer Review

On Measuring Fairness in Generative Models

Incentives in Private Collaborative Machine Learning

Strategic Behavior in Two-sided Matching Markets with Prediction-enhanced Preference-formation

WCLD: Curated Large Dataset of Criminal Cases from Wisconsin Circuit Courts

Optimal and Fair Encouragement Policy Evaluation and Learning

$k$-Means Clustering with Distance-Based Privacy

On the Gini-impurity Preservation For Privacy Random Forests

Optimal Unbiased Randomizers for Regression with Label Differential Privacy

Automatic Clipping: Differentially Private Deep Learning Made Easier and Stronger

Have it your way: Individualized Privacy Assignment for DP-SGD

Marich: A Query-efficient Distributionally Equivalent Model Extraction Attack

Fed-CO$_{2}$: Cooperation of Online and Offline Models for Severe Data Heterogeneity in Federated Learning

Minimax Risks and Optimal Procedures for Estimation under Functional Local Differential Privacy

A Randomized Approach to Tight Privacy Accounting

Private (Stochastic) Non-Convex Optimization Revisited: Second-Order Stationary Points and Excess Risks

Data Minimization at Inference Time

Causal Effect Regularization: Automated Detection and Removal of Spurious Correlations

Beyond Confidence: Reliable Models Should Also Consider Atypicality

IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AI

The Utility of “Even if” Semifactual Explanation to Optimise Positive Outcomes

BadTrack: A Poison-Only Backdoor Attack on Visual Object Tracking

Conformal Prediction Sets for Ordinal Classification

Differentially Private Decoupled Graph Convolutions for Multigranular Topology Protection

VRA: Variational Rectified Activation for Out-of-distribution Detection

IBA: Towards Irreversible Backdoor Attacks in Federated Learning

Tools for Verifying Neural Models' Training Data

BERT Lost Patience Won't Be Robust to Adversarial Slowdown

Effective Human-AI Teams via Learned Natural Language Rules and Onboarding

GAN You See Me? Enhanced Data Reconstruction Attacks against Split Inference

Dynamic Personalized Federated Learning with Adaptive Differential Privacy

Connecting Certified and Adversarial Training

A3FL: Adversarially Adaptive Backdoor Attacks to Federated Learning

Model Shapley: Equitable Model Valuation with Black-box Access

Diversified Outlier Exposure for Out-of-Distribution Detection via Informative Extrapolation

Expert load matters: operating networks at high accuracy and low manual effort

Top-Ambiguity Samples Matter: Understanding Why Deep Ensemble Works in Selective Classification

Privacy Assessment on Reconstructed Images: Are Existing Evaluation Metrics Faithful to Human Perception?

Equal Opportunity of Coverage in Fair Regression

Lockdown: Backdoor Defense for Federated Learning with Isolated Subspace Training

Robust and Actively Secure Serverless Collaborative Learning

Safety Verification of Decision-Tree Policies in Continuous Time

Max-Sliced Mutual Information

Nonparametric Teaching for Multiple Learners

Active representation learning for general task space with applications in robotics

Actively Testing Your Model While It Learns: Realizing Label-Efficient Learning in Practice

Res-Tuning: A Flexible and Efficient Tuning Paradigm via Unbinding Tuner from Backbone

Unsupervised Video Domain Adaptation for Action Recognition: A Disentanglement Perspective

Mixture Weight Estimation and Model Prediction in Multi-source Multi-target Domain Adaptation

SimMMDG: A Simple and Effective Framework for Multi-modal Domain Generalization

Errors-in-variables Fr\'echet Regression with Low-rank Covariate Approximation

Delegated Classification

The Distortion of Binomial Voting Defies Expectation

A Scalable Neural Network for DSIC Affine Maximizer Auction Design

Sample Complexity of Forecast Aggregation

Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability

Strategic Apple Tasting

Anonymous and Copy-Robust Delegations for Liquid Democracy

Polynomial-Time Linear-Swap Regret Minimization in Imperfect-Information Sequential Games

Nearly Optimal Bounds for Cyclic Forgetting

Learning Trajectories are Generalization Indicators

Attacks on Online Learners: a Teacher-Student Analysis

Structured Prediction with Stronger Consistency Guarantees

Toward Understanding Generative Data Augmentation

When can Regression-Adjusted Control Variate Help? Rare Events, Sobolev Embedding and Minimax Optimality

Cluster-aware Semi-supervised Learning: Relational Knowledge Distillation Provably Learns Clustering

On Learning Latent Models with Multi-Instance Weak Supervision

Demystifying Softmax Gating Function in Gaussian Mixture of Experts

SQ Lower Bounds for Non-Gaussian Component Analysis with Weaker Assumptions

Uniform Convergence with Square-Root Lipschitz Loss

PAC-Bayes Generalization Certificates for Learned Inductive Conformal Prediction

On the Learnability of Multilabel Ranking

Two Sides of The Same Coin: Bridging Deep Equilibrium Models and Neural ODEs via Homotopy Continuation

On Generalization Bounds for Projective Clustering

Implicit Regularization in Over-Parameterized Support Vector Machine

Sharp Recovery Thresholds of Tensor PCA Spectral Algorithms

On the Role of Entanglement and Statistics in Learning

On the Convergence of CART under Sufficient Impurity Decrease Condition

Learning From Biased Soft Labels

Fast and Regret Optimal Best Arm Identification: Fundamental Limits and Low-Complexity Algorithms

Bandit Social Learning under Myopic Behavior

Regret Minimization via Saddle Point Optimization

Beyond Black-Box Advice: Learning-Augmented Algorithms for MDPs with Q-Value Predictions

Efficient Algorithms for Generalized Linear Bandits with Heavy-tailed Rewards

Tracking Most Significant Shifts in Nonparametric Contextual Bandits

Federated Linear Bandits with Finite Adversarial Actions

An $\varepsilon$-Best-Arm Identification Algorithm for Fixed-Confidence and Beyond

Sorting with Predictions

Estimating the Rate-Distortion Function by Wasserstein Gradient Descent

Bayesian Extensive-Rank Matrix Factorization with Rotational Invariant Priors

Loss Dynamics of Temporal Difference Reinforcement Learning

Beyond Uniform Sampling: Offline Reinforcement Learning with Imbalanced Datasets

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

Double Pessimism is Provably Efficient for Distributionally Robust Offline Reinforcement Learning: Generic Algorithm and Robust Partial Coverage

Posterior Sampling for Competitive RL: Function Approximation and Partial Observation

Accelerating Value Iteration with Anchoring

Efficient Exploration in Continuous-time Model-based Reinforcement Learning

Bayesian Risk-Averse Q-Learning with Streaming Observations

Agnostic Multi-Group Active Learning

VPP: Efficient Conditional 3D Generation via Voxel-Point Progressive Representation

One-Step Diffusion Distillation via Deep Equilibrium Models

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise

Learning Regularized Monotone Graphon Mean-Field Games

Weighted ROC Curve in Cost Space: Extending AUC to Cost-Sensitive Learning

Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective

Reproducibility in Multiple Instance Learning: A Case For Algorithmic Unit Tests

Experiment Planning with Function Approximation

Epistemic Neural Networks

Dense-Exponential Random Features: Sharp Positive Estimators of the Gaussian Kernel

Nonparametric Boundary Geometry in Physics Informed Deep Learning

Deep Fractional Fourier Transform

Hyperbolic Graph Neural Networks at Scale: A Meta Learning Approach

DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation

PROTES: Probabilistic Optimization with Tensor Sampling

Neural Lad: A Neural Latent Dynamics Framework for Times Series Modeling

Cappy: Outperforming and Boosting Large Multi-Task LMs with a Small Scorer

GEQ: Gaussian Kernel Inspired Equilibrium Models

White-Box Transformers via Sparse Rate Reduction

Meta-Adapter: An Online Few-shot Learner for Vision-Language Model

The Emergence of Essential Sparsity in Large Pre-trained Models: The Weights that Matter

Distributional Model Equivalence for Risk-Sensitive Reinforcement Learning

Empowering Collaborative Filtering with Principled Adversarial Contrastive Loss

Wide Neural Networks as Gaussian Processes: Lessons from Deep Equilibrium Models

Few-shot Generation via Recalling Brain-Inspired Episodic-Semantic Memory

Self-Supervised Learning with Lie Symmetries for Partial Differential Equations

Patch n’ Pack: NaViT, a Vision Transformer for any Aspect Ratio and Resolution

NAP: Neural 3D Articulated Object Prior

Multi-Prompt Alignment for Multi-Source Unsupervised Domain Adaptation

Learning Universal Policies via Text-Guided Video Generation

MIM4DD: Mutual Information Maximization for Dataset Distillation

Characterization of Overfitting in Robust Multiclass Classification

Language Is Not All You Need: Aligning Perception with Language Models

Model-Based Reparameterization Policy Gradient Methods: Theory and Practical Algorithms

GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning

Online Control for Meta-optimization

Fair, Polylog-Approximate Low-Cost Hierarchical Clustering

LOVM: Language-Only Vision Model Selection

(ends 5:00 PM)

5 p.m.

THU 14 DEC

5:30 a.m.

Registration Desk

(ends 4:00 PM)

6:30 a.m.

Invited Talk:

Systems for Foundation Models, and Foundation Models for Systems.

Christopher Ré

(ends 7:20 AM)

7:15 a.m.

Break

8 a.m.

Oral 5A GNNs/Invariance [8:00-8:45]

Orals 8:00-8:45

[8:00] Going beyond persistent homology using persistent homology

[8:15] Clifford Group Equivariant Neural Networks

[8:30] Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis

(ends 8:45 AM)

Oral 5B Privacy/Fairness [8:00-8:45]

Orals 8:00-8:45

[8:00] Students Parrot Their Teachers: Membership Inference on Model Distillation

[8:15] Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition

[8:30] Ethical Considerations for Responsible Data Curation

(ends 8:45 AM)

Oral 5C Probability/Sampling [8:00-8:45]

Orals 8:00-8:45

[8:00] Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

[8:15] A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods

[8:30] Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method

(ends 8:45 AM)

Oral 5D Vision [8:00-8:45]

Orals 8:00-8:45

[8:00] Visual Instruction Tuning

[8:15] EgoEnv: Human-centric environment representations from egocentric video

[8:30] DataComp: In search of the next generation of multimodal datasets

(ends 8:45 AM)

8:45 a.m.

Poster Session 5 [8:45-10:45]

Posters 8:45-10:45

SpatialRank: Urban Event Ranking with NDCG Optimization on Spatiotemporal Data

Learning to Group Auxiliary Datasets for Molecule

A Hierarchical Training Paradigm for Antibody Structure-sequence Co-design

DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening

Rethinking Tokenizer and Decoder in Masked Graph Modeling for Molecules

Functional-Group-Based Diffusion for Pocket-Specific Molecule Generation and Elaboration

Learning Invariant Molecular Representation in Latent Discrete Space

Prefix-Tree Decoding for Predicting Mass Spectra from Molecules

QH9: A Quantum Hamiltonian Prediction Benchmark for QM9 Molecules

CROMA: Remote Sensing Representations with Contrastive Radar-Optical Masked Autoencoders

NeRF Revisited: Fixing Quadrature Instability in Volume Rendering

Self-Supervised Motion Magnification by Backpropagating Through Optical Flow

Point Cloud Completion with Pretrained Text-to-Image Diffusion Models

Inferring Hybrid Neural Fluid Fields from Videos

UE4-NeRF:Neural Radiance Field for Real-Time Rendering of Large-Scale Scene

CAST: Cross-Attention in Space and Time for Video Action Recognition

Unleash the Potential of Image Branch for Cross-modal 3D Object Detection

POP-3D: Open-Vocabulary 3D Occupancy Prediction from Images

A Single 2D Pose with Context is Worth Hundreds for 3D Human Pose Estimation

From ViT Features to Training-free Video Object Segmentation via Streaming-data Mixture Models

EgoEnv: Human-centric environment representations from egocentric video

Activity Grammars for Temporal Action Segmentation

Detecting Any Human-Object Interaction Relationship: Universal HOI Detector with Spatial Prompt Learning on Foundation Models

CorresNeRF: Image Correspondence Priors for Neural Radiance Fields

Q-DM: An Efficient Low-bit Quantized Diffusion Model

PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds

DäRF: Boosting Radiance Fields from Sparse Input Views with Monocular Depth Adaptation

Learn to Categorize or Categorize to Learn? Self-Coding for Generalized Category Discovery

Scaling Open-Vocabulary Object Detection

LEPARD: Learning Explicit Part Discovery for 3D Articulated Shape Reconstruction

Sensitivity in Translation Averaging

BLIP-Diffusion: Pre-trained Subject Representation for Controllable Text-to-Image Generation and Editing

ChimpACT: A Longitudinal Dataset for Understanding Chimpanzee Behaviors

FouriDown: Factoring Down-Sampling into Shuffling and Superposing

Slot-guided Volumetric Object Radiance Fields

Diffusion with Forward Models: Solving Stochastic Inverse Problems Without Direct Supervision

CLIP4HOI: Towards Adapting CLIP for Practical Zero-Shot HOI Detection

Focus on Query: Adversarial Mining Transformer for Few-Shot Segmentation

CluB: Cluster Meets BEV for LiDAR-Based 3D Object Detection

IEBins: Iterative Elastic Bins for Monocular Depth Estimation

What Makes Good Examples for Visual In-Context Learning?

Implicit Differentiable Outlier Detection Enable Robust Deep Multimodal Analysis

DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model

AutoGO: Automated Computation Graph Optimization for Neural Network Evolution

A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence

SPA: A Graph Spectral Alignment Perspective for Domain Adaptation

Learning Motion Refinement for Unsupervised Face Animation

RegBN: Batch Normalization of Multimodal Data with Regularization

Uncertainty-Aware Alignment Network for Cross-Domain Video-Text Retrieval

LaFTer: Label-Free Tuning of Zero-shot Classifier using Language and Unlabeled Image Collections

Gold-YOLO: Efficient Object Detector via Gather-and-Distribute Mechanism

DynPoint: Dynamic Neural Point For View Synthesis

Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models

Social Motion Prediction with Cognitive Hierarchies

Visual Instruction Inversion: Image Editing via Image Prompting

LART: Neural Correspondence Learning with Latent Regularization Transformer for 3D Motion Transfer

Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation

Binarized Spectral Compressive Imaging

Learning Re-sampling Methods with Parameter Attribution for Image Super-resolution

Reducing Shape-Radiance Ambiguity in Radiance Fields with a Closed-Form Color Estimation Method

Visual Instruction Tuning

ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections

Leveraging Vision-Centric Multi-Modal Expertise for 3D Object Detection

PromptRestorer: A Prompting Image Restoration Method with Degradation Perception

Rethinking Semi-Supervised Medical Image Segmentation: A Variance-Reduction Perspective

PHOTOSWAP: Personalized Subject Swapping in Images

Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback

Global-correlated 3D-decoupling Transformer for Clothed Avatar Reconstruction

Prompt Pre-Training with Twenty-Thousand Classes for Open-Vocabulary Visual Recognition

AD-PT: Autonomous Driving Pre-Training with Large-scale Point Cloud Dataset

$SE(3)$ Equivariant Convolution and Transformer in Ray Space

Flow-Based Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

Transient Neural Radiance Fields for Lidar View Synthesis and 3D Reconstruction

Toward Re-Identifying Any Animal

Prototypical Variational Autoencoder for 3D Few-shot Object Detection

Uncertainty Quantification via Neural Posterior Principal Components

UniTSFace: Unified Threshold Integrated Sample-to-Sample Loss for Face Recognition

Scattering Vision Transformer: Spectral Mixing Matters

Video Timeline Modeling For News Story Understanding

EV-Eye: Rethinking High-frequency Eye Tracking through the Lenses of Event Cameras

ISP: Multi-Layered Garment Draping with Implicit Sewing Patterns

LambdaBeam: Neural Program Search with Higher-Order Functions and Lambdas

Multi-Objective Intrinsic Reward Learning for Conversational Recommender Systems

Generate What You Prefer: Reshaping Sequential Recommendation via Guided Diffusion

xTrimoGene: An Efficient and Scalable Representation Learner for Single-Cell RNA-Seq Data

Spatially Resolved Gene Expression Prediction from Histology Images via Bi-modal Contrastive Learning

Individualized Dosing Dynamics via Neural Eigen Decomposition

DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Models

C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models

Focused Transformer: Contrastive Training for Context Scaling

High-Fidelity Audio Compression with Improved RVQGAN

Improving Language Plasticity via Pretraining with Active Forgetting

Pengi: An Audio Language Model for Audio Tasks

Continual Learning for Instruction Following from Realtime Feedback

Extensible Prompts for Language Models on Zero-shot Language Style Customization

EvoPrompting: Language Models for Code-Level Neural Architecture Search

AVeriTeC: A Dataset for Real-world Claim Verification with Evidence from the Web

SPRING: Studying Papers and Reasoning to play Games

Principle-Driven Self-Alignment of Language Models from Scratch with Minimal Human Supervision

Open Visual Knowledge Extraction via Relation-Oriented Multimodality Model Prompting

Voicebox: Text-Guided Multilingual Universal Speech Generation at Scale

Response Length Perception and Sequence Scheduling: An LLM-Empowered LLM Inference Pipeline

Learning Repeatable Speech Embeddings Using An Intra-class Correlation Regularizer

InfoPrompt: Information-Theoretic Soft Prompt Tuning for Natural Language Understanding

StyleTTS 2: Towards Human-Level Text-to-Speech through Style Diffusion and Adversarial Training with Large Speech Language Models

The Harvard USPTO Patent Dataset: A Large-Scale, Well-Structured, and Multi-Purpose Corpus of Patent Applications

Learning and processing the ordinal information of temporal sequences in recurrent neural circuits

Towards robust and generalizable representations of extracellular data using contrastive learning

Parallel Spiking Neurons with High Efficiency and Ability to Learn Long-term Dependencies

A polar prediction model for learning to represent visual transformations

Adaptive recurrent vision performs zero-shot computation scaling to unseen difficulty levels

Bayesian nonparametric (non-)renewal processes for analyzing neural spike train variability

Reconstructing the Mind's Eye: fMRI-to-Image with Contrastive Learning and Diffusion Priors

Neural Foundations of Mental Simulation: Future Prediction of Latent Representations on Dynamic Scenes

Brain Dissection: fMRI-trained Networks Reveal Spatial Selectivity in the Processing of Natural Images

Alleviating the Semantic Gap for Generalized fMRI-to-Image Reconstruction

Learning Efficient Coding of Natural Images with Maximum Manifold Capacity Representations

An information-theoretic quantification of the content of communication between brain regions

Formalizing locality for normative synaptic plasticity models

D-CIPHER: Discovery of Closed-form Partial Differential Equations

Swarm Reinforcement Learning for Adaptive Mesh Refinement

Versatile Energy-Based Probabilistic Models for High Energy Physics

CARE: Modeling Interacting Dynamics Under Temporal Environmental Variation

Wasserstein Quantum Monte Carlo: A Novel Approach for Solving the Quantum Many-Body Schrödinger Equation

NVFi: Neural Velocity Fields for 3D Physics Learning from Dynamic Videos

DiffVL: Scaling Up Soft Body Manipulation using Vision-Language Driven Differentiable Physics

Neural Lighting Simulation for Urban Scenes

Frequency-Enhanced Data Augmentation for Vision-and-Language Navigation

What Planning Problems Can A Relational Neural Network Solve?

Enhancing Robot Program Synthesis Through Environmental Context

Wasserstein Gradient Flows for Optimizing Gaussian Mixture Policies

Demo2Code: From Summarizing Demonstrations to Synthesizing Code via Extended Chain-of-Thought

Switching Autoregressive Low-rank Tensor Models

DataComp: In search of the next generation of multimodal datasets

Geometry-Aware Adaptation for Pretrained Models

Adversarial Learning for Feature Shift Detection and Correction

Learning Dictionary for Visual Attention

Modality-Independent Teachers Meet Weakly-Supervised Audio-Visual Event Parser

Neural Relation Graph: A Unified Framework for Identifying Label Noise and Outlier Data

Permutation Equivariant Neural Functionals

Explore In-Context Learning for 3D Point Cloud Understanding

Getting ViT in Shape: Scaling Laws for Compute-Optimal Model Design

Universality and Limitations of Prompt Tuning

MKOR: Momentum-Enabled Kronecker-Factor-Based Optimizer Using Rank-1 Updates

Knowledge Distillation for High Dimensional Search Index

Don't be so Monotone: Relaxing Stochastic Line Search in Over-Parameterized Models

Fine-Grained Visual Prompting

MIMONets: Multiple-Input-Multiple-Output Neural Networks Exploiting Computation in Superposition

ShiftAddViT: Mixture of Multiplication Primitives Towards Efficient Vision Transformer

CLeAR: Continual Learning on Algorithmic Reasoning for Human-like Intelligence

Softmax Output Approximation for Activation Memory-Efficient Training of Attention-based Networks

PDP: Parameter-free Differentiable Pruning is All You Need

Normalization Layers Are All That Sharpness-Aware Minimization Needs

Principled Weight Initialisation for Input-Convex Neural Networks

Direct Training of SNN using Local Zeroth Order Method

A fast heuristic to optimize time-space tradeoff for large models

Temperature Balancing, Layer-wise Weight Analysis, and Neural Network Training

Memory Efficient Optimizers with 4-bit States

Multi-modal Queried Object Detection in the Wild

Unlimiformer: Long-Range Transformers with Unlimited Length Input

Learning from Both Structural and Textual Knowledge for Inductive Knowledge Graph Completion

Coop: Memory is not a Commodity

Reward-Directed Conditional Diffusion: Provable Distribution Estimation and Reward Improvement

TabMT: Generating tabular data with masked transformers

Monitor-Guided Decoding of Code LMs with Static Analysis of Repository Context

DreamHuman: Animatable 3D Avatars from Text

Generating Behaviorally Diverse Policies with Latent Diffusion Models

GPT-ST: Generative Pre-Training of Spatio-Temporal Graph Neural Networks

Spontaneous symmetry breaking in generative diffusion models

Metropolis Sampling for Constrained Diffusion Models

Patch Diffusion: Faster and More Data-Efficient Training of Diffusion Models

PCF-GAN: generating sequential data via the characteristic function of measures on the path space

InsActor: Instruction-driven Physics-based Characters

Parts of Speech–Grounded Subspaces in Vision-Language Models

Object-Centric Slot Diffusion

AdaVAE: Bayesian Structural Adaptation for Variational Autoencoders

Are Diffusion Models Vision-And-Language Reasoners?

SA-Solver: Stochastic Adams Solver for Fast Sampling of Diffusion Models

Learning Energy-Based Prior Model with Diffusion-Amortized MCMC

Bootstrapped Training of Score-Conditioned Generator for Offline Design of Biological Sequences

Domain Re-Modulation for Few-Shot Generative Domain Adaptation

Non-adversarial training of Neural SDEs with signature kernel scores

Feature Likelihood Divergence: Evaluating the Generalization of Generative Models Using Samples

Simple and Controllable Music Generation

Diffusion Self-Guidance for Controllable Image Generation

Imagine That! Abstract-to-Intricate Text-to-Image Synthesis with Scene Graph Hallucination Diffusion

Norm-guided latent space exploration for text-to-image generation

Statistical Knowledge Assessment for Large Language Models

Free-Bloom: Zero-Shot Text-to-Video Generator with LLM Director and LDM Animator

Generator Born from Classifier

Predict, Refine, Synthesize: Self-Guiding Diffusion Models for Probabilistic Time Series Forecasting

On the choice of Perception Loss Function for Learned Video Compression

DiffComplete: Diffusion-based Generative 3D Shape Completion

The CLIP Model is Secretly an Image-to-Prompt Converter

ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation with Variational Score Distillation

Debiasing Scores and Prompts of 2D Diffusion for View-consistent Text-to-3D Generation

Multi-resolution Spectral Coherence for Graph Generation with Score-based Diffusion

Diffusion Schrödinger Bridge Matching

Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models

Parsel🐍: Algorithmic Reasoning with Language Models by Composing Decompositions

Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models

Adapting Neural Link Predictors for Data-Efficient Complex Query Answering

GraphPatcher: Mitigating Degree Bias for Graph Neural Networks via Test-time Augmentation

Transformers over Directed Acyclic Graphs

A new perspective on building efficient and expressive 3D equivariant graph neural networks

Environment-Aware Dynamic Graph Learning for Out-of-Distribution Generalization

Train Once and Explain Everywhere: Pre-training Interpretable Graph Neural Networks

Demystifying Structural Disparity in Graph Neural Networks: Can One Size Fit All?

From Trainable Negative Depth to Edge Heterophily in Graphs

Going beyond persistent homology using persistent homology

Evaluating Post-hoc Explanations for Graph Neural Networks via Robustness Analysis

Limits, approximation and size transferability for GNNs on sparse graphs via graphops

Unleashing the Power of Graph Data Augmentation on Covariate Distribution Shift

Evaluating Robustness and Uncertainty of Graph Models Under Structural Distributional Shifts

Maximum Independent Set: Self-Training through Dynamic Programming

ESSEN: Improving Evolution State Estimation for Temporal Networks using Von Neumann Entropy

When Do Graph Neural Networks Help with Node Classification? Investigating the Homophily Principle on Node Distinguishability

GALOPA: Graph Transport Learning with Optimal Plan Alignment

Curriculum Learning for Graph Neural Networks: Which Edges Should We Learn First

GNNEvaluator: Evaluating GNN Performance On Unseen Graphs Without Labels

Complex Query Answering on Eventuality Knowledge Graph with Implicit Logical Constraints

FedGCN: Convergence-Communication Tradeoffs in Federated Training of Graph Convolutional Networks

Truncated Affinity Maximization: One-class Homophily Modeling for Graph Anomaly Detection

Interpretable Prototype-based Graph Information Bottleneck

Learning Probabilistic Symmetrization for Architecture Agnostic Equivariance

Predicting Global Label Relationship Matrix for Graph Neural Networks under Heterophily

Clifford Group Equivariant Neural Networks

Cross-links Matter for Link Prediction: Rethinking the Debiased GNN from a Data Perspective

TriRE: A Multi-Mechanism Learning Paradigm for Continual Knowledge Retention and Promotion

Latent Space Translation via Semantic Alignment

Understanding and Improving Feature Learning for Out-of-Distribution Generalization

Geodesic Multi-Modal Mixup for Robust Fine-Tuning

RGMIL: Guide Your Multiple-Instance Learning Model with Regressor

PDF: Point Diffusion Implicit Function for Large-scale Scene Neural Representation

A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints

Unified Embedding: Battle-Tested Feature Representations for Web-Scale ML Systems

Gradient Flossing: Improving Gradient Descent through Dynamic Control of Jacobians

Simultaneous embedding of multiple attractor manifolds in a recurrent neural network using constrained gradient optimization

Recursion in Recursion: Two-Level Nested Recursion for Length Generalization with Scalability

Adversarial Training from Mean Field Perspective

Convolutional Visual Prompt for Robust Visual Perception

Learning Provably Robust Estimators for Inverse Problems via Jittering

SOL: Sampling-based Optimal Linear bounding of arbitrary scalar functions

Provable Adversarial Robustness for Group Equivariant Tasks: Graphs, Point Clouds, Molecules, and More

RS-Del: Edit Distance Robustness Certificates for Sequence Classifiers via Randomized Deletion

Revisiting Visual Model Robustness: A Frequency Long-Tailed Distribution View

Transformed Low-Rank Parameterization Can Help Robust Generalization for Tensor Neural Networks

DRAUC: An Instance-wise Distributionally Robust AUC Optimization Framework

FedGame: A Game-Theoretic Defense against Backdoor Attacks in Federated Learning

Label Poisoning is All You Need

Adversarial Examples Are Not Real Features

Test-Time Amendment with a Coarse Classifier for Fine-Grained Classification

Distilling Out-of-Distribution Robustness from Vision-Language Foundation Models

Theoretically Guaranteed Bidirectional Data Rectification for Robust Sequential Recommendation

Certifiably Robust Graph Contrastive Learning

Neural Harmonics: Bridging Spectral Embedding and Matrix Completion in Self-Supervised Learning

FOCAL: Contrastive Learning for Multimodal Time-Series Sensing Signals in Factorized Orthogonal Latent Space

Segment Any Point Cloud Sequences by Distilling Vision Foundation Models

Training Transitive and Commutative Multimodal Transformers with LoReTTa

Contrast Everything: A Hierarchical Contrastive Framework for Medical Time-Series

Representation Learning via Consistent Assignment of Views over Random Partitions

Analyzing the Sample Complexity of Self-Supervised Image Reconstruction Methods

Combating Representation Learning Disparity with Geometric Harmonization

Beyond Pretrained Features: Noisy Image Modeling Provides Adversarial Defense

Language-based Action Concept Spaces Improve Video Self-Supervised Learning

PointGPT: Auto-regressively Generative Pre-training from Point Clouds

CWCL: Cross-Modal Transfer with Continuously Weighted Contrastive Loss

ContiFormer: Continuous-Time Transformer for Irregular Time Series Modeling

SutraNets: Sub-series Autoregressive Networks for Long-Sequence, Probabilistic Forecasting

State-space models with layer-wise nonlinearity are universal approximators with exponential decaying memory

Frequency-domain MLPs are More Effective Learners in Time Series Forecasting

MultiMoDN—Multimodal, Multi-Task, Interpretable Modular Networks

Homotopy-based training of NeuralODEs for accurate dynamics discovery

SimMTM: A Simple Pre-Training Framework for Masked Time-Series Modeling

Multi Time Scale World Models

Nominality Score Conditioned Time Series Anomaly Detection by Point/Sequential Reconstruction

Generalization bounds for neural ordinary differential equations and deep residual networks

Leveraging the two-timescale regime to demonstrate convergence of neural networks

The Learnability of In-Context Learning

How do Minimum-Norm Shallow Denoisers Look in Function Space?

Complex-valued Neurons Can Learn More but Slower than Real-valued Neurons via Gradient Descent

Global Convergence Analysis of Local SGD for Two-layer Neural Network without Overparameterization

Stochastic Collapse: How Gradient Noise Attracts SGD Dynamics Towards Simpler Subnetworks

Dynamics of Finite Width Kernel and Prediction Fluctuations in Mean Field Neural Networks

On the impact of activation and normalization in obtaining isometric embeddings at initialization

Spectral Evolution and Invariance in Linear-width Neural Networks

Theoretical and Practical Perspectives on what Influence Functions Do

Neural (Tangent Kernel) Collapse

Relative Entropic Optimal Transport: a (Prior-aware) Matching Perspective to (Unbalanced) Classification

Unified Off-Policy Learning to Rank: a Reinforcement Learning Perspective

Locality Sensitive Hashing in Fourier Frequency Domain For Soft Set Containment Search

Using Imperfect Surrogates for Downstream Inference: Design-based Supervised Learning for Social Science Applications of Large Language Models

AMDP: An Adaptive Detection Procedure for False Discovery Rate Control in High-Dimensional Mediation Analysis

Identifiability Guarantees for Causal Disentanglement from Soft Interventions

K-Nearest-Neighbor Local Sampling Based Conditional Independence Testing

Bayesian Active Causal Discovery with Multi-Fidelity Experiments

Causal de Finetti: On the Identification of Invariant Causal Structure in Exchangeable Data

Front-door Adjustment Beyond Markov Equivalence with Limited Graph Knowledge

Sharp Bounds for Generalized Causal Sensitivity Analysis

Meek Separators and Their Applications in Targeted Causal Discovery

Causal Effect Identification in Uncertain Causal Networks

Counterfactual Evaluation of Peer-Review Assignment Policies

A Causal Framework for Decomposing Spurious Variations

On Learning Necessary and Sufficient Causal Graphs

$p$-value Adjustment for Monotonous, Unbiased, and Fast Clustering Comparison

Performance Scaling via Optimal Transport: Enabling Data Selection from Partially Revealed Sources

Joint Feature and Differentiable $ k $-NN Graph Learning using Dirichlet Energy

False Discovery Proportion control for aggregated Knockoffs

Statistical Insights into HSIC in High Dimensions

Efficient Sampling of Stochastic Differential Equations with Positive Semi-Definite Models

Kernel-Based Tests for Likelihood-Free Hypothesis Testing

Contextual Gaussian Process Bandits with Neural Networks

Towards Optimal Caching and Model Selection for Large Model Inference

On Private and Robust Bandits

How to Select Which Active Learning Strategy is Best Suited for Your Specific Problem and Budget

Marginal Density Ratio for Off-Policy Evaluation in Contextual Bandits

Multi-Fidelity Multi-Armed Bandits Revisited

Meta-Learning Adversarial Bandit Algorithms

A General Framework for Robust G-Invariance in G-Equivariant Networks

A Framework for Fast and Stable Representations of Multiparameter Persistent Homology Decompositions

Improving Compositional Generalization using Iterated Learning and Simplicial Embeddings

On the Identifiability of Sparse ICA without Assuming Non-Gaussianity

Contrastive Training of Complex-Valued Autoencoders for Object Discovery

Learning Linear Causal Representations from Interventions under General Nonlinear Mixing

DESSERT: An Efficient Algorithm for Vector Set Search with Vector Set Queries

A Unified Fast Gradient Clipping Framework for DP-SGD

Fast Optimal Transport through Sliced Generalized Wasserstein Geodesics

One Fits All: Power General Time Series Analysis by Pretrained LM

Generalized test utilities for long-tail performance in extreme multi-label classification

Multi-task learning with summary statistics

ProtoDiff: Learning to Learn Prototypical Networks by Task-Guided Diffusion

Hierarchical Gaussian Mixture based Task Generative Model for Robust Meta-Learning

Better with Less: A Data-Active Perspective on Pre-Training Graph Neural Networks

Inverse Dynamics Pretraining Learns Good Representations for Multitask Imitation

DoReMi: Optimizing Data Mixtures Speeds Up Language Model Pretraining

Differentiable Clustering with Perturbed Spanning Forests

Reward Finetuning for Faster and More Accurate Unsupervised Object Discovery

RETVec: Resilient and Efficient Text Vectorizer

Semi-Supervised Contrastive Learning for Deep Regression with Ordinal Rankings from Spectral Seriation

Doubly-Robust Self-Training

Unsupervised Anomaly Detection with Rejection

Landscape Surrogate: Learning Decision Losses for Mathematical Optimization Under Partial Information

How Does Adaptive Optimization Impact Local Neural Network Geometry?

Efficient Hyper-parameter Optimization with Cubic Regularization

Energy-based learning algorithms for analog computing: a comparative study

BiSLS/SPS: Auto-tune Step Sizes for Stable Bi-level Optimization

Online Adaptive Policy Selection in Time-Varying Systems: No-Regret via Contractive Perturbations

Continuous-time Analysis of Anchor Acceleration

Optimal Guarantees for Algorithmic Reproducibility and Gradient Complexity in Convex Optimization

Unsupervised Learning for Solving the Travelling Salesman Problem

Bicriteria Approximation Algorithms for the Submodular Cover Problem

Online Ad Allocation with Predictions

Block Broyden's Methods for Solving Nonlinear Equations

FLuID: Mitigating Stragglers in Federated Learning using Invariant Dropout

Resolving the Tug-of-War: A Separation of Communication and Learning in Federated Learning

2Direction: Theoretically Faster Distributed Training with Bidirectional Communication Compression

Private Federated Frequency Estimation: Adapting to the Hardness of the Instance

A Computation and Communication Efficient Method for Distributed Nonconvex Problems in the Partial Participation Setting

Aggregating Capacity in FL through Successive Layer Training for Computationally-Constrained Devices

Is Heterogeneity Notorious? Taming Heterogeneity to Handle Test-Time Shift in Federated Learning

Global Update Tracking: A Decentralized Learning Algorithm for Heterogeneous Data

L2T-DLN: Learning to Teach with Dynamic Loss Network

Efficient Data Subset Selection to Generalize Training Across Models: Transductive and Inductive Networks

Learning to Configure Separators in Branch-and-Cut

Algorithmic Regularization in Tensor Optimization: Towards a Lifted Approach in Matrix Sensing

Non-Smooth Weakly-Convex Finite-sum Coupled Compositional Optimization

Saddle-to-Saddle Dynamics in Diagonal Linear Networks

Riemannian stochastic optimization methods avoid strict saddle points

Two Sides of One Coin: the Limits of Untuned SGD and the Power of Adaptive Methods

Resilient Constrained Learning

Exact Generalization Guarantees for (Regularized) Wasserstein Distributionally Robust Models

Double Randomized Underdamped Langevin with Dimension-Independent Convergence Guarantee

Improved Convergence in High Probability of Clipped Gradient Methods with Heavy Tailed Noise

Sample Complexity for Quadratic Bandits: Hessian Dependent Bounds and Optimal Algorithms

Macro Placement by Wire-Mask-Guided Black-Box Optimization

End-to-End Meta-Bayesian Optimisation with Transformer Neural Processes

On Masked Pre-training and the Marginal Likelihood

On permutation symmetries in Bayesian neural network posteriors: a variational perspective

Scaling Laws for Hyperparameter Optimization

Beyond Deep Ensembles: A Large-Scale Evaluation of Bayesian Deep Learning under Distribution Shift

Flat Seeking Bayesian Neural Networks

Asymptotics of Bayesian Uncertainty Estimation in Random Features Regression

Soft-Unification in Deep Probabilistic Logic

Resilient Multiple Choice Learning: A learned scoring scheme with application to audio scene analysis

Sampling from Gaussian Process Posteriors using Stochastic Gradient Descent

GPEX, A Framework For Interpreting Artificial Neural Networks

Computing Approximate $\ell_p$ Sensitivities

Unbiased constrained sampling with Self-Concordant Barrier Hamiltonian Monte Carlo

Practical and Asymptotically Exact Conditional Sampling in Diffusion Models

Provable convergence guarantees for black-box variational inference

A Rigorous Link between Deep Ensembles and (Variational) Bayesian Methods

NPCL: Neural Processes for Uncertainty-Aware Continual Learning

Particle-based Variational Inference with Generalized Wasserstein Gradient Flow

Game Solving with Online Fine-Tuning

Prioritizing Samples in Reinforcement Learning with Reducible Loss

Provably Fast Convergence of Independent Natural Policy Gradient for Markov Potential Games

State-Action Similarity-Based Representations for Off-Policy Evaluation

Distributional Policy Evaluation: a Maximum Entropy approach to Representation Learning

Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design

Recurrent Hypernetworks are Surprisingly Strong in Meta-RL

H-InDex: Visual Reinforcement Learning with Hand-Informed Representations for Dexterous Manipulation

Gradient Informed Proximal Policy Optimization

Cross-Domain Policy Adaptation via Value-Guided Data Filtering

Taylor TD-learning

Diffusion Model is an Effective Planner and Data Synthesizer for Multi-Task Reinforcement Learning

Managing Temporal Resolution in Continuous Value Estimation: A Fundamental Trade-off

Doubly Robust Augmented Transfer for Meta-Reinforcement Learning

Team-PSRO for Learning Approximate TMECor in Large Team Games via Cooperative Reinforcement Learning

Successor-Predecessor Intrinsic Exploration

Distributional Pareto-Optimal Multi-Objective Reinforcement Learning

Seeing is not Believing: Robust Reinforcement Learning against Spurious Correlation

Reducing Blackwell and Average Optimality to Discounted MDPs via the Blackwell Discount Factor

One Risk to Rule Them All: A Risk-Sensitive Perspective on Model-Based Offline Reinforcement Learning

Offline Minimax Soft-Q-learning Under Realizability and Partial Coverage

Design from Policies: Conservative Test-Time Adaptation for Offline Policy Optimization

Look Beneath the Surface: Exploiting Fundamental Symmetry for Sample-Efficient Offline RL

VOCE: Variational Optimization with Conservative Estimation for Offline Safe Reinforcement Learning

Supported Value Regularization for Offline Reinforcement Learning

Adversarial Counterfactual Environment Model Learning

Reining Generalization in Offline Reinforcement Learning via Representation Distinction

Provable Guarantees for Generative Behavior Cloning: Bridging Low-Level Stability and High-Level Behavior

Revisiting the Minimalist Approach to Offline Reinforcement Learning

Understanding, Predicting and Better Resolving Q-Value Divergence in Offline-RL

FlowPG: Action-constrained Policy Gradient with Normalizing Flows

Flexible Attention-Based Multi-Policy Fusion for Efficient Deep Reinforcement Learning

Trust Region-Based Safe Distributional Reinforcement Learning for Multiple Constraints

SPQR: Controlling Q-ensemble Independence with Spiked Random Model for Reinforcement Learning

Contrastive Retrospection: honing in on critical steps for rapid learning and generalization in RL

Thinker: Learning to Plan and Act

ELDEN: Exploration via Local Dependencies

PID-Inspired Inductive Biases for Deep Reinforcement Learning in Partially Observable Control Tasks

Iterative Reachability Estimation for Safe Reinforcement Learning

Reinforcement Learning with Simple Sequence Priors

Deep Reinforcement Learning with Plasticity Injection

Active Vision Reinforcement Learning under Limited Visual Observability

Inverse Preference Learning: Preference-based RL without a Reward Function

Diversify \& Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement

Creating Multi-Level Skill Hierarchies in Reinforcement Learning

Ess-InfoGAIL: Semi-supervised Imitation Learning from Imbalanced Demonstrations

Can Pre-Trained Text-to-Image Models Generate Visual Goals for Reinforcement Learning?

Optimal Exploration for Model-Based RL in Nonlinear Systems

Inferring the Future by Imagining the Past

History Filtering in Imperfect Information Games: Algorithms and Complexity

Emergent Communication for Rules Reasoning

Multi-Agent Meta-Reinforcement Learning: Sharper Convergence Rates with Task Similarity

AdaPlanner: Adaptive Planning from Feedback with Language Models

Active Observing in Continuous-time Control

Adaptive Online Replanning with Diffusion Models

Beyond Average Return in Markov Decision Processes

Auxiliary Losses for Learning Generalizable Concept-based Models

Spuriosity Rankings: Sorting Data to Measure and Mitigate Biases

Break It Down: Evidence for Structural Compositionality in Neural Networks

Labeling Neural Representations with Inverse Recognition

How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained language model

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability

Learning Reliable Logical Rules with SATNet

Towards the Difficulty for a Deep Neural Network to Learn Concepts of Different Complexities

SAME: Uncovering GNN Black Box with Structure-aware Shapley-based Multipiece Explanations

Moral Responsibility for AI Systems

Individual Arbitrariness and Group Fairness

BIRD: Generalizable Backdoor Detection and Removal for Deep Reinforcement Learning

Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognition

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

Ethical Considerations for Responsible Data Curation

CoPriv: Network/Protocol Co-Optimization for Communication-Efficient Private Inference

Easy Learning from Label Proportions

Do SSL Models Have Déjà Vu? A Case of Unintended Memorization in Self-supervised Learning

Privacy Amplification via Compression: Achieving the Optimal Privacy-Accuracy-Communication Trade-off in Distributed Mean Estimation

Faster Differentially Private Convex Optimization via Second-Order Methods

Black-Box Differential Privacy for Interactive ML

Unleashing the Power of Randomization in Auditing Differentially Private ML

Students Parrot Their Teachers: Membership Inference on Model Distillation

Private Distribution Learning with Public Data: The View from Sample Compression

Eliminating Domain Bias for Federated Learning in Representation Space

Post-processing Private Synthetic Data for Improving Utility on Selected Measures

Efficient Adversarial Contrastive Learning via Robustness-Aware Coreset Selection

FedFed: Feature Distillation against Data Heterogeneity in Federated Learning

Combating Bilateral Edge Noise for Robust Link Prediction

Use perturbations when learning from explanations

Flow-Attention-based Spatio-Temporal Aggregation Network for 3D Mask Detection

Content-based Unrestricted Adversarial Attack

Class-Conditional Conformal Prediction with Many Classes

In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defer

Deconstructing Data Reconstruction: Multiclass, Weight Decay and General Losses

Regression with Cost-based Rejection

Derandomized novelty detection with FDR control via conformal e-values

Fast Partitioned Learned Bloom Filter

Minimum-Risk Recalibration of Classifiers

On the Properties of Kullback-Leibler Divergence Between Multivariate Gaussian Distributions

Not All Out-of-Distribution Data Are Harmful to Open-Set Active Learning

Learning List-Level Domain-Invariant Representations for Ranking

Creating a Public Repository for Joining Private Data

Structure of universal formulas

Incentivizing Honesty among Competitors in Collaborative Learning and Optimization

Calibrated Stackelberg Games: Learning Optimal Commitments Against Calibrated Agents

Regret Matching+: (In)Stability and Fast Convergence in Games

Computing Optimal Nash Equilibria in Multiplayer Games

On the Robustness of Mechanism Design under Total Variation Distance

Asynchronous Proportional Response Dynamics: Convergence in Markets with Adversarial Scheduling

Similarity-based cooperative equilibrium

Near-Optimal Algorithms for Gaussians with Huber Contamination: Mean Estimation and Linear Regression

Efficient Testable Learning of Halfspaces with Adversarial Label Noise

Robust Mean Estimation Without Moments for Symmetric Distributions

Learning with Explanation Constraints

Optimistic Rates for Multi-Task Representation Learning

$H$-Consistency Bounds: Characterization and Extensions

Robust Matrix Sensing in the Semi-Random Model

Demystifying the Optimal Performance of Multi-Class Classification

On Certified Generalization in Structured Prediction

Error Bounds for Learning with Vector-Valued Random Features

A Theoretical Analysis of the Test Error of Finite-Rank Kernel Ridge Regression

On the Role of Noise in the Sample Complexity of Learning Recurrent Neural Networks: Exponential Gaps for Long Sequences

Initialization-Dependent Sample Complexity of Linear Predictors and Neural Networks

Sample-Conditioned Hypothesis Stability Sharpens Information-Theoretic Generalization Bounds

An Adaptive Algorithm for Learning with Unknown Distribution Drift

Classification of Heavy-tailed Features in High Dimensions: a Superstatistical Approach

Optimality in Mean Estimation: Beyond Worst-Case, Beyond Sub-Gaussian, and Beyond $1+\alpha$ Moments

Optimizing Solution-Samplers for Combinatorial Problems: The Landscape of Policy-Gradient Method

Near-optimal learning with average Hölder smoothness

When are ensembles really effective?

Bypassing the Simulator: Near-Optimal Adversarial Linear Contextual Bandits

Unconstrained Dynamic Regret via Sparse Coding

Follow-ups Also Matter: Improving Contextual Bandits via Post-serving Contexts

An active learning framework for multi-group mean estimation

A Trichotomy for Transductive Online Learning

Best Arm Identification with Fixed Budget: A Large Deviation Perspective

Understanding Multi-phase Optimization Dynamics and Rich Nonlinear Behaviors of ReLU Networks

Stability and Generalization of the Decentralized Stochastic Gradient Descent Ascent Algorithm

Parallel Submodular Function Minimization

Composable Coresets for Determinant Maximization: Greedy is Almost Optimal

Linear Time Algorithms for k-means with Multi-Swap Local Search

Rank-1 Matrix Completion with Gradient Descent and Small Random Initialization

Lookaround Optimizer: $k$ steps around, 1 step average

Sketching Algorithms for Sparse Dictionary Learning: PTAS and Turnstile Streaming

Label Correction of Crowdsourced Noisy Annotations with an Instance-Dependent Noise Transition Model

Generalized Belief Transport

On the Consistency of Maximum Likelihood Estimation of Probabilistic Principal Component Analysis

Conformal PID Control for Time Series Prediction

Self-Predictive Universal AI

Regret-Optimal Model-Free Reinforcement Learning for Discounted MDPs with Short Burn-In Time

Tackling Heavy-Tailed Rewards in Reinforcement Learning with Function Approximation: Minimax Optimal and Instance-Dependent Regret Bounds

Provably Efficient Offline Goal-Conditioned Reinforcement Learning with General Function Approximation and Single-Policy Concentrability

Finding Safe Zones of Markov Decision Processes Policies

Tempo Adaptation in Non-stationary Reinforcement Learning

FIND: A Function Description Benchmark for Evaluating Interpretability Methods

Facilitating Graph Neural Networks with Random Walk on Simplicial Complexes

Worst-case Performance of Popular Approximate Nearest Neighbor Search Implementations: Guarantees and Limitations

Streaming Algorithms and Lower Bounds for Estimating Correlation Clustering Cost

Variational Gaussian Processes with Decoupled Conditionals

Memory-Constrained Algorithms for Convex Optimization

Collaborative Alignment of NLP Models

Coherent Soft Imitation Learning

Lower Bounds on Adaptive Sensing for Matrix Recovery

Synthetic Combinations: A Causal Inference Framework for Combinatorial Interventions

Policy Finetuning in Reinforcement Learning via Design of Experiments using Offline Data

Large Language Models Are Zero-Shot Time Series Forecasters

Rubik's Cube: High-Order Channel Interactions with a Hierarchical Receptive Field

Shape Non-rigid Kinematics (SNK): A Zero-Shot Method for Non-Rigid Shape Matching via Unsupervised Functional Map Regularized Reconstruction

Text-to-Image Diffusion Models are Zero Shot Classifiers

Equivariant Adaptation of Large Pretrained Models

Single-Pass Pivot Algorithm for Correlation Clustering. Keep it simple!

Projection-Free Online Convex Optimization via Efficient Newton Iterations

Lift Yourself Up: Retrieval-augmented Text Generation with Self-Memory

Masked Space-Time Hash Encoding for Efficient Dynamic Scene Reconstruction

SQ Lower Bounds for Learning Mixtures of Linear Classifiers

Learning To Dive In Branch And Bound

Strategyproof Voting under Correlated Beliefs

Learning to Influence Human Behavior with Offline Reinforcement Learning

A Fractional Graph Laplacian Approach to Oversmoothing

Large language models implicitly learn to straighten neural sentence trajectories to construct a predictive representation of natural language.

Model Spider: Learning to Rank Pre-Trained Models Efficiently

Directional diffusion models for graph representation learning

AIMS: All-Inclusive Multi-Level Segmentation for Anything

Triple Eagle: Simple, Fast and Practical Budget-Feasible Mechanisms

Equivariant Flow Matching with Hybrid Probability Transport for 3D Molecule Generation

Simplifying Neural Network Training Under Class Imbalance

Graph-Structured Gaussian Processes for Transferable Graph Learning

Learning Modulated Transformation in GANs

Online (Multinomial) Logistic Bandit: Improved Regret and Constant Computation Cost

Sample based Explanations via Generalized Representers

A Unified Model and Dimension for Interactive Estimation

VaRT: Variational Regression Trees

Parameter-efficient Tuning of Large-scale Multimodal Foundation Model

Scan and Snap: Understanding Training Dynamics and Token Composition in 1-layer Transformer

Multi-Head Adapter Routing for Cross-Task Generalization

Symbolic Discovery of Optimization Algorithms

Causal Discovery from Subsampled Time Series with Proxy Variables

Unified Enhancement of Privacy Bounds for Mixture Mechanisms via $f$-Differential Privacy

A Finite-Sample Analysis of Payoff-Based Independent Learning in Zero-Sum Stochastic Games

Learning Cuts via Enumeration Oracles

RAPHAEL: Text-to-Image Generation via Large Mixture of Diffusion Paths

Partial Matrix Completion

The Rise of AI Language Pathologists: Exploring Two-level Prompt Learning for Few-shot Weakly-supervised Whole Slide Image Classification

Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task

Affinity-Aware Graph Networks

TWIGMA: A dataset of AI-Generated Images with Metadata From Twitter

Information Theoretic Lower Bounds for Information Theoretic Upper Bounds

Efficient Neural Music Generation

DELIFFAS: Deformable Light Fields for Fast Avatar Synthesis

Learning to Compress Prompts with Gist Tokens

(ends 10:45 AM)

Creative AI Session 3 [8:45-12:15]

Chairs: Jean Oh · Isabelle Guyon

s 8:45-12:15

[8:45] Archi Guesser - An AI Art Architecture Educational Game

[8:45] Collaborative Synthscapes from Words

[8:45] Creating Playful Comics Together with AI

[8:45] Q's Views #1-#3 (+1)

[8:45] Resonator: An AI-assisted Musical Experience for Human Connection

[8:45] salad bowl

[8:45] NeuroView: Generative Visualization of the Diversity of Brain Responses to Jazz

[8:45] Fusion: Landscape and Beyond

(ends 12:15 PM)

10:45 a.m.

Lunch (On Your Own)

12:15 p.m.

Invited Talk:

Online Reinforcement Learning in Digital Health Interventions

Susan Murphy

(ends 1:05 PM)

1 p.m.

Coffee Only

1:20 p.m.

Oral 6A LLMs [1:20-2:20]

Orals 1:20-2:20

[1:20] Are Emergent Abilities of Large Language Models a Mirage?

[1:35] Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

[1:50] The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

[2:05] Jailbroken: How Does LLM Safety Training Fail?

(ends 2:20 PM)

Oral 6B RL [1:20-2:20]

Orals 1:20-2:20

[1:20] When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment

[1:35] Bridging RL Theory and Practice with the Effective Horizon

[1:50] Direct Preference Optimization: Your Language Model is Secretly a Reward Model

[2:05] MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning

(ends 2:20 PM)

Oral 6C Vision [1:20-2:20]

Orals 1:20-2:20

[1:20] Siamese Masked Autoencoders

[1:35] Image Captioners Are Scalable Vision Learners Too

[1:50] The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

[2:05] Spatial-frequency channels, shape bias, and adversarial robustness

(ends 2:20 PM)

Oral 6D Theory [1:20-2:20]

Orals 1:20-2:20

[1:20] Optimal Learners for Realizable Regression: PAC Learning and Online Learning

[1:35] Random Cuts are Optimal for Explainable k-Medians

[1:50] Tester-Learners for Halfspaces: Universal Algorithms

[2:05] Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures

(ends 2:20 PM)

2:20 p.m.

Break

3 p.m.

Poster Session 6 [3:00-5:00]

Posters 3:00-5:00

Sample-efficient Multi-objective Molecular Optimization with GFlowNets

Tartarus: A Benchmarking Platform for Realistic And Practical Inverse Molecular Design

Graph Denoising Diffusion for Inverse Protein Folding

Uncovering Neural Scaling Laws in Molecular Representation Learning

ProteinShake: Building datasets and benchmarks for deep learning on protein structures

Lo-Hi: Practical ML Drug Discovery Benchmark

GAUCHE: A Library for Gaussian Processes in Chemistry

Benchmark of Machine Learning Force Fields for Semiconductor Simulations: Datasets, Metrics, and Comparative Analysis

DiffPack: A Torsional Diffusion Model for Autoregressive Protein Side-Chain Packing

What can Large Language Models do in chemistry? A comprehensive benchmark on eight tasks

WildfireSpreadTS: A dataset of multi-modal time series for wildfire spread prediction

ClimateLearn: Benchmarking Machine Learning for Weather and Climate Modeling

SatBird: a Dataset for Bird Species Distribution Modeling using Remote Sensing and Citizen Science Data

Digital Typhoon: Long-term Satellite Image Dataset for the Spatio-Temporal Modeling of Tropical Cyclones

BioMassters: A Benchmark Dataset for Forest Biomass Estimation using Multi-modal Satellite Time-series

FLAIR : a Country-Scale Land Cover Semantic Segmentation Dataset From Multi-Source Optical Imagery

STARSS23: An Audio-Visual Dataset of Spatial Recordings of Real Scenes with Spatiotemporal Annotations of Sound Events

Learning Human Action Recognition Representations Without Real Humans

MiliPoint: A Point Cloud Dataset for mmWave Radar

EgoTracks: A Long-term Egocentric Visual Object Tracking Dataset

Real-World Image Variation by Aligning Diffusion Inversion Chain

trajdata: A Unified Interface to Multiple Human Trajectory Datasets

FORB: A Flat Object Retrieval Benchmark for Universal Image Embedding

D$^2$CSG: Unsupervised Learning of Compact CSG Trees with Dual Complements and Dropouts

CL-NeRF: Continual Learning of Neural Radiance Fields for Evolving Scene Representation

MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion

InfoCD: A Contrastive Chamfer Distance Loss for Point Cloud Completion

H2RBox-v2: Incorporating Symmetry for Boosting Horizontal Box Supervised Oriented Object Detection

Revisiting Evaluation Metrics for Semantic Segmentation: Optimization and Evaluation of Fine-grained Intersection over Union

UDC-SIT: A Real-World Dataset for Under-Display Cameras

WBCAtt: A White Blood Cell Dataset Annotated with Detailed Morphological Attributes

Learning to Taste: A Multimodal Wine Dataset

OBELICS: An Open Web-Scale Filtered Dataset of Interleaved Image-Text Documents

VidChapters-7M: Video Chapters at Scale

Scalable 3D Captioning with Pretrained Models

A Step Towards Worldwide Biodiversity Assessment: The BIOSCAN-1M Insect Dataset

Diverse Shape Completion via Style Modulated Generative Adversarial Networks

Image Captioners Are Scalable Vision Learners Too

Robust Model Reasoning and Fitting via Dual Sparsity Pursuit

NAVI: Category-Agnostic Image Collections with High-Quality 3D Shape and Pose Annotations

PAD: A Dataset and Benchmark for Pose-agnostic Anomaly Detection

TOA: Task-oriented Active VQA

OBJECT 3DIT: Language-guided 3D-aware Image Editing

PGDiff: Guiding Diffusion Models for Versatile Face Restoration via Partial Guidance

A Dataset of Relighted 3D Interacting Hands

AV-NeRF: Learning Neural Fields for Real-World Audio-Visual Scene Synthesis

Occ3D: A Large-Scale 3D Occupancy Prediction Benchmark for Autonomous Driving

MagicBrush: A Manually Annotated Dataset for Instruction-Guided Image Editing

Humans in Kitchens: A Dataset for Multi-Person Human Motion Forecasting with Scene Context

EgoSchema: A Diagnostic Benchmark for Very Long-form Video Language Understanding

MM-Fi: Multi-Modal Non-Intrusive 4D Human Dataset for Versatile Wireless Sensing

SAMRS: Scaling-up Remote Sensing Segmentation Dataset with Segment Anything Model

GEO-Bench: Toward Foundation Models for Earth Monitoring

Auslan-Daily: Australian Sign Language Translation for Daily Communication and News

Perception Test: A Diagnostic Benchmark for Multimodal Video Models

ImageNet-Hard: The Hardest Images Remaining from a Study of the Power of Zoom and Spatial Biases in Image Classification

Estimating Generic 3D Room Structures from 2D Annotations

The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimation

OV-PARTS: Towards Open-Vocabulary Part Segmentation

Language-driven Scene Synthesis using Multi-conditional Diffusion Model

Seeing is not always believing: Benchmarking Human and Model Perception of AI-Generated Images

Temporal Continual Learning with Prior Compensation for Human Motion Prediction

Cheap and Quick: Efficient Vision-Language Instruction Tuning for Large Language Models

Modeling Human Visual Motion Processing with Trainable Motion Energy Sensing and a Self-attention Network

FD-Align: Feature Discrimination Alignment for Fine-tuning Pre-Trained Models in Few-Shot Learning

SODA: Robust Training of Test-Time Data Adaptors

The Drunkard’s Odometry: Estimating Camera Motion in Deforming Scenes

EPIC Fields: Marrying 3D Geometry and Video Understanding

Described Object Detection: Liberating Object Detection with Flexible Expressions

All Points Matter: Entropy-Regularized Distribution Alignment for Weakly-supervised 3D Segmentation

Motion-X: A Large-scale 3D Expressive Whole-body Human Motion Dataset

Object Reprojection Error (ORE): Camera pose benchmarks from lightweight tracking annotations

Objaverse-XL: A Universe of 10M+ 3D Objects

Compact Neural Volumetric Video Representations with Dynamic Codebooks

Ego4D Goal-Step: Toward Hierarchical Understanding of Procedural Activities

Emergent Communication in Interactive Sketch Question Answering

TransHP: Image Classification with Hierarchical Prompting

AVOIDDS: Aircraft Vision-based Intruder Detection Dataset and Simulator

OpenLane-V2: A Topology Reasoning Benchmark for Unified 3D HD Mapping

Visual Programming for Step-by-Step Text-to-Image Generation and Evaluation

LAMM: Language-Assisted Multi-Modal Instruction-Tuning Dataset, Framework, and Benchmark

E2PNet: Event to Point Cloud Registration with Spatio-Temporal Representation Learning

CycleNet: Rethinking Cycle Consistency in Text-Guided Diffusion for Image Manipulation

Unleashing the Full Potential of Product Quantization for Large-Scale Image Retrieval

Training Your Image Restoration Network Better with Random Weight Network as Optimization Function

RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation

Act As You Wish: Fine-Grained Control of Motion Diffusion Model with Hierarchical Semantic Graphs

Battle of the Backbones: A Large-Scale Comparison of Pretrained Models across Computer Vision Tasks

RIO: A Benchmark for Reasoning Intention-Oriented Objects in Open Environments

On Occlusions in Video Action Detection: Benchmark Datasets And Training Recipes

TradeMaster: A Holistic Quantitative Trading Platform Empowered by Reinforcement Learning

How to Data in Datathons

Parallel-mentoring for Offline Model-based Optimization

OpenProteinSet: Training data for structural biology at scale

RL-based Stateful Neural Adaptive Sampling and Denoising for Real-Time Path Tracing

AndroidInTheWild: A Large-Scale Dataset For Android Device Control

Suggesting Variable Order for Cylindrical Algebraic Decomposition via Reinforcement Learning

Realistic Synthetic Financial Transactions for Anti-Money Laundering Models

Lending Interaction Wings to Recommender Systems with Conversational Agents

Datasets and Benchmarks for Nanophotonic Structure and Parametric Design Simulations

Sounding Bodies: Modeling 3D Spatial Sound of Humans Using Body Pose and Audio

Pairwise GUI Dataset Construction Between Android Phones and Tablets

Interpreting Unsupervised Anomaly Detection in Security via Rule Extraction

DISCO-10M: A Large-Scale Music Dataset

MVDoppler: Unleashing the Power of Multi-View Doppler for MicroMotion-based Gait Classification

DiffTraj: Generating GPS Trajectory with Diffusion Probabilistic Model

Hyper-Skin: A Hyperspectral Dataset for Reconstructing Facial Skin-Spectra from RGB Images

Deep Momentum Multi-Marginal Schrödinger Bridge

CHAMMI: A benchmark for channel-adaptive models in microscopy imaging

Into the Single Cell Multiverse: an End-to-End Dataset for Procedural Knowledge Extraction in Biomedical Texts

ProteinInvBench: Benchmarking Protein Inverse Folding on Diverse Tasks, Models, and Metrics

NIS3D: A Completely Annotated Benchmark for Dense 3D Nuclei Image Segmentation

SG×P : A Sorghum Genotype × Phenotype Prediction Dataset and Benchmark

CSMeD: Bridging the Dataset Gap in Automated Citation Screening for Systematic Literature Reviews

PPi: Pretraining Brain Signal Model for Patient-independent Seizure Detection

SARAMIS: Simulation Assets for Robotic Assisted and Minimally Invasive Surgery

Intelligent Knee Sleeves: A Real-time Multimodal Dataset for 3D Lower Body Motion Estimation Using Smart Textile

MedSat: A Public Health Dataset for England Featuring Medical Prescriptions and Satellite Imagery

Benchmarking Encoder-Decoder Architectures for Biplanar X-ray to 3D Bone Shape Reconstruction

YouTubePD: A Multimodal Benchmark for Parkinson’s Disease Analysis

Uncertainty Estimation for Safety-critical Scene Segmentation via Fine-grained Reward Maximization

Temporal Causal Mediation through a Point Process: Direct and Indirect Effects of Healthcare Interventions

EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models

Multimodal Clinical Benchmark for Emergency Care (MC-BEC): A Comprehensive Benchmark for Evaluating Foundation Models in Emergency Medicine

LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day

INSPECT: A Multimodal Dataset for Patient Outcome Prediction of Pulmonary Embolisms

ECG-QA: A Comprehensive Question Answering Dataset Combined With Electrocardiogram

Knowledge-based in silico models and dataset for the comparative evaluation of mammography AI for a range of breast characteristics, lesion conspicuities and doses

LoRA: A Logical Reasoning Augmented Dataset for Visual Question Answering

Self-Refine: Iterative Refinement with Self-Feedback

QATCH: Benchmarking SQL-centric tasks with Table Representation Learning Models on Your Data

Alexa Arena: A User-Centric Interactive Platform for Embodied AI

CMMA: Benchmarking Multi-Affection Detection in Chinese Multi-Modal Conversations

Mind2Web: Towards a Generalist Agent for the Web

HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face

Text Alignment Is An Efficient Unified Model for Massive NLP Tasks

Reflexion: language agents with verbal reinforcement learning

DinoSR: Self-Distillation and Online Clustering for Self-supervised Speech Representation Learning

BenchCLAMP: A Benchmark for Evaluating Language Models on Syntactic and Semantic Parsing

Beyond MLE: Convex Learning for Text Generation

Knowledge-Augmented Reasoning Distillation for Small Language Models in Knowledge-Intensive Tasks

Benchmarking Foundation Models with Language-Model-as-an-Examiner

A Massive Scale Semantic Similarity Dataset of Historical English

FACE: Evaluating Natural Language Generation with Fourier Analysis of Cross-Entropy

Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs

M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models

CARE-MI: Chinese Benchmark for Misinformation Evaluation in Maternity and Infant Care

InterCode: Standardizing and Benchmarking Interactive Coding with Execution Feedback

YouTube-ASL: A Large-Scale, Open-Domain American Sign Language-English Parallel Corpus

MultiVENT: Multilingual Videos of Events and Aligned Natural Text

FELM: Benchmarking Factuality Evaluation of Large Language Models

Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning

American Stories: A Large-Scale Structured Text Dataset of Historical U.S. Newspapers

PTADisc: A Cross-Course Dataset Supporting Personalized Learning in Cold-Start Scenarios

The ToMCAT Dataset

The Simplicity Bias in Multi-Task RNNs: Shared Attractors, Reuse of Dynamics, and Geometric Representation

Decoding the Enigma: Benchmarking Humans and AIs on the Many Facets of Working Memory

A Bounded Ability Estimation for Computerized Adaptive Testing

Physion++: Evaluating Physical Scene Understanding that Requires Online Inference of Different Physical Properties

SEVA: Leveraging sketches to evaluate alignment between human and machine visual abstraction

Transformer as a hippocampal memory consolidation model based on NMDAR-inspired nonlinearity

Hyper-HMM: aligning human brains and semantic features in a common latent event space

Interactive Visual Reasoning under Uncertainty

Bypassing spike sorting: Density-based decoding using spike localization from dense multielectrode probes

Understanding Social Reasoning in Language Models with Language Models

Curriculum Learning With Infant Egocentric Videos

Adaptive whitening with fast gain modulation and slow synaptic plasticity

A Unified, Scalable Framework for Neural Population Decoding

Enhancing Knowledge Transfer for Task Incremental Learning with Data-free Subnetwork

A generative model of the hippocampal formation trained with theta driven local learning rules

Probabilistic inverse optimal control for non-linear partially observable systems disentangles perceptual uncertainty and behavioral costs

SparseProp: Efficient Event-Based Simulation and Training of Sparse Recurrent Spiking Neural Networks

LithoBench: Benchmarking AI Computational Lithography for Semiconductor Manufacturing

LagrangeBench: A Lagrangian Fluid Mechanics Benchmarking Suite

Neural Ideal Large Eddy Simulation: Modeling Turbulence with Neural Stochastic Differential Equations

M$^2$Hub: Unlocking the Potential of Machine Learning for Materials Discovery

RoboHive: A Unified Framework for Robot Learning

Safety Gymnasium: A Unified Safe Reinforcement Learning Benchmark

The Waymo Open Sim Agents Challenge

HOH: Markerless Multimodal Human-Object-Human Handover Dataset with Large Object Count

CaMP: Causal Multi-policy Planning for Interactive Navigation in Multi-room Scenes

SiT Dataset: Socially Interactive Pedestrian Trajectory Dataset for Social Navigation Robots

BuildingsBench: A Large-Scale Dataset of 900K Buildings and Benchmark for Short-Term Load Forecasting

WITRAN: Water-wave Information Transmission and Recurrent Acceleration Network for Long-range Time Series Forecasting

BasisFormer: Attention-based Time Series Forecasting with Learnable and Interpretable Basis

A Dataset for Analyzing Streaming Media Performance over HTTP/3 Browsers

CrossGNN: Confronting Noisy Multivariate Time Series Via Cross Interaction Refinement

Data Pruning via Moving-one-Sample-out

Scientific Document Retrieval using Multi-level Aspect-based Queries

Data Portraits: Recording Foundation Model Training Data

Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias

SugarCrepe: Fixing Hackable Benchmarks for Vision-Language Compositionality

D4: Improving LLM Pretraining via Document De-Duplication and Diversification

Towards a Comprehensive Benchmark for High-Level Synthesis Targeted to FPGAs

Massively Multilingual Corpus of Sentiment Datasets and Multi-faceted Sentiment Classification Benchmark

Residual Alignment: Uncovering the Mechanisms of Residual Networks

Direct Preference Optimization: Your Language Model is Secretly a Reward Model

Lung250M-4B: A Combined 3D Dataset for CT- and Point Cloud-Based Intra-Patient Lung Registration

The Tunnel Effect: Building Data Representations in Deep Neural Networks

Algorithm Selection for Deep Active Learning with Imbalanced Datasets

Going Beyond Linear Mode Connectivity: The Layerwise Linear Feature Connectivity

ADGym: Design Choices for Deep Anomaly Detection

Understanding How Consistency Works in Federated Learning via Stage-wise Relaxed Initialization

Improving *day-ahead* Solar Irradiance Time Series Forecasting by Leveraging Spatio-Temporal Context

Grounding Neural Inference with Satisfiability Modulo Theories

A Comprehensive Benchmark for Neural Human Radiance Fields

Sampling weights of deep neural networks

VAST: A Vision-Audio-Subtitle-Text Omni-Modality Foundation Model and Dataset

No Train No Gain: Revisiting Efficient Training Algorithms For Transformer-based Language Models

Dynamic Context Pruning for Efficient and Interpretable Autoregressive Transformers

$S^3$: Increasing GPU Utilization during Generative Inference for Higher Throughput

Pre-RMSNorm and Pre-CRMSNorm Transformers: Equivalent and Efficient Pre-LN Transformers

Quantizable Transformers: Removing Outliers by Helping Attention Heads Do Nothing

XES3G5M: A Knowledge Tracing Benchmark Dataset with Auxiliary Information

Stable and low-precision training for large-scale vision-language models

Label-Retrieval-Augmented Diffusion Models for Learning from Noisy Labels

Stable Diffusion is Unstable

InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

Compositional Sculpting of Iterative Generative Processes

Cocktail: Mixing Multi-Modality Control for Text-Conditional Image Generation

Calibrating Neural Simulation-Based Inference with Differentiable Coverage Probability

Dissecting Chain-of-Thought: Compositionality through In-Context Filtering and Learning

Reimagining Synthetic Tabular Data Generation through Data-Centric AI: A Comprehensive Benchmark

Dynamically Masked Discriminator for GANs

A Regularized Conditional GAN for Posterior Sampling in Image Recovery Problems

Revisiting the Evaluation of Image Synthesis with GANs

Benchmarking Large Language Models on CMExam - A comprehensive Chinese Medical Exam Dataset

Benchmarking and Analyzing 3D-aware Image Synthesis with a Modularized Codebase

CAPP-130: A Corpus of Chinese Application Privacy Policy Summarization and Interpretation

UniControl: A Unified Diffusion Model for Controllable Visual Generation In the Wild

One-Line-of-Code Data Mollification Improves Optimization of Likelihood-based Generative Models

GenEval: An object-focused framework for evaluating text-to-image alignment

Star-Shaped Denoising Diffusion Probabilistic Models

Trans-Dimensional Generative Modeling via Jump Diffusion Models

Building the Bridge of Schrödinger: A Continuous Entropic Optimal Transport Benchmark

High-dimensional Asymptotics of Denoising Autoencoders

The RefinedWeb Dataset for Falcon LLM: Outperforming Curated Corpora with Web Data Only

SnapFusion: Text-to-Image Diffusion Model on Mobile Devices within Two Seconds

Extremal Domain Translation with Neural Optimal Transport

Canonical normalizing flows for manifold learning

Restart Sampling for Improving Generative Processes

OpenAGI: When LLM Meets Domain Experts

Leveraging Early-Stage Robustness in Diffusion Models for Efficient and High-Quality Image Synthesis

Optimality of Message-Passing Architectures for Sparse Graphs

Graph Neural Networks for Road Safety Modeling: Datasets and Evaluations for Accident Analysis

Expressivity-Preserving GNN Simulation

Latent Graph Inference with Limited Supervision

Improving Self-supervised Molecular Representation Learning using Persistent Homology

A Neural Collapse Perspective on Feature Evolution in Graph Neural Networks

FiGURe: Simple and Efficient Unsupervised Node Representations with Filter Augmentations

On Class Distributions Induced by Nearest Neighbor Graphs for Node Classification of Tabular Data

Tailoring Self-Attention for Graph via Rooted Subtrees

Evaluating Graph Neural Networks for Link Prediction: Current Pitfalls and New Benchmarking

Uncertainty Quantification over Graph with Conformalized Graph Neural Networks

Fused Gromov-Wasserstein Graph Mixup for Graph-level Classifications

The expressive power of pooling in Graph Neural Networks

Towards Better Dynamic Graph Learning: New Architecture and Unified Library

Graph Clustering with Graph Neural Networks

GLEMOS: Benchmark for Instantaneous Graph Learning Model Selection

Neural Algorithmic Reasoning Without Intermediate Supervision

NeuroGraph: Benchmarks for Graph Machine Learning in Brain Connectomics

GADBench: Revisiting and Benchmarking Supervised Graph Anomaly Detection

PlanE: Representation Learning over Planar Graphs

Human-Guided Complexity-Controlled Abstractions

Balanced Training for Sparse GANs

ID and OOD Performance Are Sometimes Inversely Correlated on Real-world Datasets

Revealing the unseen: Benchmarking video action recognition under occlusion

How hard are computer vision datasets? Calibrating dataset difficulty to viewing time

On Evaluating Adversarial Robustness of Large Vision-Language Models

QuadAttac$K$: A Quadratic Programming Approach to Learning Ordered Top-$K$ Adversarial Attacks

Complementary Benefits of Contrastive Learning and Self-Training Under Distribution Shift

Can You Rely on Your Model Evaluation? Improving Model Evaluation with Synthetic Test Data

COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs

Benchmarking Robustness of Adaptation Methods on Pre-trained Vision-Language Models

PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning

Benchmarking Distribution Shift in Tabular Data with TableShift

Adversarial Robustness in Graph Neural Networks: A Hamiltonian Approach

Revisiting Adversarial Robustness Distillation from the Perspective of Robust Fairness

Benchmarking Robustness to Adversarial Image Obfuscations

Exploring Geometry of Blind Spots in Vision models

Maximization of Average Precision for Deep Learning with Adversarial Ranking Robustness

Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration

Contextually Affinitive Neighborhood Refinery for Deep Clustering

HASSOD: Hierarchical Adaptive Self-Supervised Object Detection

Object-Centric Learning for Real-World Videos by Predicting Temporal Feature Similarities

Self-supervised video pretraining yields robust and more human-aligned visual representations

LVM-Med: Learning Large-Scale Self-Supervised Vision Models for Medical Imaging via Second-order Graph Matching

StableRep: Synthetic Images from Text-to-Image Models Make Strong Visual Representation Learners

Siamese Masked Autoencoders

Implicit variance regularization in non-contrastive SSL

A Novel Approach for Effective Multi-View Clustering with Information-Theoretic Perspective

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

ForecastPFN: Synthetically-Trained Zero-Shot Forecasting

Encoding Time-Series Explanations through Self-Supervised Model Behavior Consistency

Deep Equilibrium Based Neural Operators for Steady-State PDEs

What can a Single Attention Layer Learn? A Study Through the Random Features Lens

Deep Neural Collapse Is Provably Optimal for the Deep Unconstrained Features Model

Learning Curves for Noisy Heterogeneous Feature-Subsampled Ridge Ensembles

PAC-Bayesian Spectrally-Normalized Bounds for Adversarially Robust Generalization

Optimal approximation using complex-valued neural networks

Feature learning via mean-field Langevin dynamics: classifying sparse parities and beyond

A Logic for Expressing Log-Precision Transformers

Learning a 1-layer conditional generative model in total variation

Learning a Neuron by a Shallow ReLU Network: Dynamics and Implicit Bias for Correlated Inputs

Learning Causal Models under Independent Changes

Do Not Marginalize Mechanisms, Rather Consolidate!

BayesDAG: Gradient-Based Posterior Inference for Causal Discovery

Unpaired Multi-Domain Causal Representation Learning

Generator Identification for Linear SDEs with Additive and Multiplicative Noise

Optimal Treatment Regimes for Proximal Causal Learning

Sample Complexity Bounds for Score-Matching: Causal Discovery and Generative Modeling

FAST: a Fused and Accurate Shrinkage Tree for Heterogeneous Treatment Effects Estimation

Characterization and Learning of Causal Graphs with Small Conditioning Sets

A Scale-Invariant Sorting Criterion to Find a Causal Order in Additive Noise Models

Toolbox for Multimodal Learn (scikit-multimodallearn)

A benchmark of categorical encoders for binary classification

Does Continual Learning Meet Compositionality? New Benchmarks and An Evaluation Framework

AQuA: A Benchmarking Tool for Label Quality Assessment

Network Regression with Graph Laplacians

Variational Gibbs Inference for Statistical Model Estimation from Incomplete Data

Sharp Calibrated Gaussian Processes

MMD Aggregated Two-Sample Test

Kernelized Cumulants: Beyond Kernel Mean Embeddings

Annotator: A Generic Active Learning Baseline for LiDAR Semantic Segmentation

Not All Neuro-Symbolic Concepts Are Created Equal: Analysis and Mitigation of Reasoning Shortcuts

Achieving Cross Modal Generalization with Multimodal Unified Representation

Imagine the Unseen World: A Benchmark for Systematic Generalization in Visual World Models

Fundamental Limits and Tradeoffs in Invariant Representation Learning

Transitivity Recovering Decompositions: Interpretable and Robust Fine-Grained Relationships

URL: A Representation Learning Benchmark for Transferable Uncertainty Estimates

MARBLE: Music Audio Representation Benchmark for Universal Evaluation

Uncovering Meanings of Embeddings via Partial Orthogonality

Are Emergent Abilities of Large Language Models a Mirage?

An Efficient and Robust Framework for Approximate Nearest Neighbor Search with Attribute Constraint

QuIP: 2-Bit Quantization of Large Language Models With Guarantees

SPACE: Single-round Participant Amalgamation for Contribution Evaluation in Federated Learning

Towards Data-Agnostic Pruning At Initialization: What Makes a Good Sparse Mask?

Fast Online Changepoint Detection via Functional Pruning CUSUM Statistics

Augmented Memory Replay-based Continual Learning Approaches for Network Intrusion Detection

An Optimization-based Approach To Node Role Discovery in Networks: Approximating Equitable Partitions

Retrieval-Augmented Multiple Instance Learning

An Empirical Investigation of the Role of Pre-training in Lifelong Learning

TIES-Merging: Resolving Interference When Merging Models

Practical Equivariances via Relational Conditional Neural Processes

Online Constrained Meta-Learning: Provable Guarantees for Generalization

Focus Your Attention when Few-Shot Classification

Minimax Forward and Backward Learning of Evolving Tasks with Performance Guarantees

Meta-in-context learning in large language models

Secure Out-of-Distribution Task Generalization with Energy-Based Models

Recasting Continual Learning as Sequence Modeling

Task Arithmetic in the Tangent Space: Improved Editing of Pre-Trained Models

Does progress on ImageNet transfer to real-world datasets?

Data Selection for Language Models via Importance Resampling

Optimal Block-wise Asymmetric Graph Construction for Graph-based Semi-supervised Learning

Boosting Spectral Clustering on Incomplete Data via Kernel Correction and Affinity Learning

InstanT: Semi-supervised Learning with Instance-dependent Thresholds

Discover and Align Taxonomic Context Priors for Open-world Semi-Supervised Learning

Unsupervised Semantic Correspondence Using Stable Diffusion

The Pursuit of Human Labeling: A New Perspective on Unsupervised Learning

On the Overlooked Pitfalls of Weight Decay and How to Mitigate Them: A Gradient-Norm Perspective

Riemannian SAM: Sharpness-Aware Minimization on Riemannian Manifolds

Bilevel Optimization with a Lower-level Contraction: Optimal Sample Complexity without Warm-Start

Operation-Level Early Stopping for Robustifying Differentiable NAS

An Alternating Optimization Method for Bilevel Problems under the Polyak-Łojasiewicz Condition

Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control

Searching for Optimal Per-Coordinate Step-sizes with Multidimensional Backtracking

Time-Reversed Dissipation Induces Duality Between Minimizing Gradient Norm and Function Value

Let the Flows Tell: Solving Graph Combinatorial Problems with GFlowNets

Faster Discrete Convex Function Minimization with Predictions: The M-Convex Case

Accelerated Quasi-Newton Proximal Extragradient: Faster Rate for Smooth Convex Optimization

Epidemic Learning: Boosting Decentralized Learning with Randomized Communication

Federated Learning with Bilateral Curation for Partially Class-Disjoint Data

Federated Compositional Deep AUC Maximization

Towards Federated Foundation Models: Scalable Dataset Pipelines for Group-Structured Learning

Towards Personalized Federated Learning via Heterogeneous Model Reassembly

Mechanic: A Learning Rate Tuner

Alternating Gradient Descent and Mixture-of-Experts for Integrated Multimodal Perception

FAMO: Fast Adaptive Multitask Optimization

Personalized Dictionary Learning for Heterogeneous Datasets

Closing the gap between the upper bound and lower bound of Adam's iteration complexity

Convergence of Adam Under Relaxed Assumptions

Efficient Robust Bayesian Optimization for Arbitrary Uncertain inputs

Outlier-Robust Wasserstein DRO

Knowledge Distillation Performs Partial Variance Reduction

Single-Call Stochastic Extragradient Methods for Structured Non-monotone Variational Inequalities: Improved Analysis under Weaker Conditions

PriorBand: Practical Hyperparameter Optimization in the Age of Deep Learning

Robust Bayesian Satisficing

MetaBox: A Benchmark Platform for Meta-Black-Box Optimization with Reinforcement Learning

Beyond Unimodal: Generalising Neural Processes for Multimodal Uncertainty Estimation

Generalized Information-theoretic Multi-view Clustering

ContinuAR: Continuous Autoregression For Infinite-Fidelity Fusion

Physics-Informed Bayesian Optimization of Variational Quantum Circuits

Conditional score-based diffusion models for Bayesian inference in infinite dimensions

Intrinsic Gaussian Process on Unknown Manifolds with Probabilistic Metrics

Credal Marginal MAP

Quasi-Monte Carlo Graph Random Features

Stein $\Pi$-Importance Sampling

The Graph Pencil Method: Mapping Subgraph Densities to Stochastic Block Models

Sparse Graph Learning from Spatiotemporal Time Series

A Unified Framework for Uniform Signal Recovery in Nonlinear Generative Compressed Sensing

Breadcrumbs to the Goal: Goal-Conditioned Exploration from Human-in-the-Loop Feedback

Consistent Aggregation of Objectives with Diverse Time Preferences Requires Non-Markovian Rewards

Efficient Symbolic Policy Learning with Differentiable Symbolic Expression

Natural Actor-Critic for Robust Reinforcement Learning with Function Approximation

Semantic HELM: A Human-Readable Memory for Reinforcement Learning

Would I have gotten that reward? Long-term credit assignment by counterfactual contribution analysis

Minigrid & Miniworld: Modular & Customizable Reinforcement Learning Environments for Goal-Oriented Tasks

Katakomba: Tools and Benchmarks for Data-Driven NetHack

SafeDICE: Offline Safe Imitation Learning with Non-Preferred Demonstrations

Hokoff: Real Game Dataset from Honor of Kings and its Offline Reinforcement Learning Benchmarks

Offline RL with Discrete Proxy Representations for Generalizability in POMDPs

CEIL: Generalized Contextual Imitation Learning

Survival Instinct in Offline Reinforcement Learning

Decision Stacks: Flexible Reinforcement Learning via Modular Generative Models

Combinatorial Optimization with Policy Adaptation using Latent Space Search

Pgx: Hardware-Accelerated Parallel Game Simulators for Reinforcement Learning

A Toolkit for Reliable Benchmarking and Research in Multi-Objective Reinforcement Learning

Understanding and Addressing the Pitfalls of Bisimulation-based Representations in Offline Reinforcement Learning

When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment

Generalized Weighted Path Consistency for Mastering Atari Games

Self-Supervised Reinforcement Learning that Transfers using Random Features

Winner Takes It All: Training Performant RL Populations for Combinatorial Optimization

Belief Projection-Based Reinforcement Learning for Environments with Delayed Feedback

RL-ViGen: A Reinforcement Learning Benchmark for Visual Generalization

Small batch deep reinforcement learning

NetHack is Hard to Hack

BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset

Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion

Ignorance is Bliss: Robust Control via Information Gating

CQM: Curriculum Reinforcement Learning with a Quantized World Model

Rewiring Neurons in Non-Stationary Environments

A Robust and Opponent-Aware League Training Method for StarCraft II

Gigastep - One Billion Steps per Second Multi-agent Reinforcement Learning

OFCOURSE: A Multi-Agent Reinforcement Learning Environment for Order Fulfillment

Hierarchical Multi-Agent Skill Discovery

Tracr: Compiled Transformers as a Laboratory for Interpretability

GEX: A flexible method for approximating influence via Geometric Ensemble

Robust Data Valuation with Weighted Banzhaf Values

What is Flagged in Uncertainty Quantification? Latent Density Models for Uncertainty Categorization

The Clock and the Pizza: Two Stories in Mechanistic Explanation of Neural Networks

Error Discovery By Clustering Influence Embeddings

DISCOVER: Making Vision Networks Interpretable via Competition and Dissection

[Re] FOCUS: Flexible Optimizable Counterfactual Explanations for Tree Ensembles

Building Socio-culturally Inclusive Stereotype Resources with Community Engagement

Doubly Constrained Fair Clustering

GeoDE: a Geographically Diverse Evaluation Dataset for Object Recognition

Scalable Fair Influence Maximization

Fair Graph Distillation

VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution

DICES Dataset: Diversity in Conversational AI Evaluation for Safety

Into the LAION’s Den: Investigating Hate in Multimodal Datasets

Dream the Impossible: Outlier Imagination with Diffusion Models

Consensus and Subjectivity of Skin Tone Annotation for ML Fairness

Diverse Community Data for Benchmarking Data Privacy Algorithms

(Amplified) Banded Matrix Factorization: A unified approach to private training

Flocks of Stochastic Parrots: Differentially Private Prompt Learning for Large Language Models

What Can We Learn from Unlearnable Datasets?

Bullying10K: A Large-Scale Neuromorphic Dataset towards Privacy-Preserving Bullying Recognition

Counting Distinct Elements Under Person-Level Differential Privacy

Understanding Deep Gradient Leakage via Inversion Influence Functions

Sparsity-Preserving Differentially Private Training of Large Embedding Models

Fed-FA: Theoretically Modeling Client Data Divergence for Federated Language Backdoor Defense

VisAlign: Dataset for Measuring the Alignment between AI and Humans in Visual Perception

Static and Sequential Malicious Attacks in the Context of Selective Forgetting

Proximity-Informed Calibration for Deep Neural Networks

Understanding the detrimental class-level effects of data augmentation

Automated Classification of Model Errors on ImageNet

Multi-scale Diffusion Denoised Smoothing

Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examples

Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyond

A Closer Look at the Robustness of Contrastive Language-Image Pre-Training (CLIP)

Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspective

Enhancing Adversarial Contrastive Learning via Adversarial Invariant Regularization

D-Separation for Causal Self-Explanation

DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection

On the Need for a Language Describing Distribution Shifts: Illustrations on Tabular Datasets

Jailbroken: How Does LLM Safety Training Fail?

Active Learning for Semantic Segmentation with Multi-class Label Query

Comparing Apples to Oranges: Learning Similarity Functions for Data Produced by Different Distributions

MADG: Margin-based Adversarial Learning for Domain Generalization

Large Language Models are Fixated by Red Herrings: Exploring Creative Problem Solving and Einstellung Effect using the Only Connect Wall Dataset

Fitting trees to $\ell_1$-hyperbolic distances

Distribution-Free Model-Agnostic Regression Calibration via Nonparametric Methods

Exponential Lower Bounds for Fictitious Play in Potential Games

Higher-Order Uncoupled Dynamics Do Not Lead to Nash Equilibrium - Except When They Do

Calibrating “Cheap Signals” in Peer Review without a Prior

Mechanism Design for Collaborative Normal Mean Estimation

Computing Optimal Equilibria and Mechanisms via Learning in Zero-Sum Extensive-Form Games

New Complexity-Theoretic Frontiers of Tractability for Neural Network Training

Tester-Learners for Halfspaces: Universal Algorithms

Adversarial Resilience in Sequential Prediction via Abstention

Stability of Random Forests and Coverage of Random-Forest Prediction Intervals

The Bayesian Stability Zoo

Three-Way Trade-Off in Multi-Objective Learning: Optimization, Generalization and Conflict-Avoidance

Collaboratively Learning Linear Models with Structured Missing Data

Mind the spikes: Benign overfitting of kernels and neural networks in fixed dimension

Random Cuts are Optimal for Explainable k-Medians

Minimax Optimal Rate for Parameter Estimation in Multivariate Deviated Models

Provable benefits of score matching

Multiclass Boosting: Simple and Intuitive Weak Learning Criteria

The Geometry of Neural Nets' Parameter Spaces Under Reparametrization

Improved Algorithms for Stochastic Linear Bandits Using Tail Bounds for Martingale Mixtures

Online Corrupted User Detection and Regret Minimization

Kullback-Leibler Maillard Sampling for Multi-armed Bandits with Bounded Rewards

Statistical Limits of Adaptive Linear Models: Low-Dimensional Estimation and Inference

Optimal Regret Is Achievable with Bounded Approximate Inference Error: An Enhanced Bayesian Upper Confidence Bound Framework

Adaptive Algorithms for Relaxed Pareto Set Identification

Small Total-Cost Constraints in Contextual Bandits with Knapsacks, with Application to Fairness

Non-Stationary Bandits with Auto-Regressive Temporal Dependency

Adaptive Linear Estimating Equations

Exploiting Correlated Auxiliary Feedback in Parameterized Bandits

An Exploration-by-Optimization Approach to Best of Both Worlds in Linear Bandits

Covariance-adaptive best arm identification

Online List Labeling with Predictions

The Separation Capacity of Random Neural Networks

Concentration analysis of multivariate elliptic diffusions

Conditional Distribution Function Estimation Using Neural Networks for Censored and Uncensored Data

Is RLHF More Difficult than Standard RL? A Theoretical Perspective

Bridging RL Theory and Practice with the Effective Horizon

Optimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL

Replicable Reinforcement Learning

On Sample-Efficient Offline Reinforcement Learning: Data Diversity, Posterior Sampling and Beyond

A Novel Framework for Policy Mirror Descent with General Parameterization and Linear Convergence

Rethinking Incentives in Recommender Systems: Are Monotone Rewards Always Beneficial?

[Re] Bandit Theory and Thompson Sampling-guided Directed Evolution for Sequence Optimization

[Re] On Explainability of Graph Neural Networks via Subgraph Explorations

[Re] $\mathcal{G}$-Mixup: Graph Data Augmentation for Graph Classification

[Re] End-to-end Algorithm Synthesis with Recurrent Networks: Logical Extrapolation Without Overthinking

[Re] Fairness Guarantees under Demographic Shift

[Re] Numerical influence of ReLU'(0) on backpropagation

Reproducibility Study of ”Label-Free Explainability for Unsupervised Models”

$\mathbf{\mathbb{E}^{FWI}}$: Multiparameter Benchmark Datasets for Elastic Full Waveform Inversion of Geophysical Properties

RELIC: Reproducibility and Extension on LIC metric in quantifying bias in captioning models

[Re] CrossWalk: Fairness-enhanced Node Representation Learning

[Re] Pure Noise to the Rescue of Insufficient Data

Evaluating Open-QA Evaluation

On the Importance of Exploration for Generalization in Reinforcement Learning

RealTime QA: What's the Answer Right Now?

Weakly-Supervised Audio-Visual Segmentation

Structured Voronoi Sampling

Optimal Learners for Realizable Regression: PAC Learning and Online Learning

Ambient Diffusion: Learning Clean Distributions from Corrupted Data

Granger Components Analysis: Unsupervised learning of latent temporal dependencies

VillanDiffusion: A Unified Backdoor Attack Framework for Diffusion Models

FedNAR: Federated Optimization with Normalized Annealing Regularization

Stochastic Distributed Optimization under Average Second-order Similarity: Algorithms and Analysis

ReDS: Offline RL With Heteroskedastic Datasets via Support Constraints

Optimized Covariance Design for AB Test on Social Network under Interference

Easy Bayesian Transfer Learning with Informative Priors

SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning

Molecule Joint Auto-Encoding: Trajectory Pretraining with 2D and 3D Diffusion

Reproducibility Study of “Quantifying Societal Bias Amplification in Image Captioning”

P-Flow: A Fast and Data-Efficient Zero-Shot TTS through Speech Prompting

Color Equivariant Convolutional Networks

Spatial-frequency channels, shape bias, and adversarial robustness

[Re] On the Reproducibility of CartoonX

Optimal Algorithms for the Inhomogeneous Spiked Wigner Model

[Re] Exploring the Role of Grammar and Word Choice in Bias Toward African American English (AAE) in Hate Speech Classification

Inference for Gaussian Processes with Matern Covariogram on Compact Riemannian Manifolds

MLFMF: Data Sets for Machine Learning for Mathematical Formalization

Scalable Membership Inference Attacks via Quantile Regression

Generating QM1B with PySCF$_{\text{IPU}}$

Online robust non-stationary estimation

Learning from Rich Semantics and Coarse Locations for Long-tailed Object Detection

Progressive Ensemble Distillation: Building Ensembles for Efficient Inference

Neural MMO 2.0: A Massively Multi-task Addition to Massively Multi-agent Learning

[Re] On the Reproducibility of “FairCal: Fairness Calibration for Face Verification”

Event Stream GPT: A Data Pre-processing and Modeling Library for Generative, Pre-trained Transformers over Continuous-time Sequences of Complex Events

$\mathcal{M}^4$: A Unified XAI Benchmark for Faithfulness Evaluation of Feature Attribution Methods across Metrics, Modalities and Models

Thin and deep Gaussian processes

Reproducibility study of the Fairness-enhanced Node Representation Learning

When Do Neural Nets Outperform Boosted Trees on Tabular Data?

[Re] Variational Neural Cellular Automata

Towards Hybrid-grained Feature Interaction Selection for Deep Sparse Network

(ends 5:00 PM)

5 p.m.

Creative AI Performances 2 [5:00-7:00]

Chairs: Jean Oh · Isabelle Guyon

s 5:00-6:45

[5:00] Resonator: An AI-assisted Musical Experience for Human Connection

[5:00] Fusion: Landscape and Beyond

[5:00] Emergent Rhythm — Real-time AI Generative DJ Set

[5:00] The WHOOPS! Gallery: An Intersection of AI, Creativity, and the Unusual

[5:00] Entanglement

[5:00] Kiss/Crash

[6:00] Collaborative Synthscapes from Words

(ends 7:00 PM)

Town Hall:

Town Hall

(ends 6:00 PM)

6 p.m.

Reception:

Closing Reception

(ends 7:00 PM)

FRI 15 DEC

5:30 a.m.

Registration Desk

(ends 2:00 PM)

6:15 a.m.

Workshop:

UniReps: Unifying Representations in Neural Models

(ends 3:15 PM)

Workshop:

Deep Generative Models for Health

(ends 3:30 PM)

Workshop:

Causal Representation Learning

(ends 3:30 PM)

Workshop:

New Frontiers of AI for Drug Discovery and Development

(ends 3:20 PM)

Workshop:

Touch Processing: a new Sensing Modality for AI

(ends 3:30 PM)

Workshop:

NeurIPS 2023 Workshop: Machine Learning and the Physical Sciences

(ends 3:30 PM)

Workshop:

Associative Memory & Hopfield Networks in 2023

(ends 3:30 PM)

Workshop:

Foundation Models for Decision Making

(ends 3:30 PM)

Workshop:

Information-Theoretic Principles in Cognitive Systems (InfoCog)

(ends 3:30 PM)

Workshop:

AI for Accelerated Materials Design (AI4Mat-2023)

(ends 3:30 PM)

Workshop:

Generative AI for Education (GAIED): Advances, Opportunities, and Challenges

(ends 3:30 PM)

6:30 a.m.

Workshop:

Instruction Tuning and Instruction Following

(ends 3:30 PM)

Workshop:

Machine Learning in Structural Biology Workshop

(ends 3:05 PM)

Workshop:

Table Representation Learning Workshop

(ends 3:30 PM)

Competition:

Causal Structure Learning from Event Sequences and Prior Knowledge

(ends 10:00 AM)

6:35 a.m.

Competition:

Melting Pot Contest

(ends 10:00 AM)

6:45 a.m.

Workshop:

Attributing Model Behavior at Scale (ATTRIB)

(ends 3:30 PM)

Workshop:

Computational Sustainability: Promises and Pitfalls from Theory to Deployment

(ends 3:15 PM)

Workshop:

AI meets Moral Philosophy and Moral Psychology: An Interdisciplinary Dialogue about Computational Ethics

(ends 3:30 PM)

6:50 a.m.

Workshop:

Workshop on robustness of zero/few-shot learning in foundation models (R0-FoMo)

(ends 3:30 PM)

Workshop:

NeurIPS 2023 Workshop on Diffusion Models

(ends 3:30 PM)

7 a.m.

Workshop:

New Frontiers in Graph Learning (GLFrontiers)

(ends 3:00 PM)

Workshop:

Algorithmic Fairness through the Lens of Time

(ends 3:30 PM)

Workshop:

6th Workshop on Artificial Intelligence for Humanitarian Assistance and Disaster Response

(ends 2:30 PM)

Workshop:

Workshop on Distribution Shifts: New Frontiers with Foundation Models

(ends 3:00 PM)

Workshop:

Goal-Conditioned Reinforcement Learning

(ends 3:00 PM)

Workshop:

MATH-AI: The 3rd Workshop on Mathematical Reasoning and AI

(ends 3:00 PM)

Workshop:

Agent Learning in Open-Endedness Workshop

(ends 3:00 PM)

Workshop:

Heavy Tails in ML: Structure, Stability, Dynamics

(ends 3:30 PM)

Workshop:

OPT 2023: Optimization for Machine Learning

(ends 3:01 PM)

Workshop:

Backdoors in Deep Learning: The Good, the Bad, and the Ugly

(ends 3:00 PM)

Competition:

Foundation Model Prompting for Medical Image Classification Challenge 2023

(ends 10:00 AM)

Competition:

Privacy Preserving Federated Learning Document VQA

(ends 10:00 AM)

Competition:

NeurIPS 2023 Machine Unlearning Competition

(ends 10:00 AM)

Competition:

Weather4cast 2023 – Data Fusion for Quantitative Hi-Res Rain Movie Prediction under Spatio-temporal Shifts

(ends 11:00 AM)

Competition:

The NeurIPS 2023 Neural MMO Challenge: Multi-Task Reinforcement Learning and Curriculum Generation

(ends 10:00 AM)

Competition:

The Robot Air Hockey Challenge: Robust, Reliable, and Safe Learning Techniques for Real-world Robotics

(ends 10:00 AM)

8 a.m.

Competition:

The CityLearn Challenge 2023

(ends 12:00 PM)

Break

10 a.m.

Lunch (on your own)

11:30 a.m.

Competition:

The HomeRobot Open Vocabulary Mobile Manipulation Challenge

(ends 2:30 PM)

Competition:

Lux AI Challenge Season 2 NeurIPS Edition

(ends 2:30 PM)

Competition:

NeurIPS Large Language Model Efficiency Challenge: 1 LLM + 1GPU + 1Day

(ends 2:30 PM)

Competition:

The Dynamic Sensorium competition for predicting large-scale mouse visual cortex activity from videos

(ends 2:30 PM)

Competition:

ROAD-R 2023: the Road Event Detection with Requirements Challenge

(ends 2:30 PM)

1 p.m.

Break

3:30 p.m.

SAT 16 DEC

5:30 a.m.

Registration Desk

(ends 10:00 AM)

6:15 a.m.

Workshop:

Workshop on Advancing Neural Network Training (WANT): Computational Efficiency, Scalability, and Resource Optimization

(ends 3:30 PM)

Workshop:

Adaptive Experimental Design and Active Learning in the Real World

(ends 3:30 PM)

Workshop:

Generative AI and Biology (GenBio@NeurIPS2023)

(ends 3:30 PM)

Workshop:

6th Robot Learning Workshop: Pretraining, Fine-Tuning, and Generalization with Large Scale Models

(ends 3:30 PM)

Workshop:

Third Workshop on Efficient Natural Language and Speech Processing (ENLSP-III): Towards the Future of Large Language Models and their Emerging Descendants

(ends 3:15 PM)

Workshop:

Intrinsically Motivated Open-ended Learning (IMOL) Workshop

(ends 3:30 PM)

Workshop:

Gaze Meets ML

(ends 3:00 PM)

Workshop:

Generalization in Planning (GenPlan '23)

(ends 3:30 PM)

Workshop:

NeurIPS 2023 Workshop on Tackling Climate Change with Machine Learning: Blending New and Existing Knowledge Systems

(ends 3:30 PM)

Workshop:

Temporal Graph Learning Workshop @ NeurIPS 2023

(ends 3:30 PM)

Workshop:

NeurIPS 2023 Workshop on Machine Learning for Creativity and Design

(ends 2:40 PM)

Workshop:

AI for Science: from Theory to Practice

(ends 3:30 PM)

6:20 a.m.

Workshop:

Machine Learning for Audio

(ends 3:30 PM)

6:25 a.m.

Workshop:

Workshop on Federated Learning in the Age of Foundation Models in Conjunction with NeurIPS 2023 (FL@FM-NeurIPS'23)

(ends 3:30 PM)

6:30 a.m.

Workshop:

Optimal Transport and Machine Learning

(ends 3:30 PM)

Workshop:

Socially Responsible Language Modelling Research (SoLaR)

(ends 3:30 PM)

Workshop:

The Symbiosis of Deep Learning and Differential Equations -- III

(ends 2:45 PM)

6:45 a.m.

Workshop:

I Can’t Believe It’s Not Better (ICBINB): Failure Modes in the Age of Foundation Models

(ends 3:30 PM)

6:50 a.m.

Workshop:

Mathematics of Modern Machine Learning (M3L)

(ends 3:00 PM)

Workshop:

XAI in Action: Past, Present, and Future Applications

(ends 3:30 PM)

6:55 a.m.

Workshop:

Regulatable ML: Towards Bridging the Gaps between Machine Learning Research and Regulations

(ends 3:30 PM)

7 a.m.

Workshop:

Machine Learning for Systems

(ends 3:00 PM)

Workshop:

Symmetry and Geometry in Neural Representations

(ends 3:00 PM)

Workshop:

Learning-Based Solutions for Inverse Problems

(ends 3:00 PM)

Workshop:

4th Workshop on Self-Supervised Learning: Theory and Practice

(ends 3:00 PM)

Workshop:

Multi-Agent Security: Security as Key to AI Safety

(ends 3:30 PM)

Workshop:

Machine Learning with New Compute Paradigms

(ends 3:00 PM)

Workshop:

Medical Imaging meets NeurIPS

(ends 3:00 PM)

Workshop:

Synthetic Data Generation with Generative AI

(ends 3:00 PM)

Competition:

MyoChallenge 2023: Towards Human-Level Dexterity and Agility

(ends 10:00 AM)

Competition:

Practical Vector Search (Big ANN) Challenge 2023

(ends 10:00 AM)

8 a.m.

Break

9 a.m.

Competition:

NeurIPS 2023 Competition Proposal: Open Catalyst Challenge

(ends 10:10 AM)

10 a.m.

Lunch (on your own)

11:30 a.m.

Competition:

TDC 2023 (LLM Edition): The Trojan Detection Challenge

(ends 2:30 PM)

Competition:

Single-cell perturbation prediction: generalizing experimental interventions to unseen contexts

(ends 2:30 PM)

Competition:

Train Offline, Test Online: A Democratized Robotics Benchmark

(ends 2:30 PM)

1 p.m.

Break

TUE 19 DEC

7 a.m.

Affinity Poster Session:

Virtual Affinity Poster Session

(ends 10:00 AM)

7 p.m.

Affinity Poster Session:

Virtual Affinity Poster Session

(ends 9:59 PM)