Skip to yearly menu bar
Skip to main content
Main Navigation
ICLR
Help/FAQ
Contact ICLR
Downloads
ICLR Blog
Code of Conduct
Privacy Policy
Create Profile
Journal To Conference Track
Diversity & Inclusion
Proceedings at OpenReview
Future Meetings
Press
Exhibitor Information
ICLR Twitter
About ICLR
My Stuff
Login
Select Year: (2024)
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
Getting Started
Schedule
Main Conference
Invited Talks
Awards
Papers
In-person Orals
Spotlight Posters
Workshops
Community
Socials
Town Hall
Affinity Events
Sponsors
Organizers
Help
Helpdesk
RocketChat Client
Website FAQ
Browse
mini
compact
topic
detail
Showing papers for
.
×
×
title
author
topic
session
shuffle
by
serendipity
bookmarked first
visited first
not visited first
bookmarked but not visited
Enable Javascript in your browser to see the papers page.
NaturalSpeech 2: Latent Diffusion Models are Natural and Zero-Shot Speech and Singing Synthesizers
Accurate Forgetting for Heterogeneous Federated Continual Learning
Self-Consuming Generative Models Go MAD
Patched Denoising Diffusion Models For High-Resolution Image Synthesis
Learning Hierarchical World Models with Adaptive Temporal Abstractions from Discrete Latent Dynamics
Generative Adversarial Equilibrium Solvers
Meta Continual Learning Revisited: Implicitly Enhancing Online Hessian Approximation via Variance Reduction
Safe RLHF: Safe Reinforcement Learning from Human Feedback
EfficientDM: Efficient Quantization-Aware Fine-Tuning of Low-Bit Diffusion Models
Tree Cross Attention
Towards Foundational Models for Molecular Learning on Large-Scale Multi-Task Datasets
Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimators
InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
Abstractors and relational cross-attention: An inductive bias for explicit relational reasoning in Transformers
Conditional Variational Diffusion Models
PanoDiffusion: 360-degree Panorama Outpainting via Diffusion
Deep Geodesic Canonical Correlation Analysis for Covariance-Based Neuroimaging Data
Adaptive Regularization of Representation Rank as an Implicit Constraint of Bellman Equation
KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval
Representation Deficiency in Masked Language Modeling
Understanding In-Context Learning from Repetitions
R-MAE: Regions Meet Masked Autoencoders
Learning to Reject with a Fixed Predictor: Application to Decontextualization
Prompt Learning with Quaternion Networks
Minimum width for universal approximation using ReLU networks on compact domain
Decongestion by Representation: Learning to Improve Economic Welfare in Marketplaces
Are Human-generated Demonstrations Necessary for In-context Learning?
On the Parameterization of Second-Order Optimization Effective towards the Infinite Width
Neural Optimal Transport with General Cost Functionals
GPAvatar: Generalizable and Precise Head Avatar from Image(s)
Polynormer: Polynomial-Expressive Graph Transformer in Linear Time
EventRPG: Event Data Augmentation with Relevance Propagation Guidance
Scaling Laws for Sparsely-Connected Foundation Models
Kernelised Normalising Flows
LLM Augmented LLMs: Expanding Capabilities through Composition
Knowledge Fusion of Large Language Models
Towards Universal Multi-Modal Personalization: A Language Model Empowered Generative Paradigm
A Poincaré Inequality and Consistency Results for Signal Sampling on Large Graphs
Multi-scale Transformers with Adaptive Pathways for Time Series Forecasting
Non-negative Contrastive Learning
The Reasonableness Behind Unreasonable Translation Capability of Large Language Model
FedInverse: Evaluating Privacy Leakage in Federated Learning
FedCDA: Federated Learning with Cross-rounds Divergence-aware Aggregation
Efficient-3Dim: Learning a Generalizable Single-image Novel-view Synthesizer in One Day
Causal Modelling Agents: Causal Graph Discovery through Synergising Metadata- and Data-driven Reasoning
Calibrated Chaos: Variance Between Runs of Neural Network Training is Harmless and Inevitable
Conformal Language Modeling
Ferret: Refer and Ground Anything Anywhere at Any Granularity
Explaining Time Series via Contrastive and Locally Sparse Perturbations
Protein-Ligand Interaction Prior for Binding-aware 3D Molecule Diffusion Models
AnyText: Multilingual Visual Text Generation and Editing
Maximum Entropy Heterogeneous-Agent Reinforcement Learning
GROOT: Learning to Follow Instructions by Watching Gameplay Videos
Self-supervised Representation Learning from Random Data Projectors
Würstchen: An Efficient Architecture for Large-Scale Text-to-Image Diffusion Models
The Expressive Leaky Memory Neuron: an Efficient and Expressive Phenomenological Neuron Model Can Solve Long-Horizon Tasks.
CODE REPRESENTATION LEARNING AT SCALE
Bandits with Replenishable Knapsacks: the Best of both Worlds
From Bricks to Bridges: Product of Invariances to Enhance Latent Space Communication
$\texttt{NAISR}$: A 3D Neural Additive Model for Interpretable Shape Representation
Are Bert Family Good Instruction Followers? A Study on Their Potential And Limitations
Federated Recommendation with Additive Personalization
Emergent mechanisms for long timescales depend on training curriculum and affect performance in memory tasks
Equivariant Matrix Function Neural Networks
Neural Monge Map estimation and its applications
ModuLoRA: Finetuning 2-Bit LLMs on Consumer GPUs by Integrating with Modular Quantizers
Learning Semantic Proxies from Visual Prompts for Parameter-Efficient Fine-Tuning in Deep Metric Learning
Be More Active! Understanding the Differences Between Mean and Sampled Representations of Variational Autoencoders
LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection
Sparse Spiking Neural Network: Exploiting Heterogeneity in Timescales for Pruning Recurrent SNN
Enhancing Transferable Adversarial Attacks on Vision Transformers through Gradient Normalization Scaling and High-Frequency Adaptation
Dynamic Sparse No Training: Training-Free Fine-tuning for Sparse LLMs
Convolutional Deep Kernel Machines
Energy-Based Concept Bottleneck Models
MUFFIN: Curating Multi-Faceted Instructions for Improving Instruction Following
Fine-Tuning Language Models for Factuality
Neural Spectral Methods: Self-supervised learning in the spectral domain
What does the Knowledge Neuron Thesis Have to do with Knowledge?
Deep SE(3)-Equivariant Geometric Reasoning for Precise Placement Tasks
Cauchy-Schwarz Divergence Information Bottleneck for Regression
Separating common from salient patterns with Contrastive Representation Learning
Safe and Robust Watermark Injection with a Single OoD Image
Chain of Thought Empowers Transformers to Solve Inherently Serial Problems
Overcoming the Pitfalls of Vision-Language Model Finetuning for OOD Generalization
Don't Play Favorites: Minority Guidance for Diffusion Models
Space and time continuous physics simulation from partial observations
Rethinking Information-theoretic Generalization: Loss Entropy Induced PAC Bounds
Physics-Regulated Deep Reinforcement Learning: Invariant Embeddings
A Theoretical Explanation of Deep RL Performance in Stochastic Environments
Certified Adversarial Robustness for Rate Encoded Spiking Neural Networks
Robust Angular Synchronization via Directed Graph Neural Networks
Two-timescale Extragradient for Finding Local Minimax Points
Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models
BooookScore: A systematic exploration of book-length summarization in the era of LLMs
Context is Environment
DiffEnc: Variational Diffusion with a Learned Encoder
Learning Nash equilibria in Rank-1 games: Going beyond the Minty Property
Learning Decentralized Partially Observable Mean Field Control for Artificial Collective Behavior
FedCompass: Efficient Cross-Silo Federated Learning on Heterogeneous Client Devices Using a Computing Power-Aware Scheduler
ED-NeRF: Efficient Text-Guided Editing of 3D Scene With Latent Space NeRF
De novo Protein Design Using Geometric Vector Field Networks
Semantic Flow: Learning Semantic Fields of Dynamic Scenes from Monocular Videos
Out-of-Distribution Detection by Leveraging Between-Layer Transformation Smoothness
Demystifying Poisoning Backdoor Attacks from a Statistical Perspective
Solving Diffusion ODEs with Optimal Boundary Conditions for Better Image Super-Resolution
Energy-based Automated Model Evaluation
Sudden Drops in the Loss: Syntax Acquisition, Phase Transitions, and Simplicity Bias in MLMs
Output-Domain Focused Inductive Bias on Latent Feature Clusters in Visual Classification
Accelerated Convergence of Stochastic Heavy Ball Method under Anisotropic Gradient Noise
Concept Bottleneck Generative Models
Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression
SpaCE: The Spatial Confounding Environment
Improving Out-of-Domain Generalization with Domain Relations
Bounding the Expected Robustness of Graph Neural Networks Subject to Node Feature Attacks
CLIPSelf: Vision Transformer Distills Itself for Open-Vocabulary Dense Prediction
An Emulator for Fine-tuning Large Language Models using Small Language Models
Unsupervised Order Learning
FeatUp: A Model-Agnostic Framework for Features at Any Resolution
DMV3D: Denoising Multi-view Diffusion Using 3D Large Reconstruction Model
VQ-TR: Vector Quantized Attention for Time Series Forecasting
Towards Codable Text Watermarking for Large Language Models
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators
A Hard-to-Beat Baseline for Training-free CLIP-based Adaptation
Improving Natural Language Understanding with Computation-Efficient Retrieval Augmentation
Retroformer: Retrospective Large Language Agents with Policy Gradient Optimization
Unprocessing Seven Years of Algorithmic Fairness
Learning to Embed Time Series Patches Independently
Attention-Guided Contrastive Role Representations for Multi-agent Reinforcement Learning
Bilevel Optimization under Unbounded Smoothness: A New Algorithm and Convergence Analysis
Generative Neuro-Symbolic Visual Reasoning by Growing and Reusing Modules
Causal Structure Recovery with Latent Variables under Milder Distributional and Graphical Assumptions
Forward Learning with Top-Down Feedback: Empirical and Analytical Characterization
TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning
Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning
TESTAM: A Time-Enhanced Spatio-Temporal Attention Model with Mixture of Experts
CNN Kernels Can Be the Best Shapelets
Stabilizing Contrastive RL: Techniques for Robotic Goal Reaching from Offline Data
Biased Temporal Convolution Graph Network for Time Series Forecasting with Missing Values.
Defining and extracting generalizable interaction primitives from DNNs
Incentivized Truthful Communication for Federated Bandits
TapMo: Shape-aware Motion Generation of Skeleton-free Characters
Spike-driven Transformer V2: Meta Spiking Neural Network Architecture Inspiring the Design of Next-generation Neuromorphic Chips
Amortizing intractable inference in large language models
Minimax optimality of convolutional neural networks for infinite dimensional input-output problems and separation from kernel methods
The Cost of Scaling Down Large Language Models: Reducing Model Size Affects Memory before In-context Learning
Compositional VLM: Composing Visual Entities and Relationships in Large Language Models Via Communicative Decoding
Relaxing the Additivity Constraints in Decentralized No-Regret High-Dimensional Bayesian Optimization
Scalable and Effective Implicit Graph Neural Networks on Large Graphs
Efficient Heterogeneous Meta-Learning via Channel Shuffling Modulation
Large Brain Model for Learning Generic Representations with Tremendous EEG Data in BCI
Horizon-Free Regret for Linear Markov Decision Processes
Dropout-Based Rashomon Set Exploration for Efficient Predictive Multiplicity Estimation
Long-Short-Range Message-Passing: A Fragmentation-Based Framework to Capture Non-Local Atomistic Interactions
FreeDyG: Frequency Enhanced Continuous-Time Dynamic Graph Model for Link Prediction
Probabilistically Rewired Message-Passing Neural Networks
The Discovery of Binding Modes Requires Rethinking Docking Generalization
VDT: General-purpose Video Diffusion Transformers via Mask Modeling
Prompt Gradient Projection for Continual Learning
A Flexible Generative Model for Heterogeneous Tabular EHR with Missing Modality
QA-LoRA: Quantization-Aware Low-Rank Adaptation of Large Language Models
Quantifying the Plausibility of Context Reliance in Neural Machine Translation
Leveraging augmented-Lagrangian techniques for differentiating over infeasible quadratic programs in machine learning
Plugin estimators for selective classification with out-of-distribution detection
Neural Ordinary Differential Equations for Modeling Epidemic Spreading
The Hidden Language of Diffusion Models
MBR and QE Finetuning: Training-time Distillation of the Best and Most Expensive Decoding Methods
GAFormer: Enhancing Timeseries Transformers Through Group-Aware Embeddings
DistillSpec: Improving Speculative Decoding via Knowledge Distillation
GenCorres: Consistent Shape Matching via Coupled Implicit-Explicit Shape Generative Models
Think before you speak: Training Language Models With Pause Tokens
Robustness of AI-Image Detectors: Fundamental Limits and Practical Attacks
Annealing Self-Distillation Rectification Improves Adversarial Training
Enhancing Neural Subset Selection: Integrating Background Information into Set Representations
Language Model Cascades: Token-Level Uncertainty And Beyond
Convolution Meets LoRA: Parameter Efficient Finetuning for Segment Anything Model
Consistent Multi-Class Classification from Multiple Unlabeled Datasets
Path Choice Matters for Clear Attributions in Path Methods
VQGraph: Rethinking Graph Representation Space for Bridging GNNs and MLPs
Langevin Monte Carlo for strongly log-concave distributions: Randomized midpoint revisited
Learning From Simplicial Data Based on Random Walks and 1D Convolutions
PRES: Toward Scalable Memory-Based Dynamic Graph Neural Networks
CausalTime: Realistically Generated Time-series for Benchmarking of Causal Discovery
Ultra-sparse network advantage in deep learning via Cannistraci-Hebb brain-inspired training with hyperbolic meta-deep community-layered epitopology
Lightweight Language Model Calibration for Open-ended Question Answering with Varied Answer Lengths
How Many Pretraining Tasks Are Needed for In-Context Learning of Linear Regression?
Hybrid Distillation: Connecting Masked Autoencoders with Contrastive Learners
Foundation Model-oriented Robustness: Robust Image Model Evaluation with Pretrained Models
TAB: Temporal Accumulated Batch Normalization in Spiking Neural Networks
Neuron-Enhanced AutoEncoder Matrix Completion and Collaborative Filtering: Theory and Practice
Multi-Scale Representations by Varing Window Attention for Semantic Segmentation
Skeleton-of-Thought: Large Language Models Can Do Parallel Decoding
Interpretable Meta-Learning of Physical Systems
Treatment Effects Estimation By Uniform Transformer
Advancing the Lower Bounds: an Accelerated, Stochastic, Second-order Method with Optimal Adaptation to Inexactness
On Adversarial Training without Perturbing all Examples
AmortizedPeriod: Attention-based Amortized Inference for Periodicity Identification
LayoutNUWA: Revealing the Hidden Layout Expertise of Large Language Models
The Wasserstein Believer: Learning Belief Updates for Partially Observable Environments through Reliable Latent Space Models
Linear attention is (maybe) all you need (to understand Transformer optimization)
UniversalNER: Targeted Distillation from Large Language Models for Open Named Entity Recognition
Curriculum reinforcement learning for quantum architecture search under hardware errors
SALMON: Self-Alignment with Principle-Following Reward Models
Analytically Tractable Hidden-States Inference in Bayesian Neural Networks
Multi-Resolution Diffusion Models for Time Series Forecasting
An Efficient Membership Inference Attack for the Diffusion Model by Proximal Initialization
SILO Language Models: Isolating Legal Risk In a Nonparametric Datastore
Searching for High-Value Molecules Using Reinforcement Learning and Transformers
PixArt-$\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis
Alignment as Reward-Guided Search
Diffusion Posterior Sampling for Linear Inverse Problem Solving: A Filtering Perspective
Evaluating Large Language Models at Evaluating Instruction Following
Bridging Neural and Symbolic Representations with Transitional Dictionary Learning
Fine-Tuned Language Models Generate Stable Inorganic Materials as Text
Learning Grounded Action Abstractions from Language
Provably Efficient Iterated CVaR Reinforcement Learning with Function Approximation and Human Feedback
On the Hardness of Constrained Cooperative Multi-Agent Reinforcement Learning
Learning No-Regret Sparse Generalized Linear Models with Varying Observation(s)
A Unified Experiment Design Approach for Cyclic and Acyclic Causal Models
PROGRAM: PROtotype GRAph Model based Pseudo-Label Learning for Test-Time Adaptation
Tag2Text: Guiding Vision-Language Model via Image Tagging
LILO: Learning Interpretable Libraries by Compressing and Documenting Code
Score Regularized Policy Optimization through Diffusion Behavior
How Over-Parameterization Slows Down Gradient Descent in Matrix Sensing: The Curses of Symmetry and Initialization
Correlated Noise Provably Beats Independent Noise for Differentially Private Learning
Statistical Rejection Sampling Improves Preference Optimization
Threaten Spiking Neural Networks through Combining Rate and Temporal Information
Learning Stackable and Skippable LEGO Bricks for Efficient, Reconfigurable, and Variable-Resolution Diffusion Modeling
Pre-Training and Fine-Tuning Generative Flow Networks
LEMON: Lossless model expansion
Let Models Speak Ciphers: Multiagent Debate through Embeddings
Consistency Trajectory Models: Learning Probability Flow ODE Trajectory of Diffusion
Empirical Analysis of Model Selection for Heterogeneous Causal Effect Estimation
Error Norm Truncation: Robust Training in the Presence of Data Noise for Text Generation Models
On the Limitations of Temperature Scaling for Distributions with Overlaps
The Dark Side of the Hyperbolic Moon
Long-Term Typhoon Trajectory Prediction: A Physics-Conditioned Approach Without Reanalysis Data
On Characterizing the Trade-off in Invariant Representation Learning
A Stochastic Centering Framework for Improving Calibration in Graph Neural Networks
Numerical Accounting in the Shuffle Model of Differential Privacy
Sheared LLaMA: Accelerating Language Model Pre-training via Structured Pruning
AutoLoRa: A Parameter-Free Automated Robust Fine-Tuning Framework
Inner Classifier-Free Guidance and Its Taylor Expansion for Diffusion Models
MOFDiff: Coarse-grained Diffusion for Metal-Organic Framework Design
Beyond IID weights: sparse and low-rank deep Neural Networks are also Gaussian Processes
I-PHYRE: Interactive Physical Reasoning
Batched Low-Rank Adaptation of Foundation Models
Towards Offline Opponent Modeling with In-context Learning
sRGB Real Noise Modeling via Noise-Aware Sampling with Normalizing Flows
Beating Price of Anarchy and Gradient Descent without Regret in Potential Games
Quantifying the Sensitivity of Inverse Reinforcement Learning to Misspecification
Training Unbiased Diffusion Models From Biased Dataset
Detecting Machine-Generated Texts by Multi-Population Aware Optimization for Maximum Mean Discrepancy
Stable Neural Stochastic Differential Equations in Analyzing Irregular Time Series Data
EMO: EARTH MOVER DISTANCE OPTIMIZATION FOR AUTO-REGRESSIVE LANGUAGE MODELING
SEINE: Short-to-Long Video Diffusion Model for Generative Transition and Prediction
AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning
Be Aware of the Neighborhood Effect: Modeling Selection Bias under Interference for Recommendation
Interpreting CLIP's Image Representation via Text-Based Decomposition
InternVid: A Large-scale Video-Text Dataset for Multimodal Understanding and Generation
Plug-and-Play Posterior Sampling under Mismatched Measurement and Prior Models
Personalize Segment Anything Model with One Shot
UniTabE: A Universal Pretraining Protocol for Tabular Foundation Model in Data Science
STREAM: Spatio-TempoRal Evaluation and Analysis Metric for Video Generative Models
Can Sensitive Information Be Deleted From LLMs? Objectives for Defending Against Extraction Attacks
When Scaling Meets LLM Finetuning: The Effect of Data, Model and Finetuning Method
Understanding Certified Training with Interval Bound Propagation
TimeMixer: Decomposable Multiscale Mixing for Time Series Forecasting
Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control
Dynamic Neighborhood Construction for Structured Large Discrete Action Spaces
Learning Personalized Causally Invariant Representations for Heterogeneous Federated Clients
Beyond Imitation: Leveraging Fine-grained Quality Signals for Alignment
R&B: Region and Boundary Aware Zero-shot Grounded Text-to-image Generation
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
Learning Flexible Body Collision Dynamics with Hierarchical Contact Mesh Transformer
Do Large Language Models Know about Facts?
Generalization in diffusion models arises from geometry-adaptive harmonic representation
Accelerating Distributed Stochastic Optimization via Self-Repellent Random Walks
Learning Energy-Based Models by Cooperative Diffusion Recovery Likelihood
DP-SGD Without Clipping: The Lipschitz Neural Network Way
Improving Non-Transferable Representation Learning by Harnessing Content and Style
Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
Large Language Models as Optimizers
PB-LLM: Partially Binarized Large Language Models
Multi-resolution HuBERT: Multi-resolution Speech Self-Supervised Learning with Masked Unit Prediction
Jumanji: a Diverse Suite of Scalable Reinforcement Learning Environments in JAX
Graph-based Virtual Sensing from Sparse and Partial Multivariate Observations
Online Stabilization of Spiking Neural Networks
Boosting Graph Anomaly Detection with Adaptive Message Passing
Zero and Few-shot Semantic Parsing with Ambiguous Inputs
FedTrans: Client-Transparent Utility Estimation for Robust Federated Learning
HypeBoy: Generative Self-Supervised Representation Learning on Hypergraphs
Single Motion Diffusion
Decomposed Diffusion Sampler for Accelerating Large-Scale Inverse Problems
Learning from Aggregate responses: Instance Level versus Bag Level Loss Functions
Cameras as Rays: Sparse-view Pose Estimation via Ray Diffusion
SEA: Sparse Linear Attention with Estimated Attention Mask
QLLM: Accurate and Efficient Low-Bitwidth Quantization for Large Language Models
Alpagasus: Training a Better Alpaca Model with Fewer Data
Debiased Collaborative Filtering with Kernel-based Causal Balancing
A Versatile Causal Discovery Framework to Allow Causally-Related Hidden Variables
RAPTOR: Recursive Abstractive Processing for Tree-Organized Retrieval
Reward-Consistent Dynamics Models are Strongly Generalizable for Offline Reinforcement Learning
SparseDFF: Sparse-View Feature Distillation for One-Shot Dexterous Manipulation
Frequency-Aware Transformer for Learned Image Compression
Ensemble Distillation for Unsupervised Constituency Parsing
Novel Quadratic Constraints for Extending LipSDP beyond Slope-Restricted Activations
Consistent Video-to-Video Transfer Using Synthetic Dataset
A Good Learner can Teach Better: Teacher-Student Collaborative Knowledge Distillation
LEGO-Prover: Neural Theorem Proving with Growing Libraries
MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models
AirPhyNet: Harnessing Physics-Guided Neural Networks for Air Quality Prediction
ARM: Refining Multivariate Forecasting with Adaptive Temporal-Contextual Learning
A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
In-Context Pretraining: Language Modeling Beyond Document Boundaries
Large Language Models as Automated Aligners for benchmarking Vision-Language Models
An Agnostic View on the Cost of Overfitting in (Kernel) Ridge Regression
Fast Ensembling with Diffusion Schr\"odinger Bridge
COCO-Periph: Bridging the Gap Between Human and Machine Perception in the Periphery
DittoGym: Learning to Control Soft Shape-Shifting Robots
TASK PLANNING FOR VISUAL ROOM REARRANGEMENT UNDER PARTIAL OBSERVABILITY
Win-Win: Training High-Resolution Vision Transformers from Two Windows
Language-Interfaced Tabular Oversampling via Progressive Imputation and Self-Authentication
Massive Editing for Large Language Model via Meta Learning
GIM: Learning Generalizable Image Matcher From Internet Videos
MERT: Acoustic Music Understanding Model with Large-Scale Self-supervised Training
MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning
Training Socially Aligned Language Models on Simulated Social Interactions
3D Reconstruction with Generalizable Neural Fields using Scene Priors
PILOT: An $\mathcal{O}(1/K)$-Convergent Approach for Policy Evaluation with Nonlinear Function Approximation
ImagenHub: Standardizing the evaluation of conditional image generation models
PRIME: Prioritizing Interpretability in Failure Mode Extraction
Offline Data Enhanced On-Policy Policy Gradient with Provable Guarantees
Label-Agnostic Forgetting: A Supervision-Free Unlearning in Deep Models
Multilingual Jailbreak Challenges in Large Language Models
Rethinking the Benefits of Steerable Features in 3D Equivariant Graph Neural Networks
The Devil is in the Neurons: Interpreting and Mitigating Social Biases in Language Models
Learning Adaptive Multiresolution Transforms via Meta-Framelet-based Graph Convolutional Network
VCR-Graphormer: A Mini-batch Graph Transformer via Virtual Connections
OWL: A Large Language Model for IT Operations
On the Expressivity of Objective-Specification Formalisms in Reinforcement Learning
R-EDL: Relaxing Nonessential Settings of Evidential Deep Learning
Neur2RO: Neural Two-Stage Robust Optimization
Improving protein optimization with smoothed fitness landscapes
Structural Inference with Dynamics Encoding and Partial Correlation Coefficients
Distributionally Robust Optimization with Bias & Variance Reduced Gradients
Combining Axes Preconditioners through Kronecker Approximation for Deep Learning
Large Content And Behavior Models To Understand, Simulate, And Optimize Content And Behavior
CrossLoco: Human Motion Driven Control of Legged Robots via Guided Unsupervised Reinforcement Learning
Accelerating Data Generation for Neural Operators via Krylov Subspace Recycling
Towards Establishing Guaranteed Error for Learned Database Operations
GnnX-Bench: Unravelling the Utility of Perturbation-based GNN Explainers through In-depth Benchmarking
Adaptive Self-training Framework for Fine-grained Scene Graph Generation
Is ImageNet worth 1 video? Learning strong image encoders from 1 long unlabelled video
Diffusion Model for Dense Matching
Object-Centric Learning with Slot Mixture Module
DEEP NEURAL NETWORK INITIALIZATION WITH SPARSITY INDUCING ACTIVATIONS
Seeking Neural Nuggets: Knowledge Transfer in Large Language Models from a Parametric Perspective
Rethinking CNN’s Generalization to Backdoor Attack from Frequency Domain
Stabilizing Backpropagation Through Time to Learn Complex Physics
RAPPER: Reinforced Rationale-Prompted Paradigm for Natural Language Explanation in Visual Question Answering
AlignDiff: Aligning Diverse Human Preferences via Behavior-Customisable Diffusion Model
Energy-guided Entropic Neural Optimal Transport
A Generalist Agent
Periodicity Decoupling Framework for Long-term Series Forecasting
Object-Aware Inversion and Reassembly for Image Editing
BadEdit: Backdooring Large Language Models by Model Editing
AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors
ChatEval: Towards Better LLM-based Evaluators through Multi-Agent Debate
Unknown Domain Inconsistency Minimization for Domain Generalization
SEPT: Towards Efficient Scene Representation Learning for Motion Prediction
Maximally discriminative stimuli for functional cell type identification
FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores
Attention Satisfies: A Constraint-Satisfaction Lens on Factual Errors of Language Models
Efficient Subgraph GNNs by Learning Effective Selection Policies
ModernTCN: A Modern Pure Convolution Structure for General Time Series Analysis
Benign Oscillation of Stochastic Gradient Descent with Large Learning Rate
Learning to solve Class-Constrained Bin Packing Problems via Encoder-Decoder Model
To Grok or not to Grok: Disentangling Generalization and Memorization on Corrupted Algorithmic Datasets
Soft Mixture Denoising: Beyond the Expressive Bottleneck of Diffusion Models
On Error Propagation of Diffusion Models
Bayesian Optimization through Gaussian Cox Process Models for Spatio-temporal Data
Finetuning Text-to-Image Diffusion Models for Fairness
Identifying Policy Gradient Subspaces
Generating Pragmatic Examples to Train Neural Program Synthesizers
Hypothesis Search: Inductive Reasoning with Language Models
Compressing Latent Space via Least Volume
Debiasing Attention Mechanism in Transformer without Demographics
Statistical Perspective of Top-K Sparse Softmax Gating Mixture of Experts
FasterViT: Fast Vision Transformers with Hierarchical Attention
Democratizing Fine-grained Visual Recognition with Large Language Models
Text-to-3D with Classifier Score Distillation
TRAM: Bridging Trust Regions and Sharpness Aware Minimization
When can transformers reason with abstract symbols?
To the Cutoff... and Beyond? A Longitudinal Perspective on LLM Data Contamination
DENEVIL: TOWARDS DECIPHERING AND NAVIGATING THE ETHICAL VALUES OF LARGE LANGUAGE MODELS VIA INSTRUCTION LEARNING
Analyzing Feed-Forward Blocks in Transformers through the Lens of Attention Map
RLIF: Interactive Imitation Learning as Reinforcement Learning
Two-stage LLM Fine-tuning with Less Specialization and More Generalization
Few-Shot Detection of Machine-Generated Text using Style Representations
ODE Discovery for Longitudinal Heterogeneous Treatment Effects Inference
Boosting of Thoughts: Trial-and-Error Problem Solving with Large Language Models
Teach LLMs to Phish: Stealing Private Information from Language Models
Variance-aware Regret Bounds for Stochastic Contextual Dueling Bandits
Neural SDF Flow for 3D Reconstruction of Dynamic Scenes
ViDA: Homeostatic Visual Domain Adapter for Continual Test Time Adaptation
Provable Offline Preference-Based Reinforcement Learning
Boosting Selective Rationalization with Shortcuts Discovery
Denoising Diffusion Bridge Models
In-context Exploration-Exploitation for Reinforcement Learning
Self-supervised Pocket Pretraining via Protein Fragment-Surroundings Alignment
Unleashing the Potential of Fractional Calculus in Graph Neural Networks with FROND
ADoPD: A Large-Scale Document Page Decomposition Dataset
Subtractive Mixture Models via Squaring: Representation and Learning
Constrained Bi-Level Optimization: Proximal Lagrangian Value function Approach and Hessian-free Algorithm
Dual RL: Unification and New Methods for Reinforcement and Imitation Learning
TACTiS-2: Better, Faster, Simpler Attentional Copulas for Multivariate Time Series
Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data
Pre-training with Random Orthogonal Projection Image Modeling
ECoFLaP: Efficient Coarse-to-Fine Layer-Wise Pruning for Vision-Language Models
Patches Are All You Need?
On the Sample Complexity of Lipschitz Constant Estimation
MINDE: Mutual Information Neural Diffusion Estimation
SALMONN: Towards Generic Hearing Abilities for Large Language Models
Sample-Efficient Learning of POMDPs with Multiple Observations In Hindsight
RETSim: Resilient and Efficient Text Similarity
On the Over-Memorization During Natural, Robust and Catastrophic Overfitting
Generalization error of spectral algorithms
Locality-Aware Graph Rewiring in GNNs
NfgTransformer: Equivariant Representation Learning for Normal-form Games
Contextual Bandits with Online Neural Regression
Estimating Shape Distances on Neural Representations with Limited Samples
In-Context Learning Dynamics with Random Binary Sequences
Bridging State and History Representations: Understanding Self-Predictive RL
IceFormer: Accelerated Inference with Long-Sequence Transformers on CPUs
Scalable Language Model with Generalized Continual Learning
MaGIC: Multi-modality Guided Image Completion
Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning
Sample Relationship from Learning Dynamics Matters for Generalisation
Finite Scalar Quantization: VQ-VAE Made Simple
Neural Field Classifiers via Target Encoding and Classification Loss
MuSc: Zero-Shot Industrial Anomaly Classification and Segmentation with Mutual Scoring of the Unlabeled Images
ToolChain*: Efficient Action Space Navigation in Large Language Models with A* Search
Hybrid Directional Graph Neural Network for Molecules
Manifold Diffusion Fields
An improved analysis of per-sample and per-update clipping in federated learning
LLM-CXR: Instruction-Finetuned LLM for CXR Image Understanding and Generation
PARL: A Unified Framework for Policy Alignment in Reinforcement Learning
Finite-State Autoregressive Entropy Coding for Efficient Learned Lossless Compression
On the Reliability of Watermarks for Large Language Models
A Plug-and-Play Image Registration Network
BayesPrompt: Prompting Large-Scale Pre-Trained Language Models on Few-shot Inference via Debiased Domain Abstraction
CAS: A Probability-Based Approach for Universal Condition Alignment Score
HyperAttention: Long-context Attention in Near-Linear Time
Robotic Task Generalization via Hindsight Trajectory Sketches
Explaining Kernel Clustering via Decision Trees
Candidate Label Set Pruning: A Data-centric Perspective for Deep Partial-label Learning
Duolando: Follower GPT with Off-Policy Reinforcement Learning for Dance Accompaniment
Tree-Planner: Efficient Close-loop Task Planning with Large Language Models
Offline RL with Observation Histories: Analyzing and Improving Sample Complexity
PINNACLE: PINN Adaptive ColLocation and Experimental points selection
Towards a statistical theory of data selection under weak supervision
Learning Performance-Improving Code Edits
Window Attention is Bugged: How not to Interpolate Position Embeddings
Delta-AI: Local objectives for amortized inference in sparse graphical models
Confidence-aware Reward Optimization for Fine-tuning Text-to-Image Models
Plug-and-Play Policy Planner for Large Language Model Powered Dialogue Agents
Symphony: Symmetry-Equivariant Point-Centered Spherical Harmonics for Molecule Generation
CARD: Channel Aligned Robust Blend Transformer for Time Series Forecasting
Contrastive Difference Predictive Coding
Achieving Sample and Computational Efficient Reinforcement Learning by Action Space Reduction via Grouping
One-hot Generalized Linear Model for Switching Brain State Discovery
Hebbian Learning based Orthogonal Projection for Continual Learning of Spiking Neural Networks
PromptTTS 2: Describing and Generating Voices with Text Prompt
$\infty$-Diff: Infinite Resolution Diffusion with Subsampled Mollified States
Score Models for Offline Goal-Conditioned Reinforcement Learning
Effective Data Augmentation With Diffusion Models
Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors
Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks
Masked Autoencoders with Multi-Window Local-Global Attention Are Better Audio Learners
Confronting Reward Model Overoptimization with Constrained RLHF
RepoBench: Benchmarking Repository-Level Code Auto-Completion Systems
Graph Transformers on EHRs: Better Representation Improves Downstream Performance
Enhancing Group Fairness in Online Settings Using Oblique Decision Forests
Algorithms for Caching and MTS with reduced number of predictions
A Primal-Dual Approach to Solving Variational Inequalities with General Constraints
Guiding Instruction-based Image Editing via Multimodal Large Language Models
DAM: A Foundation Model for Forecasting
Understanding Transferable Representation Learning and Zero-shot Transfer in CLIP
Prediction without Preclusion: Recourse Verification with Reachable Sets
Controlled Text Generation via Language Model Arithmetic
Efficient local linearity regularization to overcome catastrophic overfitting
Incremental Randomized Smoothing Certification
Discovering Failure Modes of Text-guided Diffusion Models via Adversarial Search
Enhancing Human-AI Collaboration Through Logic-Guided Reasoning
Training Bayesian Neural Networks with Sparse Subspace Variational Inference
Source-Free and Image-Only Unsupervised Domain Adaptation for Category Level Object Pose Estimation
InstructCV: Instruction-Tuned Text-to-Image Diffusion Models as Vision Generalists
Influencer Backdoor Attack on Semantic Segmentation
Guiding Masked Representation Learning to Capture Spatio-Temporal Relationship of Electrocardiogram
Quantifying Interactions in Semi-supervised Multimodal Learning: Guarantees and Applications
Real-time Photorealistic Dynamic Scene Representation and Rendering with 4D Gaussian Splatting
Random Feature Amplification: Feature Learning and Generalization in Neural Networks
GoLLIE: Annotation Guidelines improve Zero-Shot Information-Extraction
Tuning LayerNorm in Attention: Towards Efficient Multi-Modal LLM Finetuning
Making Retrieval-Augmented Language Models Robust to Irrelevant Context
Manifold Preserving Guided Diffusion
Interpretable Sparse System Identification: Beyond Recent Deep Learning Techniques on Time-Series Prediction
LLMCarbon: Modeling the End-to-End Carbon Footprint of Large Language Models
Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making
Diffusion Models for Multi-Task Generative Modeling
Towards Optimal Feature-Shaping Methods for Out-of-Distribution Detection
SemiReward: A General Reward Model for Semi-supervised Learning
Merge, Then Compress: Demystify Efficient SMoE with Hints from Its Routing Policy
Multimodal Web Navigation with Instruction-Finetuned Foundation Models
Combining Spatial and Temporal Abstraction in Planning for Better Generalization
Towards Energy Efficient Spiking Neural Networks: An Unstructured Pruning Framework
Efficient Dynamics Modeling in Interactive Environments with Koopman Theory
VertiBench: Advancing Feature Distribution Diversity in Vertical Federated Learning Benchmarks
Dual Associated Encoder for Face Restoration
Generative Adversarial Policy Network for Modelling Protein Complexes
Self-Supervised Dataset Distillation for Transfer Learning
Dissecting sample hardness: Fine-grained analysis of Hardness Characterization Methods
Generating Images in Context with Multimodal Large Language Models
Large Language Models to Enhance Bayesian Optimization
Information Bottleneck Analysis of Deep Neural Networks via Lossy Compression
Rethinking Backdoor Attacks on Dataset Distillation: A Kernel Method Perspective
Multi-View Representation is What You Need for Point-Cloud Pre-Training
Training Graph Transformers via Curriculum-Enhanced Attention Distillation
Leveraging Unpaired Data for Vision-Language Generative Models via Cycle Consistency
DynaVol: Unsupervised Learning for Dynamic Scenes through Object-Centric Voxelization
Context-Aware Meta-Learning
Quantifying Language Models' Sensitivity to Spurious Features in Prompt Design or: How I learned to start worrying about prompt formatting
InterpGNN: Understand and Improve Generalization Ability of Transdutive GNNs through the Lens of Interplay between Train and Test Nodes
Leveraging Hyperbolic Embeddings for Coarse-to-Fine Robot Design
Ring-A-Bell! How Reliable are Concept Removal Methods For Diffusion Models?
(InThe)WildChat: 570K ChatGPT Interaction Logs In The Wild
Bounding Box Stability against Feature Dropout Reflects Detector Generalization across Environments
Faster Approximation of Probabilistic and Distributional Values via Least Squares
Can LLMs Keep a Secret? Testing Privacy Implications of Language Models via Contextual Integrity Theory
Optimal transport based adversarial patch to leverage large scale attack transferability
Sampling Multimodal Distributions with the Vanilla Score: Benefits of Data-Based Initialization
Transformer-VQ: Linear-Time Transformers via Vector Quantization
Urial: Aligning Untuned LLMs with Just the 'Write' Amount of In-Context Learning
CIFAR-10-Warehouse: Broad and More Realistic Testbeds in Model Generalization Analysis
FairSeg: A Large-scale Medical Image Segmentation Dataset for Fairness Learning with Fair Error-Bound Scaling
Robustifying and Boosting Training-Free Neural Architecture Search
Diverse Projection Ensembles for Distributional Reinforcement Learning
Gen-Z: Generative Zero-Shot Text Classification with Contextualized Label Descriptions
Memory-Assisted Sub-Prototype Mining for Universal Domain Adaptation
Tailoring Self-Rationalizers with Multi-Reward Distillation
Whole-song Hierarchical Generation of Symbolic Music Using Cascaded Diffusion Models
Matryoshka Diffusion Models
Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
Learning invariant representations of time-homogeneous stochastic dynamical systems
ScaleCrafter: Tuning-free Higher-Resolution Visual Generation with Diffusion Models
The Generative AI Paradox: “What It Can Create, It May Not Understand”
Augmenting transformers with recursively composed multi-grained representations
Understanding AI Cognition: A Neural Module for Inference Inspired by Human Memory Mechanisms
Enhancing Transfer Learning with Flexible Nonparametric Posterior Sampling
SliceGPT: Compress Large Language Models by Deleting Rows and Columns
CodeChain: Towards Modular Code Generation Through Chain of Self-revisions with Representative Sub-modules
Understanding the Robustness of Randomized Feature Defense Against Query-Based Adversarial Attacks
GRAPH-CONSTRAINED DIFFUSION FOR END-TO-END PATH PLANNING
Off-Policy Primal-Dual Safe Reinforcement Learning
Geometry-Aware Projective Mapping for Unbounded Neural Radiance Fields
LLaMA-Adapter: Efficient Fine-tuning of Large Language Models with Zero-initialized Attention
Mixture of Weak and Strong Experts on Graphs
LUM-ViT: Learnable Under-sampling Mask Vision Transformer for Bandwidth Limited Optical Signal Acquisition
Benchmarking Algorithms for Federated Domain Generalization
Sparse Model Soups: A Recipe for Improved Pruning via Model Averaging
AdjointDPM: Adjoint Sensitivity Method for Gradient Backpropagation of Diffusion Probabilistic Models
Guaranteed Approximation Bounds for Mixed-Precision Neural Operators
Investigating the Benefits of Projection Head for Representation Learning
Provable Reward-Agnostic Preference-Based Reinforcement Learning
Neural Processing of Tri-Plane Hybrid Neural Fields
Nemesis: Normalizing the soft-prompt vectors of vision-language models
Looped Transformers are Better at Learning Learning Algorithms
Enhancing Small Medical Learners with Privacy-preserving Contextual Prompting
Learning Mean Field Games on Sparse Graphs: A Hybrid Graphex Approach
Breaking Physical and Linguistic Borders: Multilingual Federated Prompt Tuning for Low-Resource Languages
Progressive Fourier Neural Representation for Sequential Video Compilation
Does Progress On Object Recognition Benchmarks Improve Generalization on Crowdsourced, Global Data?
Network Memory Footprint Compression Through Jointly Learnable Codebooks and Mappings
SolidGen: An Autoregressive Model for Direct B-rep Synthesis
Outlier-Robust Subsampling Techniques for Persistent Homology
Adapting and Evaluating Influence-Estimation Methods for Gradient-Boosted Decision Trees
Revisiting Plasticity in Visual Reinforcement Learning: Data, Modules and Training Stages
Neural Architecture Retrieval
Provable and Practical: Efficient Exploration in Reinforcement Learning via Langevin Monte Carlo
Bespoke Solvers for Generative Flow Models
Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods
ViLMA: A Zero-Shot Benchmark for Linguistic and Temporal Grounding in Video-Language Models
PromptAgent: Strategic Planning with Language Models Enables Expert-level Prompt Optimization
Selective Mixup Fine-Tuning for Optimizing Non-Decomposable Metrics
On the Analysis of GAN-based Image-to-Image Translation with Gaussian Noise Injection
Consistent4D: Consistent 360° Dynamic Object Generation from Monocular Video
More Context, Less Distraction: Zero-shot Visual Classification by Inferring and Conditioning on Contextual Attributes
Understanding when Dynamics-Invariant Data Augmentations Benefit Model-free Reinforcement Learning Updates
Large Language Models Are Not Robust Multiple Choice Selectors
Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction Model
NeurRev: Train Better Sparse Neural Network Practically via Neuron Revitalization
Where We Have Arrived in Proving the Emergence of Sparse Interaction Primitives in AI Models
OPTIMAL ROBUST MEMORIZATION WITH RELU NEURAL NETWORKS
LCOT: Linear Circular Optimal Transport
The Devil is in the Object Boundary: Towards Annotation-free Instance Segmentation using Foundation Models
Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding
Adaptive Instrument Design for Indirect Experiments
Bidirectional Temporal Diffusion Model for Temporally Consistent Human Animation
Tackling the Data Heterogeneity in Asynchronous Federated Learning with Cached Update Calibration
Learning 3D Particle-based Simulators from RGB-D Videos
Weatherproofing Retrieval for Localization with Generative AI and Geometric Consistency
How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
INViTE: INterpret and Control Vision Transformer with Text Explanations
Jointly Training Large Autoregressive Multimodal Models
Pose Modulated Avatars from Video
Online Continual Learning for Interactive Instruction Following Agents
Data-independent Module-aware Pruning for Hierarchical Vision Transformers
Flag Aggregator: Scalable Distributed Training under Failures and Augmented Losses using Convex Optimization
SpikePoint: An Efficient Point-based Spiking Neural Network for Event Cameras Action Recognition
Proper Laplacian Representation Learning
A Policy Gradient Method for Confounded POMDPs
Revisiting Link Prediction: a data perspective
Prometheus: Inducing Evaluation Capability in Language Models
Alt-Text with Context: Improving Accessibility for Images on Twitter
Hyper Evidential Deep Learning to Quantify Composite Classification Uncertainty
SpeechTokenizer: Unified Speech Tokenizer for Speech Language Models
KoLA: Carefully Benchmarking World Knowledge of Large Language Models
What Algorithms can Transformers Learn? A Study in Length Generalization
A Multi-Level Framework for Accelerating Training Transformer Models
RealChat-1M: A Large-Scale Real-World LLM Conversation Dataset
What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning
Early Stopping Against Label Noise Without Validation Data
Efficient Sharpness-Aware Minimization for Molecular Graph Transformer Models
Connecting Large Language Models with Evolutionary Algorithms Yields Powerful Prompt Optimizers
LLCP: Learning Latent Causal Processes for Reasoning-based Video Question Answer
Boosting the Adversarial Robustness of Graph Neural Networks: An OOD Perspective
Prediction Error-based Classification for Class-Incremental Learning
The Blessing of Randomness: SDE Beats ODE in General Diffusion-based Image Editing
Exploring the Common Appearance-Boundary Adaptation for Nighttime Optical Flow
FreeReg: Image-to-Point Cloud Registration Leveraging Pretrained Diffusion Models and Monocular Depth Estimators
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
Gradual Optimization Learning for Conformational Energy Minimization
Grounded Object-Centric Learning
Incentive-Aware Federated Learning with Training-Time Model Rewards
AutoChunk: Automated Activation Chunk for Memory-Efficient Deep Learning Inference
"What Data Benefits My Classifier?" Enhancing Model Performance and Interpretability through Influence-Based Data Selection
In-Context Learning through the Bayesian Prism
Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model
GraphChef: Decision-Tree Recipes to Explain Graph Neural Networks
The Update Equivalence Framework for Decision-Time Planning
Unbalancedness in Neural Monge Maps Improves Unpaired Domain Translation
Optimal criterion for feature learning of two-layer linear neural network in high dimensional interpolation regime
How connectivity structure shapes rich and lazy learning in neural circuits
Repeated Random Sampling for Minimizing the Time-to-Accuracy of Learning
ELoRA: Efficient Low-Rank Adaptation with Random Matrices
CAMBranch: Contrastive Learning with Augmented MILPs for Branching
ControlVideo: Training-free Controllable Text-to-video Generation
Synergistic Patch Pruning for Vision Transformer: Unifying Intra- & Inter-Layer Patch Importance
$\textbf{\textit{M}}^\textbf{\textit{3}}$: Towards Robust Multi-Modal Reasoning via Model Selection
NetInfoF Framework: Measuring and Exploiting Network Usable Information
Cascading Reinforcement Learning
Batch Calibration: Rethinking Calibration for In-Context Learning and Prompt Engineering
ODICE: Revealing the Mystery of Distribution Correction Estimation via Orthogonal-gradient Update
H-GAP: Humanoid Control with a Generalist Planner
Learning interpretable control inputs and dynamics underlying animal locomotion
Knowledge Distillation Based on Transformed Teacher Matching
SEABO: A Simple Search-Based Method for Offline Imitation Learning
L2P-MIP: Learning to Presolve for Mixed Integer Programming
Generalization of Deep ResNets in the Mean-Field Regime
DyST: Towards Dynamic Neural Scene Representations on Real-World Videos
CLIP-MUSED: CLIP-Guided Multi-Subject Visual Neural Information Semantic Decoding
Text-driven Prompt Generation for Vision-Language Models in Federated Learning
Predictive, scalable and interpretable knowledge tracing on structured domains
Intelligent Switching for Reset-Free RL
Modelling complex vector drawings with stroke-clouds
DragonDiffusion: Enabling Drag-style Manipulation on Diffusion Models
The Reversal Curse: LLMs trained on “A is B” fail to learn “B is A”
Follow-the-Perturbed-Leader for Adversarial Bandits: Heavy Tails, Robustness, and Privacy
Early Neuron Alignment in Two-layer ReLU Networks with Small Initialization
PAE: Reinforcement Learning from External Knowledge for Efficient Exploration
GraphCare: Enhancing Healthcare Predictions with Personalized Knowledge Graphs
Social Reward: Evaluating and Enhancing Generative AI through Million-User Feedback from an Online Creative Community
Weakly Supervised Virus Capsid Detection with Image-Level Annotations in Electron Microscopy Images
Hierarchical Data-efficient Representation Learning for Tertiary Structure-based RNA Design
Kill Two Birds with One Stone: Rethinking Data Augmentation for Deep Long-tailed Learning
A Study of Bayesian Neural Network Surrogates for Bayesian Optimization
OpenNerf: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
Variational Bayesian Last Layers
Proximal Policy Gradient Arborescence for Quality Diversity Reinforcement Learning
Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactuals
Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
On the Hardness of Online Nonconvex Optimization with Single Oracle Feedback
Doubly Robust Instance-Reweighted Adversarial Training
An LLM can Fool Itself: A Prompt-Based Adversarial Attack
RECOMBINER: Robust and Enhanced Compression with Bayesian Implicit Neural Representations
Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data
Provable Benefits of Multi-task RL under Non-Markovian Decision Making Processes
Idempotent Generative Network
BayesDiff: Estimating Pixel-wise Uncertainty in Diffusion via Bayesian Inference
BENO: Boundary-embedded Neural Operators for Elliptic PDEs
Kalman Filter Online Learning from non-Stationary Data
Understanding prompt engineering may not require rethinking generalization
Circumventing Concept Erasure Methods For Text-To-Image Generative Models
Raidar: geneRative AI Detection viA Rewriting
Structural Fairness-aware Active Learning for Graph Neural Networks
Small-scale proxies for large-scale Transformer training instabilities
Efficacy of Dual-Encoders for Extreme Multi-label Classification
DIFFTACTILE: A Physics-based Differentiable Tactile Simulator for Contact-rich Robotic Manipulation
On Trajectory Augmentations for Off-Policy Evaluation
Convergence of Bayesian Bilevel Optimization
Unifying Feature and Cost Aggregation with Transformers for Dense Correspondence
Stochastic Gradient Descent for Gaussian Processes Done Right
Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
Follow-Up Differential Descriptions: Language Models Resolve Ambiguities for Image Classification
Adaptive Rational Activations to Boost Deep Reinforcement Learning
Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs
Learning Polynomial Problems with $SL(2, \mathbb{R})$-Equivariance
A Differentially Private Clustering Algorithm for Well-Clustered Graphs
USB-NeRF: Unrolling Shutter Bundle Adjusted Neural Radiance Fields
Rethinking Branching on Exact Combinatorial Optimization Solver: The First Deep Symbolic Discovery Framework
What's in a Prior? Learned Proximal Networks for Inverse Problems
Continuous Field Reconstruction from Sparse Observations with Implicit Neural Networks
COLLIE: Systematic Construction of Constrained Text Generation Tasks
Demonstration-Regularized RL
A Dynamical View of the Question of Why
Motif: Intrinsic Motivation from Artificial Intelligence Feedback
Does CLIP’s generalization performance mainly stem from high train-test similarity?
Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
SWAP-NAS: Sample-Wise Activation Patterns for Ultra-fast NAS
Learning with Mixture of Prototypes for Out-of-Distribution Detection
Unbiased Watermark for Large Language Models
Implicit Neural Representations and the Algebra of Complex Wavelets
Statistically Optimal $K$-means Clustering via Nonnegative Low-rank Semidefinite Programming
Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To!
Let's Verify Step by Step
Intriguing Properties of Data Attribution on Diffusion Models
Efficient Backdoor Attacks for Deep Neural Networks in Real-world Scenarios
Fixed-Budget Differentially Private Best Arm Identification
Independent-Set Design of Experiments for Estimating Treatment and Spillover Effects under Network Interference
MVSFormer++: Revealing the Devil in Transformer's Details for Multi-View Stereo
Exploring Target Representations for Masked Autoencoders
Is Self-Repair a Silver Bullet for Code Generation?
Faithful and Efficient Explanations for Neural Networks via Neural Tangent Kernel Surrogate Models
Matcher: Segment Anything with One Shot Using All-Purpose Feature Matching
Byzantine Robust Cooperative Multi-Agent Reinforcement Learning as a Bayesian Game
Detecting Pretraining Data from Large Language Models
On the Joint Interaction of Models, Data, and Features
Get more for less: Principled Data Selection for Warming Up Fine-Tuning in LLMs
Workflow Discovery from Dialogues in the Low Data Regime
WOODS: Benchmarks for Out-of-Distribution Generalization in Time Series
Learning Over Molecular Conformer Ensembles: Datasets and Benchmarks
Understanding the robustness difference between stochastic gradient descent and adaptive gradient methods
Scalable Real-Time Recurrent Learning Using Columnar-Constructive Networks
Planting a SEED of Vision in Large Language Model
Dropout Enhanced Bilevel Training
Retrieval-Guided Reinforcement Learning for Boolean Circuit Minimization
MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning
Self-Alignment with Instruction Backtranslation
ConjNorm: Tractable Density Estimation for Out-of-Distribution Detection
MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
NEFTune: Noisy Embeddings Improve Instruction Finetuning
Mastering Memory Tasks with World Models
Lipsum-FT: Robust Fine-Tuning of Zero-Shot Models Using Random Text Guidance
Pooling Image Datasets with Multiple Covariate Shift and Imbalance
Efficient and Scalable Graph Generation through Iterative Local Expansion
BTR: Binary Token Representations for Efficient Retrieval Augmented Language Models
Identifying Representations for Intervention Extrapolation
LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks
Boosting Vanilla Lightweight Vision Transformers via Re-parameterization
Generative Learning for Solving Non-Convex Problem with Multi-Valued Input-Solution Mapping
Sophia: A Scalable Stochastic Second-order Optimizer for Language Model Pre-training
On-Policy Distillation of Language Models: Learning from Self-Generated Mistakes
DORSal: Diffusion for Object-centric Representations of Scenes $\textit{et al.}$
Mixed-Type Tabular Data Synthesis with Score-based Diffusion in Latent Space
Coordinate-Aware Modulation for Neural Fields
DREAM: Dual Structured Exploration with Mixup for Open-set Graph Domain Adaption
Data Distillation Can Be Like Vodka: Distilling More Times For Better Quality
Multiscale Positive-Unlabeled Detection of AI-Generated Texts
Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding
Variance Reduced Halpern Iteration for Finite-Sum Monotone Inclusions
Learning Planning Abstractions from Language
DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization
Beyond Linear Spherical Interpolation: Noise Correction for Image Interpolation with Diffusion Models
ImplicitSLIM and How it Improves Embedding-based Collaborative Filtering
Language Model Self-improvement by Reinforcement Learning Contemplation
Towards Optimal Regret in Adversarial Linear MDPs with Bandit Feedback
AutoDAN: Generating Stealthy Jailbreak Prompts on Aligned Large Language Models
Removing Biases from Molecular Representations via Information Maximization
Policy Rehearsing: Training Generalizable Policies for Reinforcement Learning
Provable Compositional Generalization for Object-Centric Learning
Detecting, Explaining, and Mitigating Memorization in Diffusion Models
OmniQuant: Omnidirectionally Calibrated Quantization for Large Language Models
Forward Learning of Graph Neural Networks
TOSS: High-quality Text-guided Novel View Synthesis from a Single Image
Machine Unlearning for Image-to-Image Generative Models
STARC: A General Framework For Quantifying Differences Between Reward Functions
Goodhart's Law in Reinforcement Learning
Unified Human-Scene Interaction via Prompted Chain-of-Contacts
One Forward is Enough for Neural Network Training via Likelihood Ratio Method
M3C: A Framework towards Convergent, Flexible, and Unsupervised Learning of Mixture Graph Matching and Clustering
Rotation has two sides: Evaluating Data Augmentation for Deep One-class Classification
T-MARS: Improving Visual Representations by Circumventing Text Feature Learning
BatchPrompt: Accomplish more with less
Exploring the cloud of feature interaction scores in a Rashomon set
GraphGuard: Provably Robust Graph Classification against Adversarial Attacks
A 2-Dimensional State Space Layer for Spatial Inductive Bias
DAFA: Distance-Aware Fair Adversarial Training
The Lipschitz-Variance-Margin Tradeoff for Enhanced Randomized Smoothing
Str2Str: A Score-based Framework for Zero-shot Protein Conformation Sampling
Unraveling the Enigma of Double Descent: An In-depth Analysis through the Lens of Learned Feature Space
Channel Vision Transformers: An Image Is Worth C x 16 x 16 Words
Translating Labels to Solve Annotation Mismatches Across Object Detection Datasets
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Robustifying State-space Models for Long Sequences via Approximate Diagonalization
TextField3D: Towards Enhancing Open-Vocabulary 3D Generation with Noisy Text Fields
Leveraging Previous Tasks in Optimizing Risk Measures with Gaussian Processes
Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
Dissecting Neural Network Robustness Proofs
Multisize Dataset Condensation
The Hedgehog & the Porcupine: Expressive Linear Attentions with Softmax Mimicry
Video Language Planning
Image Clustering via the Principle of Rate Reduction in the Age of Pretrained Models
Learning to Jointly Understand Visual and Tactile Signals
Probabilistic Adaptation of Black-Box Text-to-Video Models
MetaCoCo: A New Few-Shot Classification Benchmark with Spurious Correlation
Learning to Act from Actionless Videos through Dense Correspondences
Training Diffusion Models with Reinforcement Learning
Compositional Generative Inverse Design
Building Cooperative Embodied Agents Modularly with Large Language Models
Interpretable Diffusion via Information Decomposition
The Marginal Value of Momentum for Small Learning Rate SGD
On Representation Complexity of Model-based and Model-free Reinforcement Learning
True Knowledge Comes from Practice: Aligning Large Language Models with Embodied Environments via Reinforcement Learning
OMNI: Open-endedness via Models of human Notions of Interestingness
Quality-Diversity through AI Feedback
DisenBooth: Identity-Preserving Disentangled Tuning for Subject-Driven Text-to-Image Generation
Momentum Benefits Non-iid Federated Learning Simply and Provably
PTaRL: Prototype-based Tabular Representation Learning via Space Calibration
Interventional Fairness on Partially Known Causal Graphs: A Constrained Optimization Approach
The All-Seeing Project: Towards Panoptic Visual Recognition and Understanding of the Open World
Understanding Expressivity of Neural KG Reasoning from Rule Structure Learning
Privately Aligning Language Models with Reinforcement Learning
A Generative Pre-Training Framework for Spatio-Temporal Graph Transfer Learning
Multi-task Learning with 3D-Aware Regularization
Fake It Till Make It: Federated Learning with Consensus-Oriented Generation
An Extensible Framework for Open Heterogeneous Collaborative Perception
LLM Blueprint: Enabling Text-to-Image Generation with Complex and Detailed Prompts
Bongard-OpenWorld: Few-Shot Reasoning for Free-form Visual Concepts in the Real World
DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation
A Fast and Provable Algorithm for Sparse Phase Retrieval
Large Language Model Cascades with Mixture of Thought Representations for Cost-Efficient Reasoning
Dynamic Neural Response Tuning
Non-Exchangeable Conformal Risk Control
Geometrically Aligned Transfer Encoder for Inductive Transfer in Regression Tasks
DreamFlow: High-quality text-to-3D generation by Approximating Probability Flow
Robust Model Based Reinforcement Learning Using $\mathcal{L}_1$ Adaptive Control
Improved algorithm and bounds for successive projection
Diffusion Sampling with Momentum for Mitigating Divergence Artifacts
Language Model Decoding as Direct Metrics Optimization
Self-Guided Masked Autoencoders for Domain-Agnostic Self-Supervised Learning
SEAL: A Framework for Systematic Evaluation of Real-World Super-Resolution
Chameleon: Increasing Label-Only Membership Leakage with Adaptive Poisoning
DiffusionSat: A Generative Foundation Model for Satellite Imagery
Improved Active Learning via Dependent Leverage Score Sampling
Local Search GFlowNets
Less is More: One-shot Subgraph Reasoning on Large-scale Knowledge Graphs
Long-range Neural Atom Learning for Molecular Graphs
Toward Optimal Policy Population Growth in Two-Player Zero-Sum Games
Fast-ELECTRA for Efficient Pre-training
iTransformer: Inverted Transformers Are Effective for Time Series Forecasting
ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms
Towards Non-Asymptotic Convergence for Diffusion-Based Generative Models
A Cognitive Model for Learning Abstract Relational Structures from Memory-based Decision-Making Tasks
Towards Enhancing Time Series Contrastive Learning: A Dynamic Bad Pair Mining Approach
LUT-GEMM: Quantized Matrix Multiplication based on LUTs for Efficient Inference in Large-Scale Generative Language Models
MetaPhysiCa: Improving OOD Robustness in Physics-informed Machine Learning
Enhancing Instance-Level Image Classification with Set-Level Labels
Blending Imitation and Reinforcement Learning for Robust Policy Improvement
Submodular Reinforcement Learning
Eureka: Human-Level Reward Design via Coding Large Language Models
Learning Delays in Spiking Neural Networks using Dilated Convolutions with Learnable Spacings
The False Promise of Imitating Proprietary Language Models
MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning
Unraveling the Key Components of OOD Generalization via Diversification
TEMPO: Prompt-based Generative Pre-trained Transformer for Time Series Forecasting
SPADE: Semi-supervised Anomaly Detection under Distribution Mismatch
Dynamic Discounted Counterfactual Regret Minimization
Discovering Temporally-Aware Reinforcement Learning Algorithms
PeFLL: Personalized Federated Learning by Learning to Learn
V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection
Optimal Sample Complexity of Contrastive Learning
EXPLORING RAIN-/DETAIL-AWARE REPRESENTATION FOR INSTANCE-SPECIFIC IMAGE DE-RAINING
FOSI: Hybrid First and Second Order Optimization
Koopman-based generalization bound: New aspect for full-rank weights
Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation
Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-Image Generation
On the Vulnerability of Adversarially Trained Models Against Two-faced Attacks
Beyond Reverse KL: Generalizing Direct Preference Optimization with Diverse Divergence Constraints
CLEX: Continuous Length Extrapolation for Large Language Models
Beyond Vanilla Variational Autoencoders: Detecting Posterior Collapse in Conditional and Hierarchical Variational Autoencoders
Language Control Diffusion: Efficiently Scaling through Space, Time, and Tasks
Less is More: Fewer Interpretable Region via Submodular Subset Selection
CoT3DRef: Chain-of-Thoughts Data-Efficient 3D Visual Grounding
Anisotropy helps: improved statistical and computational complexity of the mean-field Langevin dynamics under structured data
An interpretable error correction method for enhancing code-to-code translation
DSPy: Compiling Declarative Language Model Calls into State-of-the-Art Pipelines
H2O-SDF: Two-phase Learning for 3D Indoor Reconstruction using Object Surface Fields
A Variational Perspective on Solving Inverse Problems with Diffusion Models
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
Beam Enumeration: Probabilistic Explainability For Sample Efficient Self-conditioned Molecular Design
AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation
Llemma: An Open Language Model for Mathematics
Tractable Probabilistic Graph Representation Learning with Graph-Induced Sum-Product Networks
Sparsistency for inverse optimal transport
Confidential-DPproof: Confidential Proof of Differentially Private Training
Quasi-Monte Carlo for 3D Sliced Wasserstein
Constrained Decoding for Cross-lingual Label Projection
Tensor Trust: Interpretable Prompt Injection Attacks from an Online Game
One-shot Empirical Privacy Estimation for Federated Learning
Towards Assessing and Benchmarking Risk-Return Tradeoff of Off-Policy Evaluation
SOHES: Self-supervised Open-world Hierarchical Entity Segmentation
Large-Vocabulary 3D Diffusion Model with Transformer
MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection
Rayleigh Quotient Graph Neural Networks for Graph-level Anomaly Detection
Neural Auto-designer for Enhanced Quantum Kernels
Learning Hierarchical Polynomials with Three-Layer Neural Networks
The HIM Solution for Legged Locomotion: Minimal Sensors, Efficient Learning, and Substantial Agility
Multi-granularity Correspondence Learning from Long-term Noisy Videos
Localizing and Editing Knowledge In Text-to-Image Generative Models
Exploring the Relationship Between Model Architecture and In-Context Learning Ability
On Double Descent in Reinforcement Learning with LSTD and Random Features
Memory-Consistent Neural Networks for Imitation Learning
Zipformer: A faster and better encoder for automatic speech recognition
Scaling for Training Time and Post-hoc Out-of-distribution Detection Enhancement
Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation
Mastering Symbolic Operations: Augmenting Language Models with Compiled Neural Networks
DeepSPF: Spherical SO(3)-Equivariant Patches for Scan-to-CAD Estimation
LEAD: Min-Max Optimization from a Physical Perspective
Backdoor Federated Learning by Poisoning Backdoor-Critical Layers
Causality-Inspired Spatial-Temporal Explanations for Dynamic Graph Neural Networks
A differentiable brain simulator bridging brain simulation and brain-inspired computing
Protein-ligand binding representation learning from fine-grained interactions
Learning to reconstruct signals from binary measurements alone
Adaptive Regret for Bandits Made Possible: Two Queries Suffice
$t^3$-Variational Autoencoder: Learning Heavy-tailed Data with Student's t and Power Divergence
Towards Cross Domain Generalization of Hamiltonian Representation via Meta Learning
General Stability Analysis for Zeroth-Order Optimization Algorithms
Mask-based modeling for Neural Radiance Fields
Domain-agnostic Latent Diffusion Models for Synthesizing High-Quality Implicit Neural Representations
Social-Transmotion: Promptable Human Trajectory Prediction
Plug-and-Play: An Efficient Post-training Pruning Method for Large Language Models
Domain constraints improve risk prediction when outcome data is missing
TEST: Text Prototype Aligned Embedding to Activate LLM's Ability for Time Series
Defending Against Transfer Attacks From Public Models
Compressing LLMs: The Truth is Rarely Pure and Never Simple
WizardCoder: Empowering Code Large Language Models with Evol-Instruct
AUGCAL: Improving Sim2Real Adaptation by Uncertainty Calibration on Augmented Synthetic Images
Vision-by-Language for Training-Free Compositional Image Retrieval
Provably Robust Conformal Prediction with Improved Efficiency
Light-MILPopt: Solving Large-scale Mixed Integer Linear Programs with Small-scale Optimizer and Small Training Dataset
Adding 3D Geometry Control to Diffusion Models
EQA-MX: Embodied Question Answering using Multimodal Expression
Composed Image Retrieval with Text Feedback via Multi-grained Uncertainty Regularization
Vision Transformers Need Registers
Stochastic Modified Equations and Dynamics of Dropout Algorithm
AUC-CL: A Batchsize-Robust Framework for Self-Supervised Contrastive Representation Learning
A Lightweight Method for Tackling Unknown Participation Statistics in Federated Averaging
Learning semilinear neural operators: A unified recursive framework for prediction and data assimilation.
Dirichlet-based Per-Sample Weighting by Transition Matrix for Noisy Label Learning
INSIDE: LLMs' Internal States Retain the Power of Hallucination Detection
Approximately Piecewise E(3) Equivariant Point Networks
InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
A Topological Perspective on Demystifying GNN-Based Link Prediction Performance
Boundary Denoising for Video Activity Localization
Adaptive Stochastic Gradient Algorithm for Black-box Multi-Objective Learning
Test-Time Training on Nearest Neighbors for Large Language Models
Can LLM-Generated Misinformation Be Detected?
Generalized Policy Iteration using Tensor Approximation for Hybrid Control
MG-TSD: Multi-Granularity Time Series Diffusion Models with Guided Learning Process
Closing the Curious Case of Neural Text Degeneration
Generative Human Motion Stylization in Latent Space
Generative Learning for Financial Time Series with Irregular and Scale-Invariant Patterns
Decoding Natural Images from EEG for Object Recognition
Error Feedback Reloaded: From Quadratic to Arithmetic Mean of Smoothness Constants
ArchLock: Locking DNN Transferability at the Architecture Level with a Zero-Cost Binary Predictor
Provable Robust Watermarking for AI-Generated Text
Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning
Time-Efficient Reinforcement Learning with Stochastic Stateful Policies
RECOMP: Improving Retrieval-Augmented LMs with Context Compression and Selective Augmentation
Holistic Evaluation of Language Models
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation
Sharpness-Aware Minimization Enhances Feature Quality via Balanced Learning
PINNsFormer: A Transformer-Based Framework For Physics-Informed Neural Networks
Simplicial Representation Learning with Neural $k$-Forms
Group Preference Optimization: Few-Shot Alignment of Large Language Models
Adversarial Imitation Learning via Boosting
UniAdapter: Unified Parameter-Efficient Transfer Learning for Cross-modal Modeling
One-shot Active Learning Based on Lewis Weight Sampling for Multiple Deep Models
DreamSmooth: Improving Model-based Reinforcement Learning via Reward Smoothing
Unveiling the Pitfalls of Knowledge Editing for Large Language Models
AuG-KD: Anchor-Based Mixup Generation for Out-of-Domain Knowledge Distillation
Universal Jailbreak Backdoors from Poisoned Human Feedback
Federated Orthogonal Training: Mitigating Global Catastrophic Forgetting in Continual Federated Learning
Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy
BESA: Pruning Large Language Models with Blockwise Parameter-Efficient Sparsity Allocation
GTMGC: Using Graph Transformer to Predict Molecule’s Ground-State Conformation
Domain-Agnostic Molecular Generation with Self-feedback
Multimarginal Generative Modeling with Stochastic Interpolants
A Simple Romance Between Multi-Exit Vision Transformer and Token Reduction
ZeroFlow: Scalable Scene Flow via Distillation
MVDream: Multi-view Diffusion for 3D Generation
Neural-Symbolic Recursive Machine for Systematic Generalization
DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity
Attacking Perceptual Similarity Metrics
Achieving the Pareto Frontier of Regret Minimization and Best Arm Identification in Multi-Armed Bandits
FedImpro: Measuring and Improving Client Update in Federated Learning
A Framework and Benchmark for Deep Batch Active Learning for Regression
DyVal: Graph-informed Dynamic Evaluation of Large Language Models
Learning Large DAGs is Harder than you Think: Many Losses are Minimal for the Wrong DAG
Q-Bench: A Benchmark for General-Purpose Foundation Models on Low-level Vision
Piecewise Linear Parametrization of Policies: Towards Interpretable Deep Reinforcement Learning
LipSim: A Provably Robust Perceptual Similarity Metric
Asymptotically Free Sketched Ridge Ensembles: Risks, Cross-Validation, and Tuning
Neural Contractive Dynamical Systems
Defining Expertise: Applications to Treatment Effect Estimation
Unsupervised Fact Verification by Language Model Distillation
Theoretical Analysis of Robust Overfitting for Wide DNNs: An NTK Approach
Directly Fine-Tuning Diffusion Models on Differentiable Rewards
Zero-Shot Continuous Prompt Transfer: Generalizing Task Semantics Across Language Models
Matrix Manifold Neural Networks++
Jointly-Learned Exit and Inference for a Dynamic Neural Network
Polynomial Width is Sufficient for Set Representation with High-dimensional Features
CrIBo: Self-Supervised Learning via Cross-Image Object-Level Bootstrapping
Space Group Constrained Crystal Generation
Fusion is Not Enough: Single Modal Attack on Fusion Models for 3D Object Detection
COPlanner: Plan to Roll Out Conservatively but to Explore Optimistically for Model-Based RL
PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
C-TPT: Calibrated Test-Time Prompt Tuning for Vision-Language Models via Text Feature Dispersion
SOInter: A Novel Deep Energy-Based Interpretation Method for Explaining Structured Output Models
Direct Inversion: Boosting Diffusion-based Editing with 3 Lines of Code
Lifting Architectural Constraints of Injective Flows
T-Rep: Representation Learning for Time Series using Time-Embeddings
Neural Rate Control for Learned Video Compression
Customizable Combination of Parameter-Efficient Modules for Multi-Task Learning
Selective Visual Representations Improve Convergence and Generalization for Embodied AI
Image Clustering Conditioned on Text Criteria
Neurosymbolic Grounding for Compositional Generalization
Empirical Likelihood for Fair Classification
ASMR: Activation-Sharing Multi-Resolution Coordinate Networks for Efficient Inference
Effective Structural Encodings via Local Curvature Profiles
On the Humanity of Conversational AI: Evaluating the Psychological Portrayal of LLMs
Simple Hierarchical Planning with Diffusion
Hiding in Plain Sight: Disguising Data Stealing Attacks in Federated Learning
Weakly-supervised Audio Separation via Bi-modal Semantic Similarity
Learning from Sparse Offline Datasets via Conservative Density Estimation
Learning to Compose: Improving Object Centric Learning by Injecting Compositionality
MCM: Masked Cell Modeling for Anomaly Detection in Tabular Data
Demystifying CLIP Data
Implicit Neural Representation Inference for Low-Dimensional Bayesian Deep Learning
FairVLM: Mitigating Bias In Pre-Trained Vision-Language Models
Principled Architecture-aware Scaling of Hyperparameters
Efficient Network Embedding in the Exponentially Large Quantum Hilbert Space: A High-Dimensional Perspective on Embedding
SGD Finds then Tunes Features in Two-Layer Neural Networks with near-Optimal Sample Complexity: A Case Study in the XOR problem
The Optimal Constant Solution: Predictable Extrapolation in Deep Neural Networks
IDEAL: Influence-Driven Selective Annotations Empower In-Context Learners in Large Language Models
Chain-of-Experts: When LLMs Meet Complex Operations Research Problems
Sum-Product-Set Networks: Deep Tractable Models for Tree-Structured Graphs
Some Intriguing Aspects about Lipschitz Continuity of Neural Networks
PoMe: Fleet Learning via Policy Merging
Prompt Risk Control: A Rigorous Framework for Responsible Deployment of Large Language Models
Learning Hierarchical Image Segmentation For Recognition and By Recognition
Vanishing Gradients in Reinforcement Finetuning of Language Models
Talk like a Graph: Encoding Graphs for Large Language Models
Principled Federated Domain Adaptation: Gradient Projection and Auto-Weighting
Leveraging Uncertainty Estimates To Improve Classifier Performance
Graphical Multioutput Gaussian Process with Attention
Sample-Efficient Quality-Diversity by Cooperative Coevolution
LongLoRA: Efficient Fine-tuning of Long-Context Large Language Models
STanHop: Sparse Tandem Hopfield Model for Memory-Enhanced Time Series Prediction
On the Stability of Iterative Retraining of Generative Models on their own Data
Designing Skill-Compatible AI: Methodologies and Frameworks in Chess
Multimodal Patient Representation Learning with Missing Modalities and Labels
CompA: Addressing the Gap in Compositional Reasoning in Audio-Language Models
Skill-Mix: a Flexible and Expandable Family of Evaluations for AI Models
Mitigating Severe Robustness Degradation on Graphs
Class Incremental Learning via Likelihood Ratio Based Task Prediction
IMPUS: Image Morphing with Perceptually-Uniform Sampling Using Diffusion Models
Conditional Information Bottleneck Approach for Time Series Imputation
Poisoned Forgery Face: Towards Backdoor Attacks on Face Forgery Detection
A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis
VersVideo: Leveraging Enhanced Temporal Diffusion Models for Versatile Video Generation
Towards Cheaper Inference in Deep Networks with Lower Bit-Width Accumulators
Leave-one-out Distinguishability in Machine Learning
LDReg: Local Dimensionality Regularized Self-Supervised Learning
HiGen: Hierarchical Graph Generative Networks
Whittle Index with Multiple Actions and State Constraint for Inventory Management
Bootstrapping Variational Information Pursuit with Foundation Models for Interpretable Image Classification
Universal Backdoor Attacks
CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects
On the Learnability of Watermarks for Language Models
Time Fairness in Online Knapsack Problems
CLaM-TTS: Improving Neural Codec Language Model for Zero-Shot Text-to-Speech
Entropy is not Enough for Test-time Adaptation: From the Perspective of Disentangled Factors
Depthwise Hyperparameter Transfer in Residual Networks: Dynamics and Scaling Limit
Improving the Convergence of Dynamic NeRFs via Optimal Transport
FedHyper: A Universal and Robust Learning Rate Scheduler for Federated Learning with Hypergradient Descent
Generative Pre-training for Speech with Flow Matching
METRA: Scalable Unsupervised RL with Metric-Aware Abstraction
Risk Bounds of Accelerated SGD for Overparameterized Linear Regression
Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning
CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing
Large Multilingual Models Pivot Zero-Shot Multimodal Learning across Languages
Role of Locality and Weight Sharing in Image-Based Tasks: A Sample Complexity Separation between CNNs, LCNs, and FCNs
Accelerating Sinkhorn algorithm with sparse Newton iterations
Improving Convergence and Generalization Using Parameter Symmetries
Continuous Invariance Learning
Understanding Augmentation-based Self-Supervised Representation Learning via RKHS Approximation and Regression
P2Seg: Pointly-supervised Segmentation via Mutual Distillation
Out-Of-Domain Unlabeled Data Improves Generalization
Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
CCIL: Continuity-Based Data Augmentation for Corrective Imitation Learning
Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing
Deep Temporal Graph Clustering
AttEXplore: Attribution for Explanation with model parameters eXploration
SineNet: Learning Temporal Dynamics in Time-Dependent Partial Differential Equations
AutoCast++: Enhancing World Event Prediction with Zero-shot Ranking-based Context Retrieval
What Matters to You? Towards Visual Representation Alignment for Robot Learning
A Lie Group Approach to Riemannian Batch Normalization
PAC-FNO: Parallel-Structured All-Component Fourier Neural Operators for Recognizing Low-Quality Images
Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph
Model Merging by Uncertainty-Based Gradient Matching
VBH-GNN: Variational Bayesian Heterogeneous Graph Neural Networks for Cross-subject Emotion Recognition
Backdoor Contrastive Learning via Bi-level Trigger Optimization
Efficient Episodic Memory Utilization of Cooperative Multi-Agent Reinforcement Learning
Flow to Better: Offline Preference-based Reinforcement Learning via Preferred Trajectory Generation
Transformer-Modulated Diffusion Models for Probabilistic Multivariate Time Series Forecasting
LaneSegNet: Map Learning with Lane Segment Perception for Autonomous Driving
Imitation Learning from Observation with Automatic Discount Scheduling
Ins-DetCLIP: Aligning Detection Model to Follow Human-Language Instruction
Adversarial Attacks on Fairness of Graph Neural Networks
Querying Easily Flip-flopped Samples for Deep Active Learning
ResFields: Residual Neural Fields for Spatiotemporal Signals
The Effectiveness of Random Forgetting for Robust Generalization
Towards Principled Representation Learning from Videos for Reinforcement Learning
The Truth Is In There: Improving Reasoning with Layer-Selective Rank Reduction
Fast Equilibrium of SGD in Generic Situations
ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving
Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature
PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
Illusory Attacks: Detectability Matters in Adversarial Attacks on Sequential Decision-Makers
Sparse Autoencoders Find Highly Interpretable Features in Language Models
Graph Generation with $K^2$-trees
Learning with Language-Guided State Abstractions
LOQA: Learning with Opponent Q-Learning Awareness
CLIP the Bias: How Useful is Balancing Data in Multimodal Learning?
Let's do the time-warp-attend: Learning topological invariants of dynamical systems
Experimental Design for Multi-Channel Imaging via Task-Driven Feature Selection
Memorization Capacity of Multi-Head Attention in Transformers
DiffAR: Denoising Diffusion Autoregressive Model for Raw Speech Waveform Generation
Learning Multi-Faceted Prototypical User Interests
Analyzing and Improving OT-based Adversarial Networks
Functional Interpolation for Relative Positions improves Long Context Transformers
MMD Graph Kernel: Effective Metric Learning for Graphs via Maximum Mean Discrepancy
A unique M-pattern for micro-expreesion spotting in long videos
Increasing Model Capacity for Free: A Simple Strategy for Parameter Efficient Fine-tuning
Object-Centric Semantic Vector Quantization
Reclaiming the Source of Programmatic Policies: Programmatic versus Latent Spaces
Topic Modeling as Multi-Objective Contrastive Optimization
Logical Languages Accepted by Transformer Encoders with Hard Attention
Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
Oracle Efficient Algorithms for Groupwise Regret
Long-tailed Diffusion Models with Oriented Calibration
Variational Inference for SDEs Driven by Fractional Noise
Towards Imitation Learning to Branch for MIP: A Hybrid Reinforcement Learning based Sample Augmentation Approach
Uncertainty-aware Constraint Inference in Inverse Constrained Reinforcement Learning
BaDExpert: Extracting Backdoor Functionality for Accurate Backdoor Input Detection
Private Zeroth-Order Nonsmooth Nonconvex Optimization
MOTOR: A Time-To-Event Foundation Model For Structured Medical Records
Mitigating Hallucination in Large Multi-Modal Models via Robust Instruction Tuning
SocioDojo: Building Lifelong Analytical Agents with Real-world Text and Time Series
On the Role of General Function Approximation in Offline Reinforcement Learning
Fantastic Generalization Measures are Nowhere to be Found
A Mutual Information Perspective on Federated Contrastive Learning
Branch-GAN: Improving Text Generation with (not so) Large Language Models
Rethinking Channel Dimensions to Isolate Outliers for Low-bit Weight Quantization of Large Language Models
Energy-conserving equivariant GNN for elasticity of lattice architected metamaterials
Generative Adversarial Inverse Multiagent Learning
ReMasker: Imputing Tabular Data with Masked Autoencoding
At Which Training Stage Does Code Data Help LLMs Reasoning?
MathVista: Evaluating Mathematical Reasoning of Foundation Models in Visual Contexts
Thin-Shell Object Manipulations With Differentiable Physics Simulations
Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models
Masked Distillation Advances Self-Supervised Transformer Architecture Search
Likelihood Training of Cascaded Diffusion Models via Hierarchical Volume-preserving Maps
On input-dependence and recall in convolutional language models
JoMA: Demystifying Multilayer Transformers via Joint Dynamics of MLP and Attention
Layer-wise linear mode connectivity
Transformer Fusion with Optimal Transport
3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining
A Probabilistic Framework for Modular Continual Learning
Low Rank Matrix Completion via Robust Alternating Minimization in Nearly Linear Time
Query-Dependent Prompt Evaluation and Optimization with Offline Inverse RL
Efficient Algorithms for the CCA Family: Unconstrained Objectives with Unbiased Gradients
Transport meets Variational Inference: Controlled Monte Carlo Diffusions
From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction
A Simple and Effective Pruning Approach for Large Language Models
Lemur: Integrating Large Language Models in Automated Program Verification
OpenTab: Advancing Large Language Models as Open-domain Table Reasoners
Weaker MVI Condition: Extragradient Methods with Multi-Step Exploration
Zero-Mean Regularized Spectral Contrastive Learning
Meta-Evolve: Continuous Robot Evolution for One-to-many Policy Transfer
A Stable, Fast, and Fully Automatic Learning Algorithm for Predictive Coding Networks
Measuring Vision-Language STEM Skills of Neural Models
Neuron Activation Coverage: Rethinking Out-of-distribution Detection and Generalization
CABINET: Content Relevance-based Noise Reduction for Table Question Answering
Harnessing Density Ratios for Online Reinforcement Learning
Towards Seamless Adaptation of Pre-trained Models for Visual Place Recognition
Towards Transparent Time Series Forecasting
Waxing-and-Waning: a Generic Similarity-based Framework for Efficient Self-Supervised Learning
Doubly Robust Proximal Causal Learning for Continuous Treatments
CALICO: Self-Supervised Camera-LiDAR Contrastive Pre-training for BEV Perception
Real-Fake: Effective Training Data Synthesis Through Distribution Matching
Time-LLM: Time Series Forecasting by Reprogramming Large Language Models
Tangent Transformers for Composition,Privacy and Removal
Latent Intuitive Physics: Learning to Transfer Hidden Physics from a 3D Video
DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
Continual Learning on a Diet: Learning from Sparsely Labeled Streams Under Constrained Computation
Enhanced Face Recognition using Intra-class Incoherence Constraint
Parsing neural dynamics with infinite recurrent switching linear dynamical systems
Addressing Signal Delay in Deep Reinforcement Learning
Det-CGD: Compressed Gradient Descent with Matrix Stepsizes for Non-Convex Optimization
Functional Bayesian Tucker Decomposition for Continuous-indexed Tensor Data
LipVoicer: Generating Speech from Silent Videos Guided by Lip Reading
Predictive auxiliary objectives in deep RL mimic learning in the brain
Implicit Maximum a Posteriori Filtering via Adaptive Optimization
Latent Representation and Simulation of Markov Processes via Time-Lagged Information Bottleneck
Facing the Elephant in the Room: Visual Prompt Tuning or Full finetuning?
Exploring Diffusion Time-steps for Unsupervised Representation Learning
A Simple Interpretable Transformer for Fine-Grained Image Classification and Analysis
Zero-Shot Robotic Manipulation with Pre-Trained Image-Editing Diffusion Models
Decoupling Weighing and Selecting for Integrating Multiple Graph Pre-training Tasks
Solving Challenging Math Word Problems Using GPT-4 Code Interpreter with Code-based Self-Verification
Free Lunches in Auxiliary Learning: Exploiting Auxiliary Labels with Negligibly Extra Inference Cost
Exploring Effective Stimulus Encoding via Vision System Modeling for Visual Prostheses
Improved Analysis of Sparse Linear Regression in Local Differential Privacy Model
Uncertainty Quantification via Stable Distribution Propagation
Robust NAS benchmark under adversarial training: assessment, theory, and beyond
Procedural Fairness Through Decoupling Objectionable Data Generating Components
Spurious Feature Diversification Improves Out-of-distribution Generalization
Neural Polynomial Gabor Fields for Macro Motion Analysis
DiffusionNAG: Predictor-guided Neural Architecture Generation with Diffusion Models
From Posterior Sampling to Meaningful Diversity in Image Restoration
REFACTOR: Learning to Extract Theorems from Proofs
Circuit Component Reuse Across Tasks in Transformer Language Models
Adaptive Federated Learning with Auto-Tuned Clients
PhyloGFN: Phylogenetic inference with generative flow networks
On Bias-Variance Alignment in Deep Models
Dynamics-Informed Protein Design with Structure Conditioning
Deep Reinforcement Learning Guided Improvement Heuristic for Job Shop Scheduling
Navigating the Design Space of Equivariant Diffusion-Based Generative Models for De Novo 3D Molecule Generation
Can we get the best of both Binary Neural Networks and Spiking Neural Networks for Efficient Computer Vision?
Delphic Offline Reinforcement Learning under Nonidentifiable Hidden Confounding
Sentence-level Prompts Benefit Composed Image Retrieval
$\pi$2vec: Policy Representation with Successor Features
Privacy-Preserving In-Context Learning with Differentially Private Few-Shot Generation
DeepZero: Scaling Up Zeroth-Order Optimization for Deep Model Training
How Realistic Is Your Synthetic Data? Constraining Deep Generative Models for Tabular Data
Uni-O4: Unifying Online and Offline Deep Reinforcement Learning with Multi-Step On-Policy Optimization
Enhancing One-Shot Federated Learning Through Data and Ensemble Co-Boosting
Entity-Centric Reinforcement Learning for Object Manipulation from Pixels
Expected flow networks in stochastic environments and two-player zero-sum games
BEND: Benchmarking DNA Language Models on Biologically Meaningful Tasks
Toward effective protection against diffusion-based mimicry through score distillation
Mathematical Justification of Hard Negative Mining via Isometric Approximation Theorem
Progressive3D: Progressively Local Editing for Text-to-3D Content Creation with Complex Semantic Prompts
Leveraging Optimization for Adaptive Attacks on Image Watermarks
Aligning Relational Learning with Lipschitz Fairness
Towards Characterizing Domain Counterfactuals for Invertible Latent Causal Models
RLCD: Reinforcement Learning from Contrastive Distillation for LM Alignment
MAP IT to Visualize Representations
Reward Design for Justifiable Sequential Decision-Making
Less or More From Teacher: Exploiting Trilateral Geometry For Knowledge Distillation
Learning in reverse causal strategic environments with ramifications on two sided markets
More is Better: when Infinite Overparameterization is Optimal and Overfitting is Obligatory
ALAM: Averaged Low-Precision Activation for Memory-Efficient Training of Transformer Models
Estimating Conditional Mutual Information for Dynamic Feature Selection
Decision Transformer is a Robust Contender for Offline Reinforcement Learning
CoRe-GD: A Hierarchical Framework for Scalable Graph Visualization with GNNs
Unlocking the Power of Representations in Long-term Novelty-based Exploration
Learning Energy Decompositions for Partial Inference of GFlowNets
Implicit bias of SGD in $L_2$-regularized linear DNNs: One-way jumps from high to low rank
Remote Sensing Vision-Language Foundation Models without Annotations via Ground Remote Alignment
RTFS-Net: Recurrent time-frequency modelling for efficient audio-visual speech separation
Game-Theoretic Robust Reinforcement Learning Handles Temporally-Coupled Perturbations
Consistency-guided Prompt Learning for Vision-Language Models
EasyTPP: Towards Open Benchmarking Temporal Point Processes
ACRF: Compressing Explicit Neural Radiance Fields via Attribute Compression
Decentralized Riemannian Conjugate Gradient Method on the Stiefel Manifold
Understanding the Effects of RLHF on LLM Generalisation and Diversity
From Matching to Mixing: A Graph Interpolation Approach for SAT Instance Generation
Pre-training with Synthetic Data Helps Offline Reinforcement Learning
Privacy Amplification for Matrix Mechanisms
Inherently Interpretable Time Series Classification via Multiple Instance Learning
A Linear Algebraic Framework for Counterfactual Generation
Quadratic models for understanding neural network dynamics
Masked Completion via Structured Diffusion with White-Box Transformers
SpQR: A Sparse-Quantized Representation for Near-Lossless LLM Weight Compression
Conversational Drug Editing Using Retrieval and Domain Feedback
Safe Collaborative Filtering
Adaptive Sharpness-Aware Pruning for Robust Sparse Networks
MovingParts: Motion-based 3D Part Discovery in Dynamic Radiance Field
MOFI: Learning Image Representations from Noisy Entity Annotated Images
VDC: Versatile Data Cleanser for Detecting Dirty Samples via Visual-Linguistic Inconsistency
Scaling Supervised Local Learning with Augmented Auxiliary Networks
Pathologies of Predictive Diversity in Deep Ensembles
Towards Category Unification of 3D Single Object Tracking on Point Clouds
LanguageBind: Extending Video-Language Pretraining to N-modality by Language-based Semantic Alignment
Learning Multi-Agent Communication from Graph Modeling Perspective
It's Never Too Late: Fusing Acoustic Information into Large Language Models for Automatic Speech Recognition
Pseudo-Generalized Dynamic View Synthesis from a Video
TorchRL: A data-driven decision-making library for PyTorch
MetaTool Benchmark: Deciding Whether to Use Tools and Which to Use
Demystifying Linear MDPs and Novel Dynamics Aggregation Framework
Don't Judge by the Look: A Motion Coherent Augmentation for Video Recognition
ConR: Contrastive Regularizer for Deep Imbalanced Regression
Generalized Neural Sorting Networks with Error-Free Differentiable Swap Functions
Efficient Instance-Optimal Finite-Sum Minimization
TAIL: Task-specific Adapters for Imitation Learning with Large Pretrained Models
Sufficient conditions for offline reactivation in recurrent neural networks
Tree Search-Based Policy Optimization under Stochastic Execution Delay
Learning to make adherence-aware advice
Achieving Human Parity in Content-Grounded Datasets Generation
Simplifying Transformer Blocks
A Benchmark on Robust Semi-Supervised Learning in Open Environments
What's In My Big Data?
Do Generated Data Always Help Contrastive Learning?
Complex priors and flexible inference in recurrent circuits with dendritic nonlinearities
Demystifying Local & Global Fairness Trade-offs in Federated Learning Using Partial Information Decomposition
Rethinking the symmetry-preserving circuits for constrained variational quantum algorithms
Neural Fine-Tuning Search for Few-Shot Learning
Modulate Your Spectrum in Self-Supervised Learning
Feature-aligned N-BEATS with Sinkhorn divergence
Zeroth-Order Optimization Meets Human Feedback: Provable Learning via Ranking Oracles
Overthinking the Truth: Understanding how Language Models Process False Demonstrations
Decoupling regularization from the action space
Fair and Efficient Contribution Valuation for Vertical Federated Learning
Conformal Inductive Graph Neural Networks
Generalizability of Adversarial Robustness Under Distribution Shifts
Analysis of Learning a Flow-based Generative Model from Limited Sample Complexity
When Semantic Segmentation Meets Frequency Aliasing
BatteryML:An Open-source platform for Machine Learning on Battery Degradation
Unveiling and Manipulating Prompt Influence in Large Language Models
Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning
Supervised Knowledge Makes Large Language Models Better In-context Learners
ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs
AgentBench: Evaluating LLMs as Agents
FreeNoise: Tuning-Free Longer Video Diffusion via Noise Rescheduling
NECO: NEural Collapse Based Out-of-distribution detection
NeRM: Learning Neural Representations for High-Framerate Human Motion Synthesis
Faithful Rule Extraction for Differentiable Rule Learning Models
Fourier Transporter: Bi-Equivariant Robotic Manipulation in 3D
Meaning Representations from Trajectories in Autoregressive Models
DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation
Exploring the Promise and Limits of Real-Time Recurrent Learning
FedLoGe: Joint Local and Generic Federated Learning under Long-tailed Data
Going Beyond Neural Network Feature Similarity: The Network Feature Complexity and Its Interpretation Using Category Theory
PAC Prediction Sets Under Label Shift
SWE-bench: Can Language Models Resolve Real-world Github Issues?
Generative Sliced MMD Flows with Riesz Kernels
WildFusion: Learning 3D-Aware Latent Diffusion Models in View Space
Towards Green AI in Fine-tuning Large Language Models via Adaptive Backpropagation
Learning to Relax: Setting Solver Parameters Across a Sequence of Linear System Instances
Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation
MetaGPT: Meta Programming for Multi-Agent Collaborative Framework
SaProt: Protein Language Modeling with Structure-aware Vocabulary
Learning Optimal Contracts: How to Exploit Small Action Spaces
Unmasking and Improving Data Credibility: A Study with Datasets for Training Harmless Language Models
Modeling state-dependent communication between brain regions with switching nonlinear dynamical systems
An operator preconditioning perspective on training in physics-informed machine learning
Knowledge Card: Filling LLMs' Knowledge Gaps with Plug-in Specialized Language Models
Rethinking the Uniformity Metric in Self-Supervised Learning
Uni-RLHF: Universal Platform and Benchmark Suite for Reinforcement Learning with Diverse Human Feedback
Theoretical Understanding of Learning from Adversarial Perturbations
Chain of Hindsight aligns Language Models with Feedback
Visual Data-Type Understanding does not emerge from scaling Vision-Language Models
Adversarial Training Should Be Cast as a Non-Zero-Sum Game
COLEP: Certifiably Robust Learning-Reasoning Conformal Prediction via Probabilistic Circuits
Elastic Feature Consolidation For Cold Start Exemplar-Free Incremental Learning
MogaNet: Multi-order Gated Aggregation Network
The importance of feature preprocessing for differentially private linear optimization
Dichotomy of Early and Late Phase Implicit Biases Can Provably Induce Grokking
Smooth ECE: Principled Reliability Diagrams via Kernel Smoothing
DecompOpt: Controllable and Decomposed Diffusion Models for Structure-based Molecular Optimization
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
Sparse Weight Averaging with Multiple Particles for Iterative Magnitude Pruning
Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization
Human Feedback is not Gold Standard
Domain-Inspired Sharpness Aware Minimization Under Domain Shifts
Continuous-Multiple Image Outpainting in One-Step via Positional Query and A Diffusion-based Approach
Rethinking and Extending the Probabilistic Inference Capacity of GNNs
Implicit Gaussian process representation of vector fields over arbitrary latent manifolds
Learning with a Mole: Transferable latent spatial representations for navigation without reconstruction
Differentially Private Synthetic Data via Foundation Model APIs 1: Images
Symmetric Mean-field Langevin Dynamics for Distributional Minimax Problems
Towards Poisoning Fair Representations
Sample Efficient Myopic Exploration Through Multitask Reinforcement Learning with Diverse Tasks
What does automatic differentiation compute for neural networks?
Emerging Pixel-level Semantic Knowledge in Diffusion Models
MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data
Posterior Sampling Based on Gradient Flows of the MMD with Negative Distance Kernel
Neuro-Inspired Information-Theoretic Hierarchical Perception for Multimodal Learning
Skill or Luck? Return Decomposition via Advantage Functions
SPTNet: An Efficient Alternative Framework for Generalized Category Discovery with Spatial Prompt Tuning
Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning
ZeRO++: Extremely Efficient Collective Communication for Large Model Training
DMBP: Diffusion model-based predictor for robust offline reinforcement learning against state observation perturbations
From Zero to Turbulence: Generative Modeling for 3D Flow Simulation
Retrieval-based Disentangled Representation Learning with Natural Language Supervision
Learning dynamic representations of the functional connectome in neurobiological networks
StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive Learning
Provably Efficient CVaR RL in Low-rank MDPs
Multi-modal Gaussian Process Variational Autoencoders for Neural and Behavioral Data
Mechanistically analyzing the effects of fine-tuning on procedurally defined tasks
Towards Robust Fidelity for Evaluating Explainability of Graph Neural Networks
Parametric Augmentation for Time Series Contrastive Learning
InsertNeRF: Instilling Generalizability into NeRF with HyperNet Modules
Symbol as Points: Panoptic Symbol Spotting via Point-based Representation
On the hardness of learning under symmetries
Geographic Location Encoding with Spherical Harmonics and Sinusoidal Representation Networks
SCHEMA: State CHangEs MAtter for Procedure Planning in Instructional Videos
Entropy Coding of Unordered Data Structures
Heterogeneous Personalized Federated Learning by Local-Global Updates Mixing via Convergence Rate
Manipulating dropout reveals an optimal balance of efficiency and robustness in biological and machine visual systems
LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents
Making Pre-trained Language Models Great on Tabular Prediction
Adaptive Chameleon or Stubborn Sloth: Revealing the Behavior of Large Language Models in Knowledge Conflicts
Expressivity of ReLU-Networks under Convex Relaxations
COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
Unveiling the Unseen: Identifiable Clusters in Trained Depthwise Convolutional Kernels
Meta Inverse Constrained Reinforcement Learning: Convergence Guarantee and Generalization Analysis
Transferring Learning Trajectories of Neural Networks
OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
GAIA: Zero-shot Talking Avatar Generation
FITS: Modeling Time Series with $10k$ Parameters
Multilinear Operator Networks
Bayesian Neural Controlled Differential Equations for Treatment Effect Estimation
A Neural Framework for Generalized Causal Sensitivity Analysis
Implicit regularization of deep residual networks towards neural ODEs
Bounds on Representation-Induced Confounding Bias for Treatment Effect Estimation
Causal Fairness under Unobserved Confounding: A Neural Sensitivity Framework
Rethinking Model Ensemble in Transfer-based Adversarial Attacks
Transformers vs. Message Passing GNNs: Distinguished in Uniform
Learning to Solve Bilevel Programs with Binary Tender
Mediator Interpretation and Faster Learning Algorithms for Linear Correlated Equilibria in General Sequential Games
Ghost on the Shell: An Expressive Representation of General 3D Shapes
Frozen Transformers in Language Models Are Effective Visual Encoder Layers
How Well Do Supervised Models Transfer to 3D Image Segmentation?
Efficient Planning with Latent Diffusion
AnomalyCLIP: Object-agnostic Prompt Learning for Zero-shot Anomaly Detection
Sharpness-Aware Data Poisoning Attack
FairTune: Optimizing Parameter Efficient Fine Tuning for Fairness in Medical Image Analysis
Function Vectors in Large Language Models
Denoising Diffusion Step-aware Models
Pre-training Sequence, Structure, and Surface Features for Comprehensive Protein Representation Learning
Enhancing Neural Training via a Correlated Dynamics Model
Deep Orthogonal Hypersphere Compression for Anomaly Detection
State Representation Learning Using an Unbalanced Atlas
Controlling Vision-Language Models for Universal Image Restoration
Complete and Efficient Graph Transformers for Crystal Material Property Prediction
Beyond Accuracy: Evaluating Self-Consistency of Code Large Language Models with IdentityChain
Enhancing Human Experience in Human-Agent Collaboration: A Human-Centered Modeling Approach Based on Positive Human Gain
Decoupled Marked Temporal Point Process using Neural Ordinary Differential Equations
Fast Updating of Truncated SVD for Representation Learning in Sparse Matrix
FLASK: Fine-grained Language Model Evaluation based on Alignment Skill Sets
WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions
Efficient Multi-agent Reinforcement Learning by Planning
Idempotence and Perceptual Image Compression
Optimistic Bayesian Optimization with Unknown Constraints
ReLoRA: High-Rank Training Through Low-Rank Updates
Point2SSM: Learning Morphological Variations of Anatomies from Point Clouds
End-to-End (Instance)-Image Goal Navigation through Correspondence as an Emergent Phenomenon
Invariance-based Learning of Latent Dynamics
Dynamic Layer Tying for Parameter-Efficient Transformers
Attention-based Iterative Decomposition for Tensor Product Representation
Bayesian Low-rank Adaptation for Large Language Models
Sliced Wasserstein Estimation with Control Variates
A Symmetry-Aware Exploration of Bayesian Neural Network Posteriors
Backdoor Secrets Unveiled: Identifying Backdoor Data with Optimized Scaled Prediction Consistency
Unified Language-Vision Pretraining in LLM with Dynamic Discrete Visual Tokenization
Grokking in Linear Estimators -- A Solvable Model that Groks without Understanding
Tool-Augmented Reward Modeling
Domain Randomization via Entropy Maximization
Regularized Robust MDPs and Risk-Sensitive MDPs: Equivalence, Policy Gradient, and Sample Complexity
Peering Through Preferences: Unraveling Feedback Acquisition for Aligning Large Language Models
Discovering modular solutions that generalize compositionally
Lewis's Signaling Game as beta-VAE For Natural Word Lengths and Segments
Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space
Temporal Generalization Estimation in Evolving Graphs
Efficient Video Diffusion Models via Content-Frame Motion-Latent Decomposition
Reward Model Ensembles Help Mitigate Overoptimization
SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis
Retro-fallback: retrosynthetic planning in an uncertain world
Noise-free Score Distillation
Teaching Arithmetic to Small Transformers
DP-OPT: Make Large Language Model Your Privacy-Preserving Prompt Engineer
HyperHuman: Hyper-Realistic Human Generation with Latent Structural Diffusion
On the Scalability and Memory Efficiency of Semidefinite Programs for Lipschitz Constant Estimation of Neural Networks
Initializing Models with Larger Ones
Lion Secretly Solves a Constrained Optimization: As Lyapunov Predicts
PORF: POSE RESIDUAL FIELD FOR ACCURATE NEURAL SURFACE RECONSTRUCTION
When Do Prompting and Prefix-Tuning Work? A Theory of Capabilities and Limitations
The optimality of kernel classifiers in Sobolev space
Combinatorial Bandits for Maximum Value Reward Function under Value-Index Feedback
FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing
Diffusion in Diffusion: Cyclic One-Way Diffusion for Text-Vision-Conditioned Generation
Generative Modeling of Regular and Irregular Time Series Data via Koopman VAEs
G$^2$N$^2$ : Weisfeiler and Lehman go grammatical
Learning Implicit Representation for Reconstructing Articulated Objects
SAN: Inducing Metrizability of GAN with Discriminative Normalized Linear Layer
Consistency Training with Learnable Data Augmentation for Graph Anomaly Detection with Limited Supervision
LLM-grounded Video Diffusion Models
Online GNN Evaluation Under Test-time Graph Distribution Shifts
DePT: Decomposed Prompt Tuning for Parameter-Efficient Fine-tuning
SweetDreamer: Aligning Geometric Priors in 2D diffusion for Consistent Text-to-3D
Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
Sample-Efficiency in Multi-Batch Reinforcement Learning: The Need for Dimension-Dependent Adaptivity
Teaching Large Language Models to Self-Debug
Cycle Consistency Driven Object Discovery
DIAGNOSIS: Detecting Unauthorized Data Usages in Text-to-image Diffusion Models
Instructive Decoding: Instruction-Tuned Large Language Models are Self-Refiner from Noisy Instructions
Pre-training LiDAR-based 3D Object Detectors through Colorization
A Graph is Worth 1-bit Spikes: When Graph Contrastive Learning Meets Spiking Neural Networks
CoLiDE: Concomitant Linear DAG Estimation
Sign2GPT: Leveraging Large Language Models for Gloss-Free Sign Language Translation
Magnitude Invariant Parametrizations Improve Hypernetwork Learning
$\mathcal{B}$-Coder: On Value-Based Deep Reinforcement Learning for Program Synthesis
Nougat: Neural Optical Understanding for Academic Documents
A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models
LoftQ: LoRA-Fine-Tuning-aware Quantization for Large Language Models
GAIA: a benchmark for General AI Assistants
New Insight of Variance reduce in Zero-Order Hard-Thresholding: Mitigating Gradient Error and Expansivity Contradictions
SyncDreamer: Generating Multiview-consistent Images from a Single-view Image
Ito Diffusion Approximation of Universal Ito Chains for Sampling, Optimization and Boosting
Crystalformer: Infinitely Connected Attention for Periodic Structure Encoding
Differentiable Euler Characteristic Transforms for Shape Classification
Denoising Task Routing for Diffusion Models
Neural Active Learning Beyond Bandits
A Progressive Training Framework for Spiking Neural Networks with Learnable Multi-hierarchical Model
Evaluating the Zero-shot Robustness of Instruction-tuned Language Models
Gene Regulatory Network Inference in the Presence of Dropouts: a Causal View
A Private Watermark for Large Language Models
A Sublinear Adversarial Training Algorithm
Efficient Streaming Language Models with Attention Sinks
Feature Collapse
OmniControl: Control Any Joint at Any Time for Human Motion Generation
SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation
The Expressive Power of Transformers with Chain of Thought
Generative Judge for Evaluating Alignment
CausalLM is not optimal for in-context learning
VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE
Diffeomorphic Mesh Deformation via Efficient Optimal Transport for Cortical Surface Reconstruction
Exposing Text-Image Inconsistency Using Diffusion Models
Automatic Functional Differentiation in JAX
Improved sampling via learned diffusions
Active Retrosynthetic Planning Aware of Route Quality
Multi-View Causal Representation Learning with Partial Observability
Protein Multimer Structure Prediction via PPI-guided Prompt Learning
Greedy Sequential Execution: Solving Homogeneous and Heterogeneous Cooperative Tasks with a Unified Framework
Evoke: Evoking Critical Thinking Abilities in LLMs via Reviewer-Author Prompt Editing
Spectrally Transformed Kernel Regression
Universal Humanoid Motion Representations for Physics-Based Control
PolyVoice: Language Models for Speech to Speech Translation
P$^2$OT: Progressive Partial Optimal Transport for Deep Imbalanced Clustering
Lemur: Harmonizing Natural Language and Code for Language Agents
Reinforcement Symbolic Regression Machine
Integrating Planning and Deep Reinforcement Learning via Automatic Induction of Task Substructures
Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection
Fusing Models with Complementary Expertise
FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity
Decodable and Sample Invariant Continuous Object Encoder
A path-norm toolkit for modern networks: consequences, promises and challenges
Better Neural PDE Solvers Through Data-Free Mesh Movers
Causally Aligned Curriculum Learning
InstructDET: Diversifying Referring Object Detection with Generalized Instructions
Graph Parsing Networks
Locality Sensitive Sparse Encoding for Learning World Models Online
Feature emergence via margin maximization: case studies in algebraic tasks
Negatively Correlated Ensemble Reinforcement Learning for Online Diverse Game Level Generation
Poly-View Contrastive Learning
Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning
Disentangling Time Series Representations via Contrastive based $l$-Variational Inference
Deceptive Fairness Attacks on Graphs via Meta Learning
MT-Ranker: Reference-free machine translation evaluation by inter-system ranking
Optimal Sketching for Residual Error Estimation for Matrix and Vector Norms
Contrastive Preference Learning: Learning from Human Feedback without Reinforcement Learning
Identifiable Latent Polynomial Causal Models through the Lens of Change
TiC-CLIP: Continual Training of CLIP Models
Test-time Adaption against Multi-modal Reliability Bias
Fast Hyperboloid Decision Tree Algorithms
First-order ANIL provably learns representations despite overparametrisation
Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
Mol-Instructions - A Large-Scale Biomolecular Instruction Dataset for Large Language Models
Sample-Efficient Linear Representation Learning from Non-IID Non-Isotropic Data
Spatially-Aware Transformers for Embodied Agents
FFB: A Fair Fairness Benchmark for In-Processing Group Fairness Methods
ODEFormer: Symbolic Regression of Dynamical Systems with Transformers
A Precise Characterization of SGD Stability Using Loss Surface Geometry
Separate and Diffuse: Using a Pretrained Diffusion Model for Better Source Separation
MAPE-PPI: Towards Effective and Efficient Protein-Protein Interaction Prediction via Microenvironment-Aware Protein Embedding
Query-Policy Misalignment in Preference-Based Reinforcement Learning
Spoken Question Answering and Speech Continuation Using Spectrogram-Powered LLM
A representation-learning game for classes of prediction tasks
ContextRef: Evaluating Referenceless Metrics for Image Description Generation
Language Models Represent Space and Time
Feasibility-Guided Safe Offline Reinforcement Learning
Order-Preserving GFlowNets
IRAD: Implicit Representation-driven Image Resampling against Adversarial Attacks
On the Role of Discrete Tokenization in Visual Representation Learning
Mind Your Augmentation: The Key to Decoupling Dense Self-Supervised Learning
BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs
OpenWebMath: An Open Dataset of High-Quality Mathematical Web Text
Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns
Spatio-Temporal Approximation: A Training-Free SNN Conversion for Transformers
Balancing Act: Sparse Models with Constrained Disparate Impact
ASID: Active Exploration for System Identification and Reconstruction in Robotic Manipulation
Optimal Sample Complexity for Average Reward Markov Decision Processes
Improving Intrinsic Exploration by Creating Stationary Objectives
ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
Pushing Boundaries: Mixup's Influence on Neural Collapse
Trajeglish: Learning the Language of Driving Scenarios
Mean Field Theory in Deep Metric Learning
Alleviating Exposure Bias in Diffusion Models through Sampling with Shifted Time Steps
Towards Foundation Models for Knowledge Graph Reasoning
Clifford Group Equivariant Simplicial Message Passing Networks
MuSR: Testing the Limits of Chain-of-thought with Multistep Soft Reasoning
iGraphMix: Input Graph Mixup Method for Node Classification
Gaining Wisdom from Setbacks: Aligning Large Language Models via Mistake Analysis
Stochastic Controlled Averaging for Federated Learning with Communication Compression
Retrieval-Enhanced Contrastive Vision-Text Models
MINT: Evaluating LLMs in Multi-turn Interaction with Tools and Language Feedback
Phenomenal Yet Puzzling: Testing Inductive Reasoning Capabilities of Language Models with Hypothesis Refinement
What Makes a Good Prune? Optimal Unstructured Pruning for Maximal Cosine Similarity
ETGraph: A Pioneering Dataset Bridging Ethereum and Twitter
BadChain: Backdoor Chain-of-Thought Prompting for Large Language Models
Towards Faithful XAI Evaluation via Generalization-Limited Backdoor Watermark
Chain-of-Knowledge: Grounding Large Language Models via Dynamic Knowledge Adapting over Heterogeneous Sources
Fair Classifiers that Abstain without Harm
Latent 3D Graph Diffusion
Approximating Nash Equilibria in Normal-Form Games via Stochastic Optimization
Large Language Models are Efficient Learners of Noise-Robust Speech Recognition
Learning the greatest common divisor: explaining transformer predictions
Diagnosing Transformers: Illuminating Feature Spaces for Clinical Decision-Making
Deep Generative Clustering with Multimodal Diffusion Variational Autoencoders
PlaSma: Procedural Knowledge Models for Language-based Planning and Re-Planning
Topological data analysis on noisy quantum computers
Human Motion Diffusion as a Generative Prior
Test-Time Adaptation with CLIP Reward for Zero-Shot Generalization in Vision-Language Models
Reverse Diffusion Monte Carlo
Towards Aligned Layout Generation via Diffusion Model with Aesthetic Constraints
Dynamic Sparse Training with Structured Sparsity
SF(DA)$^2$: Source-free Domain Adaptation Through the Lens of Data Augmentation
Neural Fourier Transform: A General Approach to Equivariant Representation Learning
Accelerated Sampling with Stacked Restricted Boltzmann Machines
Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions
LiDAR: Sensing Linear Probing Performance in Joint Embedding SSL Architectures
Project and Probe: Sample-Efficient Adaptation by Interpolating Orthogonal Features
FedDA: Faster Adaptive Gradient Methods for Federated Constrained Optimization
Local Composite Saddle Point Optimization
Beyond Memorization: Violating Privacy via Inference with Large Language Models
Align With Purpose: Optimize Desired Properties in CTC Models with a General Plug-and-Play Framework
On Accelerating Diffusion-Based Sampling Processes via Improved Integration Approximation
The Alignment Problem from a Deep Learning Perspective: A Position Paper
Improving Generalization of Alignment with Human Preferences through Group Invariant Learning
Global Optimality for Non-linear Constrained Restoration Problems via Invexity
Efficient Backpropagation with Variance Controlled Adaptive Sampling
Safety-Tuned LLaMAs: Lessons From Improving the Safety of Large Language Models that Follow Instructions
JointNet: Extending Text-to-Image Diffusion for Dense Distribution Modeling
Enhancing Contrastive Learning for Ordinal Regression via Ordinal Content Preserved Data Augmentation
DV-3DLane: End-to-end Multi-modal 3D Lane Detection with Dual-view Representation
Unlock Predictable Scaling from Emergent Abilities
Efficient ConvBN Blocks for Transfer Learning and Beyond
LightHGNN: Distilling Hypergraph Neural Networks into MLPs for 100x Faster Inference
Adaptive Window Pruning for Efficient Local Motion Deblurring
Bridging Vision and Language Spaces with Assignment Prediction
On Diffusion Modeling for Anomaly Detection
Strategic Preys Make Acute Predators: Enhancing Camouflaged Object Detectors by Generating Camouflaged Objects
SRL: Scaling Distributed Reinforcement Learning to Over Ten Thousand Cores
Structuring Representation Geometry with Rotationally Equivariant Contrastive Learning
Sliced Denoising: A Physics-Informed Molecular Pre-Training Method
Scaling Convex Neural Networks with Burer-Monteiro Factorization
Efficient Modulation for Vision Networks
DOS: Diverse Outlier Sampling for Out-of-Distribution Detection
The Effect of Intrinsic Dataset Properties on Generalization: Unraveling Learning Differences Between Natural and Medical Images
Parameter-Efficient Multi-Task Model Fusion with Partial Linearizeation
Time-Varying Propensity Score to Bridge the Gap between the Past and Present
Seer: Language Instructed Video Prediction with Latent Diffusion Models
Constructing Adversarial Examples for Vertical Federated Learning: Optimal Client Corruption through Multi-Armed Bandit
DRSM: De-Randomized Smoothing on Malware Classifier Providing Certified Robustness
How Does Unlabeled Data Provably Help Out-of-Distribution Detection?
An Analytical Solution to Gauss-Newton Loss for Direct Image Alignment
Language Modeling Is Compression
Bias Runs Deep: Implicit Reasoning Biases in Persona-Assigned LLMs
On the Generalization and Approximation Capacities of Neural Controlled Differential Equations
SE(3)-Stochastic Flow Matching for Protein Backbone Generation
Maximum Entropy Model Correction in Reinforcement Learning
Emu: Generative Pretraining in Multimodality
Improving equilibrium propagation without weight symmetry through Jacobian homeostasis
SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agents
Beyond task performance: evaluating and reducing the flaws of large multimodal models with in-context-learning
BrainSCUBA: Fine-Grained Natural Language Captions of Visual Cortex Selectivity
Revisiting Deep Audio-Text Retrieval Through the Lens of Transportation
Vision-Language Foundation Models as Effective Robot Imitators
Improved Efficiency Based on Learned Saccade and Continuous Scene Reconstruction From Foveated Visual Sampling
Noise Map Guidance: Inversion with Spatial Context for Real Image Editing
Enabling Efficient Equivariant Operations in the Fourier Basis via Gaunt Tensor Products
KW-Design: Pushing the Limit of Protein Deign via Knowledge Refinement
EControl: Fast Distributed Optimization with Compression and Error Control
Fantastic Gains and Where to Find Them: On the Existence and Prospect of General Knowledge Transfer between Any Pretrained Model
Federated Causal Discovery from Heterogeneous Data
EquiformerV2: Improved Equivariant Transformer for Scaling to Higher-Degree Representations
Improving Code Style for Accurate Code Generation
Class Probability Matching with Calibrated Networks for Label Shift Adaption
Open the Black Box: Step-based Policy Updates for Temporally-Correlated Episodic Reinforcement Learning
Boosting Prompting Mechanisms for Zero-Shot Speech Synthesis
Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation
OctoPack: Instruction Tuning Code Large Language Models
Expressive Losses for Verified Robustness via Convex Combinations
HAZARD Challenge: Embodied Decision Making in Dynamically Changing Environments
Mayfly: a Neural Data Structure for Graph Stream Summarization
The Consensus Game: Language Model Generation via Equilibrium Search
Self-Supervised Contrastive Forecasting
Communication-Efficient Federated Non-Linear Bandit Optimization
Monte Carlo guided Denoising Diffusion models for Bayesian linear inverse problems.
Structural Estimation of Partially Observed Linear Non-Gaussian Acyclic Model: A Practical Approach with Identifiability
Are Transformers with One Layer Self-Attention Using Low-Rank Weight Matrices Universal Approximators?
Input-gradient space particle inference for neural network ensembles
CircuitNet 2.0: An Advanced Dataset for Promoting Machine Learning Innovations in Realistic Chip Design Environment
Rethinking the Power of Graph Canonization in Graph Representation Learning with Stability
MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations
AdaMerging: Adaptive Model Merging for Multi-Task Learning
Out-of-Distribution Detection with Negative Prompts
An Image Is Worth 1000 Lies: Transferability of Adversarial Images across Prompts on Vision-Language Models
Escape Sky-high Cost: Early-stopping Self-Consistency for Multi-step Reasoning
Graph Lottery Ticket Automated
PF-LRM: Pose-Free Large Reconstruction Model for Joint Pose and Shape Prediction
Flat Minima in Linear Estimation and an Extended Gauss Markov Theorem
Pre-Training Goal-based Models for Sample-Efficient Reinforcement Learning
Sample-Efficient Multi-Agent RL: An Optimization Perspective
Information Retention via Learning Supplemental Features
Adversarial AutoMixup
LMUFormer: Low Complexity Yet Powerful Spiking Model With Legendre Memory Units
WebArena: A Realistic Web Environment for Building Autonomous Agents
Multimodal Molecular Pretraining via Modality Blending
DNABERT-2: Efficient Foundation Model and Benchmark For Multi-Species Genomes
A Unified Framework for Bayesian Optimization under Contextual Uncertainty
Graph Neural Networks for Learning Equivariant Representations of Neural Networks
Online Information Acquisition: Hiring Multiple Agents
ExeDec: Execution Decomposition for Compositional Generalization in Neural Program Synthesis
Retrieval is Accurate Generation
Magnushammer: A Transformer-Based Approach to Premise Selection
Analyzing and Mitigating Object Hallucination in Large Vision-Language Models
Reconciling Spatial and Temporal Abstractions for Goal Representation
AffineQuant: Affine Transformation Quantization for Large Language Models
Copula Conformal prediction for multi-step time series prediction
ReLU Strikes Back: Exploiting Activation Sparsity in Large Language Models
Prototypical Information Bottlenecking and Disentangling for Multimodal Cancer Survival Prediction
Recursive Generalization Transformer for Image Super-Resolution
Yet Another ICU Benchmark: A Flexible Multi-Center Framework for Clinical ML
Compose and Conquer: Diffusion-Based 3D Depth Aware Composable Image Synthesis
Differentiable Learning of Generalized Structured Matrices for Efficient Deep Neural Networks
Near-Optimal Quantum Algorithm for Minimizing the Maximal Loss
Large-scale training of foundation models for wearable biosignals
Rethinking Adversarial Policies: A Generalized Attack Formulation and Provable Defense in RL
Scalable Modular Network: A Framework for Adaptive Learning via Agreement Routing
RAIN: Your Language Models Can Align Themselves without Finetuning
Robust Adversarial Reinforcement Learning via Bounded Rationality Curricula
Robust agents learn causal world models
PBADet: A One-Stage Anchor-Free Approach for Part-Body Association
SelfCheck: Using LLMs to Zero-Shot Check Their Own Step-by-Step Reasoning
GNeRP: Gaussian-guided Neural Reconstruction of Reflective Objects with Noisy Polarization Priors
Benchmarking and Improving Generator-Validator Consistency of Language Models
Soft Contrastive Learning for Time Series
Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Models
Tractable MCMC for Private Learning with Pure and Gaussian Differential Privacy
#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models
Only Pay for What Is Uncertain: Variance-Adaptive Thompson Sampling
$\alpha$TC-VAE: On the relationship between Disentanglement and Diversity
Traveling Waves Encode The Recent Past and Enhance Sequence Learning
Lie Group Decompositions for Equivariant Neural Networks
Effective and Efficient Federated Tree Learning on Hybrid Data
Universal Guidance for Diffusion Models
Solving High Frequency and Multi-Scale PDEs with Gaussian Processes
An Investigation of Representation and Allocation Harms in Contrastive Learning
Efficient Integrators for Diffusion Generative Models
SAFLEX: Self-Adaptive Augmentation via Feature Label Extrapolation
Masks, Signs, And Learning Rate Rewinding
Guess & Sketch: Language Model Guided Transpilation
NP-GL: Extending Power of Nature from Binary Problems to Real-World Graph Learning
Counting Graph Substructures with Graph Neural Networks
Large Language Models as Tool Makers
Learning Thresholds with Latent Values and Censored Feedback
Neural Probabilistic Protein-Protein Docking via a Differentiable Energy Model
A Newborn Embodied Turing Test for Comparing Object Segmentation Across Animals and Machines
Skill Machines: Temporal Logic Skill Composition in Reinforcement Learning
Fast Imitation via Behavior Foundation Models
Grounding Language Plans in Demonstrations Through Counter-Factual Perturbations
Demystifying Embedding Spaces using Large Language Models
Towards domain-invariant Self-Supervised Learning with Batch Styles Standardization
From Graphs to Hypergraphs: Hypergraph Projection and its Remediation
Behaviour Distillation
Canonpipe: Data Debugging with Shapley Importance over Machine Learning Pipelines
Robust Training of Federated Models with Extremely Label Deficiency
Effectively Leveraging Capacity for Improved Deterministic Robustness Certification
Catastrophic Jailbreak of Open-source LLMs via Exploiting Generation
Nearly $d$-Linear Convergence Bounds for Diffusion Models via Stochastic Localization
Object centric architectures enable efficient causal representation learning
S$2$AC: Energy-Based Reinforcement Learning with Stein Soft Actor Critic
Random Sparse Lifts: Construction, Analysis and Convergence of finite sparse networks
Advancing Pose-Guided Image Synthesis with Progressive Conditional Diffusion Models
Understanding Addition in Transformers
Masked Structural Growth for 2x Faster Language Model Pre-training
Like Oil and Water: Group Robustness Methods and Poisoning Defenses Don't Mix
Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
Octavius: Mitigating Task Interference in MLLMs via MoE
TabR: Tabular Deep Learning Meets Nearest Neighbors
A Branching Decoder for Set Generation
Stylized Offline Reinforcement Learning: Extracting Diverse High-Quality Behaviors from Heterogeneous Datasets
Intriguing Properties of Generative Classifiers
Faithful Vision-Language Interpretation via Concept Bottleneck Models
Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
Conformal Prediction via Regression-as-Classification
Entropy-MCMC: Sampling from Flat Basins with Ease
CAMIL: Context-Aware Multiple Instance Learning for Cancer Detection and Subtyping in Whole Slide Images
Accurate Retraining-free Pruning for Pretrained Encoder-based Language Models
The Human-AI Substitution game: active learning from a strategic labeler
Towards Eliminating Hard Label Constraints in Gradient Inversion Attacks
MagicDrive: Street View Generation with Diverse 3D Geometry Control
Learning Interactive Real-World Simulators
Addressing Catastrophic Forgetting and Loss of Plasticity in Neural Networks
NuwaDynamics: Discovering and Updating in Causal Spatio-Temporal Modeling
Transformers can optimally learn regression mixture models
Towards Meta-Pruning via Optimal Transport
Fiber Monte Carlo
Neural Common Neighbor with Completion for Link Prediction
Adapting to Distribution Shift by Visual Domain Prompt Generation
Probabilistic Self-supervised Representation Learning via Scoring Rules Minimization
Evaluating Representation Learning on the Protein Structure Universe
Classification with Conceptual Safeguards
Language Model Inversion
Partitioning Message Passing for Graph Fraud Detection
Reasoning with Latent Diffusion in Offline Reinforcement Learning
Towards Robust Out-of-Distribution Generalization Bounds via Sharpness
Learning Conditional Invariances through Non-Commutativity
Generative Modeling with Phase Stochastic Bridge
Learning to Reject for Balanced Error and Beyond
A Benchmark for Learning to Translate a New Language from One Grammar Book
$\mathbb{D}^2$ Pruning: Message Passing for Balancing Diversity & Difficulty in Data Pruning
Compositional Preference Models for Aligning LMs
Dissecting learning and forgetting in language model finetuning
Quick-Tune: Quickly Learning Which Pretrained Model to Finetune and How
SafeDreamer: Safe Reinforcement Learning with World Models
Zero Bubble (Almost) Pipeline Parallelism
Towards Understanding Sycophancy in Language Models
The Joint Effect of Task Similarity and Overparameterization on Catastrophic Forgetting — An Analytical Model
Scaling physics-informed hard constraints with mixture-of-experts
Large Language Models as Generalizable Policies for Embodied Tasks
Adversarial Training on Purification (AToP): Advancing Both Robustness and Generalization
Differentially Private SGD Without Clipping Bias: An Error-Feedback Approach
GTA: A Geometry-Aware Attention Mechanism for Multi-View Transformers
Model Tells You What to Discard: Adaptive KV Cache Compression for LLMs
Unpaired Image-to-Image Translation via Neural Schrödinger Bridge
In-context Autoencoder for Context Compression in a Large Language Model
MoLE: Mixture of LoRA Experts
Embodied Active Defense: Leveraging Recurrent Feedback to Counter Adversarial Patches
Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs
Beyond Spatio-Temporal Representations: Evolving Fourier Transform for Temporal Graphs
On Stationary Point Convergence of PPO-Clip
How to Capture Higher-order Correlations? Generalizing Matrix Softmax Attention to Kronecker Computation
Faster Sampling from Log-Concave Densities over Polytopes via Efficient Linear Solvers
Consistency Models as a Rich and Efficient Policy Class for Reinforcement Learning
Encoding Unitig-level Assembly Graphs with Heterophilous Constraints for Metagenomic Contigs Binning
Threshold-Consistent Margin Loss for Open-World Deep Metric Learning
SYMBOL: Generating Flexible Black-Box Optimizers through Symbolic Equation Learning
Provable Memory Efficient Self-Play Algorithm for Model-free Reinforcement Learning
Vocos: Closing the gap between time-domain and Fourier-based neural vocoders for high-quality audio synthesis
Learning Multi-Agent Communication with Contrastive Learning
SAS: Structured Activation Sparsification
Universal Graph Random Features
Alice Benchmarks: Connecting Real World Object Re-Identification with the Synthetic
Can Large Language Models Infer Causation from Correlation?
LLM4QPE: Unsupervised Pretraining of Quantum Property Estimation and A Benchmark
Grokking as the transition from lazy to rich training dynamics
Are Models Biased on Text without Gender-related Language?
SuRe: Improving Open-domain Question Answering of LLMs via Summarized Retrieval
Reverse Forward Curriculum Learning for Extreme Sample and Demo Efficiency
Linearity of Relation Decoding in Transformer Language Models
Causal Inference with Conditional Front-Door Adjustment and Identifiable Variational Autoencoder
Score-based generative models break the curse of dimensionality in learning a family of sub-Gaussian distributions
BarLeRIa: An Efficient Tuning Framework for Referring Image Segmentation
AutoVP: An Automated Visual Prompting Framework and Benchmark
AutomaTikZ: Text-Guided Synthesis of Scientific Vector Graphics with TikZ
Counterfactual Density Estimation using Kernel Stein Discrepancies
Uni3D: Exploring Unified 3D Representation at Scale
Navigating Text-To-Image Customization: From LyCORIS Fine-Tuning to Model Evaluation
Bayesian Coreset Optimization for Personalized Federated Learning
Scalable Diffusion for Materials Generation
Adaptive deep spiking neural network with global-local learning via balanced excitatory and inhibitory mechanism
Toward Student-oriented Teacher Network Training for Knowledge Distillation
Privacy-Preserving In-Context Learning for Large Language Models
Synaptic Weight Distributions Depend on the Geometry of Plasticity
A Restoration Network as an Implicit Prior
On the Stability of Expressive Positional Encodings for Graph Neural Networks
Navigating Dataset Documentations in AI: A Large-Scale Analysis of Dataset Cards on HuggingFace
Elucidating the Exposure Bias in Diffusion Models
Towards 3D Molecule-Text Interpretation in Language Models
Impact of Computation in Integral Reinforcement Learning for Continuous-Time Control
Negative Label Guided OOD Detection with Pretrained Vision-Language Models
Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
Learning to design protein-protein interactions with enhanced generalization
Robust Model-Based Optimization for Challenging Fitness Landscapes
On the Fairness ROAD: Robust Optimization for Adversarial Debiasing
Teaching Language Models to Hallucinate Less with Synthetic Tasks
A Discretization Framework for Robust Contextual Stochastic Optimization
FLD: Fourier Latent Dynamics for Structured Motion Representation and Learning
ClimODE: Climate Forecasting With Physics-informed Neural ODEs
LQ-LoRA: Low-rank plus Quantized Matrix Decomposition for Efficient Language Model Finetuning
Retrieval meets Long Context Large Language Models
Un-Mixing Test-Time Normalization Statistics: Combatting Label Temporal Correlation
PolyGCL: GRAPH CONTRASTIVE LEARNING via Learnable Spectral Polynomial Filters
Adapting Large Language Models via Reading Comprehension
Inverse Approximation Theory for Nonlinear Recurrent Neural Networks
Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining
Sparse MoE with Language Guided Routing for Multilingual Machine Translation
ValUES: A Framework for Systematic Validation of Uncertainty Estimation in Semantic Segmentation
Bayes Conditional Distribution Estimation for Knowledge Distillation Based on Conditional Mutual Information
EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision
Video Decomposition Prior: Editing Videos Layer by Layer
Chain of Log-Concave Markov Chains
Image Background Serves as Good Proxy for Out-of-distribution Data
Image Translation as Diffusion Visual Programmers
A Quadratic Synchronization Rule for Distributed Deep Learning
Revisit and Outstrip Entity Alignment: A Perspective of Generative Models
Perceptual Measurements, Distances and Metrics
Protein Discovery with Discrete Walk-Jump Sampling
CADS: Unleashing the Diversity of Diffusion Models through Condition-Annealed Sampling
Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning
FROSTER: Frozen CLIP is A Strong Teacher for Open-Vocabulary Action Recognition
How do Language Models Bind Entities in Context?
A ROBUST DIFFERENTIAL NEURAL ODE OPTIMIZER
Fast and unified path gradient estimators for normalizing flows
Get What You Want, Not What You Don't: Image Content Suppression for Text-to-Image Diffusion Models
Out-of-Variable Generalisation for Discriminative Models
On the generalization capacity of neural networks during generic multimodal reasoning
A Simple and Scalable Representation for Graph Generation
Listen, Think, and Understand
FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
A Hierarchical Bayesian Model for Few-Shot Meta Learning
The Expressive Power of Low-Rank Adaptation
TokenFlow: Consistent Diffusion Features for Consistent Video Editing
Assessing Uncertainty in Similarity Scoring: Performance & Fairness in Face Recognition
CoBIT: A Contrastive Bi-directional Image-Text Generation Model
Outliers with Opposing Signals Have an Outsized Effect on Neural Network Optimization
From Sparse to Soft Mixtures of Experts
Language-Informed Visual Concept Learning
Gradual Domain Adaptation via Gradient Flow
Improving LoRA in Privacy-preserving Federated Learning
FedWon: Triumphing Multi-domain Federated Learning Without Normalization
Neural Network-Based Score Estimation in Diffusion Models: Optimization and Generalization
Modulated Phase Diffusor: Content-Oriented Feature Synthesis for Detecting Unknown Objects
Flow Matching on General Geometries
InfoCon: Concept Discovery with Generative and Discriminative Informativeness
Improved Probabilistic Image-Text Representations
Federated Q-Learning: Linear Regret Speedup with Low Communication Cost
Fully Hyperbolic Convolutional Neural Networks for Computer Vision
Turning large language models into cognitive models
SaNN: Simple Yet Powerful Simplicial-aware Neural Networks
The Unreasonable Effectiveness of Linear Prediction as a Perceptual Metric
GNNBoundary: Towards Explaining Graph Neural Networks through the Lens of Decision Boundaries
Neural Snowflakes: Universal Latent Graph Inference via Trainable Latent Geometries
TUVF: Learning Generalizable Texture UV Radiance Fields
On Differentially Private Federated Linear Contextual Bandits
Future Language Modeling from Temporal Document History
Learning model uncertainty as variance-minimizing instance weights
On the Posterior Distribution in Denoising: Application to Uncertainty Quantification
Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
Unveiling Options with Neural Network Decomposition
Towards the Fundamental Limits of Knowledge Transfer over Finite Domains
Bayesian Bi-clustering of Neural Spiking Activity with Latent Structures
How to Fine-Tune Vision Models with SGD
Adversarial Causal Bayesian Optimization
Active Test-Time Adaptation: Theoretical Analyses and An Algorithm
Quantifying and Enhancing Multi-modal Robustness with Modality Preference
Debiasing Algorithm through Model Adaptation
GRANDE: Gradient-Based Decision Tree Ensembles
Harnessing Overlap in Blockwise Transformers for Near-Infinite Context
A Statistical Analysis of Wasserstein Autoencoders for Intrinsically Low-dimensional Data
Light Schrödinger Bridge
Improved Techniques for Training Consistency Models
Modeling Boundedly Rational Agents with Latent Inference Budgets
A unified sampling framework for solver searching of Diffusion Probabilistic Models
HYPO: Hyperspherical Out-Of-Distribution Generalization
Respect the model: Fine-grained and Robust Explanation with Sharing Ratio Decomposition
Sin3DM: Learning a Diffusion Model from a Single 3D Textured Shape
On the Foundations of Shortcut Learning
Emergent Communication with Conversational Repair
THOUGHT PROPAGATION: AN ANALOGICAL APPROACH TO COMPLEX REASONING WITH LARGE LANGUAGE MODELS
SmartPlay : A Benchmark for LLMs as Intelligent Agents
Making RL with Preference-based Feedback Efficient via Randomization
Synapse: Trajectory-as-Exemplar Prompting with Memory for Computer Control
Embarrassingly Simple Dataset Distillation
TD-MPC2: Scalable, Robust World Models for Continuous Control
A General Framework for User-Guided Bayesian Optimization
Image Inpainting via Tractable Steering of Diffusion Models
Hindsight PRIORs for Reward Learning from Human Preferences
AMAGO: Scalable In-Context Reinforcement Learning for Adaptive Agents
The Curse of Diversity in Ensemble-Based Exploration
InstructScene: Instruction-Driven 3D Indoor Scene Synthesis with Semantic Graph Prior
Fast Value Tracking for Deep Reinforcement Learning
SWAP: Sparse Entropic Wasserstein Regression for Robust Network Pruning
Diving Segmentation Model into Pixels
Exploring Weight Balancing on Long-Tailed Recognition Problem
Towards Generative Abstract Reasoning: Completing Raven’s Progressive Matrix via Rule Abstraction and Selection
HIFA: High-fidelity Text-to-3D Generation with Advanced Diffusion Guidance
Adversarial Feature Map Pruning for Backdoor
Understanding Domain Generalization: A Noise Robustness Perspective
Can Transformers Capture Spatial Relations between Objects?
Compositional Conservatism: A Transductive Approach in Offline Reinforcement Learning
Symmetric Basis Convolutions for Learning Lagrangian Fluid Mechanics
A Benchmark Study on Calibration
REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes
Noisy Interpolation Learning with Shallow Univariate ReLU Networks
GeneOH Diffusion: Towards Generalizable Hand-Object Interaction Denoising via Denoising Diffusion
Does Writing with Language Models Reduce Content Diversity?
Scalable Monotonic Neural Networks
The LLM Surgeon
Causal-StoNet: Causal Inference for High-Dimensional Complex Data
Continual Momentum Filtering on Parameter Space for Online Test-time Adaptation
Learning Scalar Fields for Molecular Docking with Fast Fourier Transforms
A Unified and General Framework for Continual Learning
Coeditor: Leveraging Repo-level Diffs for Code Auto-editing
Leveraging Generative Models for Unsupervised Alignment of Neural Time Series Data
In defense of parameter sharing for model-compression
SPDER: Semiperiodic Damping-Enabled Object Representation
Amortized Network Intervention to Steer the Excitatory Point Processes
MgNO: Efficient Parameterization of Linear Operators via Multigrid
Local Graph Clustering with Noisy Labels
Belief-Enriched Pessimistic Q-Learning against Adversarial State Perturbations
A Foundation Model for Error Correction Codes
SLiMe: Segment Like Me
MiniLLM: Knowledge Distillation of Large Language Models
TEDDY: Trimming Edges with Degree-based Graph Diffusion Strategy
Towards Identifiable Unsupervised Domain Translation: A Diversified Distribution Matching Approach
Diffusion-TS: Interpretable Diffusion for General Time Series Generation
Brain decoding: toward real-time reconstruction of visual perception
Why is SAM Robust to Label Noise?
Continual Learning in the Presence of Spurious Correlations: Analyses and a Simple Baseline
GIO: Gradient Information Optimization for Training Dataset Selection
Rigid Protein-Protein Docking via Equivariant Elliptic-Paraboloid Interface Prediction
SetCSE: Set Operations using Contrastive Learning of Sentence Embeddings
An Efficient Tester-Learner for Halfspaces
Achieving Fairness in Multi-Agent MDP Using Reinforcement Learning
Hybrid Sharing for Multi-Label Image Classification
Revisiting the Last-Iterative Convergence of Stochastic Gradient Methods
On the Effect of Batch Size in Byzantine-Robust Distributed Learning
Batch normalization is sufficient for universal function approximation in CNNs
The Need for Speed: Pruning Transformers with One Recipe
Language Model Beats Diffusion - Tokenizer is key to visual generation
A Data-Driven Measure of Relative Uncertainty for Misclassification Detection
Towards Robust and Efficient Cloud-Edge Model Adaptation via Selective Entropy Distillation
Robust Classification via Regression-Based Loss Reweighting and Label Correction
DreamLLM: Synergistic Multimodal Comprehension and Creation
Efficient Score Matching with Deep Equilibrium Layers
High Fidelity Neural Audio Compression
Hard-Constrained Deep Learning for Climate Downscaling
Quantifying Network Similarity using Graph Cumulants
Rethinking Complex Queries on Knowledge Graphs with Neural Link Predictors
Denoising Diffusion via Image-Based Rendering
Be Careful What You Smooth For: Label Smoothing Can Be a Privacy Shield but Also a Catalyst for Model Inversion Attacks
Towards Few-Shot Adaptation of Foundation Models via Multitask Finetuning
Data Filtering Networks
InstaFlow: One Step is Enough for High-Quality Diffusion-Based Text-to-Image Generation
Ground-A-Video: Zero-shot Grounded Video Editing using Text-to-image Diffusion Models
Neural Neighborhood Search for Multi-agent Path Finding
Time Travel in LLMs: Tracing Data Contamination in Large Language Models
Stable Anisotropic Regularization
Enable Lanuguage Models to Implicitly Learn Self-Improvement From Data
Repelling Random Walks
On Harmonizing Implicit Subpopulations
Identifying the Risks of LM Agents with an LM-Emulated Sandbox
Droplets of Good Representations: Grokking as a First Order Phase Transition in Two Layer Networks
Retrieval-Based Reconstruction For Time-series Contrastive Learning
Curiosity-driven Red-teaming for Large Language Models
Scalable Neural Network Kernels
Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots
How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions
An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks
Compressed Context Memory for Online Language Model Interaction
DreamClean: Restoring Clean Image Using Deep Diffusion Prior
Learning Reusable Dense Rewards for Multi-Stage Tasks
Conserve-Update-Revise to Cure Generalization and Robustness Trade-off in Adversarial Training
Towards Diverse Behaviors: A Benchmark for Imitation Learning with Human Demonstrations
A Characterization Theorem for Equivariant Networks with Point-wise Activations
You Only Query Once: An Efficient Label-Only Membership Inference Attack
LEAP: Liberate Sparse-View 3D Modeling from Camera Poses
CPPO: Continual Learning for Reinforcement Learning with Human Feedback
Improved Regret Bounds for Non-Convex Online-Within-Online Meta Learning
Uncertainty-aware Graph-based Hyperspectral Image Classification
Elucidating the design space of classifier-guided diffusion generation
Contrastive Learning is Spectral Clustering on Similarity Graph
Course Correcting Koopman Representations
Critical Learning Periods Emerge Even in Deep Linear Networks
Symmetric Neural-Collapse Representations with Supervised Contrastive Loss: The Impact of ReLU and Batching
Inducing High Energy-Latency of Large Vision-Language Models with Verbose Images
Internal Cross-layer Gradients for Extending Homogeneity to Heterogeneity in Federated Learning
HoloNets: Spectral Convolutions do extend to Directed Graphs
Self-contradictory Hallucinations of Large Language Models: Evaluation, Detection and Mitigation
Privileged Sensing Scaffolds Reinforcement Learning
Meta-Learning Priors Using Unrolled Proximal Neural Networks
Understanding Catastrophic Forgetting in Language Models via Implicit Inference
Few-shot Hybrid Domain Adaptation of Image Generator
OVOR: OnePrompt with Virtual Outlier Regularization for Rehearsal-Free Class-Incremental Learning
CRAFT: Customizing LLMs by Creating and Retrieving from Specialized Toolsets
Dictionary Contrastive Forward Learning via Adaptive Label Embeddings
Forward $\chi^2$ Divergence Based Variational Importance Sampling
Efficiently Computing Similarities to Private Datasets
Beyond Weisfeiler-Lehman: A Quantitative Framework for GNN Expressiveness
Label-Noise Robust Diffusion Models
Rethinking Label Poisoning for GNNs: Pitfalls and Attacks
Memorization in Self-Supervised Learning Improves Downstream Generalization
Exploiting Causal Graph Priors with Posterior Sampling for Reinforcement Learning
High-dimensional SGD aligns with emerging outlier eigenspaces
GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher
f-FERM: A Scalable Framework for Robust Fair Empirical Risk Minimization
Conformal Risk Control
Replay across Experiments: A Natural Extension of Off-Policy RL
Perceptual Group Tokenizer: Building Perception with Iterative Grouping
Masked Audio Generative Modeling
Augmented Bayesian Policy Search
BRUSLEATTACK: QUERY-EFFICIENT SCORE-BASED SPARSE ADVERSARIAL ATTACK
Learning Unsupervised World Models for Autonomous Driving via Discrete Diffusion
BrainLM: A foundation model for brain activity recordings
A Variational Framework for Estimating Continuous Treatment Effects with Measurement Error
Generalized Schrödinger Bridge Matching
Orbit-Equivariant Graph Neural Networks
DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models
NOLA: Networks as Linear Combination of Low Rank Random Basis
GeoLLM: Extracting Geospatial Knowledge from Large Language Models
Towards Reliable and Efficient Backdoor Trigger Inversion via Decoupling Benign Features
Scaling Laws for Associative Memories
3D-Aware Hypothesis & Verification for Generalizable Relative Object Pose Estimation
CivRealm: A Learning and Reasoning Odyssey in Civilization for Decision-Making Agents
Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation
Lipschitz Singularities in Diffusion Models
Towards image compression with perfect realism at ultra-low bitrates
Hybrid LLM: Cost-Efficient and Quality-Aware Query Routing
Training-free Multi-objective Diffusion Model for 3D Molecule Generation
Near-Optimal Solutions of Constrained Learning Problems
In-Context Learning Learns Label Relationships but Is Not Conventional Learning
Proving Test Set Contamination for Black-Box Language Models
Improving Language Models with Advantage-based Offline Policy Gradients
Efficient Distributed Training with Full Communication-Computation Overlap
The mechanistic basis of data dependence and abrupt learning in an in-context classification task
Self-Supervised Speech Quality Estimation and Enhancement Using Only Clean Speech
L2MAC: Large Language Model Automatic Computer for Unbounded Code Generation
Pareto Deep Long-Tailed Recognition: A Conflict-Averse Solution
UC-NERF: Neural Radiance Field for under-calibrated multi-view cameras
GlucoBench: Curated List of Continuous Glucose Monitoring Datasets with Prediction Benchmarks
Zero-Shot Robustification of Zero-Shot Models
Symmetric Single Index Learning
Sample-efficient Learning of Infinite-horizon Average-reward MDPs with General Function Approximation
Label-free Node Classification on Graphs with Large Language Models (LLMs)
DataInf: Efficiently Estimating Data Influence in LoRA-tuned LLMs and Diffusion Models
Communication-Efficient Gradient Descent-Accent Methods for Distributed Variational Inequalities: Unified Analysis and Local Updates
Graph Metanetworks for Processing Diverse Neural Architectures
Solving Inverse Problems with Latent Diffusion Models via Hard Data Consistency
Look, Remember and Reason: Grounded Reasoning in Videos with Language Models
Horizon-free Reinforcement Learning in Adversarial Linear Mixture MDPs
Self-Supervised High Dynamic Range Imaging with Multi-Exposure Images in Dynamic Scenes
Task structure and nonlinearity jointly determine learned representational geometry
Grounding Multimodal Large Language Models to the World
Cross-Modal Contextualized Diffusion Models for Text-Guided Visual Generation and Editing
A Unified Approach for Online Continuous DR-Submodular Maximization
Tight Rates in Supervised Outlier Transfer Learning
Kernel Metric Learning for In-Sample Off-Policy Evaluation of Deterministic RL Policies
DQ-LoRe: Dual Queries with Low Rank Approximation Re-ranking for In-Context Learning
Conditional Instrumental Variable Regression with Representation Learning for Causal Inference
Image Inpainting via Iteratively Decoupled Probabilistic Modeling
Multi-Source Diffusion Models for Simultaneous Music Generation and Separation
Federated Wasserstein Distance
NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
BECLR: Batch Enhanced Contrastive Few-Shot Learning
On the Provable Advantage of Unsupervised Pretraining
LRM: Large Reconstruction Model for Single Image to 3D
Maximum Likelihood Estimation is All You Need for Well-Specified Covariate Shift
VFLAIR: A Research Library and Benchmark for Vertical Federated Learning
Enhancing High-Resolution 3D Generation through Pixel-wise Gradient Clipping
LLMs Meet VLMs: Boost Open Vocabulary Object Detection with Fine-grained Descriptors
Skip-Attention: Improving Vision Transformers by Paying Less Attention
Xformer: Hybrid X-Shaped Transformer for Image Denoising
YaRN: Efficient Context Window Extension of Large Language Models
GeoDiffusion: Text-Prompted Geometric Control for Object Detection Data Generation
Constraint-Free Structure Learning with Smooth Acyclic Orientations
SNIP: Bridging Mathematical Symbolic and Numeric Realms with Unified Pre-training
Towards Training Without Depth Limits: Batch Normalization Without Gradient Explosion
Consistent algorithms for multi-label classification with macro-at-$k$ metrics
Massively Scalable Inverse Reinforcement Learning for Route Optimization
MathCoder: Seamless Code Integration in LLMs for Enhanced Mathematical Reasoning
Inversion by Direct Iteration: An Alternative to Denoising Diffusion for Image Restoration
Improved baselines for vision-language pre-training
Nevis'22: A Stream of 100 Tasks Sampled from 30 Years of Computer Vision Research
AntGPT: Can Large Language Models Help Long-term Action Anticipation from Videos?
From Latent Graph to Latent Topology Inference: Differentiable Cell Complex Module
UNR-Explainer: Counterfactual Explanations for Unsupervised Node Representation Learning Models
Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion Priors
Understanding Hidden Context in Preference Learning: Consequences for RLHF
How I Warped Your Noise: a Temporally-Correlated Noise Prior for Diffusion Models
Feature Learning in Infinite Depth Neural Networks
Reward-Free Curricula for Training Robust World Models
Adaptive Retrieval and Scalable Indexing for k-NN Search with Cross-Encoders
DreamTime: An Improved Optimization Strategy for Diffusion-Guided 3D Generation
ReSimAD: Zero-Shot 3D Domain Transfer for Autonomous Driving with Source Reconstruction and Target Simulation
ReTaSA: A Nonparametric Functional Estimation Approach for Addressing Continuous Target Shift
RA-DIT: Retrieval-Augmented Dual Instruction Tuning
GOAt: Explaining Graph Neural Networks via Graph Output Attribution
Function-space Parameterization of Neural Networks for Sequential Learning
BroGNet: Momentum-Conserving Graph Neural Stochastic Differential Equation for Learning Brownian Dynamics
SparseFormer: Sparse Visual Recognition via Limited Latent Tokens
MEND: Meta Demonstration Distillation for Efficient and Effective In-Context Learning
Self-Supervised Heterogeneous Graph Learning: a Homophily and Heterogeneity View
On the Power of the Weisfeiler-Leman Test for Graph Motif Parameters
Evaluating Language Models Through Negotiations
Step-Back Prompting Enables Reasoning Via Abstraction in Large Language Models
A Study of Generalization in Offline Reinforcement Learning
Language Model Detectors Are Easily Optimized Against
Neural structure learning with stochastic differential equations
Pessimistic Nonlinear Least-Squares Value Iteration for Offline Reinforcement Learning
Image2Sentence based Asymmetrical Zero-shot Composed Image Retrieval
One For All: Towards Training One Graph Model For All Classification Tasks
Closing the Gap between TD Learning and Supervised Learning - A Generalisation Point of View.
Relay Diffusion: Unifying diffusion process across resolutions for image synthesis
Towards Robust Offline Reinforcement Learning under Diverse Data Corruption
Linear Log-Normal Attention with Unbiased Concentration
Simple Minimax Optimal Byzantine Robust Algorithm for Nonconvex Objectives with Uniform Gradient Heterogeneity
Scale-Adaptive Diffusion Model for Complex Sketch Synthesis
Enhancing Tail Performance in Extreme Classifiers by Label Variance Reduction
Improving Generalization in Equivariant Graph Neural Networks with Physical Inductive Biases
On the Markov Property of Neural Algorithmic Reasoning: Analyses and Methods
RobustTSF: Towards Theory and Design of Robust Time Series Forecasting with Anomalies
A Semantic Invariant Robust Watermark for Large Language Models
RetroBridge: Modeling Retrosynthesis with Markov Bridges
Mirage: Model-agnostic Graph Distillation for Graph Classification
Bandits Meet Mechanism Design to Combat Clickbait in Online Recommendation
Adversarial Adaptive Sampling: Unify PINN and Optimal Transport for the Approximation of PDEs
CLAP: Collaborative Adaptation for Checkerboard Learning
On gauge freedom, conservativity and intrinsic dimensionality estimation in diffusion models
DiLu: A Knowledge-Driven Approach to Autonomous Driving with Large Language Models
Large Language Models as Analogical Reasoners
Latent Trajectory Learning for Limited Timestamps under Distribution Shift over Time
CellPLM: Pre-training of Cell Language Model Beyond Single Cells
LogicMP: A Neuro-symbolic Approach for Encoding First-order Logic Constraints
Large Language Models Cannot Self-Correct Reasoning Yet
Effective pruning of web-scale datasets based on complexity of concept clusters
Learning to Act without Actions
On Penalty Methods for Nonconvex Bilevel Optimization and First-Order Stochastic Approximation
Beyond Worst-case Attacks: Robust RL with Adaptive Defense via Non-dominated Policies
Graphpulse: Topological representations for temporal graph property prediction
Cleanba: A Reproducible and Efficient Distributed Reinforcement Learning Platform
Revisiting Data Augmentation in Deep Reinforcement Learning
Adversarial Supervision Makes Layout-to-Image Diffusion Models Thrive
Is This the Subspace You Are Looking for? An Interpretability Illusion for Subspace Activation Patching
DATS: Difficulty-Aware Task Sampler for Meta-Learning Physics-Informed Neural Networks
Fixed Non-negative Orthogonal Classifier: Inducing Zero-mean Neural Collapse with Feature Dimension Separation
SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking
Post-hoc bias scoring is optimal for fair classification
Successor Heads: Recurring, Interpretable Attention Heads In The Wild
Parallelizing non-linear sequential models over the sequence length
Set Learning for Accurate and Calibrated Models
Bellman Optimal Step-size Straightening of Flow-Matching Models
Scaling Laws of RoPE-based Extrapolation
LabelDP-Pro: Learning with Label Differential Privacy via Projections
Robust Similarity Learning with Difference Alignment Regularization
Learning from Label Proportions: Bootstrapping Supervised Learners via Belief Propagation
Who to imitate: Imitating desired behavior from divserse multi-agent datasets
ZipIt! Merging Models from Different Tasks without Training
Improving Offline RL by Blending Heuristics
The Trickle-down Impact of Reward Inconsistency on RLHF
Hypergraph Dynamic System
Unified Generative Modeling of 3D Molecules with Bayesian Flow Networks
Steve-Eye: Equipping LLM-based Embodied Agents with Visual Perception in Open Worlds
fairret: a Framework for Differentiable Fairness Regularization Terms
Lagrangian Flow Networks for Conservation Laws
GenSim: Generating Robotic Simulation Tasks via Large Language Models
Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization
Headless Language Models: Learning without Predicting with Contrastive Weight Tying
Cross$Q$: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity
We use cookies to store which papers have been visited.
I agree
Successful Page Load
ICLR uses cookies to remember that you are logged in. By using our websites, you agree to the placement of cookies.
Our Privacy Policy »
Accept Cookies
We use cookies to store which papers have been visited.
I agree
