ICLR 2024 Schedule

Filter Events

TUE 7 MAY

7 a.m.

Registration Desk

(ends 7:00 PM)

8:15 a.m.

Remarks:

Opening Remark

(ends 8:30 AM)

8:30 a.m.

Invited Talk:

Why your work matters for climate in more ways than you think

Priya Donti

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral 1A [10:00-10:45]

Predictive auxiliary objectives in deep RL mimic learning in the brain

ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs

Protein Discovery with Discrete Walk-Jump Sampling

(ends 10:45 AM)

Oral 1B [10:00-10:45]

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

ASID: Active Exploration for System Identification in Robotic Manipulation

Learning Interactive Real-World Simulators

(ends 10:45 AM)

Oral 1C [10:00-10:45]

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 10:45 AM)

Oral 1D [10:00-10:45]

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

Robust agents learn causal world models

(ends 10:45 AM)

10:45 a.m.

Poster Session 1 [10:45-12:45]

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

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

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

Boosting Graph Anomaly Detection with Adaptive Message Passing

Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL

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

A Simple and Effective Pruning Approach for Large Language Models

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

A Mutual Information Perspective on Federated Contrastive Learning

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

Weakly-supervised Audio Separation via Bi-modal Semantic Similarity

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

Towards Principled Representation Learning from Videos for Reinforcement Learning

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

Robust Classification via Regression for Learning with Noisy Labels

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

Expressive Losses for Verified Robustness via Convex Combinations

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

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

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

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

Aux-NAS: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost

Multimodal Molecular Pretraining via Modality Blending

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

ReMasker: Imputing Tabular Data with Masked Autoencoding

Exploring Weight Balancing on Long-Tailed Recognition Problem

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

Matrix Manifold Neural Networks++

DreamLLM: Synergistic Multimodal Comprehension and Creation

Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory

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

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

Towards Understanding Sycophancy in Language Models

Evaluating Representation Learning on the Protein Structure Universe

Dissecting learning and forgetting in language model finetuning

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

Emu: Generative Pretraining in Multimodality

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

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

EBMDock: Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model

Circuit Component Reuse Across Tasks in Transformer Language Models

Reward Model Ensembles Help Mitigate Overoptimization

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

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

Protein Discovery with Discrete Walk-Jump Sampling

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

Zero-Mean Regularized Spectral Contrastive Learning: Implicitly Mitigating Wrong Connections in Positive-Pair Graphs

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

LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures

InfoCon: Concept Discovery with Generative and Discriminative Informativeness

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

Probabilistic Self-supervised Representation Learning via Scoring Rules Minimization

Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data

Layer-wise linear mode connectivity

Pushing Boundaries: Mixup's Influence on Neural Collapse

Neural Rate Control for Learned Video Compression

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

Soft Contrastive Learning for Time Series

Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation

Transformer Fusion with Optimal Transport

REFACTOR: Learning to Extract Theorems from Proofs

On Bias-Variance Alignment in Deep Models

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

Weaker MVI Condition: Extragradient Methods with Multi-Step Exploration

Revisiting the Last-Iterate Convergence of Stochastic Gradient Methods

Neural Neighborhood Search for Multi-agent Path Finding

Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels

L2P-MIP: Learning to Presolve for Mixed Integer Programming

MixSATGEN: Learning Graph Mixing for SAT Instance Generation

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

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

Fiber Monte Carlo

Optimistic Bayesian Optimization with Unknown Constraints

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

Adaptive Federated Learning with Auto-Tuned Clients

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

Learning from Sparse Offline Datasets via Conservative Density Estimation

Efficient Streaming Language Models with Attention Sinks

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

Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding

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

Contrastive Difference Predictive Coding

Illusory Attacks: Information-theoretic detectability matters in adversarial attacks

Efficient ConvBN Blocks for Transfer Learning and Beyond

Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting

Identifiable Latent Polynomial Causal Models through the Lens of Change

Towards LLM4QPE: Unsupervised Pretraining of Quantum Property Estimation and A Benchmark

P2Seg: Pointly-supervised Segmentation via Mutual Distillation

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

Doubly Robust Proximal Causal Learning for Continuous Treatments

A Data-Driven Measure of Relative Uncertainty for Misclassification Detection

Time Fairness in Online Knapsack Problems

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

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

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

Out-Of-Domain Unlabeled Data Improves Generalization

Risk Bounds of Accelerated SGD for Overparameterized Linear Regression

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

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

Robust agents learn causal world models

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

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

Some Fundamental Aspects about Lipschitz Continuity of Neural Networks

Node2ket: Efficient High-Dimensional Network Embedding in Quantum Hilbert Space

Reverse Diffusion Monte Carlo

Graphical Multioutput Gaussian Process with Attention

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

Implicit Neural Representation Inference for Low-Dimensional Bayesian Deep Learning

ResFields: Residual Neural Fields for Spatiotemporal Signals

Analytically Tractable Hidden-States Inference in Bayesian Neural Networks

Implicit Maximum a Posteriori Filtering via Adaptive Optimization

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

Modeling Boundedly Rational Agents with Latent Inference Budgets

Locality Sensitive Sparse Encoding for Learning World Models Online

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

A Semantic Invariant Robust Watermark for Large Language Models

Fast Imitation via Behavior Foundation Models

Efficient Inverse Multiagent Learning

Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement Learning

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

Addressing Signal Delay in Deep Reinforcement Learning

Demystifying CLIP Data

Topic Modeling as Multi-Objective Contrastive Optimization

Retrieval-Enhanced Contrastive Vision-Text Models

Exploring Diffusion Time-steps for Unsupervised Representation Learning

Learning to Reject Meets Long-tail Learning

Unsupervised Order Learning

A Framework and Benchmark for Deep Batch Active Learning for Regression

Class Incremental Learning via Likelihood Ratio Based Task Prediction

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

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

Model Merging by Uncertainty-Based Gradient Matching

A Probabilistic Framework for Modular Continual Learning

Tangent Transformers for Composition,Privacy and Removal

Spurious Feature Diversification Improves Out-of-distribution Generalization

AdaMerging: Adaptive Model Merging for Multi-Task Learning

Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches

Beyond Memorization: Violating Privacy via Inference with Large Language Models

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

Don't Judge by the Look: Towards Motion Coherent Video Representation

Effective and Efficient Federated Tree Learning on Hybrid Data

LipSim: A Provably Robust Perceptual Similarity Metric

Conformal Risk Control

Fusion Is Not Enough: Single Modal Attacks on Fusion Models for 3D Object Detection

A Fast and Provable Algorithm for Sparse Phase Retrieval

Exploring the cloud of feature interaction scores in a Rashomon set

Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment

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

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

Bootstrapping Variational Information Pursuit with Large Language and Vision Models for Interpretable Image Classification

Sparse Autoencoders Find Highly Interpretable Features in Language Models

Leveraging Optimization for Adaptive Attacks on Image Watermarks

Towards Transparent Time Series Forecasting

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

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

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

DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models

Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries

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

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

Predictive auxiliary objectives in deep RL mimic learning in the brain

Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data

Active Test-Time Adaptation: Theoretical Analyses and An Algorithm

Harnessing Density Ratios for Online Reinforcement Learning

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

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

Lemur: Integrating Large Language Models in Automated Program Verification

Transport meets Variational Inference: Controlled Monte Carlo Diffusions

Training Socially Aligned Language Models on Simulated Social Interactions

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

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

Thin-Shell Object Manipulations With Differentiable Physics Simulations

Mitigating Emergent Robustness Degradation while Scaling Graph Learning

Private Zeroth-Order Nonsmooth Nonconvex Optimization

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

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

LOQA: Learning with Opponent Q-Learning Awareness

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

Multimodal Learning Without Labeled Multimodal Data: Guarantees and Applications

Rethinking and Extending the Probabilistic Inference Capacity of GNNs

Neural Polynomial Gabor Fields for Macro Motion Analysis

Chain of Hindsight aligns Language Models with Feedback

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

PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization

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

A Generalist Agent

Multilingual Jailbreak Challenges in Large Language Models

Procedural Fairness Through Decoupling Objectionable Data Generating Components

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

Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection

On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection

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

ASID: Active Exploration for System Identification in Robotic Manipulation

EX-Graph: A Pioneering Dataset Bridging Ethereum and X

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

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

Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation

WebArena: A Realistic Web Environment for Building Autonomous Agents

AffineQuant: Affine Transformation Quantization for Large Language Models

Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models

Neural SDF Flow for 3D Reconstruction of Dynamic Scenes

Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate

Teaching Language Models to Hallucinate Less with Synthetic Tasks

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

Compositional Generative Inverse Design

Better Neural PDE Solvers Through Data-Free Mesh Movers

BadEdit: Backdooring Large Language Models by Model Editing

Toward effective protection against diffusion-based mimicry through score distillation

Hybrid Sharing for Multi-Label Image Classification

Multimodal Patient Representation Learning with Missing Modalities and Labels

GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs

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

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

Learning Planning Abstractions from Language

Neurosymbolic Grounding for Compositional World Models

Directly Fine-Tuning Diffusion Models on Differentiable Rewards

A Variational Perspective on Solving Inverse Problems with Diffusion Models

CausalLM is not optimal for in-context learning

A Foundation Model for Error Correction Codes

Masks, Signs, And Learning Rate Rewinding

LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading

Fast-ELECTRA for Efficient Pre-training

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

Initializing Models with Larger Ones

Effective Data Augmentation With Diffusion Models

LEMON: Lossless model expansion

Defining Expertise: Applications to Treatment Effect Estimation

Measuring Vision-Language STEM Skills of Neural Models

Synaptic Weight Distributions Depend on the Geometry of Plasticity

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

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

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

Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data

Generative Judge for Evaluating Alignment

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

CPPO: Continual Learning for Reinforcement Learning with Human Feedback

DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation

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

InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules

MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts

PhyloGFN: Phylogenetic inference with generative flow networks

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

ClimODE: Climate and Weather Forecasting with Physics-informed Neural ODEs

Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting

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

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

Parametric Augmentation for Time Series Contrastive Learning

Learning with Language-Guided State Abstractions

Task Planning for Visual Room Rearrangement under Partial Observability

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

Equivariant Scalar Fields for Molecular Docking with Fast Fourier Transforms

Domain Randomization via Entropy Maximization

Neural Language of Thought Models

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

Graph Generation with $K^2$-trees

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

TUVF: Learning Generalizable Texture UV Radiance Fields

SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer

From Posterior Sampling to Meaningful Diversity in Image Restoration

Revisiting Link Prediction: a data perspective

Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders

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

MagicDrive: Street View Generation with Diverse 3D Geometry Control

Unpaired Image-to-Image Translation via Neural Schrödinger Bridge

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

Elucidating the Exposure Bias in Diffusion Models

FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning

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

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

Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics

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

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

Dynamics-Informed Protein Design with Structure Conditioning

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

Unsupervised Pretraining for Fact Verification by Language Model Distillation

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

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

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

IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs

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

On the Learnability of Watermarks for Language Models

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

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

(ends 12:45 PM)

Affinity Posters:

Blog Track Session 1

(ends 12:45 PM)

Affinity Posters:

Tiny Papers Poster Session 1

(ends 12:45 PM)

12:45 p.m.

Break:

Lunch Break

(ends 2:15 PM)

Expo Talk Panel:

Zhipu GLM: train, develop, and deploy your own LLMs

(ends 2:15 PM)

Office Hours:

Lili Mou

(ends 1:30 PM)

Office Hours:

Priya Donti

(ends 1:30 PM)

1:15 p.m.

Affinity Workshop:

Tiny Papers Oral Session 1

(ends 2:15 PM)

1:30 p.m.

Office Hours:

Mihaela van der Schaar

(ends 2:15 PM)

Office Hours:

Furong Huang

(ends 2:15 PM)

Office Hours:

Anna Rumshisky

(ends 2:15 PM)

2:15 p.m.

Invited Talk:

Kate Downing

(ends 3:15 PM)

3:15 p.m.

Break:

Coffee Break

(ends 3:45 PM)

3:45 p.m.

Oral 2A [3:45-4:30]

MetaGPT: Meta Programming for A 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 4:30 PM)

Oral 2B [3:45-4:30]

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 4:30 PM)

Oral 2C [3:45-4:30]

Lipschitz Singularities in Diffusion Models

Improved Techniques for Training Consistency Models

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

(ends 4:30 PM)

Oral 2D [3:45-4:30]

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 4:30 PM)

4:30 p.m.

Poster Session 2 [4:30-6:30]

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

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

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

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

MiniLLM: Knowledge Distillation of Large Language Models

Compressed Context Memory for Online Language Model Interaction

MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data

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

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

Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning

Harnessing Joint Rain-/Detail-aware Representations to Eliminate Intricate Rains

DreamClean: Restoring Clean Image Using Deep Diffusion Prior

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

Bridging Vision and Language Spaces with Assignment Prediction

Task structure and nonlinearity jointly determine learned representational geometry

When Semantic Segmentation Meets Frequency Aliasing

Improving Non-Transferable Representation Learning by Harnessing Content and Style

EQA-MX: Embodied Question Answering using Multimodal Expression

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

Coordinate-Aware Modulation for Neural Fields

BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation

AgentBench: Evaluating LLMs as Agents

Diving Segmentation Model into Pixels

Adapting Large Language Models via Reading Comprehension

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

Demystifying Embedding Spaces using Large Language Models

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

Benchmarking and Improving Generator-Validator Consistency of Language Models

Grounding Multimodal Large Language Models to the World

SOHES: Self-supervised Open-world Hierarchical Entity Segmentation

Confronting Reward Model Overoptimization with Constrained RLHF

Teaching Arithmetic to Small Transformers

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

LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving

Fine-Tuning Language Models for Factuality

MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework

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

GeoLLM: Extracting Geospatial Knowledge from Large Language Models

RT-Trajectory: Robotic Task Generalization via Hindsight Trajectory Sketches

Provable Robust Watermarking for AI-Generated Text

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

Massive Editing for Large Language Models via Meta Learning

Large Language Models Cannot Self-Correct Reasoning Yet

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

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

ReLoRA: High-Rank Training Through Low-Rank Updates

Uncertainty-aware Graph-based Hyperspectral Image Classification

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

Scalable Monotonic Neural Networks

Quantifying and Enhancing Multi-modal Robustness with Modality Preference

Zero-Shot Robustification of Zero-Shot Models

Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning

Protein-ligand binding representation learning from fine-grained interactions

Memorization in Self-Supervised Learning Improves Downstream Generalization

Copilot4D: Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion

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

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

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

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

Transferring Learning Trajectories of Neural Networks

Feature emergence via margin maximization: case studies in algebraic tasks

Batch normalization is sufficient for universal function approximation in CNNs

REBAR: Retrieval-Based Reconstruction for Time-series Contrastive Learning

Course Correcting Koopman Representations

iTransformer: Inverted Transformers Are Effective for Time Series Forecasting

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

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

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

Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold

Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts

Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy

Combining Axes Preconditioners through Kronecker Approximation for Deep Learning

Scaling Convex Neural Networks with Burer-Monteiro Factorization

Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions

Global Optimality for Non-linear Constrained Restoration Problems via Invexity

NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks

The Marginal Value of Momentum for Small Learning Rate SGD

MogaNet: Multi-order Gated Aggregation Network

Symmetric Single Index Learning

CO2: Efficient Distributed Training with Full Communication-Computation Overlap

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

SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores

lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning

Time-Efficient Reinforcement Learning with Stochastic Stateful Policies

A Variational Framework for Estimating Continuous Treatment Effects with Measurement Error

Non-Exchangeable Conformal Risk Control

PAC Prediction Sets Under Label Shift

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

UC-NERF: Neural Radiance Field for Under-Calibrated Multi-View Cameras in Autonomous Driving

Tight Rates in Supervised Outlier Transfer Learning

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

Theoretical Understanding of Learning from Adversarial Perturbations

Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC Bounds

Noisy Interpolation Learning with Shallow Univariate ReLU Networks

Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models

Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion

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

Entropy Coding of Unordered Data Structures

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

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

Repelling Random Walks

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

Estimating Conditional Mutual Information for Dynamic Feature Selection

Input-gradient space particle inference for neural network ensembles

Provably Efficient UCB-type Algorithms For Learning Predictive State Representations

Making RL with Preference-based Feedback Efficient via Randomization

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

Massively Scalable Inverse Reinforcement Learning in Google Maps

KoLA: Carefully Benchmarking World Knowledge of Large Language Models

DrS: Learning Reusable Dense Rewards for Multi-Stage Tasks

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

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

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

DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization

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

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

Reconciling Spatial and Temporal Abstractions for Goal Representation

Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models

Augmented Bayesian Policy Search

Privileged Sensing Scaffolds Reinforcement Learning

Provably Efficient CVaR RL in Low-rank MDPs

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

Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations

Conditional Instrumental Variable Regression with Representation Learning for Causal Inference

Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models

Grokking as a First Order Phase Transition in Two Layer Networks

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

Learning to Compose: Improving Object Centric Learning by Injecting Compositionality

Label-Focused Inductive Bias over Latent Object Features in Visual Classification

Object centric architectures enable efficient causal representation learning

Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions

Continuous Invariance Learning

Language-Informed Visual Concept Learning

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

Multi-task Learning with 3D-Aware Regularization

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

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

The importance of feature preprocessing for differentially private linear optimization

Federated Wasserstein Distance

VFLAIR: A Research Library and Benchmark for Vertical Federated Learning

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

Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features

Expressivity of ReLU-Networks under Convex Relaxations

At Which Training Stage Does Code Data Help LLMs Reasoning?

Dissecting Sample Hardness: A Fine-Grained Analysis of Hardness Characterization Methods for Data-Centric AI

VDC: Versatile Data Cleanser based on Visual-Linguistic Inconsistency by Multimodal Large Language Models

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

Exposing Text-Image Inconsistency Using Diffusion Models

Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing

An Unforgeable Publicly Verifiable Watermark for Large Language Models

Holistic Evaluation of Language Models

High Fidelity Neural Audio Compression

Generalizability of Adversarial Robustness Under Distribution Shifts

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

Adversarial AutoMixup

Enabling Lanuguage Models to Implicitly Learn Self-Improvement

Curiosity-driven Red-teaming for Large Language Models

SEABO: A Simple Search-Based Method for Offline Imitation Learning

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

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

Sentence-level Prompts Benefit Composed Image Retrieval

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

Multilinear Operator Networks

COSA: Concatenated Sample Pretrained Vision-Language Foundation Model

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

LRM: Large Reconstruction Model for Single Image to 3D

Unveiling Options with Neural Network Decomposition

Towards the Fundamental Limits of Knowledge Transfer over Finite Domains

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

Accurate and Scalable Estimation of Epistemic Uncertainty for Graph Neural Networks

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

Improved Techniques for Training Consistency Models

Lipschitz Singularities in Diffusion Models

Scaling Laws for Associative Memories

NOLA: Compressing LoRA using Linear Combination of Random Basis

Fast Hyperboloid Decision Tree Algorithms

Controlling Vision-Language Models for Multi-Task Image Restoration

SmartPlay : A Benchmark for LLMs as Intelligent Agents

Learning to Make Adherence-aware Advice

Fusing Models with Complementary Expertise

Reinforcement Symbolic Regression Machine

BRUSLEATTACK: A QUERY-EFFICIENT SCORE- BASED BLACK-BOX SPARSE ADVERSARIAL ATTACK

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

Perceptual Group Tokenizer: Building Perception with Iterative Grouping

High-dimensional SGD aligns with emerging outlier eigenspaces

Accelerating Sinkhorn algorithm with sparse Newton iterations

$\mathcal{B}$-Coder: Value-Based Deep Reinforcement Learning for Program Synthesis

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

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

Learning Hierarchical Image Segmentation For Recognition and By Recognition

Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness

A Benchmark Study on Calibration

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

MVDream: Multi-view Diffusion for 3D Generation

Denoising Diffusion Bridge Models

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

Stochastic Modified Equations and Dynamics of Dropout Algorithm

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

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

Neural Auto-designer for Enhanced Quantum Kernels

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

Improved Probabilistic Image-Text Representations

Solving Homogeneous and Heterogeneous Cooperative Tasks with Greedy Sequential Execution

Poly-View Contrastive Learning

Deceptive Fairness Attacks on Graphs via Meta Learning

IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks

Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting

Predicting Emergent Abilities with Infinite Resolution Evaluation

Xformer: Hybrid X-Shaped Transformer for Image Denoising

On Diffusion Modeling for Anomaly Detection

Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning

Learning to Jointly Understand Visual and Tactile Signals

Retrieval is Accurate Generation

SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation

From Graphs to Hypergraphs: Hypergraph Projection and its Reconstruction

Image Inpainting via Iteratively Decoupled Probabilistic Modeling

Conformal Prediction via Regression-as-Classification

Mixture of LoRA Experts

YaRN: Efficient Context Window Extension of Large Language Models

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

Uni3D: Exploring Unified 3D Representation at Scale

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

MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning

A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER

Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers

ADOPD: A Large-Scale Document Page Decomposition Dataset

Frequency-Aware Transformer for Learned Image Compression

Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners

Deep Temporal Graph Clustering

Deep Orthogonal Hypersphere Compression for Anomaly Detection

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

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

Language Model Decoding as Direct Metrics Optimization

Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss

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

Complete and Efficient Graph Transformers for Crystal Material Property Prediction

Stabilizing Backpropagation Through Time to Learn Complex Physics

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

Few-shot Hybrid Domain Adaptation of Image Generator

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

Elucidating the design space of classifier-guided diffusion generation

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

Hard-Constrained Deep Learning for Climate Downscaling

Don't Play Favorites: Minority Guidance for Diffusion Models

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

Denoising Diffusion via Image-Based Rendering

Skip-Attention: Improving Vision Transformers by Paying Less Attention

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

Vision Transformers Need Registers

Understanding Addition in Transformers

Dynamic Sparse Training with Structured Sparsity

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

Scalable Neural Network Kernels

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

Large-Vocabulary 3D Diffusion Model with Transformer

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

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

On Harmonizing Implicit Subpopulations

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

Generating Pragmatic Examples to Train Neural Program Synthesizers

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

Exploring Effective Stimulus Encoding via Vision System Modeling for Visual Prostheses

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

BrainLM: A foundation model for brain activity recordings

BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs

Critical Learning Periods Emerge Even in Deep Linear Networks

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

Most discriminative stimuli for functional cell type clustering

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

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

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

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

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

Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations

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

Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment

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

Label-Noise Robust Diffusion Models

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

H-GAP: Humanoid Control with a Generalist Planner

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

Masked Audio Generation using a Single Non-Autoregressive Transformer

Generalized Schrödinger Bridge Matching

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

Denoising Diffusion Step-aware Models

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

Learning to design protein-protein interactions with enhanced generalization

Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency

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

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

Video Decomposition Prior: Editing Videos Layer by Layer

Seer: Language Instructed Video Prediction with Latent Diffusion Models

Relay Diffusion: Unifying diffusion process across resolutions for image synthesis

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

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

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

SEGNO: Generalizing Equivariant Graph Neural Networks with Physical Inductive Biases

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

A Characterization Theorem for Equivariant Networks with Point-wise Activations

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

Distinguished In Uniform: Self-Attention Vs. Virtual Nodes

HoloNets: Spectral Convolutions do extend to Directed Graphs

Orbit-Equivariant Graph Neural Networks

Rethinking Label Poisoning for GNNs: Pitfalls and Attacks

Clifford Group Equivariant Simplicial Message Passing Networks

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

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

PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial Filters

(ends 6:30 PM)

Affinity Posters:

Blog Track Session 2

(ends 6:30 PM)

Affinity Posters:

Tiny Papers Poster Session 2

(ends 6:30 PM)

6:30 p.m.

Remarks:

Opening Ceremony

(ends 6:45 PM)

6:45 p.m.

Reception:

Reception

(ends 8:00 PM)

WED 8 MAY

8 a.m.

Registration Desk

(ends 6:30 PM)

8:30 a.m.

Invited Talk:

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

Raia Hadsell

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral 3A [10:00-10:45]

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 10:45 AM)

Oral 3B [10:00-10:45]

Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks

Learning Energy Decompositions for Partial Inference in GFlowNets

Cameras as Rays: Pose Estimation via Ray Diffusion

(ends 10:45 AM)

Oral 3C [10:00-10:45]

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 10:45 AM)

Oral 3D [10:00-10:45]

How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?

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

(ends 10:45 AM)

10:45 a.m.

Poster Session 3 [10:45-12:45]

Posters 10:45-12:45

TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning

Temporal Generalization Estimation in Evolving Graphs

Hypergraph Dynamic System

SaNN: Simple Yet Powerful Simplicial-aware Neural Networks

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

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

Polynormer: Polynomial-Expressive Graph Transformer in Linear Time

The Consensus Game: Language Model Generation via Equilibrium Search

LLM Augmented LLMs: Expanding Capabilities through Composition

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

Lemur: Harmonizing Natural Language and Code for Language Agents

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

DyVal: Dynamic Evaluation of Large Language Models for Reasoning Tasks

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

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

Tool-Augmented Reward Modeling

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

Efficiently Computing Similarities to Private Datasets

Supervised Knowledge Makes Large Language Models Better In-context Learners

Representation Deficiency in Masked Language Modeling

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

Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning

SparseFormer: Sparse Visual Recognition via Limited Latent Tokens

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

MetaTool Benchmark for Large Language Models: Deciding Whether to Use Tools and Which to Use

Understanding the Effects of RLHF on LLM Generalisation and Diversity

The Trickle-down Impact of Reward Inconsistency on RLHF

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

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

Vanishing Gradients in Reinforcement Finetuning of Language Models

Prompt Gradient Projection for Continual Learning

Test-Time Training on Nearest Neighbors for Large Language Models

Large Language Models as Analogical Reasoners

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

Human Feedback is not Gold Standard

Take a Step Back: Evoking Reasoning via Abstraction in Large Language Models

Evaluating Language Model Agency Through Negotiations

RA-DIT: Retrieval-Augmented Dual Instruction Tuning

Equivariant Matrix Function Neural Networks

Partitioning Message Passing for Graph Fraud Detection

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

Towards Foundation Models for Knowledge Graph Reasoning

Graph Parsing Networks

Cameras as Rays: Pose Estimation via Ray Diffusion

Conformal Inductive Graph Neural Networks

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

Zero and Few-shot Semantic Parsing with Ambiguous Inputs

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

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

Channel Vision Transformers: An Image Is Worth 1 x 16 x 16 Words

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

Robust Similarity Learning with Difference Alignment Regularization

ZipIt! Merging Models from Different Tasks without Training

Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces

VersVideo: Leveraging Enhanced Temporal Diffusion Models for Versatile Video Generation

Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning

Federated Recommendation with Additive Personalization

CLAP: Collaborative Adaptation for Patchwork Learning

Universal Jailbreak Backdoors from Poisoned Human Feedback

ConR: Contrastive Regularizer for Deep Imbalanced Regression

Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning

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

Sharpness-Aware Data Poisoning Attack

Learning Grounded Action Abstractions from Language

A Recipe for Improved Certifiable Robustness

Patched Denoising Diffusion Models For High-Resolution Image Synthesis

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

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

Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds

Self-supervised Representation Learning from Random Data Projectors

Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning

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

Headless Language Models: Learning without Predicting with Contrastive Weight Tying

Non-negative Contrastive Learning

CODE REPRESENTATION LEARNING AT SCALE

Tensor Programs VI: Feature Learning in Infinite Depth Neural Networks

InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image

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

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

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

Robustifying State-space Models for Long Sequences via Approximate Diagonalization

Feature-aligned N-BEATS with Sinkhorn divergence

TabR: Tabular Deep Learning Meets Nearest Neighbors

Function-space Parameterization of Neural Networks for Sequential Learning

Local Search GFlowNets

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

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

Trajeglish: Traffic Modeling as Next-Token Prediction

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

Improving Intrinsic Exploration by Creating Stationary Objectives

Select to Perfect: Imitating desired behavior from large multi-agent data

Designing Skill-Compatible AI: Methodologies and Frameworks in Chess

Learning to Act without Actions

Reward Design for Justifiable Sequential Decision-Making

AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents

Fast Value Tracking for Deep Reinforcement Learning

Revisiting Data Augmentation in Deep Reinforcement Learning

GROOT: Learning to Follow Instructions by Watching Gameplay Videos

PanoDiffusion: 360-degree Panorama Outpainting via Diffusion

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

Pre-training with Synthetic Data Helps Offline Reinforcement Learning

Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning

The Generalization Gap in Offline Reinforcement Learning

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

Tree Search-Based Policy Optimization under Stochastic Execution Delay

Hindsight PRIORs for Reward Learning from Human Preferences

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

Towards Robust Offline Reinforcement Learning under Diverse Data Corruption

Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning

SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos

A Quadratic Synchronization Rule for Distributed Deep Learning

Stochastic Controlled Averaging for Federated Learning with Communication Compression

A Restoration Network as an Implicit Prior

Outlier-Robust Subsampling Techniques for Persistent Homology

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

Improving Convergence and Generalization Using Parameter Symmetries

Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling

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

FOSI: Hybrid First and Second Order Optimization

Democratizing Fine-grained Visual Recognition with Large Language Models

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

A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors

Implicit Gaussian process representation of vector fields over arbitrary latent manifolds

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

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

Accelerated Sampling with Stacked Restricted Boltzmann Machines

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

Fast and unified path gradient estimators for normalizing flows

On the Posterior Distribution in Denoising: Application to Uncertainty Quantification

Kernelised Normalising Flows

Prompt Learning with Quaternion Networks

Towards Establishing Guaranteed Error for Learned Database Operations

On Double Descent in Reinforcement Learning with LSTD and Random Features

Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization

Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift

Learning Conditional Invariances through Non-Commutativity

Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization

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

Fantastic Generalization Measures are Nowhere to be Found

Learning to Reject with a Fixed Predictor: Application to Decontextualization

Minimum width for universal approximation using ReLU networks on compact domain

PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis

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

What does automatic differentiation compute for neural networks?

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

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

Quasi-Monte Carlo for 3D Sliced Wasserstein

Improved baselines for vision-language pre-training

Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval

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

R-MAE: Regions Meet Masked Autoencoders

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

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

Consistency-guided Prompt Learning for Vision-Language Models

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

Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks

Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction

Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation

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

General Stability Analysis for Zeroth-Order Optimization Algorithms

Video Language Planning

Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization

RetroBridge: Modeling Retrosynthesis with Markov Bridges

Fully Hyperbolic Convolutional Neural Networks for Computer Vision

Language Model Detectors Are Easily Optimized Against

Rethinking the Uniformity Metric in Self-Supervised Learning

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

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

Fair Classifiers that Abstain without Harm

fairret: a Framework for Differentiable Fairness Regularization Terms

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

Retrieval-based Disentangled Representation Learning with Natural Language Supervision

Explaining Time Series via Contrastive and Locally Sparse Perturbations

Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making

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

Language Models Represent Space and Time

Quantifying the Plausibility of Context Reliance in Neural Machine Translation

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

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

GOAt: Explaining Graph Neural Networks via Graph Output Attribution

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

FedInverse: Evaluating Privacy Leakage in Federated Learning

KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval

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

What Algorithms can Transformers Learn? A Study in Length Generalization

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

Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning

On Differentially Private Federated Linear Contextual Bandits

LabelDP-Pro: Learning with Label Differential Privacy via Projections

Distributional Preference Learning: Understanding and Accounting for Hidden Context in RLHF

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

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

Test-time Adaptation against Multi-modal Reliability Bias

PeFLL: Personalized Federated Learning by Learning to Learn

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

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

Accurate Forgetting for Heterogeneous Federated Continual Learning

How Well Do Supervised 3D Models Transfer to Medical Imaging Tasks?

Function Vectors in Large Language Models

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

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

Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform

Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory

Post-hoc bias scoring is optimal for fair classification

Effective Structural Encodings via Local Curvature Profiles

Set Learning for Accurate and Calibrated Models

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

Scaling Laws of RoPE-based Extrapolation

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

Improving Offline RL by Blending Heuristics

Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks

The Expressive Power of Transformers with Chain of Thought

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

Aligning Relational Learning with Lipschitz Fairness

MAP IT to Visualize Representations

CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity

Querying Easily Flip-flopped Samples for Deep Active Learning

Why is SAM Robust to Label Noise?

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

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

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

Towards Poisoning Fair Representations

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

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

CAMBranch: Contrastive Learning with Augmented MILPs for Branching

Automatic Functional Differentiation in JAX

ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion

Scaling Laws for Sparsely-Connected Foundation Models

On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback

Enhanced Face Recognition using Intra-class Incoherence Constraint

On the Generalization and Approximation Capacities of Neural Controlled Differential Equations

Towards Unified Multi-Modal Personalization: Large Vision-Language Models for Generative Recommendation and Beyond

TokenFlow: Consistent Diffusion Features for Consistent Video Editing

The Expressive Power of Low-Rank Adaptation

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

Mega-TTS 2: Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis

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

Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages

Efficient Multi-agent Reinforcement Learning by Planning

Sample-Efficient Quality-Diversity by Cooperative Coevolution

Improving Generalization of Alignment with Human Preferences through Group Invariant Learning

Neural Architecture Retrieval

CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets

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

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

Near-Optimal Solutions of Constrained Learning Problems

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

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

Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning

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

Deep Reinforcement Learning for Modelling Protein Complexes

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

Maximum Entropy Heterogeneous-Agent Reinforcement Learning

NuwaDynamics: Discovering and Updating in Causal Spatio-Temporal Modeling

Conformal Language Modeling

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

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

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

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

A Simple and Scalable Representation for Graph Generation

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

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

Transformers can optimally learn regression mixture models

FasterViT: Fast Vision Transformers with Hierarchical Attention

Protein Multimer Structure Prediction via Prompt Learning

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

Tree Cross Attention

Linear Log-Normal Attention with Unbiased Concentration

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

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

LEAD: Min-Max Optimization from a Physical Perspective

Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit

Bellman Optimal Stepsize Straightening of Flow-Matching Models

Guess & Sketch: Language Model Guided Transpilation

Whittle Index with Multiple Actions and State Constraint for Inventory Management

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

Perceptual Scales Predicted by Fisher Information Metrics

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

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

Sufficient conditions for offline reactivation in recurrent neural networks

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

SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents

ContextRef: Evaluating Referenceless Metrics for Image Description Generation

Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM

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

Safe RLHF: Safe Reinforcement Learning from Human Feedback

Space Group Constrained Crystal Generation

Ensemble Distillation for Unsupervised Constituency Parsing

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

AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors

The Reasonableness Behind Unreasonable Translation Capability of Large Language Model

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

Pathformer: Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting

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

GenSim: Generating Robotic Simulation Tasks via Large Language Models

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

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

Searching for High-Value Molecules Using Reinforcement Learning and Transformers

Lagrangian Flow Networks for Conservation Laws

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

Scale-Adaptive Diffusion Model for Complex Sketch Synthesis

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

Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive

SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking

PromptTTS 2: Describing and Generating Voices with Text Prompt

Learning Energy Decompositions for Partial Inference in GFlowNets

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

Self-Consuming Generative Models Go MAD

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

Generative Adversarial Equilibrium Solvers

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

Conditional Variational Diffusion Models

EmerDiff: Emerging Pixel-level Semantic Knowledge in Diffusion Models

AttEXplore: Attribution for Explanation with model parameters eXploration

LLM-grounded Video Diffusion Models

Energy-guided Entropic Neural Optimal Transport

Analyzing and Improving Optimal-Transport-based Adversarial Networks

Towards image compression with perfect realism at ultra-low bitrates

ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models

Towards 3D Molecule-Text Interpretation in Language Models

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

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

A Branching Decoder for Set Generation

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

Image Translation as Diffusion Visual Programmers

Revisit and Outstrip Entity Alignment: A Perspective of Generative Models

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

Mirage: Model-agnostic Graph Distillation for Graph Classification

GraphPulse: Topological representations for temporal graph property prediction

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

(ends 12:45 PM)

Affinity Posters:

Blog Track Session 3

(ends 12:45 PM)

Affinity Posters:

Tiny Papers Poster Session 3

(ends 12:45 PM)

12:45 p.m.

Break:

Lunch Break

(ends 2:15 PM)

Office Hours:

Samy Bengio

(ends 1:30 PM)

Office Hours:

Andrej Risteski

(ends 1:30 PM)

Office Hours:

Andrea Bajcsy

(ends 1:30 PM)

Office Hours:

Yao Qin

(ends 1:30 PM)

1 p.m.

Expo Talk Panel:

“Beyond Algorithms: Navigating the Data Deluge in AI”

(ends 1:45 PM)

1:15 p.m.

Town Hall:

Town Hall

(ends 2:15 PM)

Affinity Workshop:

Tiny Papers Oral Session 2

(ends 2:15 PM)

1:30 p.m.

Office Hours:

Yoshua Bengio

(ends 2:15 PM)

Office Hours:

Eunsoi Choi

(ends 2:15 PM)

Office Hours:

Aditi Raghunathan

(ends 2:15 PM)

2:15 p.m.

Test Of Time:

Auto-Encoding Variational Bayes

(ends 2:45 PM)

2:45 p.m.

Test Of Time Runner Up:

Intriguing properties of neural networks

(ends 3:15 PM)

3:15 p.m.

Break:

Coffee Break

(ends 3:45 PM)

3:45 p.m.

Oral 4A [3:45-4:30]

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

Batched Low-Rank Adaptation of Foundation Models

(ends 4:30 PM)

Oral 4B [3:45-4:30]

Topological data analysis on noisy quantum computers

Flow Matching on General Geometries

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

(ends 4:30 PM)

Oral 4C [3:45-4:30]

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 4:30 PM)

Oral 4D [3:45-4:30]

Amortizing intractable inference in large language models

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

(ends 4:30 PM)

4:30 p.m.

Poster Session 4 [4:30-6:30]

Robust Model-Based Optimization for Challenging Fitness Landscapes

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

Zoology: Measuring and Improving Recall in Efficient Language Models

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

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

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

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

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

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

Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching

Social-Transmotion: Promptable Human Trajectory Prediction

Dual-Encoders for Extreme Multi-label Classification

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

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

A Sublinear Adversarial Training Algorithm

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

EasyTPP: Towards Open Benchmarking Temporal Point Processes

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

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

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

Contrastive Learning is Spectral Clustering on Similarity Graph

AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation

Neural Fourier Transform: A General Approach to Equivariant Representation Learning

Modulate Your Spectrum in Self-Supervised Learning

Separating common from salient patterns with Contrastive Representation Learning

Learning to reconstruct signals from binary measurements alone

AutoVP: An Automated Visual Prompting Framework and Benchmark

On Adversarial Training without Perturbing all Examples

Annealing Self-Distillation Rectification Improves Adversarial Training

PubDef: Defending Against Transfer Attacks From Public Models

Improving Domain Generalization with Domain Relations

Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks

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

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

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

Entropy-MCMC: Sampling from Flat Basins with Ease

Statistical Rejection Sampling Improves Preference Optimization

SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs

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

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

DistillSpec: Improving Speculative Decoding via Knowledge Distillation

LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models

The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction

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

Skeleton-of-Thought: Prompting LLMs for Efficient Parallel Generation

Bayesian Coreset Optimization for Personalized Federated Learning

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

Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise

Two-timescale Extragradient for Finding Local Minimax Points

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

Unified Projection-Free Algorithms for Adversarial DR-Submodular Optimization

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

Chain of Log-Concave Markov Chains

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

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

Momentum Benefits Non-iid Federated Learning Simply and Provably

FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization

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

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

Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings

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

Query-Policy Misalignment in Preference-Based Reinforcement Learning

Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks

Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning

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

Improving the Convergence of Dynamic NeRFs via Optimal Transport

Universal Humanoid Motion Representations for Physics-Based Control

METRA: Scalable Unsupervised RL with Metric-Aware Abstraction

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

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

Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior

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

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

On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning

Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning

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

Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning

Convolutional Deep Kernel Machines

Image Inpainting via Tractable Steering of Diffusion Models

Sliced Wasserstein Estimation with Control Variates

Neural Active Learning Beyond Bandits

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

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

Addressing Loss of Plasticity and Catastrophic Forgetting in Continual Learning

Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks

Efficient Heterogeneous Meta-Learning via Channel Shuffling Modulation

ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression

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

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

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

Topological data analysis on noisy quantum computers

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

The Need for Speed: Pruning Transformers with One Recipe

Shadow Cones: A Generalized Framework for Partial Order Embeddings

Bridging Neural and Symbolic Representations with Transitional Dictionary Learning

A representation-learning game for classes of prediction tasks

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

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

Invariance-based Learning of Latent Dynamics

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

Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation

Treatment Effects Estimation By Uniform Transformer

Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework

Logical Languages Accepted by Transformer Encoders with Hard Attention

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

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

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

Submodular Reinforcement Learning

Pseudo-Generalized Dynamic View Synthesis from a Video

The Effective Horizon Explains Deep RL Performance in Stochastic Environments

On the Limitations of Temperature Scaling for Distributions with Overlaps

Learning Thresholds with Latent Values and Censored Feedback

Improving equilibrium propagation without weight symmetry through Jacobian homeostasis

Online Information Acquisition: Hiring Multiple Agents

Learning Nash Equilibria in Rank-1 Games

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

Class Probability Matching with Calibrated Networks for Label Shift Adaption

Unknown Domain Inconsistency Minimization for Domain Generalization

Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning

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

Toward Student-oriented Teacher Network Training for Knowledge Distillation

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

Differentially Private Synthetic Data via Foundation Model APIs 1: Images

Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model

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

Privacy-Preserving In-Context Learning for Large Language Models

Correlated Noise Provably Beats Independent Noise for Differentially Private Learning

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

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

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

Demystifying Poisoning Backdoor Attacks from a Statistical Perspective

Balancing Act: Constraining Disparate Impact in Sparse Models

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

Understanding Certified Training with Interval Bound Propagation

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

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

Out-of-Distribution Detection with Negative Prompts

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

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

Defining and extracting generalizable interaction primitives from DNNs

Adaptive Window Pruning for Efficient Local Motion Deblurring

Path Choice Matters for Clear Attributions in Path Methods

Faithful Vision-Language Interpretation via Concept Bottleneck Models

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

Like Oil and Water: Group Robustness Methods and Poisoning Defenses May Be at Odds

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

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

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

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

Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation

Chain of Thought Empowers Transformers to Solve Inherently Serial Problems

HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments

Brain decoding: toward real-time reconstruction of visual perception

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

Context is Environment

Energy-based Automated Model Evaluation

SpaCE: The Spatial Confounding Environment

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

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

True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning

Flow Matching on General Geometries

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

Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic

Consistent Multi-Class Classification from Multiple Unlabeled Datasets

Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model

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

GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings

Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs

A Flexible Generative Model for Heterogeneous Tabular EHR with Missing Modality

Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation

VDT: General-purpose Video Diffusion Transformers via Mask Modeling

Tag2Text: Guiding Vision-Language Model via Image Tagging

Deep Confident Steps to New Pockets: Strategies for Docking Generalization

On the Foundations of Shortcut Learning

Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation

Horizon-Free Regret for Linear Markov Decision Processes

On Error Propagation of Diffusion Models

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

Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks

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

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

CNN Kernels Can Be the Best Shapelets

Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction

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

GENOME: Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules

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

Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning

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

Online GNN Evaluation Under Test-time Graph Distribution Shifts

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

SEA: Sparse Linear Attention with Estimated Attention Mask

Towards Codable Watermarking for Injecting Multi-Bits Information to LLMs

Space and time continuous physics simulation from partial observations

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

InstructDET: Diversifying Referring Object Detection with Generalized Instructions

Epitopological learning and Cannistraci-Hebb network shape intelligence brain-inspired theory for ultra-sparse advantage in deep learning

On Accelerating Diffusion-Based Sampling Processes via Improved Integration Approximation

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

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

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

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

SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore

Neural Common Neighbor with Completion for Link Prediction

Interpretable Meta-Learning of Physical Systems

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

ARGS: Alignment as Reward-Guided Search

Towards Robust Out-of-Distribution Generalization Bounds via Sharpness

Evaluating Large Language Models at Evaluating Instruction Following

On Stationary Point Convergence of PPO-Clip

Batched Low-Rank Adaptation of Foundation Models

Score Regularized Policy Optimization through Diffusion Behavior

Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion

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

$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence

Curriculum reinforcement learning for quantum architecture search under hardware errors

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

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

Robot Fleet Learning via Policy Merging

Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D

Grounding Language Plans in Demonstrations Through Counterfactual Perturbations

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

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

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

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

De novo Protein Design Using Geometric Vector Field Networks

LitCab: Lightweight Language Model Calibration over Short- and Long-form Responses

HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion

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

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

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

Generative Sliced MMD Flows with Riesz Kernels

Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective

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

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

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

Domain-Agnostic Molecular Generation with Chemical Feedback

DiffEnc: Variational Diffusion with a Learned Encoder

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

Neural Monge Map estimation and its applications

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

Multi-Scale Representations by Varying Window Attention for Semantic Segmentation

GRANDE: Gradient-Based Decision Tree Ensembles for Tabular Data

From Sparse to Soft Mixtures of Experts

Discovering modular solutions that generalize compositionally

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

Threaten Spiking Neural Networks through Combining Rate and Temporal Information

Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks

How connectivity structure shapes rich and lazy learning in neural circuits

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

TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks

Learning dynamic representations of the functional connectome in neurobiological networks

Bayesian Bi-clustering of Neural Spiking Activity with Latent Structures

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

Nougat: Neural Optical Understanding for Academic Documents

SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models

AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification

Retro-fallback: retrosynthetic planning in an uncertain world

VQ-TR: Vector Quantized Attention for Time Series Forecasting

Pre-Training and Fine-Tuning Generative Flow Networks

Robust Angular Synchronization via Directed Graph Neural Networks

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

Scalable and Effective Implicit Graph Neural Networks on Large Graphs

Probabilistically Rewired Message-Passing Neural Networks

VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs

Graph Neural Networks for Learning Equivariant Representations of Neural Networks

Making LLaMA SEE and Draw with SEED Tokenizer

NEFTune: Noisy Embeddings Improve Instruction Finetuning

Improving protein optimization with smoothed fitness landscapes

MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following

Ferret: Refer and Ground Anything Anywhere at Any Granularity

Language Model Self-improvement by Reinforcement Learning Contemplation

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

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

Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks

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

Learning Interactive Real-World Simulators

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

Talk like a Graph: Encoding Graphs for Large Language Models

Fine-Tuned Language Models Generate Stable Inorganic Materials as Text

Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization

Language Model Cascades: Token-Level Uncertainty And Beyond

Teaching Large Language Models to Self-Debug

Amortizing intractable inference in large language models

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

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

EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

LILO: Learning Interpretable Libraries by Compressing and Documenting Code

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

Understanding Catastrophic Forgetting in Language Models via Implicit Inference

(ends 6:30 PM)

Affinity Posters:

Blog Track Session 4

(ends 6:30 PM)

Affinity Posters:

Tiny Papers Poster Session 4

(ends 6:30 PM)

THU 9 MAY

8 a.m.

Registration Desk

(ends 6:30 PM)

8:30 a.m.

Invited Talk:

Stories from my life

Devi Parikh

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral 5A [10:00-10:45]

Generalization in diffusion models arises from geometry-adaptive harmonic representations

Diffusion Model for Dense Matching

Generative Modeling with Phase Stochastic Bridge

(ends 10:45 AM)

Oral 5B [10:00-10:45]

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 10:45 AM)

Oral 5C [10:00-10:45]

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 10:45 AM)

Oral 5D [10:00-10:45]

Interpreting CLIP's Image Representation via Text-Based Decomposition

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

(ends 10:45 AM)

10:45 a.m.

Poster Session 5 [10:45-12:45]

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

Debiasing Algorithm through Model Adaptation

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

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

EventRPG: Event Data Augmentation with Relevance Propagation Guidance

Dynamic Layer Tying for Parameter-Efficient Transformers

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

Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data

Memorization Capacity of Multi-Head Attention in Transformers

Pre-training with Random Orthogonal Projection Image Modeling

BECLR: Batch Enhanced Contrastive Few-Shot Learning

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

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

Goodhart's Law in Reinforcement Learning

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

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

Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game

Realistic Evaluation of Semi-supervised Learning Algorithms in Open Environments

Adaptive Sharpness-Aware Pruning for Robust Sparse Networks

The Effectiveness of Random Forgetting for Robust Generalization

Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations

Investigating the Benefits of Projection Head for Representation Learning

SLiMe: Segment Like Me

Early Stopping Against Label Noise Without Validation Data

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

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

Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation

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

Cycle Consistency Driven Object Discovery

Object-Centric Learning with Slot Mixture Module

To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets

Scaling Supervised Local Learning with Augmented Auxiliary Networks

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

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

How do Language Models Bind Entities in Context?

Linearity of Relation Decoding in Transformer Language Models

Are Models Biased on Text without Gender-related Language?

Compositional Preference Models for Aligning LMs

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

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

Think before you speak: Training Language Models With Pause Tokens

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

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

Language Modeling Is Compression

Learning Implicit Representation for Reconstructing Articulated Objects

FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores

TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting

Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations

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

Copula Conformal prediction for multi-step time series prediction

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

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

Magnitude Invariant Parametrizations Improve Hypernetwork Learning

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

A Precise Characterization of SGD Stability Using Loss Surface Geometry

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

TRAM: Bridging Trust Regions and Sharpness Aware Minimization

Learning to Solve Bilevel Programs with Binary Tender

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

Neur2RO: Neural Two-Stage Robust Optimization

Distributionally Robust Optimization with Bias and Variance Reduction

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

Towards Offline Opponent Modeling with In-context Learning

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

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

RLIF: Interactive Imitation Learning as Reinforcement Learning

3D Reconstruction with Generalizable Neural Fields using Scene Priors

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

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

Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model

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

Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces

DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing

Skill or Luck? Return Decomposition via Advantage Functions

Identifying Policy Gradient Subspaces

In-context Exploration-Exploitation for Reinforcement Learning

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

ImagenHub: Standardizing the evaluation of conditional image generation models

Scalable Diffusion for Materials Generation

Learning Multi-Agent Communication with Contrastive Learning

I-PHYRE: Interactive Physical Reasoning

Maximum Entropy Model Correction in Reinforcement Learning

Order-Preserving GFlowNets

FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning

DP-SGD Without Clipping: The Lipschitz Neural Network Way

Numerical Accounting in the Shuffle Model of Differential Privacy

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

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

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

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

Neural Fine-Tuning Search for Few-Shot Learning

Spatio-Temporal Few-Shot Learning via Diffusive Neural Network Generation

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

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

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

Learning Multi-Faceted Prototypical User Interests

Compressing Latent Space via Least Volume

HYPO: Hyperspherical Out-Of-Distribution Generalization

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

MOFI: Learning Image Representations from Noisy Entity Annotated Images

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

Counterfactual Density Estimation using Kernel Stein Discrepancies

Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning

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

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

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

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

Quadratic models for understanding catapult dynamics of neural networks

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

Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits

Communication-Efficient Federated Non-Linear Bandit Optimization

On the hardness of learning under symmetries

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

Improved sampling via learned diffusions

Structural Inference with Dynamics Encoding and Partial Correlation Coefficients

A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models

General Graph Random Features

R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning

Domain constraints improve risk prediction when outcome data is missing

Training Diffusion Models with Reinforcement Learning

Subtractive Mixture Models via Squaring: Representation and Learning

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

Improving LoRA in Privacy-preserving Federated Learning

Fair and Efficient Contribution Valuation for Vertical Federated Learning

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

AutoLoRa: An Automated Robust Fine-Tuning Framework

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

Backdoor Federated Learning by Poisoning Backdoor-Critical Layers

PRIME: Prioritizing Interpretability in Failure Mode Extraction

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

Diffusion Model for Dense Matching

Teach LLMs to Phish: Stealing Private Information from Language Models

Towards Faithful Explanations: Boosting Rationalization with Shortcuts Discovery

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

On Characterizing the Trade-off in Invariant Representation Learning

FairerCLIP: Debiasing CLIP's Zero-Shot Predictions using Functions in RKHSs

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

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

Finetuning Text-to-Image Diffusion Models for Fairness

Debiasing Attention Mechanism in Transformer without Demographics

Unprocessing Seven Years of Algorithmic Fairness

Object-Aware Inversion and Reassembly for Image Editing

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

Long-Short-Range Message-Passing: A Physics-Informed Framework to Capture Non-Local Interaction for Scalable Molecular Dynamics Simulation

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

GIO: Gradient Information Optimization for Training Dataset Selection

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

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

Personalize Segment Anything Model with One Shot

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

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

Towards Understanding Factual Knowledge of Large Language Models

PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION

NECO: NEural Collapse Based Out-of-distribution detection

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

PB-LLM: Partially Binarized Large Language Models

Online Stabilization of Spiking Neural Networks

AlpaGasus: Training a Better Alpaca with Fewer Data

Debiased Collaborative Filtering with Kernel-Based Causal Balancing

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

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

Provable Offline Preference-Based Reinforcement Learning

Frozen Transformers in Language Models Are Effective Visual Encoder Layers

Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction

Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification

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

RAIN: Your Language Models Can Align Themselves without Finetuning

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

Learning Performance-Improving Code Edits

Efficient Modulation for Vision Networks

Leave-one-out Distinguishability in Machine Learning

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

Blending Imitation and Reinforcement Learning for Robust Policy Improvement

DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation

HiGen: Hierarchical Graph Generative Networks

Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time

Future Language Modeling from Temporal Document History

Making Pre-trained Language Models Great on Tabular Prediction

RingAttention with Blockwise Transformers for Near-Infinite Context

Spatially-Aware Transformers for Embodied Agents

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

Understanding In-Context Learning from Repetitions

When can transformers reason with abstract symbols?

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

Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees

Embarrassingly Simple Dataset Distillation

Adversarial Imitation Learning via Boosting

GIM: Learning Generalizable Image Matcher From Internet Videos

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

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

Fast Ensembling with Diffusion Schrödinger Bridge

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

CCIL: Continuity-Based Data Augmentation for Corrective Imitation Learning

ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning

Text-to-3D with Classifier Score Distillation

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

Grokking as the transition from lazy to rich training dynamics

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

Reverse Forward Curriculum Learning for Extreme Sample and Demo Efficiency

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

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

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

On the Stability of Expressive Positional Encodings for Graphs

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

Negative Label Guided OOD Detection with Pretrained Vision-Language Models

Neural Ordinary Differential Equations for Modeling Epidemic Spreading

An Efficient Tester-Learner for Halfspaces

Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators

Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning

The Hidden Language of Diffusion Models

Imitation Learning from Observation with Automatic Discount Scheduling

Light Schrödinger Bridge

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

Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer

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

Hybrid Internal Model: Learning Agile Legged Locomotion with Simulated Robot Response

DittoGym: Learning to Control Soft Shape-Shifting Robots

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

SEPT: Towards Efficient Scene Representation Learning for Motion Prediction

Rethinking Branching on Exact Combinatorial Optimization Solver: The First Deep Symbolic Discovery Framework

Interpretable Diffusion via Information Decomposition

A Unified Sampling Framework for Solver Searching of Diffusion Probabilistic Models

Masked Completion via Structured Diffusion with White-Box Transformers

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

Denoising Task Routing for Diffusion Models

Consistent Video-to-Video Transfer Using Synthetic Dataset

Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems

Single Motion Diffusion

Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood

Generalization in diffusion models arises from geometry-adaptive harmonic representations

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

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

Training Unbiased Diffusion Models From Biased Dataset

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

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

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

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

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

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

Learning Personalized Causally Invariant Representations for Heterogeneous Federated Clients

DEEP NEURAL NETWORK INITIALIZATION WITH SPARSITY INDUCING ACTIVATIONS

ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation

RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation

Dictionary Contrastive Learning for Efficient Local Supervision without Auxiliary Networks

Magnushammer: A Transformer-Based Approach to Premise Selection

Active Retrosynthetic Planning Aware of Route Quality

Causally Aligned Curriculum Learning

TOSS: High-quality Text-guided Novel View Synthesis from a Single Image

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

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

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

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

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

Achieving Human Parity in Content-Grounded Datasets Generation

Generative Pre-training for Speech with Flow Matching

Periodicity Decoupling Framework for Long-term Series Forecasting

SALMON: Self-Alignment with Instructable Reward Models

Diffusion-TS: Interpretable Diffusion for General Time Series Generation

Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization

FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling

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

LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts

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

Quality-Diversity through AI Feedback

Generative Modeling with Phase Stochastic Bridge

Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation

TEDDY: Trimming Edges with Degree-based Discrimination Strategy

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

Forward Learning of Graph Neural Networks

HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs

Simplicial Representation Learning with Neural $k$-Forms

GNNX-BENCH: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking

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

Efficient Subgraph GNNs by Learning Effective Selection Policies

Counting Graph Substructures with Graph Neural Networks

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

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

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

Interpreting CLIP's Image Representation via Text-Based Decomposition

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

L2MAC: Large Language Model Automatic Computer for Extensive Code Generation

Hypothesis Search: Inductive Reasoning with Language Models

RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval

Looped Transformers are Better at Learning Learning Algorithms

In-Context Pretraining: Language Modeling Beyond Document Boundaries

Large Language Models to Enhance Bayesian Optimization

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

What's In My Big Data?

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

(ends 12:45 PM)

Affinity Posters:

Blog Track Session 5

(ends 12:45 PM)

Affinity Posters:

Tiny Papers Poster Session 5

(ends 12:45 PM)

12:45 p.m.

Break:

Lunch Break

(ends 2:15 PM)

Office Hours:

Andrew Gordon Wilson

(ends 1:30 PM)

Office Hours:

Erin Grant

(ends 1:30 PM)

Office Hours:

René Vidal

(ends 1:30 PM)

Office Hours:

Masashi Sugiyama

(ends 1:30 PM)

1:15 p.m.

Expo Talk Panel:

Advances in private training for production on-device language models

(ends 2:15 PM)

Affinity Workshop:

Tiny Papers Oral Session 3

(ends 2:15 PM)

1:30 p.m.

Office Hours:

Kyunghyun Cho

(ends 2:15 PM)

Office Hours:

Danqi Chen

(ends 2:15 PM)

Office Hours:

Amy Zhang

(ends 2:15 PM)

Office Hours:

Piotr Koniusz

(ends 2:15 PM)

2:15 p.m.

Invited Talk:

The ChatGLM's Road to AGI

Jie Tang

(ends 3:15 PM)

3:15 p.m.

Break:

Coffee Break

(ends 3:45 PM)

3:45 p.m.

Oral 6A [3:45-4:30]

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 4:30 PM)

Oral 6B [3:45-4:30]

GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations

Proving Test Set Contamination in Black-Box Language Models

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

(ends 4:30 PM)

Oral 6C [3:45-4:30]

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 4:30 PM)

Oral 6D [3:45-4:30]

Multi-granularity Correspondence Learning from Long-term Noisy Videos

Zipformer: A faster and better encoder for automatic speech recognition

(ends 4:30 PM)

4:30 p.m.

Poster Session 6 [4:30-6:30]

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

BatchPrompt: Accomplish more with less

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

Compressing LLMs: The Truth is Rarely Pure and Never Simple

Large Language Models as Optimizers

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

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

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

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

Self-Supervised Dataset Distillation for Transfer Learning

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

Neural Field Classifiers via Target Encoding and Classification Loss

Multi-granularity Correspondence Learning from Long-term Noisy Videos

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

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

Adapting to Distribution Shift by Visual Domain Prompt Generation

Influencer Backdoor Attack on Semantic Segmentation

Incremental Randomized Smoothing Certification

Doubly Robust Instance-Reweighted Adversarial Training

Provably Robust Conformal Prediction with Improved Efficiency

Pathologies of Predictive Diversity in Deep Ensembles

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

Learning invariant representations of time-homogeneous stochastic dynamical systems

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

MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning

Can Large Language Models Infer Causation from Correlation?

SliceGPT: Compress Large Language Models by Deleting Rows and Columns

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

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

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

Knowledge Fusion of Large Language Models

Multimodal Web Navigation with Instruction-Finetuned Foundation Models

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

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

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

Unveiling and Manipulating Prompt Influence in Large Language Models

Making Retrieval-Augmented Language Models Robust to Irrelevant Context

GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction

Meaning Representations from Trajectories in Autoregressive Models

Controlled Text Generation via Language Model Arithmetic

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

VeRA: Vector-based Random Matrix Adaptation

On the generalization capacity of neural networks during generic multimodal reasoning

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

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

ODEFormer: Symbolic Regression of Dynamical Systems with Transformers

Efficient Dynamics Modeling in Interactive Environments with Koopman Theory

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

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

A General Framework for User-Guided Bayesian Optimization

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

Algorithms for Caching and MTS with reduced number of predictions

Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization

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

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

EControl: Fast Distributed Optimization with Compression and Error Control

Zero Bubble (Almost) Pipeline Parallelism

Benchmarking Algorithms for Federated Domain Generalization

Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning

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

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

Efficient Planning with Latent Diffusion

Reasoning with Latent Diffusion in Offline Reinforcement Learning

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

Negatively Correlated Ensemble Reinforcement Learning for Online Diverse Game Level Generation

Window Attention is Bugged: How not to Interpolate Position Embeddings

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

Diverse Projection Ensembles for Distributional Reinforcement Learning

Off-Policy Primal-Dual Safe Reinforcement Learning

Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning

Consciousness-Inspired Spatio-Temporal Abstractions for Better Generalization in Reinforcement Learning

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

Behaviour Distillation

MINDE: Mutual Information Neural Diffusion Estimation

A Unified Framework for Bayesian Optimization under Contextual Uncertainty

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

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

Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling

Constraint-Free Structure Learning with Smooth Acyclic Orientations

CoLiDE: Concomitant Linear DAG Estimation

Training Bayesian Neural Networks with Sparse Subspace Variational Inference

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

Random Feature Amplification: Feature Learning and Generalization in Neural Networks

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

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

Context-Aware Meta-Learning

Meta-Learning Priors Using Unrolled Proximal Networks

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

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

Domain-Inspired Sharpness-Aware Minimization Under Domain Shifts

Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks

SemiReward: A General Reward Model for Semi-supervised Learning

SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series

Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach

Nemesis: Normalizing the Soft-prompt Vectors of Vision-Language Models

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

Enhancing Neural Training via a Correlated Dynamics Model

Towards a statistical theory of data selection under weak supervision

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

Out-of-Variable Generalisation for Discriminative Models

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

Federated Causal Discovery from Heterogeneous Data

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

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

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

Optimal Sample Complexity for Average Reward Markov Decision Processes

Demystifying Linear MDPs and Novel Dynamics Aggregation Framework

Contextual Bandits with Online Neural Regression

Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression

Dual Associated Encoder for Face Restoration

Spectrally Transformed Kernel Regression

The optimality of kernel classifiers in Sobolev space

Generalization error of spectral algorithms

On the Sample Complexity of Lipschitz Constant Estimation

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

Learning Optimal Contracts: How to Exploit Small Action Spaces

Dynamic Discounted Counterfactual Regret Minimization

NfgTransformer: Equivariant Representation Learning for Normal-form Games

Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation

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

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

Implicit regularization of deep residual networks towards neural ODEs

Sparsistency for inverse optimal transport

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

Privately Aligning Language Models with Reinforcement Learning

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

Attacking Perceptual Similarity Metrics

GNNCert: Deterministic Certification of Graph Neural Networks against Adversarial Perturbations

SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning

Efficient local linearity regularization to overcome catastrophic overfitting

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

Geometry-Aware Projective Mapping for Unbounded Neural Radiance Fields

VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks

Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective

Optimal transport based adversarial patch to leverage large scale attack transferability

Explaining Kernel Clustering via Decision Trees

Prediction without Preclusion: Recourse Verification with Reachable Sets

BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection

Faster Approximation of Probabilistic and Distributional Values via Least Squares

Classification with Conceptual Safeguards

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

Empirical Likelihood for Fair Classification

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

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

FairSeg: A Large-Scale Medical Image Segmentation Dataset for Fairness Learning Using Segment Anything Model with Fair Error-Bound Scaling

On the Fairness ROAD: Robust Optimization for Adversarial Debiasing

Patches Are All You Need?

Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings

Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight

Locality-Aware Graph Rewiring in GNNs

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

Hybrid Directional Graph Neural Network for Molecules

WildChat: 1M ChatGPT Interaction Logs in the Wild

Neural Processing of Tri-Plane Hybrid Neural Fields

PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback

Fast Updating Truncated SVD for Representation Learning with Sparse Matrices

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

Finite-State Autoregressive Entropy Coding for Efficient Learned Lossless Compression

On the Reliability of Watermarks for Large Language Models

HyperAttention: Long-context Attention in Near-Linear Time

Matryoshka Diffusion Models

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

Robust Training of Federated Models with Extremely Label Deficiency

On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning

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

Robustifying and Boosting Training-Free Neural Architecture Search

Solving High Frequency and Multi-Scale PDEs with Gaussian Processes

Adaptive Regret for Bandits Made Possible: Two Queries Suffice

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

Graph Lottery Ticket Automated

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

Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments

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

WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series

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

A Plug-and-Play Image Registration Network

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

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

Learning the greatest common divisor: explaining transformer predictions

Learning model uncertainty as variance-minimizing instance weights

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

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

Enhancing Human-AI Collaboration Through Logic-Guided Reasoning

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

Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP

Guiding Instruction-based Image Editing via Multimodal Large Language Models

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

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

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

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

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

Proving Test Set Contamination in Black-Box Language Models

Quantifying Network Similarity using Graph Cumulants

Efficient Score Matching with Deep Equilibrium Layers

Offline RL with Observation Histories: Analyzing and Improving Sample Complexity

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

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

Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance

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

SafeDreamer: Safe Reinforcement Learning with World Models

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

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

Provable Reward-Agnostic Preference-Based Reinforcement Learning

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

Learning Multi-Agent Communication from Graph Modeling Perspective

Recursive Generalization Transformer for Image Super-Resolution

Long-tailed Diffusion Models with Oriented Calibration

SPDER: Semiperiodic Damping-Enabled Object Representation

MgNO: Efficient Parameterization of Linear Operators via Multigrid

ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference

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

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

PINNACLE: PINN Adaptive ColLocation and Experimental points selection

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

Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding

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

Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models

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

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

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

Manifold Diffusion Fields

Finite Scalar Quantization: VQ-VAE Made Simple

Rethinking the symmetry-preserving circuits for constrained variational quantum algorithms

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

A Framework for Inference Inspired by Human Memory Mechanisms

Transformer-VQ: Linear-Time Transformers via Vector Quantization

Training Graph Transformers via Curriculum-Enhanced Attention Distillation

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

Image Clustering Conditioned on Text Criteria

NeurRev: Train Better Sparse Neural Network Practically via Neuron Revitalization

Lie Group Decompositions for Equivariant Neural Networks

FedWon: Triumphing Multi-domain Federated Learning Without Normalization

Efficient Backpropagation with Variance Controlled Adaptive Sampling

Multi-Source Diffusion Models for Simultaneous Music Generation and Separation

Data Filtering Networks

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

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

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

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

Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework

Parsing neural dynamics with infinite recurrent switching linear dynamical systems

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

Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities

One-hot Generalized Linear Model for Switching Brain State Discovery

Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for 3D Molecule Generation

Listen, Think, and Understand

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

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

Mayfly: a Neural Data Structure for Graph Stream Summarization

Constrained Decoding for Cross-lingual Label Projection

Zipformer: A faster and better encoder for automatic speech recognition

Self-Supervised Contrastive Learning for Long-term Forecasting

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

CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting

DAM: Towards a Foundation Model for Forecasting

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning

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

Concept Bottleneck Generative Models

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

Diffusion Models for Multi-Task Generative Modeling

Noise-free Score Distillation

Kosmos-G: Generating Images in Context with Multimodal Large Language Models

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

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

ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis

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

Grounded Object-Centric Learning

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

Efficient Integrators for Diffusion Generative Models

Intriguing Properties of Generative Classifiers

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

Augmenting Transformers with Recursively Composed Multi-grained Representations

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

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

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

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

Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow

iGraphMix: Input Graph Mixup Method for Node Classification

PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks

Mixture of Weak and Strong Experts on Graphs

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

SALMONN: Towards Generic Hearing Abilities for Large Language Models

MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models

Llemma: An Open Language Model for Mathematics

In-Context Learning Dynamics with Random Binary Sequences

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

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

(ends 6:30 PM)

Affinity Posters:

Blog Track Session 6

(ends 6:30 PM)

Affinity Posters:

Tiny Papers Poster Session 6

(ends 6:30 PM)

5:30 p.m.

FRI 10 MAY

8 a.m.

Registration Desk

(ends 6:30 PM)

8:30 a.m.

Invited Talk:

The emerging science of benchmarks

Moritz Hardt

(ends 9:30 AM)

9:30 a.m.

Break:

Coffee Break

(ends 10:00 AM)

10 a.m.

Oral 7A [10:00-10:45]

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 10:45 AM)

Oral 7B [10:00-10:45]

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

"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 10:45 AM)

Oral 7C [10:00-10:45]

Less is More: Fewer Interpretable Region via Submodular Subset Selection

On the Joint Interaction of Models, Data, and Features

(ends 10:45 AM)

Oral 7D [10:00-10:45]

One-shot Empirical Privacy Estimation for Federated Learning

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

(ends 10:45 AM)

10:45 a.m.

Poster Session 7 [10:45-12:45]

Posters 10:45-12:45

Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency

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

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

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

Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data

Implicit Neural Representations and the Algebra of Complex Wavelets

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

Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting

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

Decoupling regularization from the action space

Pose Modulated Avatars from Video

PAE: Reinforcement Learning from External Knowledge for Efficient Exploration

A Policy Gradient Method for Confounded POMDPs

On Representation Complexity of Model-based and Model-free Reinforcement Learning

Local Composite Saddle Point Optimization

AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference

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

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

A Discretization Framework for Robust Contextual Stochastic Optimization

A Study of Bayesian Neural Network Surrogates for Bayesian Optimization

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

A Differentially Private Clustering Algorithm for Well-Clustered Graphs

Threshold-Consistent Margin Loss for Open-World Deep Metric Learning

Knowledge Distillation Based on Transformed Teacher Matching

Progressive Fourier Neural Representation for Sequential Video Compilation

Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks

FITS: Modeling Time Series with $10k$ Parameters

Learning to Embed Time Series Patches Independently

Generalization of Scaled Deep ResNets in the Mean-Field Regime

Feature Collapse

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

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

Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime

Exploring Target Representations for Masked Autoencoders

An Investigation of Representation and Allocation Harms in Contrastive Learning

Improved Efficiency Based on Learned Saccade and Continuous Scene Reconstruction From Foveated Visual Sampling

Do Generated Data Always Help Contrastive Learning?

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

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

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

Understanding Domain Generalization: A Noise Robustness Perspective

Rethinking Model Ensemble in Transfer-based Adversarial Attacks

ZeroFlow: Scalable Scene Flow via Distillation

OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS

On Trajectory Augmentations for Off-Policy Evaluation

Score Models for Offline Goal-Conditioned Reinforcement Learning

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

Proper Laplacian Representation Learning

REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes

Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling

Exploring the Promise and Limits of Real-Time Recurrent Learning

Adaptive Rational Activations to Boost Deep Reinforcement Learning

Bridging State and History Representations: Understanding Self-Predictive RL

DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models

Understanding when Dynamics-Invariant Data Augmentations Benefit Model-free Reinforcement Learning Updates

Sample-Efficient Multi-Agent RL: An Optimization Perspective

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

The Update-Equivalence Framework for Decision-Time Planning

Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula

Intelligent Switching for Reset-Free RL

Extending Power of Nature from Binary to Real-Valued Graph Learning in Real World

A Hierarchical Bayesian Model for Few-Shot Meta Learning

Stochastic Gradient Descent for Gaussian Processes Done Right

Neural-Symbolic Recursive Machine for Systematic Generalization

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

Neural structure learning with stochastic differential equations

RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations

One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models

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

Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?

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

Understanding prompt engineering may not require rethinking generalization

Convergence of Bayesian Bilevel Optimization

Cascading Reinforcement Learning

Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation

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

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

Fixed-Budget Differentially Private Best Arm Identification

Incentivized Truthful Communication for Federated Bandits

Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods

Demonstration-Regularized RL

LCOT: Linear Circular Optimal Transport

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

An LLM can Fool Itself: A Prompt-Based Adversarial Attack

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

Incentive-Aware Federated Learning with Training-Time Model Rewards

Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence

Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty

Universal Backdoor Attacks

Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning

One-shot Empirical Privacy Estimation for Federated Learning

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

Parameter-Efficient Multi-Task Model Fusion with Partial Linearization

Gradual Domain Adaptation via Gradient Flow

Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline

Kalman Filter for Online Classification of Non-Stationary Data

Prediction Error-based Classification for Class-Incremental Learning

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

Adaptive Instrument Design for Indirect Experiments

Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Objectives

On the Provable Advantage of Unsupervised Pretraining

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

Multi-View Causal Representation Learning with Partial Observability

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

SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch

Plugin estimators for selective classification with out-of-distribution detection

In defense of parameter sharing for model-compression

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

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

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

Decodable and Sample Invariant Continuous Object Encoder

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

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

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

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

A Dynamical View of the Question of Why

Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation

A Linear Algebraic Framework for Counterfactual Generation

LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer

Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video

Data Debugging with Shapley Importance over Machine Learning Pipelines

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

Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain

Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced, Global Data?

Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks

Intriguing Properties of Data Attribution on Diffusion Models

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

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

SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models

Less is More: Fewer Interpretable Region via Submodular Subset Selection

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

Faithful Rule Extraction for Differentiable Rule Learning Models

Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models

Enhancing Group Fairness in Online Settings Using Oblique Decision Forests

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

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

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

SolidGen: An Autoregressive Model for Direct B-rep Synthesis

Scaling Autoregressive Models for Content-Rich Text-to-Image Generation

Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals

Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration

Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching

Data-independent Module-aware Pruning for Hierarchical Vision Transformers

Prometheus: Inducing Fine-Grained Evaluation Capability in Language Models

GAIA: Zero-shot Talking Avatar Generation

Enhancing Instance-Level Image Classification with Set-Level Labels

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

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

RETSim: Resilient and Efficient Text Similarity

Principled Architecture-aware Scaling of Hyperparameters

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

Ins-DetCLIP: Aligning Detection Model to Follow Human-Language Instruction

Graph Transformers on EHRs: Better Representation Improves Downstream Performance

Learning to Act from Actionless Videos through Dense Correspondences

Federated Text-driven Prompt Generation for Vision-Language Models

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

Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms

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

Variational Bayesian Last Layers

BENO: Boundary-embedded Neural Operators for Elliptic PDEs

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

On the Joint Interaction of Models, Data, and Features

Sparse MoE with Language Guided Routing for Multilingual Machine Translation

Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors

Inverse Approximation Theory for Nonlinear Recurrent Neural Networks

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

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

Unbiased Watermark for Large Language Models

Large Language Models as Generalizable Policies for Embodied Tasks

Motif: Intrinsic Motivation from Artificial Intelligence Feedback

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

Towards Meta-Pruning via Optimal Transport

Analyzing and Mitigating Object Hallucination in Large Vision-Language Models

Scalable Language Model with Generalized Continual Learning

Online Continual Learning for Interactive Instruction Following Agents

Multi-Resolution Diffusion Models for Time Series Forecasting

FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning

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

COLLIE: Systematic Construction of Constrained Text Generation Tasks

USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields

Learning Polynomial Problems with $SL(2, \mathbb{R})$-Equivariance

DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation

Small-scale proxies for large-scale Transformer training instabilities

Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces

Raidar: geneRative AI Detection viA Rewriting

An Extensible Framework for Open Heterogeneous Collaborative Perception

Mol-Instructions: A Large-Scale Biomolecular Instruction Dataset for Large Language Models

Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design

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

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

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

MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models

CLEX: Continuous Length Extrapolation for Large Language Models

Learning interpretable control inputs and dynamics underlying animal locomotion

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

G$^2$N$^2$ : Weisfeiler and Lehman go grammatical

Structural Fairness-aware Active Learning for Graph Neural Networks

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

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

NetInfoF Framework: Measuring and Exploiting Network Usable Information

GraphChef: Decision-Tree Recipes to Explain Graph Neural Networks

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

NoiseDiffusion: Correcting Noise for Image Interpolation with Diffusion Models beyond Spherical Linear Interpolation

Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection

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

MaGIC: Multi-modality Guided Image Completion

Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints

AnyText: Multilingual Visual Text Generation and Editing

Human Motion Diffusion as a Generative Prior

Neural Atoms: Propagating Long-range Interaction in Molecular Graphs through Efficient Communication Channel

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

BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference

Idempotent Generative Network

DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation

Modelling complex vector drawings with stroke-clouds

Multimarginal Generative Modeling with Stochastic Interpolants

The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing

Idempotence and Perceptual Image Compression

Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach

Jointly Training Large Autoregressive Multimodal Models

Gradual Optimization Learning for Conformational Energy Minimization

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

Bespoke Solvers for Generative Flow Models

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

Information Retention via Learning Supplemental Features

Mean Field Theory in Deep Metric Learning

Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning

Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning

Turning large language models into cognitive models

Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data

Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging Data

Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction

Predictive, scalable and interpretable knowledge tracing on structured domains

InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes

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

Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding

OWL: A Large Language Model for IT Operations

Conversational Drug Editing Using Retrieval and Domain Feedback

A Multi-Level Framework for Accelerating Training Transformer Models

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

Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning

Bayesian Low-rank Adaptation for Large Language Models

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

In-Context Learning through the Bayesian Prism

Towards Robust Multi-Modal Reasoning via Model Selection

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

Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs

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

Few-Shot Detection of Machine-Generated Text using Style Representations

Stable Anisotropic Regularization

GAIA: a benchmark for General AI Assistants

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

LLM-Assisted Code Cleaning For Training Accurate Code Generators

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

RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems

Octavius: Mitigating Task Interference in MLLMs via LoRA-MoE

Large Language Models Are Not Robust Multiple Choice Selectors

Let's Verify Step by Step

Is Self-Repair a Silver Bullet for Code Generation?

Detecting Pretraining Data from Large Language Models

PerceptionCLIP: Visual Classification by Inferring and Conditioning on Contexts

INViTE: INterpret and Control Vision-Language Models with Text Explanations

Dynamic Neural Response Tuning

Unconstrained Stochastic CCA: Unifying Multiview and Self-Supervised Learning

(ends 12:45 PM)

Affinity Posters:

Blog Track Session 7

(ends 12:45 PM)

Affinity Posters:

Tiny Papers Poster Session 7

(ends 12:45 PM)

12:45 p.m.

Break:

Lunch Break

(ends 2:15 PM)

Expo Talk Panel:

Trustworthy human evaluations for Large Language Models

(ends 2:15 PM)

Office Hours:

Moritz Hardt

(ends 1:30 PM)

Office Hours:

Sasha Rush

(ends 1:30 PM)

Office Hours:

Rosanne Liu

(ends 1:30 PM)

Office Hours:

Hanwang Zhang

(ends 1:30 PM)

1:15 p.m.

Affinity Workshop:

Tiny Papers Oral Session 4

(ends 2:15 PM)

1:30 p.m.

Office Hours:

Claire Vernade

(ends 2:15 PM)

Office Hours:

Xuezhi Wang

(ends 2:15 PM)

Office Hours:

Tatsunori Hashimoto

(ends 2:15 PM)

Office Hours:

Luke Zettlemoyer

(ends 2:15 PM)

2:15 p.m.

Invited Talk:

Machine Learning in Prescient Design's Lab-in-the-Loop Antibody Design

Kyunghyun Cho

(ends 3:10 PM)

3:10 p.m.

Remarks:

Closing Remarks

(ends 3:15 PM)

3:15 p.m.

Break:

Coffee Break

(ends 3:45 PM)

3:45 p.m.

Oral 8A [3:45-4:30]

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 4:30 PM)

Oral 8B [3:45-4:30]

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 4:30 PM)

Oral 8C [3:45-4:30]

Mastering Memory Tasks with World Models

LEGO-Prover: Neural Theorem Proving with Growing Libraries

(ends 4:30 PM)

Oral 8D [3:45-4:30]

Provable Compositional Generalization for Object-Centric Learning

Multisize Dataset Condensation

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

(ends 4:30 PM)

4:30 p.m.

Poster:

Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning

(ends 6:30 PM)

Poster Session 8 [4:30-6:30]

Transferring Labels to Solve Annotation Mismatches Across Object Detection Datasets

Real-Fake: Effective Training Data Synthesis Through Distribution Matching

Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods

Uncertainty Quantification via Stable Distribution Propagation

DAFA: Distance-Aware Fair Adversarial Training

The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing

Unraveling the Key Components of OOD Generalization via Diversification

Discovering Temporally-Aware Reinforcement Learning Algorithms

The Curse of Diversity in Ensemble-Based Exploration

When should we prefer Decision Transformers for Offline Reinforcement Learning?

Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization

Can Transformers Capture Spatial Relations between Objects?

S$2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic

Selective Visual Representations Improve Convergence and Generalization for Embodied AI

Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning

A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging

Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning

Adversarial Causal Bayesian Optimization

One Forward is Enough for Neural Network Training via Likelihood Ratio Method

InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning

Fast Equilibrium of SGD in Generic Situations

DiffusionSat: A Generative Foundation Model for Satellite Imagery

Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach

Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping

Efficient Continual Finite-Sum Minimization

Dropout Enhanced Bilevel Training

Graph Metanetworks for Processing Diverse Neural Architectures

Is attention required for ICL? Exploring the Relationship Between Model Architecture and In-Context Learning Ability

H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields

Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach

Learning Hierarchical Polynomials with Three-Layer Neural Networks

V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection

LDReg: Local Dimensionality Regularized Self-Supervised Learning

MCM: Masked Cell Modeling for Anomaly Detection in Tabular Data

AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation Learning

On the Role of General Function Approximation in Offline Reinforcement Learning

On the Role of Discrete Tokenization in Visual Representation Learning

Safe and Robust Watermark Injection with a Single OoD Image

Rotation Has Two Sides: Evaluating Data Augmentation for Deep One-class Classification

Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding

TiC-CLIP: Continual Training of CLIP Models

CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding

Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement

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

Reward-Free Curricula for Training Robust World Models

Entity-Centric Reinforcement Learning for Object Manipulation from Pixels

Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations

Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization Analysis

Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes

Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control

Expected flow networks in stochastic environments and two-player zero-sum games

MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection

Meta-VBO: Utilizing Prior Tasks in Optimizing Risk Measures with Gaussian Processes

Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG

Variational Inference for SDEs Driven by Fractional Noise

Improved Active Learning via Dependent Leverage Score Sampling

Provable Compositional Generalization for Object-Centric Learning

Koopman-based generalization bound: New aspect for full-rank weights

Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning

Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games

Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space

Mask-Based Modeling for Neural Radiance Fields

Optimal Sample Complexity of Contrastive Learning

Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem

Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining

Bandits with Replenishable Knapsacks: the Best of both Worlds

Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems

STARC: A General Framework For Quantifying Differences Between Reward Functions

Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem

Identifying Representations for Intervention Extrapolation

A Neural Framework for Generalized Causal Sensitivity Analysis

FedImpro: Measuring and Improving Client Update in Federated Learning

Learning semilinear neural operators: A unified recursive framework for prediction and data assimilation.

Pooling Image Datasets with Multiple Covariate Shift and Imbalance

Cauchy-Schwarz Divergence Information Bottleneck for Regression

Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning

Consistent algorithms for multi-label classification with macro-at-$k$ metrics

Local Graph Clustering with Noisy Labels

DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior

A 2-Dimensional State Space Layer for Spatial Inductive Bias

OMNI: Open-endedness via Models of human Notions of Interestingness

Removing Biases from Molecular Representations via Information Maximization

Generating Images with 3D Annotations Using Diffusion Models

Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback

Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training

LEGO-Prover: Neural Theorem Proving with Growing Libraries

Mastering Memory Tasks with World Models

Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks

Safe Collaborative Filtering

Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation

Can LLM-Generated Misinformation Be Detected?

Does Writing with Language Models Reduce Content Diversity?

Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization

Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks

Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning

Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark

Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations

Machine Unlearning for Image-to-Image Generative Models

Adversarial Attacks on Fairness of Graph Neural Networks

Backdoor Contrastive Learning via Bi-level Trigger Optimization

ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor

Adversarial Feature Map Pruning for Backdoor

Boundary Denoising for Video Activity Localization

Interpreting Robustness Proofs of Deep Neural Networks

AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models

ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection

Privacy Amplification for Matrix Mechanisms

Confidential-DPproof: Confidential Proof of Differentially Private Training

Detecting, Explaining, and Mitigating Memorization in Diffusion Models

Learning in reverse causal strategic environments with ramifications on two sided markets

Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model

First-order ANIL provably learns representations despite overparametrisation

AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images

Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment

A Unified and General Framework for Continual Learning

The LLM Surgeon

Parallelizing non-linear sequential models over the sequence length

Building Cooperative Embodied Agents Modularly with Large Language Models

Multisize Dataset Condensation

PTaRL: Prototype-based Tabular Representation Learning via Space Calibration

DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow

Improved algorithm and bounds for successive projection

Chain-of-Experts: When LLMs Meet Complex Operations Research Problems

Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models

Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML

The False Promise of Imitating Proprietary Language Models

Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts

Improved statistical and computational complexity of the mean-field Langevin dynamics under structured data

Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs

Overthinking the Truth: Understanding how Language Models Process False Demonstrations

Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models

How to Fine-Tune Vision Models with SGD

INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection

Large-scale Training of Foundation Models for Wearable Biosignals

A Topological Perspective on Demystifying GNN-Based Link Prediction Performance

Generalized Policy Iteration using Tensor Approximation for Hybrid Control

UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling

Unveiling the Pitfalls of Knowledge Editing for Large Language Models

AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation

Language Model Beats Diffusion - Tokenizer is key to visual generation

How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations

Jointly-Learned Exit and Inference for a Dynamic Neural Network

COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL

C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion

MetaPhysiCa: Improving OOD Robustness in Physics-informed Machine Learning

Simple Hierarchical Planning with Diffusion

Large Language Models as Automated Aligners for benchmarking Vision-Language Models

Deep Neural Networks Tend To Extrapolate Predictably

Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning

Leveraging Uncertainty Estimates To Improve Classifier Performance

LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents

Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation

Memory-Consistent Neural Networks for Imitation Learning

Enhancing Neural Subset Selection: Integrating Background Information into Set Representations

PolyVoice: Language Models for Speech to Speech Translation

Inherently Interpretable Time Series Classification via Multiple Instance Learning

Language Model Inversion

End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon

Large Language Models as Tool Makers

Neural Contractive Dynamical Systems

Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization

Conditional Information Bottleneck Approach for Time Series Imputation

TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series

SaProt: Protein Language Modeling with Structure-aware Vocabulary

BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks

Vision-Language Foundation Models as Effective Robot Imitators

A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks

DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption

Understanding Expressivity of GNN in Rule Learning

Efficient and Scalable Graph Generation through Iterative Local Expansion

Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials

Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps

Universal Guidance for Diffusion Models

Manifold Preserving Guided Diffusion

Lifting Architectural Constraints of Injective Flows

Generative Human Motion Stylization in Latent Space

Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition

Latent 3D Graph Diffusion

The Unlocking Spell on Base LLMs: Rethinking Alignment via In-Context Learning

Localizing and Editing Knowledge In Text-to-Image Generative Models

Diffusion Sampling with Momentum for Mitigating Divergence Artifacts

Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling

DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation

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

Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space

DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$

A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction

Simplifying Transformer Blocks

The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric

ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference

Guaranteed Approximation Bounds for Mixed-Precision Neural Operators

Boosting Vanilla Lightweight Vision Transformers via Re-parameterization

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks

ImplicitSLIM and How it Improves Embedding-based Collaborative Filtering

Traveling Waves Encode The Recent Past and Enhance Sequence Learning

Estimating Shape Distances on Neural Representations with Limited Samples

Decoding Natural Images from EEG for Object Recognition

A Cognitive Model for Learning Abstract Relational Structures from Memory-based Decision-Making Tasks

SetCSE: Set Operations using Contrastive Learning of Sentence Embeddings

Tailoring Self-Rationalizers with Multi-Reward Distillation

CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech

Emergent Communication with Conversational Repair

Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation

Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models

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

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

CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs

Workflow Discovery from Dialogues in the Low Data Regime

Self-Alignment with Instruction Backtranslation

BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models

On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes

Multiscale Positive-Unlabeled Detection of AI-Generated Texts

OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models

FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets

Neural Optimal Transport with General Cost Functionals

Identifying the Risks of LM Agents with an LM-Emulated Sandbox

SKILL-MIX: a Flexible and Expandable Family of Evaluations for AI Models

Disentangling Time Series Representations via Contrastive Independence-of-Support on l-Variational Inference

WizardCoder: Empowering Code Large Language Models with Evol-Instruct

Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources

Closing the Curious Case of Neural Text Degeneration

OctoPack: Instruction Tuning Code Large Language Models

BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation

Functional Interpolation for Relative Positions improves Long Context Transformers

Branch-GAN: Improving Text Generation with (not so) Large Language Models

M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering

Let Models Speak Ciphers: Multiagent Debate through Embeddings

RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment

Retrieval meets Long Context Large Language Models

Attention-based Iterative Decomposition for Tensor Product Representation

Differentiable Euler Characteristic Transforms for Shape Classification

T-MARS: Improving Visual Representations by Circumventing Text Feature Learning

Approximately Piecewise E(3) Equivariant Point Networks

State Representation Learning Using an Unbalanced Atlas

Successor Heads: Recurring, Interpretable Attention Heads In The Wild

A Lie Group Approach to Riemannian Batch Normalization

(ends 6:30 PM)

Affinity Posters:

Blog Track Session 8

(ends 6:30 PM)

Affinity Posters:

Tiny Papers Poster Session 8

(ends 6:30 PM)

SAT 11 MAY

7 a.m.

Registration Desk

(ends 1:00 PM)

8 a.m.

Workshop:

Tackling Climate Change with Machine Learning: Fostering the Maturity of ML Applications for Climate Change

(ends 5:00 PM)

Workshop:

First Workshop on Representational Alignment (Re-Align)

(ends 5:00 PM)

8:15 a.m.

Workshop:

AI4DifferentialEquations In Science

(ends 5:00 PM)

8:25 a.m.

Workshop:

Privacy Regulation and Protection in Machine Learning

(ends 4:50 PM)

8:30 a.m.

Workshop:

How Far Are We From AGI

(ends 5:00 PM)

Workshop:

Generative Models for Decision Making

(ends 5:00 PM)

Workshop:

5th Workshop on practical ML for limited/low resource settings (PML4LRS) @ ICLR 2024

(ends 5:00 PM)

8:40 a.m.

Workshop:

Workshop on Large Language Models for Agents

(ends 5:00 PM)

8:50 a.m.

Workshop:

ICLR 2024 Workshop on Reliable and Responsible Foundation Models

(ends 5:00 PM)

9 a.m.

Workshop:

Machine Learning for Genomics Explorations (MLGenX)

(ends 5:00 PM)

Workshop:

Bridging the Gap Between Practice and Theory in Deep Learning

(ends 5:00 PM)

Workshop:

Global AI Cultures

(ends 5:00 PM)

Workshop:

Secure and Trustworthy Large Language Models

(ends 5:00 PM)

Workshop:

5th Workshop on African Natural Language Processing (AfricaNLP 2024)

(ends 5:00 PM)

Workshop:

Workshop on Learning from Time Series for Health

(ends 5:00 PM)

Workshop:

Generative and Experimental Perspectives for Biomolecular Design

(ends 5:00 PM)

Workshop:

Navigating and Addressing Data Problems for Foundation Models (DPFM)

(ends 5:00 PM)

Workshop:

Machine Learning for Remote Sensing (ML4RS)

(ends 5:00 PM)

Workshop:

Data-centric Machine Learning Research (DMLR): Harnessing Momentum for Science

(ends 5:00 PM)

Workshop:

2nd Workshop on Mathematical and Empirical Understanding of Foundation Models

(ends 5:00 PM)

9:30 a.m.

Break:

Coffee Break

(ends 10:30 AM)

12:45 p.m.

Break:

Lunch Break

(ends 2:15 PM)

3:15 p.m.

Break:

Coffee Break

(ends 3:45 PM)