ICLR 2024 Schedule

Filter Events

MON 6 MAY

5 a.m.

Registration Desk

(ends 9:00 AM)

10 p.m.

Registration Desk

(ends 10:00 AM)

11:15 p.m.

Remarks:

Opening Remark

(ends 11:30 PM)

11:30 p.m.

Invited Talk:

Optimization-in-the-loop ML for climate and energy

Priya Donti

(ends 12:30 AM)

TUE 7 MAY

12:30 a.m.

Coffee Break

1 a.m.

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

Predictive auxiliary objectives in deep RL mimic learning in the brain

ClimODE: Climate Forecasting With Physics-informed Neural ODEs

Protein Discovery with Discrete Walk-Jump Sampling

(ends 1:45 AM)

Oral 1C [1:00-1:45]

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

(ends 1:45 AM)

Oral 1D [1:00-1:45]

Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View

Robust agents learn causal world models

(ends 1:45 AM)

Oral 1B [1:00-1:45]

A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis

ASID: Active Exploration for System Identification and Reconstruction in Robotic Manipulation

Learning Interactive Real-World Simulators

(ends 1:45 AM)

1:45 a.m.

Poster Session 1 [1:45-3:45]

Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation

Reward Model Ensembles Help Mitigate Overoptimization

Harnessing Density Ratios for Online Reinforcement Learning

Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal Data

Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data

Initializing Models with Larger Ones

STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction

A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks

BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models

Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer

Layer-wise linear mode connectivity

From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction

ClimODE: Climate Forecasting With Physics-informed Neural ODEs

Towards Understanding Sycophancy in Language Models

A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis

Weakly-supervised Audio Separation via Bi-modal Semantic Similarity

Topic Modeling as Multi-Objective Contrastive Optimization

PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization

Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework

FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning

Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs

Elucidating the Exposure Bias in Diffusion Models

LEMON: Lossless model expansion

Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate

Predictive auxiliary objectives in deep RL mimic learning in the brain

Dissecting learning and forgetting in language model finetuning

On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters

DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation

Zero-Mean Regularized Spectral Contrastive Learning

Object-Centric Semantic Vector Quantization

Waxing-and-Waning: a Generic Similarity-based Framework for Efficient Self-Supervised Learning

Quantifying Interactions in Semi-supervised Multimodal Learning: Guarantees and Applications

LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models

CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception

Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis

AttEXplore: Attribution for Explanation with model parameters eXploration

A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis

DreamLLM: Synergistic Multimodal Comprehension and Creation

Fast Imitation via Behavior Foundation Models

Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation

Pushing Boundaries: Mixup's Influence on Neural Collapse

3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining

Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition

A Foundation Model for Error Correction Codes

Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision

BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity

Rethinking and Extending the Probabilistic Inference Capacity of GNNs

ETGraph: A Pioneering Dataset Bridging Ethereum and Twitter

Fiber Monte Carlo

Towards Principled Representation Learning from Videos for Reinforcement Learning

Exploring the cloud of feature interaction scores in a Rashomon set

Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks

Disentangling Time Series Representations via Contrastive based $l$-Variational Inference

Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement Learning

A Mutual Information Perspective on Federated Contrastive Learning

WebArena: A Realistic Web Environment for Building Autonomous Agents

Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models

Robust Classification via Regression-Based Loss Reweighting and Label Correction

Exploring Diffusion Time-steps for Unsupervised Representation Learning

Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck

Masks, Signs, And Learning Rate Rewinding

Transformer Fusion with Optimal Transport

Lemur: Integrating Large Language Models in Automated Program Verification

Goodhart's Law in Reinforcement Learning

Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models

Dynamics-Informed Protein Design with Structure Conditioning

CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping

Learning to Reject for Balanced Error and Beyond

Towards domain-invariant Self-Supervised Learning with Batch Styles Standardization

Exploring Effective Stimulus Encoding via Vision System Modeling for Visual Prostheses

AdaMerging: Adaptive Model Merging for Multi-Task Learning

Effective and Efficient Federated Tree Learning on Hybrid Data

Effective Data Augmentation With Diffusion Models

Fast-ELECTRA for Efficient Pre-training

Transformers can optimally learn regression mixture models

Learning Planning Abstractions from Language

A Simple and Scalable Representation for Graph Generation

TUVF: Learning Generalizable Texture UV Radiance Fields

Sparse Autoencoders Find Highly Interpretable Features in Language Models

Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models

Robust agents learn causal world models

Contrastive Difference Predictive Coding

Demystifying CLIP Data

Linear attention is (maybe) all you need (to understand Transformer optimization)

Safe and Robust Watermark Injection with a Single OoD Image

Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation

Parametric Augmentation for Time Series Contrastive Learning

Sliced Denoising: A Physics-Informed Molecular Pre-Training Method

Tangent Transformers for Composition,Privacy and Removal

Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition

Implicit Maximum a Posteriori Filtering via Adaptive Optimization

Circuit Component Reuse Across Tasks in Transformer Language Models

Out-Of-Domain Unlabeled Data Improves Generalization

Learning from Sparse Offline Datasets via Conservative Density Estimation

PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training

On Bias-Variance Alignment in Deep Models

Class Incremental Learning via Likelihood Ratio Based Task Prediction

Linearity of Relation Decoding in Transformer Language Models

LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster Inference

Leveraging Optimization for Adaptive Attacks on Image Watermarks

Let's do the time-warp-attend: Learning topological invariants of dynamical systems

DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models

LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading

PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images

ASID: Active Exploration for System Identification and Reconstruction in Robotic Manipulation

Active Test-Time Adaptation: Theoretical Analyses and An Algorithm

Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting

At Which Training Stage Does Code Data Help LLMs Reasoning?

Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches

AffineQuant: Affine Transformation Quantization for Large Language Models

Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation

Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization

Reverse Diffusion Monte Carlo

Leave-one-out Distinguishability in Machine Learning

Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression

Bootstrapping Variational Information Pursuit with Foundation Models for Interpretable Image Classification

SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation

From Posterior Sampling to Meaningful Diversity in Image Restoration

A Variational Perspective on Solving Inverse Problems with Diffusion Models

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer

Private Zeroth-Order Nonsmooth Nonconvex Optimization

DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training

Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time

CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models

Thin-Shell Object Manipulations With Differentiable Physics Simulations

Efficient Algorithms for the CCA Family: Unconstrained Objectives with Unbiased Gradients

Unsupervised Order Learning

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

Graphical Multioutput Gaussian Process with Attention

Emu: Generative Pretraining in Multimodality

RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies

Generative Adversarial Inverse Multiagent Learning

On input-dependence and recall in convolutional language models

MMD Graph Kernel: Effective Metric Learning for Graphs via Maximum Mean Discrepancy

Identifiable Latent Polynomial Causal Models through the Lens of Change

Addressing Signal Delay in Deep Reinforcement Learning

Doubly Robust Proximal Causal Learning for Continuous Treatments

The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning

Optimistic Bayesian Optimization with Unknown Constraints

Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL

Evaluating Representation Learning on the Protein Structure Universe

Spurious Feature Diversification Improves Out-of-distribution Generalization

Towards Transparent Time Series Forecasting

Uncertainty Quantification via Stable Distribution Propagation

CABINET: Content Relevance-based Noise Reduction for Table Question Answering

Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders

AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval

Domain Randomization via Entropy Maximization

Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity

Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models

Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models

Illusory Attacks: Detectability Matters in Adversarial Attacks on Sequential Decision-Makers

Learning Multi-Agent Communication from Graph Modeling Perspective

Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries

Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View

FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing

Robust NAS benchmark under adversarial training: assessment, theory, and beyond

Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization

Risk Bounds of Accelerated SGD for Overparameterized Linear Regression

Training Socially Aligned Language Models on Simulated Social Interactions

Implicit Neural Representation Inference for Low-Dimensional Bayesian Deep Learning

Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification

ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving

Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs

Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning

Time Fairness in Online Knapsack Problems

Exploring Weight Balancing on Long-Tailed Recognition Problem

Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling

TASK PLANNING FOR VISUAL ROOM REARRANGEMENT UNDER PARTIAL OBSERVABILITY

Generative Judge for Evaluating Alignment

LOQA: Learning with Opponent Q-Learning Awareness

Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach

PhyloGFN: Phylogenetic inference with generative flow networks

Protein Discovery with Discrete Walk-Jump Sampling

Can we get the best of both Binary Neural Networks and Spiking Neural Networks for Efficient Computer Vision?

Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization

Oracle Efficient Algorithms for Groupwise Regret

Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation

Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation

Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting

Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation

Conformal Risk Control

Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models

CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?

Polynomial Width is Sufficient for Set Representation with High-dimensional Features

Some Intriguing Aspects about Lipschitz Continuity of Neural Networks

Improving Generalization of Alignment with Human Preferences through Group Invariant Learning

Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?

MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning

A unique M-pattern for micro-expreesion spotting in long videos

Why is SAM Robust to Label Noise?

Weaker MVI Condition: Extragradient Methods with Multi-Step Exploration

Fusion is Not Enough: Single Modal Attack on Fusion Models for 3D Object Detection

Masked Distillation Advances Self-Supervised Transformer Architecture Search

Multilingual Jailbreak Challenges in Large Language Models

ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models

DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing

Successor Heads: Recurring, Interpretable Attention Heads In The Wild

InfoCon: Concept Discovery with Generative and Discriminative Informativeness

Don't Judge by the Look: A Motion Coherent Augmentation for Video Recognition

Mitigating Severe Robustness Degradation on Graphs

Neurosymbolic Grounding for Compositional Generalization

VBH-GNN: Variational Bayesian Heterogeneous Graph Neural Networks for Cross-subject Emotion Recognition

On the generalization capacity of neural networks during generic multimodal reasoning

MagicDrive: Street View Generation with Diverse 3D Geometry Control

Expressive Losses for Verified Robustness via Convex Combinations

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Model Merging by Uncertainty-Based Gradient Matching

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods

Teaching Language Models to Hallucinate Less with Synthetic Tasks

CausalLM is not optimal for in-context learning

Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models

Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data

SLiMe: Segment Like Me

Neural Polynomial Gabor Fields for Macro Motion Analysis

Beyond Memorization: Violating Privacy via Inference with Large Language Models

Neural Rate Control for Learned Video Compression

Efficient ConvBN Blocks for Transfer Learning and Beyond

Sentence-level Prompts Benefit Composed Image Retrieval

Analytically Tractable Hidden-States Inference in Bayesian Neural Networks

Towards Robust and Efficient Cloud-Edge Model Adaptation via Selective Entropy Distillation

Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning

ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process

Learning Scalar Fields for Molecular Docking with Fast Fourier Transforms

A Generalist Agent

Retrieval-Enhanced Contrastive Vision-Text Models

Directly Fine-Tuning Diffusion Models on Differentiable Rewards

Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits

JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention

SALMON: Self-Alignment with Principle-Following Reward Models

Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding

DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text

Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models

Graph Generation with $K^2$-trees

Probabilistic Self-supervised Representation Learning via Scoring Rules Minimization

Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels

Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions

Free Lunches in Auxiliary Learning: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

Deep Temporal Graph Clustering

Latent Intuitive Physics: Learning to Transfer Hidden Physics from a 3D Video

SAS: Structured Activation Sparsification

Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning

Defining Expertise: Applications to Treatment Effect Estimation

Designing Skill-Compatible AI: Methodologies and Frameworks in Chess

Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

A Probabilistic Framework for Modular Continual Learning

Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs

Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning

Time-LLM: Time Series Forecasting by Reprogramming Large Language Models

Entropy is not Enough for Test-time Adaptation: From the Perspective of Disentangled Factors

Causally Aligned Curriculum Learning

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback

Chain of Hindsight aligns Language Models with Feedback

A Simple and Effective Pruning Approach for Large Language Models

Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs

REFACTOR: Learning to Extract Theorems from Proofs

LipSim: A Provably Robust Perceptual Similarity Metric

ResFields: Residual Neural Fields for Spatiotemporal Signals

AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ

Procedural Fairness Through Decoupling Objectionable Data Generating Components

Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation

Adaptive Federated Learning with Auto-Tuned Clients

Unsupervised Fact Verification by Language Model Distillation

ReMasker: Imputing Tabular Data with Masked Autoencoding

Attacking Perceptual Similarity Metrics

$\pi$2vec: Policy Representation with Successor Features

TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting

Revisiting the Last-Iterative Convergence of Stochastic Gradient Methods

OpenTab: Advancing Large Language Models as Open-domain Table Reasoners

DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genomes

Transport meets Variational Inference: Controlled Monte Carlo Diffusions

On the Role of General Function Approximation in Offline Reinforcement Learning

P2Seg: Pointly-supervised Segmentation via Mutual Distillation

Synaptic Weight Distributions Depend on the Geometry of Plasticity

FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity

Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift

A Framework and Benchmark for Deep Batch Active Learning for Regression

Learning Interactive Real-World Simulators

ContextRef: Evaluating Referenceless Metrics for Image Description Generation

Soft Contrastive Learning for Time Series

On the Learnability of Watermarks for Language Models

Matrix Manifold Neural Networks++

Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization

Faithful Vision-Language Interpretation via Concept Bottleneck Models

(ends 3:45 AM)

Affinity Posters:

Blog Track Session 1

(ends 3:45 AM)

Affinity Posters:

Tiny Papers Poster Session 1

(ends 3:45 AM)

3:45 a.m.

Expo Talk Panel:

GLM-4: A New Generation of General Language Model Pretraining with Autoregressive Blank Infilling

(ends 5:15 AM)

Lunch Break

4:15 a.m.

Affinity Workshop:

Tiny Papers Oral Session 1

(ends 5:15 AM)

5:15 a.m.

Invited Talk:

Legal Fundamentals for AI Researchers

Kate Downing

(ends 6:15 AM)

6:15 a.m.

Coffee Break

6:45 a.m.

Oral 2D [6:45-7:30]

Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness

The mechanistic basis of data dependence and abrupt learning in an in-context classification task

(ends 7:30 AM)

Oral 2A [6:45-7:30]

MetaGPT: Meta Programming for Multi-Agent Collaborative Framework

Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

(ends 7:30 AM)

Oral 2C [6:45-7:30]

Lipschitz Singularities in Diffusion Models

Improved Techniques for Training Consistency Models

Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models

(ends 7:30 AM)

Oral 2B [6:45-7:30]

Vision Transformers Need Registers

Ghost on the Shell: An Expressive Representation of General 3D Shapes

LRM: Large Reconstruction Model for Single Image to 3D

(ends 7:30 AM)

7:30 a.m.

Poster Session 2 [7:30-9:30]

Generative Adversarial Policy Network for Modelling Protein Complexes

OmniControl: Control Any Joint at Any Time for Human Motion Generation

The mechanistic basis of data dependence and abrupt learning in an in-context classification task

Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots

MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data

Fusing Models with Complementary Expertise

LLM4QPE: Unsupervised Pretraining of Quantum Property Estimation and A Benchmark

Generating Pragmatic Examples to Train Neural Program Synthesizers

Pre-training Sequence, Structure, and Surface Features for Comprehensive Protein Representation Learning

High-dimensional SGD aligns with emerging outlier eigenspaces

Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation

Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

Time-Efficient Reinforcement Learning with Stochastic Stateful Policies

Vision-Language Foundation Models as Effective Robot Imitators

Vision Transformers Need Registers

Improving Non-Transferable Representation Learning by Harnessing Content and Style

Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks

HoloNets: Spectral Convolutions do extend to Directed Graphs

Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation

ReLoRA: High-Rank Training Through Low-Rank Updates

A Variational Framework for Estimating Continuous Treatment Effects with Measurement Error

Course Correcting Koopman Representations

More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory

Dissecting sample hardness: Fine-grained analysis of Hardness Characterization Methods

Combining Axes Preconditioners through Kronecker Approximation for Deep Learning

Perceptual Group Tokenizer: Building Perception with Iterative Grouping

A path-norm toolkit for modern networks: consequences, promises and challenges

High Fidelity Neural Audio Compression

VFLAIR: A Research Library and Benchmark for Vertical Federated Learning

A Characterization Theorem for Equivariant Networks with Point-wise Activations

Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts

The importance of feature preprocessing for differentially private linear optimization

SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

On Harmonizing Implicit Subpopulations

Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns

Reconciling Spatial and Temporal Abstractions for Goal Representation

Deceptive Fairness Attacks on Graphs via Meta Learning

Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns

Improving Generalization in Equivariant Graph Neural Networks with Physical Inductive Biases

Seer: Language Instructed Video Prediction with Latent Diffusion Models

Reinforcement Symbolic Regression Machine

Adversarial Imitation Learning via Boosting

MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback

Learning Reusable Dense Rewards for Multi-Stage Tasks

Input-gradient space particle inference for neural network ensembles

Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel

PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial Filters

DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation

PAC Prediction Sets Under Label Shift

SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D

CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding

Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes

Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning

SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning

Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions

Provably Efficient CVaR RL in Low-rank MDPs

Unveiling Options with Neural Network Decomposition

Unlock Predictable Scaling from Emergent Abilities

Continuous Invariance Learning

GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation

Provable Robust Watermarking for AI-Generated Text

Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing

Augmented Bayesian Policy Search

SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning

Non-Exchangeable Conformal Risk Control

Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations

Quantifying Network Similarity using Graph Cumulants

Language-Informed Visual Concept Learning

MiniLLM: Knowledge Distillation of Large Language Models

Denoising Diffusion Step-aware Models

Accelerating Sinkhorn algorithm with sparse Newton iterations

Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates

Making RL with Preference-based Feedback Efficient via Randomization

Provably Efficient UCB-type Algorithms For Learning Predictive State Representations

TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields

Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning

DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models

When Semantic Segmentation Meets Frequency Aliasing

Curiosity-driven Red-teaming for Large Language Models

EXPLORING RAIN-/DETAIL-AWARE REPRESENTATION FOR INSTANCE-SPECIFIC IMAGE DE-RAINING

Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies

Estimating Conditional Mutual Information for Dynamic Feature Selection

MoLE: Mixture of LoRA Experts

NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks

Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech

Multimodal Molecular Pretraining via Modality Blending

Generalized Schrödinger Bridge Matching

Modeling Boundedly Rational Agents with Latent Inference Budgets

Elucidating the design space of classifier-guided diffusion generation

Scalable Neural Network Kernels

Greedy Sequential Execution: Solving Homogeneous and Heterogeneous Cooperative Tasks with a Unified Framework

Zero-Shot Robustification of Zero-Shot Models

Time-Varying Propensity Score to Bridge the Gap between the Past and Present

Dictionary Contrastive Forward Learning via Adaptive Label Embeddings

Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models

Massively Scalable Inverse Reinforcement Learning for Route Optimization

LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors

Critical Learning Periods Emerge Even in Deep Linear Networks

Noisy Interpolation Learning with Shallow Univariate ReLU Networks

Entropy Coding of Unordered Data Structures

Uncertainty-aware Graph-based Hyperspectral Image Classification

Learning Hierarchical Image Segmentation For Recognition and By Recognition

FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link Prediction

Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion

WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions

Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC Bounds

MetaGPT: Meta Programming for Multi-Agent Collaborative Framework

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists

Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors

A Precise Characterization of SGD Stability Using Loss Surface Geometry

Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing

On the Stability of Iterative Retraining of Generative Models on their own Data

A representation-learning game for classes of prediction tasks

Neural Neighborhood Search for Multi-agent Path Finding

LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units

Transformers vs. Message Passing GNNs: Distinguished in Uniform

Orbit-Equivariant Graph Neural Networks

BrainLM: A foundation model for brain activity recordings

Replay across Experiments: A Natural Extension of Off-Policy RL

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning

Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions

Masked Audio Generative Modeling

Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs

Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping

Poly-View Contrastive Learning

Rethinking Label Poisoning for GNNs: Pitfalls and Attacks

DreamClean: Restoring Clean Image Using Deep Diffusion Prior

Few-shot Hybrid Domain Adaptation of Image Generator

Grounding Multimodal Large Language Models to the World

Diving Segmentation Model into Pixels

Neural Auto-designer for Enhanced Quantum Kernels

SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem

Look, Remember and Reason: Grounded Reasoning in Videos with Language Models

MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations

Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models

From Graphs to Hypergraphs: Hypergraph Projection and its Remediation

JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling

Expressivity of ReLU-Networks under Convex Relaxations

Coordinate-Aware Modulation for Neural Fields

You Only Query Once: An Efficient Label-Only Membership Inference Attack

A Stochastic Centering Framework for Improving Calibration in Graph Neural Networks

A Private Watermark for Large Language Models

Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching

CPPO: Continual Learning for Reinforcement Learning with Human Feedback

Efficient Distributed Training with Full Communication-Computation Overlap

A Benchmark Study on Calibration

Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances

Stochastic Modified Equations and Dynamics of Dropout Algorithm

Repelling Random Walks

Privileged Sensing Scaffolds Reinforcement Learning

Multilinear Operator Networks

Scaling Convex Neural Networks with Burer-Monteiro Factorization

Object centric architectures enable efficient causal representation learning

Improved Techniques for Training Consistency Models

OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning

Symmetric Single Index Learning

Theoretical Understanding of Learning from Adversarial Perturbations

Time Travel in LLMs: Tracing Data Contamination in Large Language Models

DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning

Fast Hyperboloid Decision Tree Algorithms

Conditional Instrumental Variable Regression with Representation Learning for Causal Inference

In-Context Learning Learns Label Relationships but Is Not Conventional Learning

Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space

MVDream: Multi-view Diffusion for 3D Generation

Understanding Addition in Transformers

Massive Editing for Large Language Model via Meta Learning

Adversarial AutoMixup

Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects

Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality

Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection

Federated Wasserstein Distance

Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images

GeoLLM: Extracting Geospatial Knowledge from Large Language Models

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators

Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions

BRUSLEATTACK: QUERY-EFFICIENT SCORE-BASED SPARSE ADVERSARIAL ATTACK

Video Decomposition Prior: Editing Videos Layer by Layer

SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores

CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling

Holistic Evaluation of Language Models

Complete and Efficient Graph Transformers for Crystal Material Property Prediction

Image Inpainting via Iteratively Decoupled Probabilistic Modeling

CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents

Relay Diffusion: Unifying diffusion process across resolutions for image synthesis

COSA: Concatenated Sample Pretrained Vision-Language Foundation Model

Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations

Controlling Vision-Language Models for Universal Image Restoration

Pareto Deep Long-Tailed Recognition: A Conflict-Averse Solution

Global Optimality for Non-linear Constrained Restoration Problems via Invexity

Memorization in Self-Supervised Learning Improves Downstream Generalization

Hard-Constrained Deep Learning for Climate Downscaling

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data

Regularized Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity

A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER

A differentiable brain simulator bridging brain simulation and brain-inspired computing

BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs

Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps

SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation

Clifford Group Equivariant Simplicial Message Passing Networks

Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation

Label-Noise Robust Diffusion Models

Scaling Laws for Associative Memories

Learning to make adherence-aware advice

A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models

IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks

MogaNet: Multi-order Gated Aggregation Network

Droplets of Good Representations: Grokking as a First Order Phase Transition in Two Layer Networks

Ghost on the Shell: An Expressive Representation of General 3D Shapes

Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs

SmartPlay : A Benchmark for LLMs as Intelligent Agents

Fine-Tuning Language Models for Factuality

Large-Vocabulary 3D Diffusion Model with Transformer

Teaching Arithmetic to Small Transformers

Output-Domain Focused Inductive Bias on Latent Feature Clusters in Visual Classification

Maximally discriminative stimuli for functional cell type identification

LRM: Large Reconstruction Model for Single Image to 3D

Large Language Models Cannot Self-Correct Reasoning Yet

Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation

Learning to Compose: Improving Object Centric Learning by Injecting Compositionality

Quadratic models for understanding neural network dynamics

AgentBench: Evaluating LLMs as Agents

Retrieval is Accurate Generation

Lipschitz Singularities in Diffusion Models

Feature emergence via margin maximization: case studies in algebraic tasks

The Marginal Value of Momentum for Small Learning Rate SGD

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets

Xformer: Hybrid X-Shaped Transformer for Image Denoising

Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models

HiGen: Hierarchical Graph Generative Networks

Denoising Diffusion via Image-Based Rendering

Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization

Enable Lanuguage Models to Implicitly Learn Self-Improvement From Data

Denoising Diffusion Bridge Models

DistillSpec: Improving Speculative Decoding via Knowledge Distillation

Pre-training LiDAR-based 3D Object Detectors through Colorization

InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation

Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features

Tight Rates in Supervised Outlier Transfer Learning

Confronting Reward Model Overoptimization with Constrained RLHF

Demystifying Embedding Spaces using Large Language Models

How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions

Conformal Prediction via Regression-as-Classification

Compressed Context Memory for Online Language Model Interaction

Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy

Eureka: Human-Level Reward Design via Coding Large Language Models

Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features

UC-NERF: Neural Radiance Field for under-calibrated multi-view cameras

Bridging Vision and Language Spaces with Assignment Prediction

Uni3D: Exploring Unified 3D Representation at Scale

An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks

Dynamic Sparse Training with Structured Sparsity

Quantifying and Enhancing Multi-modal Robustness with Modality Preference

GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher

GlucoBench: Curated List of Continuous Glucose Monitoring Datasets with Prediction Benchmarks

Task structure and nonlinearity jointly determine learned representational geometry

DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models

Transferring Learning Trajectories of Neural Networks

3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation

When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations

Scalable Monotonic Neural Networks

Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations

Batch normalization is sufficient for universal function approximation in CNNs

Retrieval-based Disentangled Representation Learning with Natural Language Supervision

Label-free Node Classification on Graphs with Large Language Models (LLMs)

Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness

NOLA: Networks as Linear Combination of Low Rank Random Basis

Generalizability of Adversarial Robustness Under Distribution Shifts

Exposing Text-Image Inconsistency Using Diffusion Models

YaRN: Efficient Context Window Extension of Large Language Models

Learning to design protein-protein interactions with enhanced generalization

Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints

Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training

Benchmarking and Improving Generator-Validator Consistency of Language Models

Towards the Fundamental Limits of Knowledge Transfer over Finite Domains

Multi-task Learning with 3D-Aware Regularization

Skip-Attention: Improving Vision Transformers by Paying Less Attention

LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning

Training-free Multi-objective Diffusion Model for 3D Molecule Generation

Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency

Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day

EQA-MX: Embodied Question Answering using Multimodal Expression

On Diffusion Modeling for Anomaly Detection

Forward $\chi^2$ Divergence Based Variational Importance Sampling

Improved Probabilistic Image-Text Representations

Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models

Improving Language Models with Advantage-based Offline Policy Gradients

Retrieval-Based Reconstruction For Time-series Contrastive Learning

(ends 9:30 AM)

Affinity Posters:

Blog Track Session 2

(ends 9:30 AM)

Affinity Posters:

Tiny Papers Poster Session 2

(ends 9:30 AM)

9:30 a.m.

Reception

11 p.m.

Registration Desk

(ends 9:30 AM)

11:30 p.m.

Invited Talk:

Learning through AI’s winters and springs: unexpected truths on the road to AGI

Raia Hadsell

(ends 12:30 AM)

WED 8 MAY

12:30 a.m.

Coffee Break

1 a.m.

Oral 3C [1:00-1:45]

Improving Convergence and Generalization Using Parameter Symmetries

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization

(ends 1:45 AM)

Oral 3A [1:00-1:45]

LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement

ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models

(ends 1:45 AM)

Oral 3B [1:00-1:45]

Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks

Learning Energy Decompositions for Partial Inference of GFlowNets

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

(ends 1:45 AM)

Oral 3D [1:00-1:45]

How Well Do Supervised Models Transfer to 3D Image Segmentation?

ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation

(ends 1:45 AM)

1:45 a.m.

Poster Session 3 [1:45-3:45]

Posters 1:45-3:45

Improving Offline RL by Blending Heuristics

A Restoration Network as an Implicit Prior

Long-Short-Range Message-Passing: A Fragmentation-Based Framework to Capture Non-Local Atomistic Interactions

Mirage: Model-agnostic Graph Distillation for Graph Classification

Effectively Leveraging Capacity for Improved Deterministic Robustness Certification

RetroBridge: Modeling Retrosynthesis with Markov Bridges

A Quadratic Synchronization Rule for Distributed Deep Learning

Learning to solve Class-Constrained Bin Packing Problems via Encoder-Decoder Model

Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions

Lagrangian Flow Networks for Conservation Laws

From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module

MetaTool Benchmark: Deciding Whether to Use Tools and Which to Use

FedInverse: Evaluating Privacy Leakage in Federated Learning

Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning

Calibrated Chaos: Variance Between Runs of Neural Network Training is Harmless and Inevitable

OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text

SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents

Zero and Few-shot Semantic Parsing with Ambiguous Inputs

Language Model Detectors Are Easily Optimized Against

Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors

Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs

Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning

CLAP: Collaborative Adaptation for Checkerboard Learning

Scalable Diffusion for Materials Generation

Function Vectors in Large Language Models

Emerging Pixel-level Semantic Knowledge in Diffusion Models

Querying Easily Flip-flopped Samples for Deep Active Learning

NuwaDynamics: Discovering and Updating in Causal Spatio-Temporal Modeling

A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs

Unpaired Image-to-Image Translation via Neural Schrödinger Bridge

RA-DIT: Retrieval-Augmented Dual Instruction Tuning

Scaling Laws of RoPE-based Extrapolation

MOTOR: A Time-To-Event Foundation Model For Structured Medical Records

Conformal Language Modeling

Local Search GFlowNets

Tree Search-Based Policy Optimization under Stochastic Execution Delay

Simplicial Representation Learning with Neural $k$-Forms

Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies

Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks

DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation

Scale-Adaptive Diffusion Model for Complex Sketch Synthesis

Towards image compression with perfect realism at ultra-low bitrates

Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks

Polynormer: Polynomial-Expressive Graph Transformer in Linear Time

On the Generalization and Approximation Capacities of Neural Controlled Differential Equations

ConR: Contrastive Regularizer for Deep Imbalanced Regression

ControlVideo: Training-free Controllable Text-to-video Generation

Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets

CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images

Feature-aligned N-BEATS with Sinkhorn divergence

Feature Learning in Infinite Depth Neural Networks

TokenFlow: Consistent Diffusion Features for Consistent Video Editing

Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs

Non-negative Contrastive Learning

Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling

Effective Structural Encodings via Local Curvature Profiles

Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis

ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models

Learning to Reject with a Fixed Predictor: Application to Decontextualization

Language Models Represent Space and Time

The Generative AI Paradox: “What It Can Create, It May Not Understand”

Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

The Alignment Problem from a Deep Learning Perspective: A Position Paper

Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting

Automatic Functional Differentiation in JAX

VersVideo: Leveraging Enhanced Temporal Diffusion Models for Versatile Video Generation

Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning

PanoDiffusion: 360-degree Panorama Outpainting via Diffusion

Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration

Pre-training with Synthetic Data Helps Offline Reinforcement Learning

What Matters to You? Towards Visual Representation Alignment for Robot Learning

An operator preconditioning perspective on training in physics-informed machine learning

Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation

Rethinking the Uniformity Metric in Self-Supervised Learning

SetCSE: Set Operations using Contrastive Learning of Sentence Embeddings

Separate and Diffuse: Using a Pretrained Diffusion Model for Better Source Separation

Amortized Network Intervention to Steer the Excitatory Point Processes

CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects

Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding

Fair Classifiers that Abstain without Harm

Whittle Index with Multiple Actions and State Constraint for Inventory Management

Representation Deficiency in Masked Language Modeling

Cameras as Rays: Sparse-view Pose Estimation via Ray Diffusion

Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement

Robust Similarity Learning with Difference Alignment Regularization

Explaining Time Series via Contrastive and Locally Sparse Perturbations

Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature

LLM Augmented LLMs: Expanding Capabilities through Composition

LLM-grounded Video Diffusion Models

LabelDP-Pro: Learning with Label Differential Privacy via Projections

Graphpulse: Topological representations for temporal graph property prediction

Self-supervised Representation Learning from Random Data Projectors

Self-Consuming Generative Models Go MAD

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation

Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency

Minimum width for universal approximation using ReLU networks on compact domain

Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks

COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits

BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation

CellPLM: Pre-training of Cell Language Model Beyond Single Cells

Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM

Effective pruning of web-scale datasets based on complexity of concept clusters

Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models

DATS: Difficulty-Aware Task Sampler for Meta-Learning Physics-Informed Neural Networks

A Semantic Invariant Robust Watermark for Large Language Models

Are Human-generated Demonstrations Necessary for In-context Learning?

UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models

SparseFormer: Sparse Visual Recognition via Limited Latent Tokens

Revisiting Data Augmentation in Deep Reinforcement Learning

Protein Multimer Structure Prediction via PPI-guided Prompt Learning

Trajeglish: Learning the Language of Driving Scenarios

Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation

Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned Generation

Post-hoc bias scoring is optimal for fair classification

Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning

Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization

Aligning Relational Learning with Lipschitz Fairness

BroGNet: Momentum-Conserving Graph Neural Stochastic Differential Equation for Learning Brownian Dynamics

A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors

FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation

Equivariant Matrix Function Neural Networks

Sharpness-Aware Data Poisoning Attack

Understanding the Effects of RLHF on LLM Generalisation and Diversity

NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making

On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks

DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning

Cross$Q$: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity

Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive

Conditional Variational Diffusion Models

Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations

Towards 3D Molecule-Text Interpretation in Language Models

Improving Intrinsic Exploration by Creating Stationary Objectives

Ensemble Distillation for Unsupervised Constituency Parsing

Fast and unified path gradient estimators for normalizing flows

MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation

Hypergraph Dynamic System

DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models

fairret: a Framework for Differentiable Fairness Regularization Terms

SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking

Safe RLHF: Safe Reinforcement Learning from Human Feedback

From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication

Towards Poisoning Fair Representations

The Trickle-down Impact of Reward Inconsistency on RLHF

Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

On Double Descent in Reinforcement Learning with LSTD and Random Features

Better Neural PDE Solvers Through Data-Free Mesh Movers

GOAt: Explaining Graph Neural Networks via Graph Output Attribution

Vanishing Gradients in Reinforcement Finetuning of Language Models

CircuitNet 2.0: An Advanced Dataset for Promoting Machine Learning Innovations in Realistic Chip Design Environment

Adaptive Regret for Bandits Made Possible: Two Queries Suffice

Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian distributions

Guess & Sketch: Language Model Guided Transpilation

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning

On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback

TabR: Tabular Deep Learning Meets Nearest Neighbors

Improving Convergence and Generalization Using Parameter Symmetries

The Reasonableness Behind Unreasonable Translation Capability of Large Language Model

Linear Log-Normal Attention with Unbiased Concentration

On the Posterior Distribution in Denoising: Application to Uncertainty Quantification

MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process

Accurate Forgetting for Heterogeneous Federated Continual Learning

A Study of Generalization in Offline Reinforcement Learning

Hindsight PRIORs for Reward Learning from Human Preferences

Tool-Augmented Reward Modeling

An interpretable error correction method for enhancing code-to-code translation

Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks

ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation

SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos

ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate

Unified Human-Scene Interaction via Prompted Chain-of-Contacts

LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models

GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors

How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?

InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image

R-MAE: Regions Meet Masked Autoencoders

EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models

Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven Reasoning

Nevis'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research

Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers

It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition

Accelerated Sampling with Stacked Restricted Boltzmann Machines

Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction

Patched Denoising Diffusion Models For High-Resolution Image Synthesis

Towards Foundation Models for Knowledge Graph Reasoning

Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching

PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction

Video Language Planning

KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints

Partitioning Message Passing for Graph Fraud Detection

Bellman Optimal Step-size Straightening of Flow-Matching Models

Test-time Adaption against Multi-modal Reliability Bias

Manipulating dropout reveals an optimal balance of efficiency and robustness in biological and machine visual systems

Function-space Parameterization of Neural Networks for Sequential Learning

A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data

Large Language Models as Analogical Reasoners

General Stability Analysis for Zeroth-Order Optimization Algorithms

From Matching to Mixing: A Graph Interpolation Approach for SAT Instance Generation

Analyzing and Improving OT-based Adversarial Networks

Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators

On the Parameterization of Second-Order Optimization Effective towards the Infinite Width

Understanding Hidden Context in Preference Learning: Consequences for RLHF

Headless Language Models: Learning without Predicting with Contrastive Weight Tying

Tree Cross Attention

Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders

Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation

Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory

Sufficient conditions for offline reactivation in recurrent neural networks

NeRM: Learning Neural Representations for High-Framerate Human Motion Synthesis

Generative Adversarial Equilibrium Solvers

Graph Parsing Networks

Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models

Improved baselines for vision-language pre-training

Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization

Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation

Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit

Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting

Learning Energy Decompositions for Partial Inference of GFlowNets

TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning

Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction

AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents

#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models

$\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation

Temporal Generalization Estimation in Evolving Graphs

CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery

Fast Value Tracking for Deep Reinforcement Learning

LEAD: Min-Max Optimization from a Physical Perspective

Fully Hyperbolic Convolutional Neural Networks for Computer Vision

Searching for High-Value Molecules Using Reinforcement Learning and Transformers

MAP IT to Visualize Representations

Self-Supervised Heterogeneous Graph Learning: a Homophily and Heterogeneity View

DMBP: Diffusion model-based predictor for robust offline reinforcement learning against state observation perturbations

Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis

Lemur: Harmonizing Natural Language and Code for Language Agents

ZipIt! Merging Models from Different Tasks without Training

Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks

Reward Design for Justifiable Sequential Decision-Making

Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data

Towards Robust Offline Reinforcement Learning under Diverse Data Corruption

On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models

Revisit and Outstrip Entity Alignment: A Perspective of Generative Models

DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models

In-context Autoencoder for Context Compression in a Large Language Model

FOSI: Hybrid First and Second Order Optimization

Supervised Knowledge Makes Large Language Models Better In-context Learners

Federated Recommendation with Additive Personalization

Towards Establishing Guaranteed Error for Learned Database Operations

GenSim: Generating Robotic Simulation Tasks via Large Language Models

Set Learning for Accurate and Calibrated Models

CODE REPRESENTATION LEARNING AT SCALE

Who to imitate: Imitating desired behavior from divserse multi-agent datasets

Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval

How Well Do Supervised Models Transfer to 3D Image Segmentation?

Prompt Learning with Quaternion Networks

On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation

Prompt Gradient Projection for Continual Learning

Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision

Perceptual Measurements, Distances and Metrics

Stochastic Controlled Averaging for Federated Learning with Communication Compression

GPAvatar: Generalizable and Precise Head Avatar from Image(s)

Neural Optimal Transport with General Cost Functionals

Fantastic Generalization Measures are Nowhere to be Found

Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform

Kernelised Normalising Flows

The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.

A Branching Decoder for Set Generation

Consistency-guided Prompt Learning for Vision-Language Models

Scaling Laws for Sparsely-Connected Foundation Models

Step-Back Prompting Enables Reasoning Via Abstraction in Large Language Models

Towards Universal Multi-Modal Personalization: A Language Model Empowered Generative Paradigm

Learning Conditional Invariances through Non-Commutativity

The Expressive Power of Transformers with Chain of Thought

The Expressive Power of Low-Rank Adaptation

Quasi-Monte Carlo for 3D Sliced Wasserstein

An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression

SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression

Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning

GROOT: Learning to Follow Instructions by Watching Gameplay Videos

Image Translation as Diffusion Visual Programmers

Democratizing Fine-grained Visual Recognition with Large Language Models

Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds

Evaluating Language Models Through Negotiations

What does automatic differentiation compute for neural networks?

Understanding In-Context Learning from Repetitions

Implicit Gaussian process representation of vector fields over arbitrary latent manifolds

Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics

Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks

(ends 3:45 AM)

Affinity Posters:

Blog Track Session 3

(ends 3:45 AM)

Affinity Posters:

Tiny Papers Poster Session 3

(ends 3:45 AM)

3:45 a.m.

Lunch Break

Expo Talk Panel:

Huawei Innovation Bridge – “Beyond Algorithms: Navigating the Data Deluge in AI”

(ends 5:15 AM)

4:15 a.m.

Town Hall:

Town Hall

(ends 5:15 AM)

Affinity Workshop:

Tiny Papers Oral Session 2

(ends 5:15 AM)

5:15 a.m.

Test Of Time:

Test of Time Award & Test of Time Runner-up

(ends 6:15 AM)

6:15 a.m.

Coffee Break

6:45 a.m.

Oral 4C [6:45-7:30]

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning

(ends 7:30 AM)

Oral 4A [6:45-7:30]

BooookScore: A systematic exploration of book-length summarization in the era of LLMs

SWE-bench: Can Language Models Resolve Real-world Github Issues?

Batched Low-Rank Adaptation of Foundation Models

(ends 7:30 AM)

Oral 4B [6:45-7:30]

Topological data analysis on noisy quantum computers

Flow Matching on General Geometries

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

(ends 7:30 AM)

Oral 4D [6:45-7:30]

Amortizing intractable inference in large language models

Monte Carlo guided Denoising Diffusion models for Bayesian linear inverse problems.

(ends 7:30 AM)

7:30 a.m.

Poster Session 4 [7:30-9:30]

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior

The Dark Side of the Hyperbolic Moon

LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models

The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images

Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation

Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL

Scalable and Effective Implicit Graph Neural Networks on Large Graphs

Universal Humanoid Motion Representations for Physics-Based Control

Momentum Benefits Non-iid Federated Learning Simply and Provably

Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders

Lightweight Language Model Calibration for Open-ended Question Answering with Varied Answer Lengths

ZeRO++: Extremely Efficient Collective Communication for Large Model Training

On the Foundations of Shortcut Learning

Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning

Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework

Statistical Rejection Sampling Improves Preference Optimization

Horizon-Free Regret for Linear Markov Decision Processes

Class Probability Matching with Calibrated Networks for Label Shift Adaption

Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models

Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models

SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis

Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation

The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”

Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs

Learning dynamic representations of the functional connectome in neurobiological networks

On the Effect of Batch Size in Byzantine-Robust Distributed Learning

Teaching Large Language Models to Self-Debug

On Adversarial Training without Perturbing all Examples

LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment

Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles

Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN

Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation

Brain decoding: toward real-time reconstruction of visual perception

Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks

How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data

Understanding Catastrophic Forgetting in Language Models via Implicit Inference

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation

Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs

Energy-based Automated Model Evaluation

Curriculum reinforcement learning for quantum architecture search under hardware errors

Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback

Annealing Self-Distillation Rectification Improves Adversarial Training

Path Choice Matters for Clear Attributions in Path Methods

Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning

MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods

CoBIT: A Contrastive Bi-directional Image-Text Generation Model

BooookScore: A systematic exploration of book-length summarization in the era of LLMs

GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings

The Hidden Language of Diffusion Models

Fake It Till Make It: Federated Learning with Consensus-Oriented Generation

Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules

Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning

Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings

FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization

ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression

EasyTPP: Towards Open Benchmarking Temporal Point Processes

Neural Fourier Transform: A General Approach to Equivariant Representation Learning

LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection

Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks

A Newborn Embodied Turing Test for Comparing Object Segmentation Across Animals and Machines

Improving Natural Language Understanding with Computation-Efficient Retrieval Augmentation

Improving the Convergence of Dynamic NeRFs via Optimal Transport

Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning

PoMe: Fleet Learning via Policy Merging

Neural Active Learning Beyond Bandits

The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry

SpaCE: The Spatial Confounding Environment

Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning

TD-MPC2: Scalable, Robust World Models for Continuous Control

Bayesian Coreset Optimization for Personalized Federated Learning

Robust Model-Based Optimization for Challenging Fitness Landscapes

SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore

Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness

Neural Common Neighbor with Completion for Link Prediction

$\alpha$TC-VAE: On the relationship between Disentanglement and Diversity

Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning

Test-Time Training on Nearest Neighbors for Large Language Models

A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation

TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks

De novo Protein Design Using Geometric Vector Field Networks

Towards Codable Text Watermarking for Large Language Models

TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts

Online Information Acquisition: Hiring Multiple Agents

Mayfly: a Neural Data Structure for Graph Stream Summarization

Ultra-sparse network advantage in deep learning via Cannistraci-Hebb brain-inspired training with hyperbolic meta-deep community-layered epitopology

LILO: Learning Interpretable Libraries by Compressing and Documenting Code

Retro-fallback: retrosynthetic planning in an uncertain world

InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior

Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks

Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos

Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.

Language Model Cascades: Token-Level Uncertainty And Beyond

Score Regularized Policy Optimization through Diffusion Behavior

Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments

Pre-Training and Fine-Tuning Generative Flow Networks

Federated Q-Learning: Linear Regret Speedup with Low Communication Cost

Demystifying Poisoning Backdoor Attacks from a Statistical Perspective

VQ-TR: Vector Quantized Attention for Time Series Forecasting

GRANDE: Gradient-Based Decision Tree Ensembles

Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators

Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution

InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules

A Sublinear Adversarial Training Algorithm

Image Background Serves as Good Proxy for Out-of-distribution Data

Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks

Efficient Heterogeneous Meta-Learning via Channel Shuffling Modulation

Query-Policy Misalignment in Preference-Based Reinforcement Learning

Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions

Ferret: Refer and Ground Anything Anywhere at Any Granularity

Flow Matching on General Geometries

Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks

Robust Angular Synchronization via Directed Graph Neural Networks

Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory

When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method

SuRe: Improving Open-domain Question Answering of LLMs via Summarized Retrieval

Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers

Long-tailed Diffusion Models with Oriented Calibration

Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks

Learning to reconstruct signals from binary measurements alone

Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning

TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

Bridging Neural and Symbolic Representations with Transitional Dictionary Learning

Visual Data-Type Understanding does not emerge from scaling Vision-Language Models

On Error Propagation of Diffusion Models

Separating common from salient patterns with Contrastive Representation Learning

Enhancing Neural Subset Selection: Integrating Background Information into Set Representations

Domain-Agnostic Molecular Generation with Self-feedback

Quantifying the Plausibility of Context Reliance in Neural Machine Translation

OctoPack: Instruction Tuning Code Large Language Models

An Emulator for Fine-tuning Large Language Models using Small Language Models

Logical Languages Accepted by Transformer Encoders with Hard Attention

Learning Nash equilibria in Rank-1 games: Going beyond the Minty Property

SEA: Sparse Linear Attention with Estimated Attention Mask

DiffEnc: Variational Diffusion with a Learned Encoder

DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model

Convolutional Deep Kernel Machines

Like Oil and Water: Group Robustness Methods and Poisoning Defenses Don't Mix

Learning Thresholds with Latent Values and Censored Feedback

On Accelerating Diffusion-Based Sampling Processes via Improved Integration Approximation

Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

From Sparse to Soft Mixtures of Experts

ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF

Modulate Your Spectrum in Self-Supervised Learning

DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines

Batched Low-Rank Adaptation of Foundation Models

Improving protein optimization with smoothed fitness landscapes

Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field

Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise

Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI

Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners

Neuron-Enhanced AutoEncoder Matrix Completion and Collaborative Filtering: Theory and Practice

Amortizing intractable inference in large language models

FeatUp: A Model-Agnostic Framework for Features at Any Resolution

Planting a SEED of Vision in Large Language Model

Improving equilibrium propagation without weight symmetry through Jacobian homeostasis

InstructDET: Diversifying Referring Object Detection with Generalized Instructions

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

Privacy-Preserving In-Context Learning for Large Language Models

BatteryML:An Open-source platform for Machine Learning on Battery Degradation

Neural Spectral Methods: Self-supervised learning in the spectral domain

Probabilistically Rewired Message-Passing Neural Networks

Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models

Consistent Multi-Class Classification from Multiple Unlabeled Datasets

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

TapMo: Shape-aware Motion Generation of Skeleton-free Characters

Interpretable Meta-Learning of Physical Systems

Learning model uncertainty as variance-minimizing instance weights

Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods

Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control

CNN Kernels Can Be the Best Shapelets

AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

Alignment as Reward-Guided Search

Context is Environment

Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning

Nougat: Neural Optical Understanding for Academic Documents

Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited

Treatment Effects Estimation By Uniform Transformer

Language Model Self-improvement by Reinforcement Learning Contemplation

Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)

Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization

HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion

Threaten Spiking Neural Networks through Combining Rate and Temporal Information

Contrastive Learning is Spectral Clustering on Similarity Graph

Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding

Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors

The Discovery of Binding Modes Requires Rethinking Docking Generalization

Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models

An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization

A Benchmark for Learning to Translate a New Language from One Grammar Book

Generative Sliced MMD Flows with Riesz Kernels

Improving Out-of-Domain Generalization with Domain Relations

Fine-Tuned Language Models Generate Stable Inorganic Materials as Text

Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Small-scale Optimizer and Small Training Dataset

The Truth Is In There: Improving Reasoning with Layer-Selective Rank Reduction

SWE-bench: Can Language Models Resolve Real-world Github Issues?

HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

A Theoretical Explanation of Deep RL Performance in Stochastic Environments

Learning Grounded Action Abstractions from Language

UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition

A Unified Approach for Online Continuous DR-Submodular Maximization

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Hybrid Sharing for Multi-Label Image Classification

Compositional VLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding

Space and time continuous physics simulation from partial observations

Don't Play Favorites: Minority Guidance for Diffusion Models

PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation

Protein-ligand binding representation learning from fine-grained interactions

VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

Grounding Language Plans in Demonstrations Through Counter-Factual Perturbations

Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models

The Need for Speed: Pruning Transformers with One Recipe

Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following

How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization

Talk like a Graph: Encoding Graphs for Large Language Models

ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

Follow-the-Perturbed-Leader for Adversarial Bandits: Heavy Tails, Robustness, and Privacy

Toward Student-oriented Teacher Network Training for Knowledge Distillation

FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler

Neural Monge Map estimation and its applications

Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFace

What does the Knowledge Neuron Thesis Have to do with Knowledge?

Adversarial Training Should Be Cast as a Non-Zero-Sum Game

Towards Robust Out-of-Distribution Generalization Bounds via Sharpness

Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit

Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering Perspective

Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression

Multi-Scale Representations by Varing Window Attention for Semantic Segmentation

Tag2Text: Guiding Vision-Language Model via Image Tagging

Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning

QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models

Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching

Evaluating Large Language Models at Evaluating Instruction Following

CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction

A Flexible Generative Model for Heterogeneous Tabular EHR with Missing Modality

Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization

Bayesian Bi-clustering of Neural Spiking Activity with Latent Structures

Vision-by-Language for Training-Free Compositional Image Retrieval

Online GNN Evaluation Under Test-time Graph Distribution Shifts

Monte Carlo guided Denoising Diffusion models for Bayesian linear inverse problems.

Pseudo-Generalized Dynamic View Synthesis from a Video

Two-timescale Extragradient for Finding Local Minimax Points

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model

On Stationary Point Convergence of PPO-Clip

GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers

On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning

Image Inpainting via Tractable Steering of Diffusion Models

On the Limitations of Temperature Scaling for Distributions with Overlaps

ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms

Submodular Reinforcement Learning

Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values.

AutoVP: An Automated Visual Prompting Framework and Benchmark

Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks

Understanding Certified Training with Interval Bound Propagation

VDT: General-purpose Video Diffusion Transformers via Mask Modeling

ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs

Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation

Symbol as Points: Panoptic Symbol Spotting via Point-based Representation

New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions

Chain of Log-Concave Markov Chains

AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification

SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation

Topological data analysis on noisy quantum computers

An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models

Sliced Wasserstein Estimation with Control Variates

Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks

Invariance-based Learning of Latent Dynamics

Adaptive Window Pruning for Efficient Local Motion Deblurring

Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning

Be More Active! Understanding the Differences Between Mean and Sampled Representations of Variational Autoencoders

Listen, Think, and Understand

Out-of-Distribution Detection with Negative Prompts

GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models

Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis Data

Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning

PlaSma: Procedural Knowledge Models for Language-based Planning and Re-Planning

Addressing Catastrophic Forgetting and Loss of Plasticity in Neural Networks

Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis

Defining and extracting generalizable interaction primitives from DNNs

(ends 9:30 AM)

Affinity Posters:

Blog Track Session 4

(ends 9:30 AM)

Affinity Posters:

Tiny Papers Poster Session 4

(ends 9:30 AM)

11 p.m.

Registration Desk

(ends 9:30 AM)

11:30 p.m.

Invited Talk:

Devi Parikh

(ends 12:30 AM)

THU 9 MAY

12:30 a.m.

Coffee Break

1 a.m.

Oral 5D [1:00-1:45]

Interpreting CLIP's Image Representation via Text-Based Decomposition

Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video

(ends 1:45 AM)

Oral 5B [1:00-1:45]

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Finetuning Text-to-Image Diffusion Models for Fairness

Unprocessing Seven Years of Algorithmic Fairness

(ends 1:45 AM)

Oral 5C [1:00-1:45]

Neural Fine-Tuning Search for Few-Shot Learning

Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time

Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How

(ends 1:45 AM)

Oral 5A [1:00-1:45]

Generalization in diffusion models arises from geometry-adaptive harmonic representation

Diffusion Model for Dense Matching

Generative Modeling with Phase Stochastic Bridge

(ends 1:45 AM)

1:45 a.m.

Poster Session 5 [1:45-3:45]

Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion Models

Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products

Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control

When can transformers reason with abstract symbols?

Learning Multi-Agent Communication with Contrastive Learning

Debiased Collaborative Filtering with Kernel-based Causal Balancing

Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data

Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer

Domain constraints improve risk prediction when outcome data is missing

Personalize Segment Anything Model with One Shot

Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX

Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning

R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning

MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training

Masked Structural Growth for 2x Faster Language Model Pre-training

Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time

Learning Implicit Representation for Reconstructing Articulated Objects

Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?

Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape

Neural Fine-Tuning Search for Few-Shot Learning

FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning

Object-Aware Inversion and Reassembly for Image Editing

PRIME: Prioritizing Interpretability in Failure Mode Extraction

Online Stabilization of Spiking Neural Networks

TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series

GIM: Learning Generalizable Image Matcher From Internet Videos

T-Rep: Representation Learning for Time Series using Time-Embeddings

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Efficient Modulation for Vision Networks

Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model

StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive Learning

P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering

Two-stage LLM Fine-tuning with Less Specialization and More Generalization

AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model

Cycle Consistency Driven Object Discovery

Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network

PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation

CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing

SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation

On the Stability of Expressive Positional Encodings for Graph Neural Networks

Pre-training with Random Orthogonal Projection Image Modeling

TorchRL: A data-driven decision-making library for PyTorch

One Step of Gradient Descent is Provably the Optimal In-Context Learner with One Layer of Linear Self-Attention

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

Language Modeling Is Compression

Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-Image Generation

How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation

Think before you speak: Training Language Models With Pause Tokens

Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes

3D Reconstruction with Generalizable Neural Fields using Scene Priors

Fair and Efficient Contribution Valuation for Vertical Federated Learning

Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis

FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent

Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models

Diffusion-TS: Interpretable Diffusion for General Time Series Generation

An Efficient Tester-Learner for Halfspaces

Masked Completion via Structured Diffusion with White-Box Transformers

Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems

Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation

Investigating the Benefits of Projection Head for Representation Learning

Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations

Training Unbiased Diffusion Models From Biased Dataset

Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing

Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity

Efficient Subgraph GNNs by Learning Effective Selection Policies

RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering

Neur2RO: Neural Two-Stage Robust Optimization

Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data

IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models

Denoising Task Routing for Diffusion Models

In-context Exploration-Exploitation for Reinforcement Learning

Learning Personalized Causally Invariant Representations for Heterogeneous Federated Clients

I-PHYRE: Interactive Physical Reasoning

Counting Graph Substructures with Graph Neural Networks

A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning

Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits

DeepSPF: Spherical SO(3)-Equivariant Patches for Scan-to-CAD Estimation

Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World

MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design

The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model

Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability

DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness

Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation

sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows

Embarrassingly Simple Dataset Distillation

Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning

Finetuning Text-to-Image Diffusion Models for Fairness

Win-Win: Training High-Resolution Vision Transformers from Two Windows

Improved sampling via learned diffusions

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers

Towards Category Unification of 3D Single Object Tracking on Point Clouds

Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions

UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science

NECO: NEural Collapse Based Out-of-distribution detection

Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations

Provable Offline Preference-Based Reinforcement Learning

Distributionally Robust Optimization with Bias & Variance Reduced Gradients

Text-to-3D with Classifier Score Distillation

Making Pre-trained Language Models Great on Tabular Prediction

Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND

Negative Label Guided OOD Detection with Pretrained Vision-Language Models

DEEP NEURAL NETWORK INITIALIZATION WITH SPARSITY INDUCING ACTIVATIONS

The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models

Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models

Compositional Preference Models for Aligning LMs

FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition

Do Large Language Models Know about Facts?

To the Cutoff... and Beyond? A Longitudinal Perspective on LLM Data Contamination

Universal Graph Random Features

Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback

GTMGC: Using Graph Transformer to Predict Molecule’s Ground-State Conformation

Experimental Design for Multi-Channel Imaging via Task-Driven Feature Selection

The Effectiveness of Random Forgetting for Robust Generalization

Near-Optimal Solutions of Constrained Learning Problems

Fast Ensembling with Diffusion Schr\"odinger Bridge

Beating Price of Anarchy and Gradient Descent without Regret in Potential Games

Adaptive deep spiking neural network with global-local learning via balanced excitatory and inhibitory mechanism

VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections

Multi-Resolution Diffusion Models for Time Series Forecasting

Coeditor: Leveraging Repo-level Diffs for Code Auto-editing

Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach

Identifying Policy Gradient Subspaces

Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior

Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank

Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification

Learning to Solve Bilevel Programs with Binary Tender

TEDDY: Trimming Edges with Degree-based Graph Diffusion Strategy

MEND: Meta Demonstration Distillation for Efficient and Effective In-Context Learning

ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning

DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation

Large Language Models to Enhance Bayesian Optimization

AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Framework

Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm

PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks

On the hardness of learning under symmetries

A Benchmark on Robust Semi-Supervised Learning in Open Environments

Training Diffusion Models with Reinforcement Learning

Unprocessing Seven Years of Algorithmic Fairness

Boosting Graph Anomaly Detection with Adaptive Message Passing

In-Context Pretraining: Language Modeling Beyond Document Boundaries

Unknown Domain Inconsistency Minimization for Domain Generalization

DENEVIL: TOWARDS DECIPHERING AND NAVIGATING THE ETHICAL VALUES OF LARGE LANGUAGE MODELS VIA INSTRUCTION LEARNING

Structural Inference with Dynamics Encoding and Partial Correlation Coefficients

A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling

Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing

Quality-Diversity through AI Feedback

Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning

Learning Performance-Improving Code Edits

The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World

Energy-guided Entropic Neural Optimal Transport

Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips

DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization

ADoPD: A Large-Scale Document Page Decomposition Dataset

Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees

Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment

Consistent Video-to-Video Transfer Using Synthetic Dataset

BECLR: Batch Enhanced Contrastive Few-Shot Learning

Numerical Accounting in the Shuffle Model of Differential Privacy

Frozen Transformers in Language Models Are Effective Visual Encoder Layers

Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy

Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data

PB-LLM: Partially Binarized Large Language Models

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling

HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs

HYPO: Hyperspherical Out-Of-Distribution Generalization

Boosting Selective Rationalization with Shortcuts Discovery

Subtractive Mixture Models via Squaring: Representation and Learning

QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models

Magnushammer: A Transformer-Based Approach to Premise Selection

Object-Centric Learning with Slot Mixture Module

Neural Ordinary Differential Equations for Modeling Epidemic Spreading

FasterViT: Fast Vision Transformers with Hierarchical Attention

RLIF: Interactive Imitation Learning as Reinforcement Learning

Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces

Dynamic Layer Tying for Parameter-Efficient Transformers

Universal Jailbreak Backdoors from Poisoned Human Feedback

A unified sampling framework for solver searching of Diffusion Probabilistic Models

Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models

Learning to Jointly Understand Visual and Tactile Signals

How do Language Models Bind Entities in Context?

Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!

Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts

Improving LoRA in Privacy-preserving Federated Learning

A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation

A Generative Pre-Training Framework for Spatio-Temporal Graph Transfer Learning

DittoGym: Learning to Control Soft Shape-Shifting Robots

What's In My Big Data?

Generalization in diffusion models arises from geometry-adaptive harmonic representation

Dual RL: Unification and New Methods for Reinforcement and Imitation Learning

Adaptive Sharpness-Aware Pruning for Robust Sparse Networks

Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning

Scaling Supervised Local Learning with Augmented Auxiliary Networks

Evaluating the Zero-shot Robustness of Instruction-tuned Language Models

Looped Transformers are Better at Learning Learning Algorithms

GnnX-Bench: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking

A Fast and Provable Algorithm for Sparse Phase Retrieval

Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models

RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation

Reverse Forward Curriculum Learning for Extreme Sample and Demo Efficiency

Harnessing Overlap in Blockwise Transformers for Near-Infinite Context

Blending Imitation and Reinforcement Learning for Robust Policy Improvement

Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models

DP-SGD Without Clipping: The Lipschitz Neural Network Way

MT-Ranker: Reference-free machine translation evaluation by inter-system ranking

Copula Conformal prediction for multi-step time series prediction

STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models

Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference for Recommendation

Spatially-Aware Transformers for Embodied Agents

RAIN: Your Language Models Can Align Themselves without Finetuning

On Characterizing the Trade-off in Invariant Representation Learning

BadEdit: Backdooring Large Language Models by Model Editing

Learning Multi-Faceted Prototypical User Interests

Adaptive Self-training Framework for Fine-grained Scene Graph Generation

Efficient Multi-agent Reinforcement Learning by Planning

Diffusion Model for Dense Matching

Teach LLMs to Phish: Stealing Private Information from Language Models

The HIM Solution for Legged Locomotion: Minimal Sensors, Efficient Learning, and Substantial Agility

Compressing Latent Space via Least Volume

Communication-Efficient Federated Non-Linear Bandit Optimization

Neural SDF Flow for 3D Reconstruction of Dynamic Scenes

Memorization Capacity of Multi-Head Attention in Transformers

InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation

PolyVoice: Language Models for Speech to Speech Translation

RTFS-Net: Recurrent time-frequency modelling for efficient audio-visual speech separation

Counterfactual Density Estimation using Kernel Stein Discrepancies

Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Map

Order-Preserving GFlowNets

Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How

Towards Offline Opponent Modeling with In-context Learning

TRAM: Bridging Trust Regions and Sharpness Aware Minimization

COCO-Periph: Bridging the Gap Between Human and Machine Perception in the Periphery

Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks

Interpreting CLIP's Image Representation via Text-Based Decomposition

R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation

Periodicity Decoupling Framework for Long-term Series Forecasting

Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions

Forward Learning of Graph Neural Networks

Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video

SEPT: Towards Efficient Scene Representation Learning for Motion Prediction

A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables

Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood

PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION

Future Language Modeling from Temporal Document History

L2MAC: Large Language Model Automatic Computer for Unbounded Code Generation

Stabilizing Backpropagation Through Time to Learn Complex Physics

Urial: Aligning Untuned LLMs with Just the 'Write' Amount of In-Context Learning

Grokking as the transition from lazy to rich training dynamics

Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets

Interpretable Diffusion via Information Decomposition

OWL: A Large Language Model for IT Operations

AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction

Feasibility-Guided Safe Offline Reinforcement Learning

Debiasing Attention Mechanism in Transformer without Demographics

Frequency-Aware Transformer for Learned Image Compression

Debiasing Algorithm through Model Adaptation

ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference

Maximum Entropy Model Correction in Reinforcement Learning

Encoding Unitig-level Assembly Graphs with Heterophilous Constraints for Metagenomic Contigs Binning

Single Motion Diffusion

Active Retrosynthetic Planning Aware of Route Quality

Are Models Biased on Text without Gender-related Language?

Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity Tracking

Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity

ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation

Spatio-Temporal Approximation: A Training-Free SNN Conversion for Transformers

Magnitude Invariant Parametrizations Improve Hypernetwork Learning

SE(3)-Stochastic Flow Matching for Protein Backbone Generation

CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning

Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control

CCIL: Continuity-Based Data Augmentation for Corrective Imitation Learning

Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction

FairVLM: Mitigating Bias In Pre-Trained Vision-Language Models

Generative Modeling with Phase Stochastic Bridge

Divide and not forget: Ensemble of selectively trained experts in Continual Learning

EMO: EARTH MOVER DISTANCE OPTIMIZATION FOR AUTO-REGRESSIVE LANGUAGE MODELING

Skill or Luck? Return Decomposition via Advantage Functions

KW-Design: Pushing the Limit of Protein Deign via Knowledge Refinement

Achieving Human Parity in Content-Grounded Datasets Generation

TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting

ImagenHub: Standardizing the evaluation of conditional image generation models

Alpagasus: Training a Better Alpaca Model with Fewer Data

(ends 3:45 AM)

Affinity Posters:

Blog Track Session 5

(ends 3:45 AM)

Affinity Posters:

Tiny Papers Poster Session 5

(ends 3:45 AM)

3:45 a.m.

Expo Talk Panel:

Advances in private training for production on-device language models

(ends 5:15 AM)

Lunch Break

4:15 a.m.

Affinity Workshop:

Tiny Papers Oral Session 3

(ends 5:15 AM)

5:15 a.m.

Invited Talk:

The ChatGLM's Road to AGI

Jie Tang

(ends 6:15 AM)

6:15 a.m.

Coffee Break

6:45 a.m.

Oral 6C [6:45-7:30]

Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning

Towards a statistical theory of data selection under weak supervision

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors

(ends 7:30 AM)

Oral 6D [6:45-7:30]

Multi-granularity Correspondence Learning from Long-term Noisy Videos

Zipformer: A faster and better encoder for automatic speech recognition

(ends 7:30 AM)

Oral 6A [6:45-7:30]

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation

ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis

How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models

(ends 7:30 AM)

Oral 6B [6:45-7:30]

GraphGuard: Provably Robust Graph Classification against Adversarial Attacks

Proving Test Set Contamination for Black-Box Language Models

LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language Models

(ends 7:30 AM)

7:30 a.m.

Poster Session 6 [7:30-9:30]

Lie Group Decompositions for Equivariant Neural Networks

Neural Field Classifiers via Target Encoding and Classification Loss

Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing

From Zero to Turbulence: Generative Modeling for 3D Flow Simulation

Robust Training of Federated Models with Extremely Label Deficiency

IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models

Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages

Concept Bottleneck Generative Models

Fast Updating of Truncated SVD for Representation Learning in Sparse Matrix

$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States

Compressing LLMs: The Truth is Rarely Pure and Never Simple

Context-Aware Meta-Learning

Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks

Combining Spatial and Temporal Abstraction in Planning for Better Generalization

Federated Causal Discovery from Heterogeneous Data

Explaining Kernel Clustering via Decision Trees

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis

Finite Scalar Quantization: VQ-VAE Made Simple

Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection

Enhancing Contrastive Learning for Ordinal Regression via Ordinal Content Preserved Data Augmentation

EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations

Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?

Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search

GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion

FedWon: Triumphing Multi-domain Federated Learning Without Normalization

Sparsistency for inverse optimal transport

Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency

Diverse Projection Ensembles for Distributional Reinforcement Learning

Solving High Frequency and Multi-Scale PDEs with Gaussian Processes

Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments

NeurRev: Train Better Sparse Neural Network Practically via Neuron Revitalization

Contextual Bandits with Online Neural Regression

MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images

Pathologies of Predictive Diversity in Deep Ensembles

MOFI: Learning Image Representations from Noisy Entity Annotated Images

Scaling physics-informed hard constraints with mixture-of-experts

Domain-Inspired Sharpness Aware Minimization Under Domain Shifts

A Unified Framework for Bayesian Optimization under Contextual Uncertainty

LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention

Nemesis: Normalizing the soft-prompt vectors of vision-language models

Guiding Instruction-based Image Editing via Multimodal Large Language Models

Parsing neural dynamics with infinite recurrent switching linear dynamical systems

Delta-AI: Local objectives for amortized inference in sparse graphical models

Hybrid Directional Graph Neural Network for Molecules

Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging

Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning

Sample Relationship from Learning Dynamics Matters for Generalisation

Negatively Correlated Ensemble Reinforcement Learning for Online Diverse Game Level Generation

Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment

How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models

Neural Processing of Tri-Plane Hybrid Neural Fields

SliceGPT: Compress Large Language Models by Deleting Rows and Columns

Window Attention is Bugged: How not to Interpolate Position Embeddings

CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting

Efficient local linearity regularization to overcome catastrophic overfitting

HyperAttention: Long-context Attention in Near-Linear Time

Transformer-VQ: Linear-Time Transformers via Vector Quantization

Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models

Language-Interfaced Tabular Oversampling via Progressive Imputation and Self-Authentication

Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling

Empirical Likelihood for Fair Classification

DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization

Towards a statistical theory of data selection under weak supervision

SafeDreamer: Safe Reinforcement Learning with World Models

SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction

CAS: A Probability-Based Approach for Universal Condition Alignment Score

Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach

Learning the greatest common divisor: explaining transformer predictions

Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models

PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks

Meta-Learning Priors Using Unrolled Proximal Neural Networks

Optimal transport based adversarial patch to leverage large scale attack transferability

GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction

Self-Supervised Dataset Distillation for Transfer Learning

CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis

Large Language Models are Efficient Learners of Noise-Robust Speech Recognition

Classification with Conceptual Safeguards

ReTaSA: A Nonparametric Functional Estimation Approach for Addressing Continuous Target Shift

Reasoning with Latent Diffusion in Offline Reinforcement Learning

On the Over-Memorization During Natural, Robust and Catastrophic Overfitting

Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis

Enhancing Human-AI Collaboration Through Logic-Guided Reasoning

Learning invariant representations of time-homogeneous stochastic dynamical systems

Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting

Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability

Knowledge Fusion of Large Language Models

Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation

Group Preference Optimization: Few-Shot Alignment of Large Language Models

Noise-free Score Distillation

AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection

Robustifying and Boosting Training-Free Neural Architecture Search

Grounded Object-Centric Learning

CoLiDE: Concomitant Linear DAG Estimation

Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding

A Plug-and-Play Image Registration Network

LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition

CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules

LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language Models

Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning

SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning

MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Unveiling and Manipulating Prompt Influence in Large Language Models

Benchmarking Algorithms for Federated Domain Generalization

Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight

Learning Optimal Contracts: How to Exploit Small Action Spaces

Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning

Noise Map Guidance: Inversion with Spatial Context for Real Image Editing

PINNACLE: PINN Adaptive ColLocation and Experimental points selection

Implicit regularization of deep residual networks towards neural ODEs

Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo

Spectrally Transformed Kernel Regression

Sample-Efficient Quality-Diversity by Cooperative Coevolution

PromptTTS 2: Describing and Generating Voices with Text Prompt

On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods

Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems

On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks

Manifold Diffusion Fields

AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

What Makes a Good Prune? Optimal Unstructured Pruning for Maximal Cosine Similarity

Mixture of Weak and Strong Experts on Graphs

Controlled Text Generation via Language Model Arithmetic

The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric

Patches Are All You Need?

On the Sample Complexity of Lipschitz Constant Estimation

Dual Associated Encoder for Face Restoration

Efficient Score Matching with Deep Equilibrium Layers

A Progressive Training Framework for Spiking Neural Networks with Learnable Multi-hierarchical Model

Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures

Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective

Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning

GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision Boundaries

Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory

Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning

On the Reliability of Watermarks for Large Language Models

Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions

Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation

Constrained Decoding for Cross-lingual Label Projection

Hypothesis Search: Inductive Reasoning with Language Models

On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning

Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction

Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection

Off-Policy Primal-Dual Safe Reinforcement Learning

IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs

Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach

Optimal Sample Complexity for Average Reward Markov Decision Processes

One-hot Generalized Linear Model for Switching Brain State Discovery

Zipformer: A faster and better encoder for automatic speech recognition

SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution

PBADet: A One-Stage Anchor-Free Approach for Part-Body Association

Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP

Provably Robust Conformal Prediction with Improved Efficiency

Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy

Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation

EControl: Fast Distributed Optimization with Compression and Error Control

Multimodal Web Navigation with Instruction-Finetuned Foundation Models

Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs

Influencer Backdoor Attack on Semantic Segmentation

Rethinking the symmetry-preserving circuits for constrained variational quantum algorithms

SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training

Balancing Act: Sparse Models with Constrained Disparate Impact

GRAPH-CONSTRAINED DIFFUSION FOR END-TO-END PATH PLANNING

ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models

GraphGuard: Provably Robust Graph Classification against Adversarial Attacks

iGraphMix: Input Graph Mixup Method for Node Classification

Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents

Generating Images in Context with Multimodal Large Language Models

Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization

LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models

Proving Test Set Contamination for Black-Box Language Models

Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction

FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis

Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping

Matryoshka Diffusion Models

Efficient Integrators for Diffusion Generative Models

Constraint-Free Structure Learning with Smooth Acyclic Orientations

A General Framework for User-Guided Bayesian Optimization

LEAP: Liberate Sparse-View 3D Modeling from Camera Poses

FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods

Enhancing Neural Training via a Correlated Dynamics Model

Finite-State Autoregressive Entropy Coding for Efficient Learned Lossless Compression

ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models

Diffusion Models for Multi-Task Generative Modeling

The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models

Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks

ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search

Adapting to Distribution Shift by Visual Domain Prompt Generation

Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts

Efficient Backpropagation with Variance Controlled Adaptive Sampling

Can Large Language Models Infer Causation from Correlation?

ELoRA: Efficient Low-Rank Adaptation with Random Matrices

Large Language Models as Optimizers

Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram

Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning

Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors

Intriguing Properties of Generative Classifiers

Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners

Enhanced Face Recognition using Intra-class Incoherence Constraint

Privately Aligning Language Models with Reinforcement Learning

Faster Approximation of Probabilistic and Distributional Values via Least Squares

Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations

Robotic Task Generalization via Hindsight Trajectory Sketches

Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization

Graph Lottery Ticket Automated

DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer

NfgTransformer: Equivariant Representation Learning for Normal-form Games

LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation

Training Graph Transformers via Curriculum-Enhanced Attention Distillation

Synergistic Patch Pruning for Vision Transformer: Unifying Intra- & Inter-Layer Patch Importance

Training Bayesian Neural Networks with Sparse Subspace Variational Inference

Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework

AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?

SALMONN: Towards Generic Hearing Abilities for Large Language Models

In-Context Learning Dynamics with Random Binary Sequences

Doubly Robust Instance-Reweighted Adversarial Training

Offline RL with Observation Histories: Analyzing and Improving Sample Complexity

Causal-StoNet: Causal Inference for High-Dimensional Complex Data

SemiReward: A General Reward Model for Semi-supervised Learning

Self-Supervised Contrastive Forecasting

Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks

Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach

MgNO: Efficient Parameterization of Linear Operators via Multigrid

Image Clustering Conditioned on Text Criteria

Data Filtering Networks

On the Fairness ROAD: Robust Optimization for Adversarial Debiasing

Locality-Aware Graph Rewiring in GNNs

FairSeg: A Large-scale Medical Image Segmentation Dataset for Fairness Learning with Fair Error-Bound Scaling

Algorithms for Caching and MTS with reduced number of predictions

Llemma: An Open Language Model for Mathematics

Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting

The optimality of kernel classifiers in Sobolev space

Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction

RETSim: Resilient and Efficient Text Similarity

FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data

Probabilistic Adaptation of Black-Box Text-to-Video Models

Demystifying Linear MDPs and Novel Dynamics Aggregation Framework

Geometry-Aware Projective Mapping for Unbounded Neural Radiance Fields

Prediction without Preclusion: Recourse Verification with Reachable Sets

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning

Causality-Inspired Spatial-Temporal Explanations for Dynamic Graph Neural Networks

Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment

Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting

DAM: A Foundation Model for Forecasting

AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation

BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction

Multi-granularity Correspondence Learning from Long-term Noisy Videos

Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning

Out-of-Variable Generalisation for Discriminative Models

Meaning Representations from Trajectories in Autoregressive Models

Generalization error of spectral algorithms

Provable Reward-Agnostic Preference-Based Reinforcement Learning

ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models

GIO: Gradient Information Optimization for Training Dataset Selection

Understanding AI Cognition: A Neural Module for Inference Inspired by Human Memory Mechanisms

Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy

Tree-Planner: Efficient Close-loop Task Planning with Large Language Models

Dynamic Discounted Counterfactual Regret Minimization

f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization

Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow

Augmenting transformers with recursively composed multi-grained representations

Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings

Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants

Multi-View Representation is What You Need for Point-Cloud Pre-Training

Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression

Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning

Behaviour Distillation

Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning

Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate

One For All: Towards Training One Graph Model For All Classification Tasks

Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder

(InThe)WildChat: 570K ChatGPT Interaction Logs In The Wild

Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for Molecule Generation

MINDE: Mutual Information Neural Diffusion Estimation

Whole-song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models

Making Retrieval-Augmented Language Models Robust to Irrelevant Context

Unlocking the Power of Representations in Long-term Novelty-based Exploration

The Human-AI Substitution game: active learning from a strategic labeler

A Primal-Dual Approach to Solving Variational Inequalities with General Constraints

Incremental Randomized Smoothing Certification

Zero Bubble (Almost) Pipeline Parallelism

ODEFormer: Symbolic Regression of Dynamical Systems with Transformers

Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities

VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks

Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph

An improved analysis of per-sample and per-update clipping in federated learning

Efficient Planning with Latent Diffusion

SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning

NP-GL: Extending Power of Nature from Binary Problems to Real-World Graph Learning

(ends 9:30 AM)

Affinity Posters:

Blog Track Session 6

(ends 9:30 AM)

Affinity Posters:

Tiny Papers Poster Session 6

(ends 9:30 AM)

11 p.m.

Registration Desk

(ends 9:30 AM)

11:30 p.m.

Invited Talk:

The emerging science of benchmarks

Moritz Hardt

(ends 12:30 AM)

FRI 10 MAY

12:30 a.m.

Coffee Break

1 a.m.

Oral 7B [1:00-1:45]

Cameras as Rays: Sparse-view Pose Estimation via Ray Diffusion

"What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data Selection

Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models

(ends 1:45 AM)

Oral 7C [1:00-1:45]

Less is More: Fewer Interpretable Region via Submodular Subset Selection

On the Joint Interaction of Models, Data, and Features

(ends 1:45 AM)

Oral 7A [1:00-1:45]

Small-scale proxies for large-scale Transformer training instabilities

An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment

Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming

(ends 1:45 AM)

Oral 7D [1:00-1:45]

One-shot Empirical Privacy Estimation for Federated Learning

On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs

(ends 1:45 AM)

1:45 a.m.

Poster Session 7 [1:45-3:45]

Posters 1:45-3:45

SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS

SaNN: Simple Yet Powerful Simplicial-aware Neural Networks

Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios

Revisiting Link Prediction: a data perspective

Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks

One-shot Empirical Privacy Estimation for Federated Learning

In defense of parameter sharing for model-compression

Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization

Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation

Pose Modulated Avatars from Video

Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation

RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems

ZeroFlow: Scalable Scene Flow via Distillation

Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers

Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula

$\mathbb{D}^2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning

NetInfoF Framework: Measuring and Exploiting Network Usable Information

MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo

DyST: Towards Dynamic Neural Scene Representations on Real-World Videos

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests

Multi-View Causal Representation Learning with Partial Observability

MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding

Structural Fairness-aware Active Learning for Graph Neural Networks

Learning to Act from Actionless Videos through Dense Correspondences

A Discretization Framework for Robust Contextual Stochastic Optimization

Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming

Human Motion Diffusion as a Generative Prior

On Differentially Private Federated Linear Contextual Bandits

Alt-Text with Context: Improving Accessibility for Images on Twitter

Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification

Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees

A Study of Bayesian Neural Network Surrogates for Bayesian Optimization

Locality Sensitive Sparse Encoding for Learning World Models Online

Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition

Decodable and Sample Invariant Continuous Object Encoder

Scalable Language Model with Generalized Continual Learning

Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design

Prometheus: Inducing Evaluation Capability in Language Models

Towards Meta-Pruning via Optimal Transport

Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code

Dynamic Neural Response Tuning

Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks

Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain

Let's Verify Step by Step

Knowledge Distillation Based on Transformed Teacher Matching

Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games

Exploring the Promise and Limits of Real-Time Recurrent Learning

Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in AI Models

Entropy-MCMC: Sampling from Flat Basins with Ease

LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures

How Does Unlabeled Data Provably Help Out-of-Distribution Detection?

The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models

WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video

Bayesian Low-rank Adaptation for Large Language Models

Variational Bayesian Last Layers

Local Composite Saddle Point Optimization

Cascading Reinforcement Learning

Text-driven Prompt Generation for Vision-Language Models in Federated Learning

Kalman Filter Online Learning from non-Stationary Data

Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information

Large Language Models Are Not Robust Multiple Choice Selectors

Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models

L2P-MIP: Learning to Presolve for Mixed Integer Programming

SolidGen: An Autoregressive Model for Direct B-rep Synthesis

PAE: Reinforcement Learning from External Knowledge for Efficient Exploration

GAIA: a benchmark for General AI Assistants

Does CLIP’s generalization performance mainly stem from high train-test similarity?

An Investigation of Representation and Allocation Harms in Contrastive Learning

What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning

Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection

Bespoke Solvers for Generative Flow Models

Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks

Feature Collapse

Online Continual Learning for Interactive Instruction Following Agents

Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages

Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game

FITS: Modeling Time Series with $10k$ Parameters

SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

Conformal Inductive Graph Neural Networks

HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance

Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation

Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces

OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS

Mean Field Theory in Deep Metric Learning

Learning with Mixture of Prototypes for Out-of-Distribution Detection

Proper Laplacian Representation Learning

A Linear Algebraic Framework for Counterfactual Generation

Learning From Simplicial Data Based on Random Walks and 1D Convolutions

Convergence of Bayesian Bilevel Optimization

Canonpipe: Data Debugging with Shapley Importance over Machine Learning Pipelines

Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty

LCOT: Linear Circular Optimal Transport

Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization

Universal Backdoor Attacks

Long-range Neural Atom Learning for Molecular Graphs

DOS: Diverse Outlier Sampling for Out-of-Distribution Detection

Independent-Set Design of Experiments for Estimating Treatment and Spillover Effects under Network Interference

Efficacy of Dual-Encoders for Extreme Multi-label Classification

ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis

Jointly Training Large Autoregressive Multimodal Models

PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization

ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update

Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model

OpenNerf: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking

On the Provable Advantage of Unsupervised Pretraining

Early Stopping Against Label Noise Without Validation Data

Idempotent Generative Network

Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain

Gradual Optimization Learning for Conformational Energy Minimization

Score Models for Offline Goal-Conditioned Reinforcement Learning

Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community

Raidar: geneRative AI Detection viA Rewriting

GraphChef: Decision-Tree Recipes to Explain Graph Neural Networks

Learning 3D Particle-based Simulators from RGB-D Videos

Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain

What's in a Prior? Learned Proximal Networks for Inverse Problems

Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images

Adaptive Instrument Design for Indirect Experiments

Incentivized Truthful Communication for Federated Bandits

Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning

Modulated Phase Diffusor: Content-Oriented Feature Synthesis for Detecting Unknown Objects

Octavius: Mitigating Task Interference in MLLMs via MoE

What Algorithms can Transformers Learn? A Study in Length Generalization

Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition

GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs

RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations

Understanding prompt engineering may not require rethinking generalization

How connectivity structure shapes rich and lazy learning in neural circuits

On Trajectory Augmentations for Off-Policy Evaluation

Exploring Target Representations for Masked Autoencoders

Incentive-Aware Federated Learning with Training-Time Model Rewards

SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models

Fixed-Budget Differentially Private Best Arm Identification

Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular Design

A Differentially Private Clustering Algorithm for Well-Clustered Graphs

Modelling complex vector drawings with stroke-clouds

Outlier-Robust Subsampling Techniques for Persistent Homology

Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective

Is Self-Repair a Silver Bullet for Code Generation?

Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model

Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering

THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS

Implicit Neural Representations and the Algebra of Complex Wavelets

Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling

SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition

Turning large language models into cognitive models

A Policy Gradient Method for Confounded POMDPs

Motif: Intrinsic Motivation from Artificial Intelligence Feedback

Decoupling regularization from the action space

Generalization of Deep ResNets in the Mean-Field Regime

Small-scale proxies for large-scale Transformer training instabilities

Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data

Adaptive Rational Activations to Boost Deep Reinforcement Learning

Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods

Circumventing Concept Erasure Methods For Text-To-Image Generative Models

Neural structure learning with stochastic differential equations

CLEX: Continuous Length Extrapolation for Large Language Models

RealChat-1M: A Large-Scale Real-World LLM Conversation Dataset

Compositional Generative Inverse Design

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing

PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes

The Consensus Game: Language Model Generation via Equilibrium Search

An LLM can Fool Itself: A Prompt-Based Adversarial Attack

On Representation Complexity of Model-based and Model-free Reinforcement Learning

Graph Transformers on EHRs: Better Representation Improves Downstream Performance

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

Gradual Domain Adaptation via Gradient Flow

Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration

Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization

Enhancing Instance-Level Image Classification with Set-Level Labels

Understanding when Dynamics-Invariant Data Augmentations Benefit Model-free Reinforcement Learning Updates

Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning

Principled Architecture-aware Scaling of Hyperparameters

Learning Polynomial Problems with $SL(2, \mathbb{R})$-Equivariance

Intriguing Properties of Data Attribution on Diffusion Models

On the Joint Interaction of Models, Data, and Features

DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation

Understanding Domain Generalization: A Noise Robustness Perspective

Bridging State and History Representations: Understanding Self-Predictive RL

DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models

Sample-Efficient Multi-Agent RL: An Optimization Perspective

On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection

Improving Code Style for Accurate Code Generation

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference

Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning

USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields

An Extensible Framework for Open Heterogeneous Collaborative Perception

Prediction Error-based Classification for Class-Incremental Learning

Toward effective protection against diffusion-based mimicry through score distillation

Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning

Learning interpretable control inputs and dynamics underlying animal locomotion

Information Retention via Learning Supplemental Features

Neural-Symbolic Recursive Machine for Systematic Generalization

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

Recursive Generalization Transformer for Image Super-Resolution

SEABO: A Simple Search-Based Method for Offline Imitation Learning

Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints

Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning

SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models

Faithful Rule Extraction for Differentiable Rule Learning Models

AnyText: Multilingual Visual Text Generation and Editing

Rethinking Branching on Exact Combinatorial Optimization Solver: The First Deep Symbolic Discovery Framework

GAIA: Zero-shot Talking Avatar Generation

True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning

Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach

Learning to Embed Time Series Patches Independently

Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced, Global Data?

Stable Anisotropic Regularization

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

Few-Shot Detection of Machine-Generated Text using Style Representations

A Dynamical View of the Question of Why

Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals

Improved Efficiency Based on Learned Saccade and Continuous Scene Reconstruction From Foveated Visual Sampling

Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging Data

Unifying Feature and Cost Aggregation with Transformers for Dense Correspondence

Unbiased Watermark for Large Language Models

Multimarginal Generative Modeling with Stochastic Interpolants

Efficiently Computing Similarities to Private Datasets

Do Generated Data Always Help Contrastive Learning?

More Context, Less Distraction: Zero-shot Visual Classification by Inferring and Conditioning on Contextual Attributes

Detecting Pretraining Data from Large Language Models

G$^2$N$^2$ : Weisfeiler and Lehman go grammatical

Neural Architecture Retrieval

Progressive Fourier Neural Representation for Sequential Video Compilation

Alice Benchmarks: Connecting Real World Object Re-Identification with the Synthetic

INViTE: INterpret and Control Vision Transformer with Text Explanations

Data-independent Module-aware Pruning for Hierarchical Vision Transformers

Mol-Instructions - A Large-Scale Biomolecular Instruction Dataset for Large Language Models

A Hierarchical Bayesian Model for Few-Shot Meta Learning

Plugin estimators for selective classification with out-of-distribution detection

MaGIC: Multi-modality Guided Image Completion

Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

Efficient Streaming Language Models with Attention Sinks

Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Metrics

Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?

LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer

"What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data Selection

$\textbf{\textit{M}}^\textbf{\textit{3}}$: Towards Robust Multi-Modal Reasoning via Model Selection

Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms

FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization

Sparse MoE with Language Guided Routing for Multilingual Machine Translation

Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction

BENO: Boundary-embedded Neural Operators for Elliptic PDEs

In-Context Learning through the Bayesian Prism

Idempotence and Perceptual Image Compression

Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective

A Multi-Level Framework for Accelerating Training Transformer Models

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

The Update Equivalence Framework for Decision-Time Planning

COLLIE: Systematic Construction of Constrained Text Generation Tasks

Intelligent Switching for Reset-Free RL

Ins-DetCLIP: Aligning Detection Model to Follow Human-Language Instruction

Threshold-Consistent Margin Loss for Open-World Deep Metric Learning

Predictive, scalable and interpretable knowledge tracing on structured domains

AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference

Large Language Models as Generalizable Policies for Embodied Tasks

Demonstration-Regularized RL

CAMBranch: Contrastive Learning with Augmented MILPs for Branching

Less is More: Fewer Interpretable Region via Submodular Subset Selection

Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing

Parameter-Efficient Multi-Task Model Fusion with Partial Linearizeation

On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs

Stochastic Gradient Descent for Gaussian Processes Done Right

REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes

Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models

Inverse Approximation Theory for Nonlinear Recurrent Neural Networks

Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime

An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment

Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline

H-GAP: Humanoid Control with a Generalist Planner

(ends 3:45 AM)

Affinity Posters:

Blog Track Session 7

(ends 3:45 AM)

Affinity Posters:

Tiny Papers Poster Session 7

(ends 3:45 AM)

3:45 a.m.

Expo Talk Panel:

Trustworthy human evaluations for Large Language Models

(ends 5:15 AM)

Lunch Break

4:15 a.m.

Affinity Workshop:

Tiny Papers Oral Session 4

(ends 5:15 AM)

5:15 a.m.

Invited Talk:

Machine Learning in Prescient Design's Lab-in-the-Loop Antibody Design

Kyunghyun Cho

(ends 6:15 AM)

6:15 a.m.

Coffee Break

6:45 a.m.

Oral 8C [6:45-7:30]

Mastering Memory Tasks with World Models

LEGO-Prover: Neural Theorem Proving with Growing Libraries

(ends 7:30 AM)

Oral 8B [6:45-7:30]

Accelerating Distributed Stochastic Optimization via Self-Repellent Random Walks

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Improved Active Learning via Dependent Leverage Score Sampling

(ends 7:30 AM)

Oral 8D [6:45-7:30]

Provable Compositional Generalization for Object-Centric Learning

Multisize Dataset Condensation

(ends 7:30 AM)

Oral 8A [6:45-7:30]

Self-Alignment with Instruction Backtranslation

Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space

Detecting, Explaining, and Mitigating Memorization in Diffusion Models

(ends 7:30 AM)

7:30 a.m.

Poster Session 8 [7:30-9:30]

The Optimal Constant Solution: Predictable Extrapolation in Deep Neural Networks

Robustifying State-space Models for Long Sequences via Approximate Diagonalization

DAFA: Distance-Aware Fair Adversarial Training

Learning with Language-Guided State Abstractions

S$2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic

Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization Analysis

UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling

Light Schrödinger Bridge

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks

To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets

Pooling Image Datasets with Multiple Covariate Shift and Imbalance

Branch-GAN: Improving Text Generation with (not so) Large Language Models

Efficient Instance-Optimal Finite-Sum Minimization

Measuring Vision-Language STEM Skills of Neural Models

Dropout Enhanced Bilevel Training

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems

TOSS: High-quality Text-guided Novel View Synthesis from a Single Image

Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks

Adapting Large Language Models via Reading Comprehension

Multiscale Positive-Unlabeled Detection of AI-Generated Texts

BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks

Rotation has two sides: Evaluating Data Augmentation for Deep One-class Classification

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

A Cognitive Model for Learning Abstract Relational Structures from Memory-based Decision-Making Tasks

Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games

Multisize Dataset Condensation

Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning

Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach

Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation

PTaRL: Prototype-based Tabular Representation Learning via Space Calibration

Detecting, Explaining, and Mitigating Memorization in Diffusion Models

How to Fine-Tune Vision Models with SGD

Efficient Network Embedding in the Exponentially Large Quantum Hilbert Space: A High-Dimensional Perspective on Embedding

WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series

TiC-CLIP: Continual Training of CLIP Models

A 2-Dimensional State Space Layer for Spatial Inductive Bias

Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

Self-Alignment with Instruction Backtranslation

Unveiling the Pitfalls of Knowledge Editing for Large Language Models

Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators

Optimal Sample Complexity of Contrastive Learning

SOHES: Self-supervised Open-world Hierarchical Entity Segmentation

Lifting Architectural Constraints of Injective Flows

Can Transformers Capture Spatial Relations between Objects?

Adding 3D Geometry Control to Diffusion Models

Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization

State Representation Learning Using an Unbalanced Atlas

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection

Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem

Translating Labels to Solve Annotation Mismatches Across Object Detection Datasets

ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference

Does Writing with Language Models Reduce Content Diversity?

Graph Metanetworks for Processing Diverse Neural Architectures

One Forward is Enough for Neural Network Training via Likelihood Ratio Method

Guaranteed Approximation Bounds for Mixed-Precision Neural Operators

Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning

Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods

Removing Biases from Molecular Representations via Information Maximization

Exploring the Relationship Between Model Architecture and In-Context Learning Ability

Leveraging Previous Tasks in Optimizing Risk Measures with Gaussian Processes

LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents

Differentiable Euler Characteristic Transforms for Shape Classification

How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations

Diffusion Sampling with Momentum for Mitigating Divergence Artifacts

Learning in reverse causal strategic environments with ramifications on two sided markets

Large Language Models as Tool Makers

Conditional Information Bottleneck Approach for Time Series Imputation

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Conversational Drug Editing Using Retrieval and Domain Feedback

A Unified and General Framework for Continual Learning

Energy-Based Concept Bottleneck Models

Imitation Learning from Observation with Automatic Discount Scheduling

Discovering modular solutions that generalize compositionally

MCM: Masked Cell Modeling for Anomaly Detection in Tabular Data

CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs

Understanding Expressivity of Neural KG Reasoning from Rule Structure Learning

Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss

DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation

Backdoor Contrastive Learning via Bi-level Trigger Optimization

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning

MetaPhysiCa: Improving OOD Robustness in Physics-informed Machine Learning

Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning

Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models

Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs

Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models

Leveraging Uncertainty Estimates To Improve Classifier Performance

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Large Language Models as Automated Aligners for benchmarking Vision-Language Models

Provable Compositional Generalization for Object-Centric Learning

INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection

Anisotropy helps: improved statistical and computational complexity of the mean-field Langevin dynamics under structured data

Identifying the Risks of LM Agents with an LM-Emulated Sandbox

Safe Collaborative Filtering

Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds

Dissecting Neural Network Robustness Proofs

Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources

Building Cooperative Embodied Agents Modularly with Large Language Models

FedImpro: Measuring and Improving Client Update in Federated Learning

The LLM Surgeon

C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion

Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control

AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images

DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption

Reward-Free Curricula for Training Robust World Models

A Neural Framework for Generalized Causal Sensitivity Analysis

$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence

Language Model Decoding as Direct Metrics Optimization

Consistent algorithms for multi-label classification with macro-at-$k$ metrics

VDC: Versatile Data Cleanser for Detecting Dirty Samples via Visual-Linguistic Inconsistency

STARC: A General Framework For Quantifying Differences Between Reward Functions

SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series

Efficient and Scalable Graph Generation through Iterative Local Expansion

The Curse of Diversity in Ensemble-Based Exploration

Generative Human Motion Stylization in Latent Space

Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps

Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling

Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark

MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning

Tailoring Self-Rationalizers with Multi-Reward Distillation

Boundary Denoising for Video Activity Localization

Retrieval meets Long Context Large Language Models

Simplifying Transformer Blocks

Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement

Can LLM-Generated Misinformation Be Detected?

Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting

Traveling Waves Encode The Recent Past and Enhance Sequence Learning

A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging

Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts

Defending Against Transfer Attacks From Public Models

Overthinking the Truth: Understanding how Language Models Process False Demonstrations

Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining

Approximately Piecewise E(3) Equivariant Point Networks

Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback

LDReg: Local Dimensionality Regularized Self-Supervised Learning

LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts

Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory

DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

Jointly-Learned Exit and Inference for a Dynamic Neural Network

Let Models Speak Ciphers: Multiagent Debate through Embeddings

Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning

The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing

Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials

Emergent Communication with Conversational Repair

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

Expected flow networks in stochastic environments and two-player zero-sum games

Manifold Preserving Guided Diffusion

Workflow Discovery from Dialogues in the Low Data Regime

The False Promise of Imitating Proprietary Language Models

EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space

ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection

A Lie Group Approach to Riemannian Batch Normalization

Koopman-based generalization bound: New aspect for full-rank weights

Social-Transmotion: Promptable Human Trajectory Prediction

Learning Hierarchical Polynomials with Three-Layer Neural Networks

Channel Vision Transformers: An Image Is Worth C x 16 x 16 Words

H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields

Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model

Neural Contractive Dynamical Systems

Adversarial Causal Bayesian Optimization

Local Graph Clustering with Noisy Labels

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Universal Guidance for Diffusion Models

Machine Unlearning for Image-to-Image Generative Models

Human Feedback is not Gold Standard

ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor

A Topological Perspective on Demystifying GNN-Based Link Prediction Performance

Adversarial Feature Map Pruning for Backdoor

Learning to Act without Actions

Improved algorithm and bounds for successive projection

Accelerating Distributed Stochastic Optimization via Self-Repellent Random Walks

End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon

First-order ANIL provably learns representations despite overparametrisation

Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping

Confidential-DPproof: Confidential Proof of Differentially Private Training

Localizing and Editing Knowledge In Text-to-Image Generative Models

TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization

iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

Deep Orthogonal Hypersphere Compression for Anomaly Detection

Functional Interpolation for Relative Positions improves Long Context Transformers

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

Privacy Amplification for Matrix Mechanisms

Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance

DyVal: Graph-informed Dynamic Evaluation of Large Language Models

FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets

Attention-based Iterative Decomposition for Tensor Product Representation

Bandits with Replenishable Knapsacks: the Best of both Worlds

Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

Latent 3D Graph Diffusion

Improved Active Learning via Dependent Leverage Score Sampling

DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$

DiffusionSat: A Generative Foundation Model for Satellite Imagery

Adversarial Attacks on Fairness of Graph Neural Networks

AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation Learning

Mask-based modeling for Neural Radiance Fields

Variational Inference for SDEs Driven by Fractional Noise

Language Model Inversion

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

Boosting Vanilla Lightweight Vision Transformers via Re-parameterization

Space Group Constrained Crystal Generation

Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models

Simple Hierarchical Planning with Diffusion

MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection

PeFLL: Personalized Federated Learning by Learning to Learn

RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment

Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation

Memory-Consistent Neural Networks for Imitation Learning

Cauchy-Schwarz Divergence Information Bottleneck for Regression

Generative Pre-training for Speech with Flow Matching

Closing the Curious Case of Neural Text Degeneration

Large-scale training of foundation models for wearable biosignals

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks

Decision Transformer is a Robust Contender for Offline Reinforcement Learning

Generalized Policy Iteration using Tensor Approximation for Hybrid Control

Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG

LEGO-Prover: Neural Theorem Proving with Growing Libraries

Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts

Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics

Parallelizing non-linear sequential models over the sequence length

Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach

A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks

SPDER: Semiperiodic Damping-Enabled Object Representation

ImplicitSLIM and How it Improves Embedding-based Collaborative Filtering

Mastering Memory Tasks with World Models

Beyond Linear Spherical Interpolation: Noise Correction for Image Interpolation with Diffusion Models

Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML

Language Model Beats Diffusion - Tokenizer is key to visual generation

SaProt: Protein Language Modeling with Structure-aware Vocabulary

Unraveling the Key Components of OOD Generalization via Diversification

Selective Visual Representations Improve Convergence and Generalization for Embodied AI

Inherently Interpretable Time Series Classification via Multiple Instance Learning

OMNI: Open-endedness via Models of human Notions of Interestingness

BatchPrompt: Accomplish more with less

On the Role of Discrete Tokenization in Visual Representation Learning

M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding

Discovering Temporally-Aware Reinforcement Learning Algorithms

Decoding Natural Images from EEG for Object Recognition

Identifying Representations for Intervention Extrapolation

V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection

Learning semilinear neural operators: A unified recursive framework for prediction and data assimilation.

Skill-Mix: a Flexible and Expandable Family of Evaluations for AI Models

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models

Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning

Multimodal Patient Representation Learning with Missing Modalities and Labels

Chain-of-Experts: When LLMs Meet Complex Operations Research Problems

Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs

A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction

Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization

Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks

Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation

Estimating Shape Distances on Neural Representations with Limited Samples

Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes

$\mathcal{B}$-Coder: On Value-Based Deep Reinforcement Learning for Program Synthesis

Fast Equilibrium of SGD in Generic Situations

(ends 9:30 AM)

Affinity Posters:

Blog Track Session 8

(ends 9:30 AM)

Affinity Posters:

Tiny Papers Poster Session 8

(ends 9:30 AM)

10 p.m.

Registration Desk

(ends 4:00 AM)

11 p.m.

Workshop:

Tackling Climate Change with Machine Learning: Fostering the Maturity of ML Applications for Climate Change

(ends 8:00 AM)

11:15 p.m.

Workshop:

AI4DifferentialEquations In Science

(ends 8:00 AM)

SAT 11 MAY

midnight

Workshop:

How Far Are We From AGI

(ends 8:00 AM)

Workshop:

Machine Learning for Genomics Explorations (MLGenX)

(ends 8:00 AM)

Workshop:

Generative Models for Decision Making

(ends 8:00 AM)

Workshop:

Bridging the Gap Between Practice and Theory in Deep Learning

(ends 8:00 AM)

Workshop:

Workshop on Large Language Models for Agents

(ends 8:00 AM)

Workshop:

Global AI Cultures

(ends 8:00 AM)

Workshop:

Secure and Trustworthy Large Language Models

(ends 8:00 AM)

Workshop:

First Workshop on Representational Alignment (Re-Align)

(ends 8:00 AM)

Workshop:

5th Workshop on African Natural Language Processing (AfricaNLP 2024)

(ends 8:00 AM)

Workshop:

5th Workshop on practical ML for limited/low resource settings (PML4LRS) @ ICLR 2024

(ends 8:00 AM)

Workshop:

Workshop on Learning from Time Series for Health

(ends 8:00 AM)

Workshop:

Generative and Experimental Perspectives for Biomolecular Design

(ends 8:00 AM)

Workshop:

Privacy Regulation and Protection in Machine Learning

(ends 8:00 AM)

Workshop:

Navigating and Addressing Data Problems for Foundation Models (DPFM)

(ends 8:00 AM)

Workshop:

Machine Learning for Remote Sensing (ML4RS)

(ends 8:00 AM)

Workshop:

Data-centric Machine Learning Research (DMLR): Harnessing Momentum for Science

(ends 8:00 AM)

Workshop:

ICLR 2024 Workshop on Reliable and Responsible Foundation Models

(ends 8:00 AM)

Workshop:

2nd Workshop on Mathematical and Empirical Understanding of Foundation Models

(ends 8:00 AM)

12:30 a.m.

Coffee Break

3:45 a.m.

Lunch Break

6:15 a.m.

Coffee Break