Skip to yearly menu bar
Skip to main content
Main Navigation
NeurIPS
Help/FAQ
Contact NeurIPS
Code of Ethics
Code of Conduct
Create Profile
Journal To Conference Track
Diversity & Inclusion
Proceedings
Future Meetings
Press
Exhibitor Information
Privacy Policy
Downloads
My Stuff
Login
Select Year: (2024)
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
Getting Started
Schedule
Tutorials
Main Conference
Invited Talks
Orals
Papers
Competitions
Datasets & Benchmarks
Journal Track
Creative AI Track
Outstanding Paper Awards
Workshops
Community
Sponsors
Help
What is a Draft Website
Presenters Instructions
Moderators Instructions
FAQ
Helpdesk in RocketChat
Organizers
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.
Cracking the Code of Juxtaposition: Can AI Models Understand the Humorous Contradictions
On the Adversarial Robustness of Benjamini Hochberg
Efficient Graph Matching for Correlated Stochastic Block Models
LaSe-E2V: Towards Language-guided Semantic-Aware Event-to-Video Reconstruction
A two-scale Complexity Measure for Deep Learning Models
MG-Net: Automatically Customize QAOA with Quantum Hardware Constraints for Enhanced Performance
The Prevalence of Neural Collapse in Neural Multivariate Regression
How does PDE order affect the convergence of PINNs?
BPQP: A Differentiable Convex Optimization Framework for Efficient End-to-End Learning
Spiking Transformer with Experts Mixture
Resource-Aware Federated Self-Supervised Learning with Global Class Representations
Cross-video Identity Correlating for Person Re-identification Pre-training
Complete Graphical Criterion for Sequential Covariate Adjustment in Causal Inference
Limits of Transformer Language Models on Learning to Compose Algorithms
Rethinking Inverse Reinforcement Learning: from Data Alignment to Task Alignment
Lambda: Learning Matchable Prior For Entity Alignment with Unlabeled Dangling Cases
PROSPECT PTMs: Rich Labeled Tandem Mass Spectrometry Dataset of Modified Peptides for Machine Learning in Proteomics
GVKF: Gaussian Voxel Kernel Functions for Highly Efficient Surface Reconstruction in Open Scenes
Mitigating Object Hallucination via Concentric Causal Attention
CryoGEM: Physics-Informed Generative Cryo-Electron Microscopy
OlympicArena: Benchmarking Multi-discipline Cognitive Reasoning for Superintelligent AI
Benchmarking Trustworthiness of Multimodal Large Language Models: A Comprehensive Study
ReMoDetect: Reward Models Recognize Aligned LLM's Generations
Association of Objects May Engender Stereotypes: Mitigating Association-Engendered Stereotypes in Text-to-Image Generation
A Large-Scale Human-Centric Benchmark for Referring Expression Comprehension in the LMM Era
Self-Supervised Adversarial Training via Diverse Augmented Queries and Self-Supervised Double Perturbation
Multi-Instance Partial-Label Learning with Margin Adjustment
LLaMo: Large Language Model-based Molecular Graph Assistant
Discretely beyond $1/e$: Guided Combinatorial Algortihms for Submodular Maximization
What Factors Affect Multi-modal In-Context Learning? An In-Depth Exploration
Unified Mechanism-Specific Amplification by Subsampling and Group Privacy Amplification
Accelerating Matroid Optimization through Fast Imprecise Oracles
Exploring Context Window of Large Language Models via Decomposed Positional Vectors
Kernel Language Entropy: Fine-grained Uncertainty Quantification for LLMs from Semantic Similarities
IMAGPose: A Unified Conditional Framework for Pose-Guided Person Generation
Mobility-LLM: Learning Visiting Intentions and Travel Preference from Human Mobility Data with Large Language Models
In-Context Learning State Vector with Inner and Momentum Optimization
Human-Readable Fingerprint for Large Language Models
(FL)${}^2$: Overcoming Few Labels in Federated Semi-Supervised Learning
UMB: Understanding Model Behavior for Open-World Object Detection
COLD: Causal reasOning in cLosed Daily activities
Kermut: Composite kernel regression for protein variant effects
StreamFlow: Streamlined Multi-Frame Optical Flow Estimation for Video Sequences
DF40: Toward Next-Generation Deepfake Detection
UNION: Unsupervised 3D Object Detection using Object Appearance-based Pseudo-Classes
Differentiable Structure Learning with Partial Orders
RAGraph: A General Retrieval-Augmented Graph Learning Framework
The Collusion of Memory and Nonlinearity in Stochastic Approximation With Constant Stepsize
Second-order forward-mode optimization of recurrent neural networks for neuroscience
START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation
Satformer: Accurate and Robust Traffic Data Estimation for Satellite Networks
SafeWorld: Geo-Diverse Safety Alignment
Tiny Time Mixers (TTMs): Fast Pre-trained Models for Enhanced Zero/Few-Shot Forecasting of Multivariate Time Series
ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer
Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting
ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons
MATES: Model-Aware Data Selection for Efficient Pretraining with Data Influence Models
INQUIRE: A Natural World Text-to-Image Retrieval Benchmark
Retrieval-Augumented Diffusion Models for Time Series Forecasting
Dealing with Synthetic Data Contamination in Online Continual Learning
VFIMamba: Video Frame Interpolation with State Space Models
Logical characterizations of recurrent graph neural networks with reals and floats
On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection
Perplexity-aware Correction for Robust Alignment with Noisy Preferences
Chimera: Effectively Modeling Multivariate Time Series with 2-Dimensional State Space Models
Diffusion-based Layer-wise Semantic Reconstruction for Unsupervised Out-of-Distribution Detection
Curvature Clues: Decoding Deep Learning Privacy with Input Loss Curvature
PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competition
On the Necessity of Collaboration for Online Model Selection with Decentralized Data
Generalization Error Bounds for Two-stage Recommender Systems with Tree Structure
HW-GPT-Bench: Hardware-Aware Architecture Benchmark for Language Models
Achieving Efficient Alignment through Learned Correction
Adversarial Moment-Matching Distillation of Large Language Models
Homology Consistency Constrained Efficient Tuning for Vision-Language Models
Causal discovery in the presence of endogenous context variables
MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding
Theoretical guarantees in KL for Diffusion Flow Matching
IntraMix: Intra-Class Mixup Generation for Accurate Labels and Neighbors
Understanding and Minimising Outlier Features in Neural Network Training
MoME: Mixture of Multimodal Experts for Generalist Multimodal Large Language Models
DPIC: Decoupling Prompt and Intrinsic Characteristics for LLM Generated Text Detection
Evaluating alignment between humans and neural network representations in image-based learning tasks
Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
Unscrambling disease progression at scale: fast inference of event permutations with optimal transport
Bandits with Ranking Feedback
Algebraic Positional Encodings
Learning Structure-Aware Representations of Dependent Types
Derivatives of Stochastic Gradient Descent
IndicVoices-R: Unlocking a Massive Multilingual Multi-speaker Speech Corpus for Scaling Indian TTS
Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
OAM-TCD: A globally diverse dataset of high-resolution tree cover maps
Testably Learning Polynomial Threshold Functions
Learning Superconductivity from Ordered and Disordered Material Structures
Smoke and Mirrors in Causal Downstream Tasks
Scanning Trojaned Models Using Out-of-Distribution Samples
Stable-Pose: Leveraging Transformers for Pose-Guided Text-to-Image Generation
A Cross-Domain Benchmark for Active Learning
Soft Prompt Threats: Attacking Safety Alignment and Unlearning in Open-Source LLMs through the Embedding Space
On the Scalability of Certified Adversarial Robustness with Generated Data
LaSCal: Label-Shift Calibration without target labels
Synthetic Programming Elicitation and Repair for Text-to-Code in Very Low-Resource Programming Languages
Boosting the Transferability of Adversarial Attack on Vision Transformer with Adaptive Token Tuning
Mechanism design augmented with output advice
TinyTTA: Efficient Test-time Adaptation via Early-exit Ensembles on Edge Devices
UltraPixel: Advancing Ultra High-Resolution Image Synthesis to New Peaks
RestoreAgent: Autonomous Image Restoration Agent via Multimodal Large Language Models
ContactField: Implicit Field Representation for Multi-Person Interaction Geometry
The Minimax Rate of HSIC Estimation for Translation-Invariant Kernels
Sub-optimal Experts mitigate Ambiguity in Inverse Reinforcement Learning
Learnability Matters: Active Learning for Video Captionin
Personalized Instance-based Navigation Toward User-Specific Objects in Realistic Environments
Constrained Binary Decision Making
A multi-UAV dataset for multi-object tracking and re-identification of wild antelopes
GeoLife: Spacial Plant Species Prediction Dataset
3D Focusing-and-Matching Network for Multi-Instance Point Cloud Registration
Star-Agents: Automatic Data Optimization with LLM Agents for Instruction Tuning
Stability and Generalizability in SDE Diffusion Models with Measure-Preserving Dynamics
Wasserstein Distributionally Robust Optimization through the Lens of Structural Causal Models and Individual Fairness
Space-Time Continuous PDE Forecasting using Equivariant Neural Fields
Are Multiple Instance Learning Algorithms Learnable for Instances?
Posture-Informed Muscular Force Learning for Robust Hand Pressure Estimation
Fair Kernel K-Means: from Single Kernel towards Multiple Kernel
Enhancing Consistency-Based Image Generation via Adversarialy-Trained Classification and Energy-Based Discrimination
Topological obstruction to the training of shallow ReLU neural networks
A Kernel Perspective on Distillation-based Collaborative Learning
Any2Graph: Deep End-To-End Supervised Graph Prediction With An Optimal Transport Loss
Mitigating Spurious Correlations via Disagreement Probability
RegExplainer: Generating Explanations for Graph Neural Networks in Regression Tasks
Generative Retrieval Meets Multi-Graded Relevance
Self-Distilled Depth Refinement with Noisy Poisson Fusion
Motif-oriented influence maximization for viral marketing in large-scale social networks
Continual Counting with Gradual Privacy Expiration
SCOREQ: Speech Quality Assessment with Contrastive Regression
Shape analysis for time series
FIRE: A Dataset for Feedback Integration and Refinement Evaluation of Multimodal Models
Saliency-driven Experience Replay for Continual Learning
ROIDICE: Offline Return on Investment Maximization for Efficient Decision Making
On improved Conditioning Mechanisms and Pre-training Strategies for Diffusion Models
Med-Real2Sim: Non-Invasive Medical Digital Twins using Physics-Informed Self-Supervised Learning
Consistency Models for Scalable and Fast Simulation-Based Inference
Semi-Discrete Optimal Transport: Nearly Minimax Estimation With Stochastic Gradient Descent and Adaptive Entropic Regularization
AgentGym: A Dynamic Environment to Evaluate Attacks and Defenses for LLM Agents
JailbreakBench: An Open Robustness Benchmark for Jailbreaking Large Language Models
NetworkGym: Reinforcement Learning Environments for Multi-Access Traffic Management in Network Simulation
RL-GPT: Integrating Reinforcement Learning and Code-as-policy
Near-Optimal Methods for Convex Simple Bilevel Problems
FNP: Fourier Neural Processes for Arbitrary-Resolution Data Assimilation
Gradual Domain Adaptation via Manifold-Constrained Distributionally Robust Optimization
A simplicity bias in the learning dynamics of transformers
SMART: Towards Pre-trained Missing-Aware Model for Patient Health Status Prediction
Game-Traversal-Benchmark: Evaluating Planning Abilities Of Large Language Models Via Traversing 2D Game Maps
Task-recency bias strikes back: Adapting covariances in Exemplar-Free Class Incremental Learning
Almost-Linear RNNs Yield Highly Interpretable Symbolic Codes in Dynamical Systems Reconstruction
Frustratingly Easy Test-Time Adaptation of Vision-Language Models
Iterative Methods via Locally Evolving Set Process
High Rank Path Development: an approach of learning the filtration of stochastic processes
Improved Few-Shot Jailbreaking Can Circumvent Aligned Language Models and Their Defenses
Diffusion-based Curriculum Reinforcement Learning
Deep linear networks for regression are implicitly regularized towards flat minima
Learning to compute Gröbner bases
A Versatile Diffusion Transformer with Mixture of Noise Levels for Audiovisual Generation
WebUOT-1M: Advancing Deep Underwater Object Tracking with A Million-Scale Benchmark
Foundation Inference Models for Markov Jump Processes
Multi-Scale VMamba: Hierarchy in Hierarchy Visual State Space Model
Self-Labeling the Job Shop Scheduling Problem
LocCa: Visual Pretraining with Location-aware Captioners
CausalChaos! Dataset for Comprehensive Causal Action Question Answering Over Longer Causal Chains Grounded in Dynamic Visual Scenes
RoleAgent: Building, Interacting, and Benchmarking High-quality Role-Playing Agents from Scripts
Flow Snapshot Neurons in Action: Deep Neural Networks Generalize to Biological Motion Perception
iVideoGPT: Interactive VideoGPTs are Scalable World Models
Credal Deep Ensembles for Uncertainty Quantification
Fairness in Social Influence Maximization via Optimal Transport
Conditioning non-linear and infinite-dimensional diffusion processes
ConvBench: A Multi-Turn Conversation Evaluation Benchmark with Hierarchical Ablation Capability for Large Vision-Language Models
UDC: A Unified Neural Divide-and-Conquer Framework for Large-Scale Combinatorial Optimization Problems
A Benchmark Suite for Systematically Evaluating Reasoning Shortcuts
Multi-Agent Domain Calibration with a Handful of Offline Data
ConStat: Performance-Based Contamination Detection in Large Language Models
Enhancing Semi-Supervised Learning via Representative and Diverse Sample Selection
Learning 3D Equivariant Implicit Function with Patch-Level Pose-Invariant Representation
SPARKLE: A Unified Single-Loop Primal-Dual Framework for Decentralized Bilevel Optimization
Wasserstein Gradient Boosting: A General Framework with Applications to Posterior Regression
Benchmarking Structural Inference Methods for Interacting Dynamical Systems with Synthetic Data
On Softmax Direct Preference Optimization for Recommendation
A Locally Optimal Portfolio for m-Sparse Sharpe Ratio Maximization
GAIA: Rethinking Action Quality Assessment for AI-Generated Videos
AED: Adaptable Error Detection for Few-shot Imitation Policy
SILENCE: Protecting privacy in offloaded speech understanding on wimpy devices
Direct Preference-Based Evolutionary Multi-Objective Optimization with Dueling Bandits
Dissecting the Failure of Invariant Learning on Graphs
Federated Behavioural Planes: Explaining the Evolution of Client Behaviour in Federated Learning
Parallel Backpropagation for Shared-Feature Visualization
Lever LM: Configuring In-Context Sequence to Lever Large Vision Language Models
Inferring Neural Signed Distance Functions by Overfitting on Single Noisy Point Clouds through Finetuning Data-Driven based Priors
DiffGS: Functional Gaussian Splatting Diffusion
MultiPull: Detailing Signed Distance Functions by Pulling Multi-Level Queries at Multi-Step
Metric Flow Matching for Smooth Interpolations on the Data Manifold
Towards Principled Graph Transformers
How Sparse Can We Prune A Deep Network: A Fundamental Limit Perspective
Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently
Faster Repeated Evasion Attacks in Tree Ensembles
$C^2M^3$: Cycle-Consistent Multi-Model Merging
B$\oplus$LD: Boolean Logic Deep Learning
Back to the Continuous Attractors
Hierarchical Programmatic Option Framework for Solving Long and Repetitive Tasks
Localized Adaptive Risk Control
SaulLM-54B & SaulLM-141B: Scaling Up Domain Adaptation for the Legal Domain
InterControl: Zero-shot Human Interaction Generation by Controlling Every Joint
Neural networks with fast and bounded units learn flexible task abstractions
HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation
Arctique: An artificial histopathological dataset unifying realism and controllability for uncertainty quantification
NeuralThink: Learning Algorithms For Consistent and Efficient Extrapolation Across General Tasks
Enhancing Robustness in Deep Reinforcement Learning: A Lyapunov Exponent Approach
Learning to Predict Structural Vibrations
Towards General Loop Invariant Generation: A Benchmark of Programs with Memory Manipulation
MetaAligner: Towards Generalizable Multi-Objective Alignment of Language Models
Vision Foundation Model Enables Generalizable Object Pose Estimation
Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control
MOTI$\mathcal{V}\mathcal{E}$: A Drug-Target Interaction Graph For Inductive Link Prediction
AV-GS: Learning Material and Geometry Aware Priors for Novel View Acoustic Synthesis
Continuous Partitioning for Graph-Based Semi-Supervised Learning
Neuc-MDS: Non-Euclidean Multidimensional Scaling Through Bilinear Forms
DAT: Improving Adversarial Robustness via Generative Amplitude Mix-up in Frequency Domain
Pseudo-Private Data Guided Model Inversion Attacks
Multi-Label Open Set Recognition
Mesa-Extrapolation: A Weave Position Encoding Method for Enhanced Extrapolation in LLMs
Semi-supervised Multi-label Learning with Balanced Binary Angular Margin Loss
DeBaRA: Denoising-Based 3D Room Arrangement Generation
WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
Can Transformers Smell Like Humans?
Provable Benefits of Complex Parameterizations for Structured State Space Models
X-Ray: A Sequential 3D Representation For Generation
Neural Conditional Probability for Inference
Harmonizing Stochasticity and Determinism: Scene-responsive Diverse Human Motion Prediction
Fourier Amplitude and Correlation Loss: Beyond Using L2 loss for Skillful Precipitation Nowcasting
Outlier-Robust Distributionally Robust Optimization via Unbalanced Optimal Transport
Grid4D: 4D Decomposed Hash Encoding for High-fidelity Dynamic Scene Rendering
Variational Multi-scale Representation for Estimating Uncertainty in 3D Gaussian Splatting
PaDeLLM-NER: Parallel Decoding in Large Language Models for Named Entity Recognition
GaussianMarker: Uncertainty-Aware Copyright Protection of 3D Gaussian Splatting
Efficient Pipeline Parallelism with Controllable Memory
Challenges of Generating Structurally Diverse Graphs
VQ-Map: Bird's-Eye-View Map Layout Estimation in Tokenized Discrete Space via Vector Quantization
UDPM: Upsampling Diffusion Probabilistic Models
A Synthetic Dataset for Personal Attribute Inference
Dataset and Lessons Learned from the 2024 SaTML LLM Capture-the-Flag Competition
SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models
Semidefinite Relaxations of the Gromov-Wasserstein Distance
Sample-Efficient Constrained Reinforcement Learning with General Parameterization
Learning General Parameterized Policies for Infinite Horizon Average Reward Constrained MDPs via Primal-Dual Policy Gradient Algorithm
StoryDiffusion: Consistent Self-Attention for Long-Range Image and Video Generation
How do Large Language Models Handle Multilingualism?
SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words
Neural Collapse Inspired Feature Alignment for Out-of-Distribution Generalization
MoTE: Reconciling Generalization with Specialization for Visual-Language to Video Knowledge Transfer
CoMix: A Comprehensive Benchmark for Multi-Task Comic Understanding
DisC-GS: Discontinuity-aware Gaussian Splatting
Real-world Image Dehazing with Coherence-based Pseudo Labeling and Cooperative Unfolding Network
BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval
DiffuLT: Diffusion for Long-tail Recognition Without External Knowledge
Group and Shuffle: Efficient Structured Orthogonal Parametrization
FewViewGS: Gaussian Splatting with Few View Matching and Multi-stage Training
A Novel Unified Architecture for Low-Shot Counting by Detection and Segmentation
Exploiting Descriptive Completeness Prior for Cross Modal Hashing with Incomplete Labels
FasMe: Fast and Sample-efficient Meta Estimator for Precision Matrix Learning in Small Sample Settings
DOFEN: Deep Oblivious Forest ENsemble
General Detection-based Text Line Recognition
Credal Learning Theory
FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference
Beware of Road Markings: A New Adversarial Patch Attack to Monocular Depth Estimation
Multimodal Conformal Prediction in Dynamic Environments
Differentiable Modal Synthesis for Physical Modeling of Planar String Sound and Motion Simulation
LVD-2M: A Long-take Video Dataset with Temporally Dense Captions
CRAYM: Neural Field Optimization via Camera RAY Matching
4DBInfer: A 4D Benchmarking Toolbox for Graph-Centric Predictive Modeling on RDBs
A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences
RClicks: Realistic Click Simulation for Benchmarking Interactive Segmentation
Entropy-regularized Diffusion Policy with Q-Ensembles for Offline Reinforcement Learning
DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation
RealCompo: Balancing Realism and Compositionality Improves Text-to-Image Diffusion Models
Subsurface Scattering for Gaussian Splatting
Multi-Winner Reconfiguration
Autoregressive Policy Optimization for Constrained Allocation Tasks
Utilizing Image Transforms and Diffusion Models for Generative Modeling of Short and Long Time Series
Spider2-V: How Far Are Multimodal Agents From Automating Data Science and Engineering Workflows?
FactorSim: Generative Simulation via Factorized Representation
Cross-Care: Assessing the Healthcare Implications of Pre-training Data on Language Model Bias
Adaptive Proximal Gradient Method for Convex Optimization
Wasserstein convergence of Cech persistence diagrams for samplings of submanifolds
Iteration Head: A Mechanistic Study of Chain-of-Thought
Improved Analysis for Bandit Learning in Matching Markets
VERIFIED: A Video Corpus Moment Retrieval Benchmark for Fine-Grained Video Understanding
Exploiting LLM Quantization
Private Attribute Inference from Images with Vision-Language Models
Transferring disentangled representations: bridging the gap between synthetic and real images
Controlling Continuous Relaxation for Combinatorial Optimization
HiCo: Hierarchical Controllable Diffusion Model for Layout-to-image Generation
Dimension-free deterministic equivalents for random feature regression
Accelerating Transformers with Spectrum-Preserving Token Merging
Reconstruction of Manipulated Garment with Guided Deformation Prior
Semi-supervised Knowledge Transfer Across Multi-omic Single-cell Data
Statistical Multicriteria Benchmarking via the GSD-Front
Instance-adaptive Zero-shot Chain-of-Thought Prompting
Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning
Demystify Mamba in Vision: A Linear Attention Perspective
ProgressGym: Alignment with a Millennium of Moral Progress
Persistence Homology Distillation for Semi-supervised Continual Learning
CRAG - Comprehensive RAG Benchmark
Linking In-context Learning in Transformers to Human Episodic Memory
DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving
A Generative Model of Symmetry Transformations
Improving Visual Prompt Tuning by Gaussian Neighborhood Minimization for Long-Tailed Visual Recognition
Resfusion: Denoising Diffusion Probabilistic Models for Image Restoration Based on Prior Residual Noise
Improved learning rates in multi-unit uniform price auctions
Balancing Multimodal Learning with Classifier-guided Gradient Modulation
$E^3$: Exploring Embodied Emotion Through A Large-Scale Egocentric Video Dataset
FRIEREN: Efficient Video-to-Audio Generation with Rectified Flow Matching
Action Imitation in Common Action Space for Customized Action Image Synthesis
Bridging 3D Scene and Large Language Models with Object Identifiers
Extending Multi-modal Contrastive Representations
MimicTalk: Mimicking a personalized and expressive 3D talking face in minutes
GTSinger: A Global Multi-Technique Singing Corpus with Realistic Music Scores for All Singing Tasks
Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation
Few-shot Algorithms for Consistent Neural Decoding (FALCON) Benchmark
Batched Energy-Entropy acquisition for Bayesian Optimization
PersonalSum: A User-Subjective Guided Personalized Summarization Dataset for Large Language Models
Bandit-Feedback Online Multiclass Classification: Variants and Tradeoffs
Off to new Shores: A Dataset & Benchmark for (near-)coastal Flood Inundation Forecasting
Nature-Inspired Local Propagation
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows
The Surprising Ineffectiveness of Pre-Trained Visual Representations for Model-Based Reinforcement Learning
MaVEn: An Effective Multi-granularity Hybrid Visual Encoding Framework for Multimodal Large Language Model
The Expressive Capacity of State Space Models: A Formal Language Perspective
Reasons and solutions for the decline in model performance after editing
Adversarial Robust Decision Transformer: Enhancing RvS Robustness via Minimax Returns
Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks?
G2D: From Global to Dense Radiography Representation Learning via Vision-Language Pre-training
AsEP: Benchmarking Deep Learning Methods for Antibody-specific Epitope Prediction
Optimal Algorithms for Online Convex Optimization with Adversarial Constraints
The Implicit Bias of Gradient Descent toward Collaboration between Layers: A Dynamic Analysis of Multilayer Perceptions
Initialization is Critical to Whether Transformers Fit Composite Functions by Inference or Memorizing
Connectivity Shapes Implicit Regularization in Matrix Factorization Models for Matrix Completion
Voila-A: Aligning Vision-Language Models with User's Gaze Attention
A Functional Extension of Semi-Structured Networks
Generating Code World Models with Large Language Models Guided by Monte Carlo Tree Search
MonkeySee: Space-time-resolved reconstructions of natural images from macaque multi-unit activity
On-Road Object Importance Estimation: A New Dataset and A Model with Multi-Fold Top-Down Guidance
Teach Better or Show Smarter? On Instructions and Exemplars in Automatic Prompt Optimization
Can Graph Learning Improve Task Planning?
Compressive Sensing with Sparsity Inducing Conditionally Gaussian Generative Models
Efficiently Learning Significant Fourier Feature Pairs for Statistical Independence Testing
Data subsampling for Poisson regression
DI-MaskDINO: A Joint Object Detection and Instance Segmentation Model
II-Bench: An Image Implication Understanding Benchmark for Multimodal Large Language Models
EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals
Is Multiple Object Tracking a Matter of Specialization?
HydraViT: Stacking Heads for a Scalable ViT
Archaeoscape: Bringing Aerial Laser Scanning Archaeology to the Deep Learning Era
Differentiable Task Graph Learning: Procedural Activity Representation and Online Mistake Detection from Egocentric Videos
Exploring Fixed Point in Image Editing: Theoretical Support and Convergence Optimization
InternLM-XComposer2-4KHD: A Pioneering Large Vision-Language Model Handling Resolutions from 336 Pixels to 4K HD
Tight Bounds for Learning RUMs from Small Slates
Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?
Stochastic Concept Bottleneck Models
Online Learning with Sublinear Best-Action Queries
Elucidating the Design Space of Dataset Condensation
What do Graph Neural Networks learn? Insights from Tropical Geometry
LFME: A Simple Framework for Learning from Multiple Experts in Domain Generalization
$\textit{Trans-LoRA}$: towards data-free Transferable Parameter Efficient Finetuning
PUZZLES: A Benchmark for Neural Algorithmic Reasoning
Token Merging for Training-Free Semantic Binding in Text-to-Image Synthesis
Faster Diffusion: Rethinking the Role of the Encoder for Diffusion Model Inference
Leveraging Catastrophic Forgetting to Develop Safe Diffusion Models against Malicious Finetuning
Learning Conjunctive Representations
The Scandinavian Embedding Benchmarks: Comprehensive Assessment of Multilingual and Monolingual Text Embedding
EMVP: Embracing Visual Foundation Model for Visual Place Recognition with Centroid-Free Probing
Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents
Faster Local Solvers for Graph Diffusion Equations
Performative Control for Linear Dynamical Systems
Unveiling the Hidden: Online Vectorized HD Map Construction with Clip-Level Token Interaction and Propagation
Why Go Full? Elevating Federated Learning Through Partial Network Updates
EGODE: An Event-attended Graph ODE Framework for Modeling Rigid Dynamics
LiteVAE: Lightweight and Efficient Variational Autoencoders for Latent Diffusion Models
Generating Origin-Destination Matrices in Neural Spatial Interaction Models
Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
Provable and Efficient Dataset Distillation for Kernel Ridge Regression
ProG: A Graph Prompt Learning Benchmark
Optimus-1: Hybrid Multimodal Memory Empowered Agents Excel in Long-Horizon Tasks
CoMERA: Computing- and Memory-Efficient Training via Rank-Adaptive Tensor Optimization
TAIA: Large Language Models are Out-of-Distribution Data Learners
Exploiting the Replay Memory Before Exploring the Environment: Enhancing Reinforcement Learning Through Empirical MDP Iteration
RLE: A Unified Perspective of Data Augmentation for Cross-Spectral Re-Identification
Language Models as Hierarchy Encoders
Image Reconstruction Via Autoencoding Sequential Deep Image Prior
DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices
Federated Learning over Connected Modes
COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing
GrootVL: Tree Topology is All You Need in State Space Model
Evaluating Numerical Reasoning in Text-to-Image Models
SA3DIP: Segment Any 3D Instance with Potential 3D Priors
Towards Open Respiratory Acoustic Foundation Models: Pretraining and Benchmarking
On the Complexity of Identification in Linear Structural Causal Models
NaturalBench: Evaluating Vision-Language Models on Natural Adversarial Samples
LinNet: Linear Network for Efficient Point Cloud Representation Learning
OpenMathInstruct-1: A 1.8 Million Math Instruction Tuning Dataset
PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs
The Best of Both Worlds: On the Dilemma of Out-of-distribution Detection
Mutual Information Estimation via Normalizing Flows
Enhancing Motion in Text-to-Video Generation with Decomposed Encoding and Conditioning
Spiking Neural Network as Adaptive Event Stream Slicer
Boosting Generalization in Parametric PDE Neural Solvers through Adaptive Conditioning
Mixture of Experts Meets Prompt-Based Continual Learning
How Do Large Language Models Acquire Factual Knowledge During Pretraining?
HyperPrism: An Adaptive Non-linear Aggregation Framework for Distributed Machine Learning over Non-IID Data and Time-varying Communication Links
ReF-LDM: A Latent Diffusion Model for Reference-based Face Image Restoration
The Many Faces of Optimal Weak-to-Strong Learning
Optimal Parallelization of Boosting
OneActor: Consistent Subject Generation via Cluster-Conditioned Guidance
A Hitchhikers Guide to Fine-Grained Face Forgery Detection Using Common Sense Reasoning
Du-IN: Discrete units-guided mask modeling for decoding speech from Intracranial Neural signals
Equivariant Flow-Matching for Molecular Conformer Generation
Over-parameterized Student Model via Tensor Decomposition Boosted Knowledge Distillation
Reshuffling Resampling Splits Can Improve Generalization of Hyperparameter Optimization
Gradient Methods for Online DR-Submodular Maximization with Stochastic Long Term Constraints
Dueling over Dessert, Mastering the Art of Repeated Cake Cutting
Trade-Offs of Diagonal Fisher Information Matrix Estimators
Rejection via Learning Density Ratios
Conditional Outcome Equivalence: A Quantile Alternative to CATE
Cascade Speculative Drafting for Even Faster LLM Inference
Federated Transformer: Scalable Vertical Federated Learning on Practical Fuzzily Linked Data
Only Strict Saddles in the Energy Landscape of Predictive Coding Networks?
Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation
Get Rid of Isolation: A Continuous Multi-task Spatio-Temporal Learning Framework
ControlSynth Neural ODEs: Modeling Dynamical Systems with Guaranteed Convergence
Fetch and Forge: Efficient Dataset Condensation for Object Detection
Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models
Relational Concept Bottleneck Models
Interpretable Concept-Based Memory Reasoning
fMRI predictors based on language models of increasing complexity recover brain left lateralization
MoGU: A Framework for Enhancing Safety of Open-Sourced LLMs While Preserving Their Usability
Rethinking The Training And Evaluation of Rich-Context Layout-to-Image Generation
Sequential Harmful Shift Detection Without Labels
Derivative-enhanced Deep Operator Network
Towards Harmless Rawlsian Fairness Regardless of Demographic Prior
MotionBooth: Motion-Aware Customized Text-to-Video Generation
Randomized Minor-Value Rectification: A Novel Matrix Sparsification Algorithm for Solving Constrained Optimizations in Cancer Radiation Therapy
EyeGraph: Modularity-aware Spatio Temporal Graph Clustering for Continuous Event-based Eye Tracking
Weak-to-Strong Search: Align Large Language Models via Searching over Small Language Models
DDK: Distilling Domain Knowledge for Efficient Large Language Models
DRACO: A Denoising-Reconstruction Autoencoder for Cryo-EM
Relationship Prompt Learning is Enough for Open-Vocabulary Semantic Segmentation
Data curation via joint example selection further accelerates multimodal learning
Neural Model Checking
MeshFormer : High-Quality Mesh Generation with 3D-Guided Reconstruction Model
Learning from Pattern Completion: Self-supervised Controllable Generation
Universal Sample Coding
Graph Neural Networks and Arithmetic Circuits
EAI: Emotional Decision-Making of LLMs in Strategic Games and Ethical Dilemmas
CAPE: Context-Adaptive Positional Encoding for Length Extrapolation
Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
NewTerm: Benchmarking Real-Time New Terms for Large Language Models with Annual Updates
REBEL: Reinforcement Learning via Regressing Relative Rewards
Poseidon: Efficient Foundation Models for PDEs
Moving Off-the-Grid: Scene-Grounded Video Representations
DEFT: Efficient Finetuning of Conditional Diffusion Models by Learning the Generalised $h$-transform
Neuronal Competition Groups with Supervised STDP for Spike-Based Classification
kGym: A Platform and Dataset to Benchmark Large Language Models on Linux Kernel Crash Resolution
ZOPP: A Framework of Zero-shot Offboard Panoptic Perception for Autonomous Driving
Learning Generalized Linear Programming Value Functions
LLMs Can Evolve Continually on Modality for $\mathbb{X}$-Modal Reasoning
Generalization Bounds via Conditional $f$-Information
On $f$-Divergence Principled Domain Adaptation: An Improved Framework
An Expectation-Maximization Algorithm for Training Clean Diffusion Models from Corrupted Observations
Data-Efficient Learning with Neural Programs
Overcoming Common Flaws in the Evaluation of Selective Classification Systems
JaxMARL: Multi-Agent RL Environments and Algorithms in JAX
Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metrics
SkipPredict: When to Invest in Predictions for Scheduling
Quasi-Bayes meets Vines
Task Confusion and Catastrophic Forgetting in Class-Incremental Learning: A Mathematical Framework for Discriminative and Generative Modelings
A Phase Transition between Positional and Semantic Learning in a Solvable Model of Dot-Product Attention
Empowering Active Learning for 3D Molecular Graphs with Geometric Graph Isomorphism
Geometric Analysis of Nonlinear Manifold Clustering
Semantics and Spatiality of Emergent Communication
Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
Theoretical Characterisation of the Gauss Newton Conditioning in Neural Networks
Towards More Efficient Property Inference Attacks on Graph Neural Networks
Extracting Training Data from Molecular Pre-trained Models
Chain of Agents: Large Language Models Collaborating on Long-Context Tasks
TableRAG: Million-Token Tabular Reasoning with Large Language Models
AGILE: A Novel Framework of LLM Agent
MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark
The Challenges of the Nonlinear Regime for Physics-Informed Neural Netowrks
On the Robustness of Spectral Algorithms for Semirandom Stochastic Block Models
Learning an Actionable Discrete Diffusion Policy via Large-Scale Actionless Video Pre-Training
Regularized Conditional Diffusion Model for Multi-Task Preference Alignment
LLM-ESR: Large Language Models Enhancement for Long-tailed Sequential Recommendation
WATT: Weight Average Test Time Adaptation of CLIP
Extending Video Masked Autoencoders to 128 frames
Foundations of Multivariate Distributional Reinforcement Learning
Action Gaps and Advantages in Continuous-Time Distributional Reinforcement Learning
Contrastive dimension reduction: when and how?
Global Rewards in Restless Multi-Armed Bandits
EgoSim: An Egocentric Multi-view Simulator for Body-worn Cameras during Human Motion
ReXTime: A Benchmark Suite for Reasoning-Across-Time in Videos
What Variables Affect Out-Of-Distribution Generalization in Pretrained Models?
Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insights
Normal-GS: 3D Gaussian Splatting with Normal-Involved Rendering
NaRCan: Natural Refined Canonical Image with Integration of Diffusion Prior for Video Editing
Flex-MoE: Addressing Missing Modalities in Alzheimer’s Disease with Flexible Mixture-of-Experts
MECD: Unlocking Multi-Event Causal Discovery in Video Reasoning
Seeing Beyond the Crop: Using Language Priors for Out-of-Bounding Box Keypoint Prediction
Stochastic Kernel Regularisation Improves Generalisation in Deep Kernel Machines
SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead
MmCows: A Multimodal Dataset for Dairy Cattle Monitoring
ChronoEpilogi: Scalable Time Series Selection with Multiple Solutions
CTIBench: A Benchmark for Evaluating LLMs in Cyber Threat Intelligence
How Transformers Utilize Multi-Head Attention in In-Context Learning? A Case Study on Sparse Linear Regression
SM3-Text-to-Query: Synthetic Multi-Model Medical Text-to-Query Benchmark
MedCalc-Bench: Evaluating Large Language Models for Medical Calculations
Differentially Private Set Representations
Stealth edits to large language models
ACFun: Abstract-Concrete Fusion Facial Stylization
Bayes-optimal learning of an extensive-width neural network from quadratically many samples
Predicting the Performance of Foundation Models via Agreement-on-the-Line
Understanding the Transferability of Representations via Task-Relatedness
emg2qwerty: A Large Dataset with Baselines for Touch Typing using Surface Electromyography
Adaptive $Q$-Aid for Conditional Supervised Learning in Offline Reinforcement Learning
NYU CTF Dataset: A Scalable Open-Source Benchmark Dataset for Evaluating LLMs in Offensive Security
Linearly Decomposing and Recomposing Vision Transformers for Diverse-Scale Models
Fisher Flow Matching for Discrete Data
Integrating Paralinguistics in Speech-Empowered Large Language Models for Natural Conversation
Hypothesis Testing the Circuit Hypothesis in LLMs
Provable Tempered Overfitting of Minimal Nets and Typical Nets
Efficient multi-prompt evaluation of LLMs
SciCode: A Research Coding Benchmark Curated by Scientists
SLICE-100K: A Multimodal Dataset for Extrusion-based 3D Printing
Optimal Algorithms for Learning Partitions with Faulty Oracles
The Multimodal Universe: Enabling Large-Scale Machine Learning with 70TBs of Astronomical Scientific Data
Block Sparse Bayesian Learning: A Diversified Scheme
DeSparsify: Adversarial Attack Against Token Sparsification Mechanisms
MassSpecGym: A benchmark for the discovery and identification of molecules
DEL: Discrete Element Learner for Learning 3D Dynamics from 2D Observations
HYDRA-FL: Hybrid Knowledge Distillation for Robust and Accurate Federated Learning
Uncertainty-aware Fine-tuning of Segmentation Foundation Models
IRCAN: Mitigating Knowledge Conflicts in LLM Generation via Identifying and Reweighting Context-Aware Neurons
SegVol: Universal and Interactive Volumetric Medical Image Segmentation
The Art of Saying No: Contextual Noncompliance in Language Models
MAGNET: Improving the Multilingual Fairness of Language Models with Adaptive Gradient-Based Tokenization
WildTeaming at Scale: From In-the-Wild Jailbreaks to (Adversarially) Safer Language Models
Non-geodesically-convex optimization in the Wasserstein space
CycleNet: Enhancing Time Series Forecasting through Modeling Periodic Patterns
TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs
Towards Heterogeneous Long-tailed Learning: Benchmarking, Metrics, and Toolbox
Tactile DreamFusion: Exploiting Tactile Sensing for 3D Generation
Designs for Enabling Collaboration in Human-Machine Teaming via Interactive and Explainable Systems
Mercury: A Code Efficiency Benchmark for Code Large Language Models
Scaling Law for Time Series Forecasting
Sim2Real-Fire: A Multi-modal Simulation Dataset for Forecast and Backtracking of Real-world Forest Fire
Toward Efficient Inference for Mixtures of Experts
Upping the Game: How 2D U-Net Skip Connections Dominate 3D Segmentation
NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarking
DINTR: Tracking via Diffusion-based Interpolation
CYCLO: Cyclic Graph Transformer Approach to Multi-Object Relationship Modeling in Aerial Videos
Watch Out for Your Agents! Investigating Backdoor Threats to LLM-Based Agents
FineCLIP: Self-distilled Region-based CLIP for Better Fine-Grained Understanding
Deep Learning for Computing Convergence Rates of Markov Chains
A Taxonomy of Challenges to Curating Fair Datasets
Multivariate Probabilistic Time Series Forecasting with Correlated Errors
E2E-MFD: Towards End-to-End Synchronous Multimodal Fusion Detection
The State of Data Curation at NeurIPS: An Assessment of Dataset Development Practices in the Datasets and Benchmarks Track
SLIM: Style-Linguistics Mismatch Model for Generalized Audio Deepfake Detection
VLKEB: A Large Vision-Language Model Knowledge Editing Benchmark
SSDM: Scalable Speech Dysfluency Modeling
ZeroMark: Towards Dataset Ownership Verification without Disclosing Dataset-specified Watermarks
Speculative Monte-Carlo Tree Search
LP-3DGS: Learning to Prune 3D Gaussian Splatting
Beyond Assouad, Fano, and Le Cam: Toward Unified Lower Bounds for Statistical Estimation and Interactive Decision Making
DEPrune: Depth-wise Separable Convolution Pruning for Maximizing GPU Parallelism
Probing Social Bias in Labor Market Text Generation by ChatGPT: A Masked Language Model Approach
OpenDlign: Enhancing Open-World 3D Learning with Depth-Aligned Images
Image Textualization: An Automatic Framework for Generating Rich and Detailed Image Descriptions
Model Decides How to Tokenize: Adaptive DNA Sequence Tokenization with MxDNA
Empowering and Assessing the Utility of Large Language Models in Crop Science
Continuous Product Graph Neural Networks
MoLE: Enhancing Human-centric Text-to-image Diffusion via Mixture of Low-rank Experts
Would I Lie To You? Inference Time Alignment of Language Models using Direct Preference Heads
Physics-Regularized Multi-Modal Image Assimilation for Brain Tumor Localization
Analysing the Generalisation and Reliability of Steering Vectors
Goal Conditioned Reinforcement Learning for Photo Finishing Tuning
Soft Tensor Product Representations for Fully Continuous, Compositional Visual Representations
Interventionally Consistent Surrogates for Complex Simulation Models
Lorentz-Equivariant Geometric Algebra Transformers for High-Energy Physics
Atlas3D: Physically Constrained Self-Supporting Text-to-3D for Simulation and Fabrication
emg2pose: A Large and Diverse Benchmark for Surface Electromyographic Hand Pose Estimation
Multiview Scene Graph
MUVERA: Multi-Vector Retrieval via Fixed Dimensional Encoding
Learning Cortico-Muscular Dependence through Orthonormal Decomposition of Density Ratios
Federated Black-Box Adaptation for Semantic Segmentation
ChaosBench: A Multi-Channel, Physics-Based Benchmark for Subseasonal-to-Seasonal Climate Prediction
Identifying and Solving Conditional Image Leakage in Image-to-Video Generation
AttnDreamBooth: Towards Text-Aligned Personalized Text-to-Image Generation
IaC-Eval: A code generation benchmark for Infrastructure-as-Code programs
ALOHA: from Attention to Likes – a unified mOdel for understanding HumAn responses to diverse visual content
FM-Delta: Lossless Compression for Storing Massive Fine-tuned Foundation Models
EpiCare: A Reinforcement Learning Benchmark for Dynamic Treatment Regimes
Cross-model Control: Improving Multiple Large Language Models in One-time Training
The Map Equation Goes Neural: Mapping Network Flows with Graph Neural Networks
AllClear: A Comprehensive Dataset and Benchmark for Cloud Removal in Satellite Imagery
Faster Algorithms for User-Level Private Stochastic Convex Optimization
GuardT2I: Defending Text-to-Image Models from Adversarial Prompts
Learning Action and Reasoning-Centric Image Editing from Videos and Simulation
Efficient Availability Attacks against Supervised and Contrastive Learning Simultaneously
T2VSafetyBench: Evaluating the Safety of Text-to-Video Generative Models
Randomized Strategic Facility Location with Predictions
Stylebreeder: Exploring and Democratizing Artistic Styles through Text-to-Image Models
Semi-Truths: A Large-Scale Dataset for Testing Robustness of AI-Generated Image Detectors
ClavaDDPM: Multi-relational Data Synthesis with Cluster-guided Diffusion Models
Generating compositional scenes via Text-to-image RGBA Instance Generation
On the Limitations of Fractal Dimension as a Measure of Generalization
The GAN is dead; long live the GAN! A Modern GAN Baseline
Multi-Object Hallucination in Vision Language Models
CA-SSLR: Condition-Aware Self-Supervised Learning Representation for Generalized Speech Processing
Leveraging partial stragglers within gradient coding
VideoLLM-MoD: Efficient Video-Language Streaming with Mixture-of-Depths Vision Computation
Perception of Knowledge Boundary for Large Language Models through Semi-open-ended Question Answering
MAN TruckScenes: A multimodal dataset for autonomous trucking in diverse conditions
Computation Tree: A Transferable Pattern Towards Graph Foundation Models
Efficient Attention using Low-Dimensional Keys
PrivAuditor: Benchmarking Data Protection Vulnerabilities in LLM Adaptation Techniques
Non-asymptotic Analysis of Biased Adaptive Stochastic Approximation
AnonFair: A Flexible Toolkit for Algorithmic Fairness
Unified Guidance for Geometry-Conditioned Molecular Generation
SCAFFLSA: Taming Heterogeneity in Federated Linear Stochastic Approximation and TD Learning
Estimating the Hallucination Rate of Generative AI
Graph neural networks and non-commuting operators
Beyond Optimism: Exploration With Partially Observable Rewards
Preventing Dimensional Collapse in Self-Supervised Learning via Orthogonality Regularization
Preventing Model Collapse in Deep Canonical Correlation Analysis by Noise Regularization
Confidence Calibration of Classifiers with Many Classes
Neural decoding from stereotactic EEG: accounting for electrode variability across subjects
Reimagining Mutual Information for Enhanced Defense against Data Leakage in Collaborative Inference
Auditing Privacy Mechanisms via Label Inference Attacks
Exploring the trade-off between deep-learning and explainable models for brain-machine interfaces
Model-based Diffusion for Trajectory Optimization
Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training
Learning from Uncertain Data: From Possible Worlds to Possible Models
Exploring Jacobian Inexactness in Second-Order Methods for Variational Inequalities: Lower Bounds, Optimal Algorithms and Quasi-Newton Approximations
Off-policy estimation with adaptively collected data: the power of online learning
Coherence-free Entrywise Estimation of Eigenvectors in Low-rank Signal-plus-noise Matrix Models
Who’s Gaming the System? A Causally-Motivated Approach for Detecting Strategic Adaptation
Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
Bayesian Optimization of Functions over Node Subsets in Graphs
IllumiNeRF: 3D Relighting without Inverse Rendering
Physically Compatible 3D Object Modeling from a Single Image
Interpretable Machine Learning for Datasets with Missing Values
Are Large Language Models Good Statisticians?
DMC-VB: A Benchmark for Representation Learning for Control with Visual Distractors
A Concept-Based Explainability Framework for Large Multimodal Models
MInference: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention
einspace: Searching for Neural Architectures from Fundamental Operations
Verifiably Robust Conformal Prediction
AdjointDEIS: Efficient Gradients for Diffusion Models
Artemis: Towards Referential Understanding in Complex Videos
Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
Federated Online Prediction from Experts with Differential Privacy: Separations and Regret Speed-ups
Scale-invariant Optimal Sampling for Rare-events Data and Sparse Models
Higher-Rank Irreducible Cartesian Tensors for Equivariant Message Passing
Trading off Consistency and Dimensionality of Convex Surrogates for Multiclass Classification
LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation
Drago: Primal-Dual Coupled Variance Reduction for Faster Distributionally Robust Optimization
The Benefits of Balance: From Information Projections to Variance Reduction
QUEST: Quality-Aware Metropolis-Hastings Sampling for Machine Translation
Latent Representation Matters: Human-like Sketches in One-shot Drawing Tasks
Advancing Open-Set Domain Generalization Using Evidential Bi-Level Hardest Domain Scheduler
SARAD: Spatial Association-Aware Anomaly Detection and Diagnosis for Multivariate Time Series
Diffusion-based Reinforcement Learning via Q-weighted Variational Policy Optimization
A Topology-aware Graph Coarsening Framework for Continual Graph Learning
Look, Listen, and Answer: Overcoming Biases for Audio-Visual Question Answering
HGDL: Heterogeneous Graph Label Distribution Learning
Benchmarking Counterfactual Image Generation
Learning Heuristics for Numeric Planning
Divergences between Language Models and Human Brains
Training Binary Neural Networks via Gaussian Variational Inference and Low-Rank Semidefinite Programming
Emu3D: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials
FIDE: Frequency-Inflated Conditional Diffusion Model for Extreme-Aware Time Series Generation
Nonconvex Federated Learning on Compact Smooth Submanifolds With Heterogeneous Data
DreamCatcher: A Wearer-aware Multi-modal Sleep Event Dataset Based on Earables in Non-restrictive Environments
Rainbow Teaming: Open-Ended Generation of Diverse Adversarial Prompts
Retrospective for the Dynamic Sensorium Competition for predicting large-scale mouse primary visual cortex activity from videos
The Closeness of In-Context Learning and Weight Shifting for Softmax Regression
On conditional diffusion models for PDE simulations
Learning Identifiable Factorized Causal Representations of Cellular Responses
Learning from Teaching Regularization: Generalizable Correlations Should be Easy to Imitate
MotionTTT: 2D Test-Time-Training Motion Estimation for 3D Motion Corrected MRI
Bandits with Abstention under Expert Advice
InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
Query-Efficient Correlation Clustering with Noisy Oracle
APIGen: Automated PIpeline for Generating Verifiable and Diverse Function-Calling Datasets
Constructing Semantics-Aware Adversarial Examples with Probabilistic Perspective
MTGS: A Novel Framework for Multi-Person Temporal Gaze Following and Social Gaze Prediction
Toward Semantic Gaze Target Detection
Implicit Regularization Paths of Weighted Neural Representations
JourneyBench: A Challenging One-Stop Vision-Language Understanding Benchmark of Generated Images
Constrained Synthesis with Projected Diffusion Models
MatrixNet: Learning over symmetry groups using learned group representations
Neural Isometries: Taming Transformations for Equivariant ML
Full-Distance Evasion of Pedestrian Detectors in the Physical World
BMRS: Bayesian Model Reduction for Structured Pruning
A probability contrastive learning framework for 3D molecular representation learning
Measuring Per-Unit Interpretability at Scale Without Humans
Global Distortions from Local Rewards: Neural Coding Strategies in Path-Integrating Neural Systems
Get rich quick: exact solutions reveal how unbalanced initializations promote rapid feature learning
Proximal Causal Inference With Text Data
Overfitting Behaviour of Gaussian Kernel Ridge Regression: Varying Bandwidth or Dimensionality
The Well: a Large-Scale Collection of Diverse Physics Simulations for Machine Learning
Leveraging Hallucinations to Reduce Manual Prompt Dependency in Promptable Segmentation
Transductive Sample Complexities Are Compact
Seshat Global History Databank Text Dataset and Benchmark of Large Language Models' History Knowledge
LLM Evaluators Recognize and Favor Their Own Generations
Graph Neural Networks Do Not Always Oversmooth
Aligning Large Language Models with Representation Editing: A Control Perspective
Intrinsic Self-Supervision for Data Quality Audits
ImageNet++: A Large-Scale Benchmark of Data Curation Strategies
SubjECTive-QA: A dataset for the subjective evaluation of answers in Earnings Call Transcripts (ECTs)
MACM: Utilizing a Multi-Agent System for Condition Mining in Solving Complex Mathematical Problems
Generating Highly Designable Proteins with Geometric Algebra Flow Matching
Hierarchical Federated Learning with Multi-Timescale Gradient Correction
Don't Look Twice: Faster Video Transformers with Run-Length Tokenization
On the Complexity of Learning Sparse Functions with Statistical and Gradient Queries
Efficient LLM Scheduling by Learning to Rank
Constrained Diffusion with Trust Sampling
Exploring Prompting Methods for Mitigating Class Imbalance through Synthetic Data Generation with Large Language Models
Population Predictive Coding: a structured Bayesian inference algorithm
Learning Neural Contracting Dynamics: Extended Linearization and Global Guarantees
RTify: Aligning Deep Neural Networks with Human Behavioral Decisions
Computation-Aware Gaussian Processes: Model Selection And Linear-Time Inference
SleeperNets: Universal Backdoor Poisoning Attacks Against Reinforcement Learning Agents
Beyond Slow Signs in High-fidelity Model Extraction
LLM-Check: Investigating Detection of Hallucinations in Large Language Models
Learning Spatially-Aware Language and Audio Embeddings
VLM4Bio: A Benchmark Dataset to Evaluate Pretrained Vision-Language Models for Trait Discovery from Biological Images
Local Linearity: the Key for No-regret Reinforcement Learning in Continuous MDPs
Community Detection Guarantees using Embeddings Learned by Node2Vec
Unified Domain Generalization and Adaptation for Multi-View 3D Object Detection
Locally Private and Robust Multi-Armed Bandits
Non-Euclidean Mixture Model for Social Network Embedding
DistrictNet: Decision-aware learning for geographical districting
Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs
Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
Copycats: the many lives of a publicly available medical imaging dataset
NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping
Reinforcement Learning with Adaptive Control Regularization for Safe Control of Critical Systems
Unsupervised Discovery of Formulas for Mathematical Constants
USCILab3D: A Large-scale, Long-term, Semantically Annotated Outdoor Dataset
Transfer Learning for Diffusion Models
Reinforcement Learning with Euclidean Data Augmentation for State-Based Continuous Control
SETBENCH: Assessing the Analytical and Semantic Robustness of Language Models
UniSDF: Unifying Neural Representations for High-Fidelity 3D Reconstruction of Complex Scenes with Reflections
BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languages
Toward Conditional Distribution Calibration in Survival Prediction
Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networks
BeanCounter: A low-toxicity, large-scale, and open dataset of business-oriented text
Boosted Conformal Prediction Intervals
Modeling Latent Neural Dynamics with Gaussian Process Switching Linear Dynamical Systems
Error Correction Output Codes for Robust Neural Networks against Weight-errors: A Neural Tangent Kernel Point of View
Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning
Truthfulness of Calibration Measures
Spectral Learning of Shared Dynamics Between Generalized-Linear Processes
$\textit{Bifr\"ost}$: 3D-Aware Image Composing with Language Instructions
Cooperative Hardware-Prompt Learning for Snapshot Compressive Imaging
Diffusion-Inspired Truncated Sampler for Text-Video Retrieval
Thought of Search: Planning with Language Models Through The Lens of Efficiency
InstructG2I: Synthesizing Images from Multimodal Attributed Graphs
Oracle-Efficient Differentially Private Learning with Public Data
Solving Inverse Problems via Diffusion Optimal Control
BertaQA: How Much Do Language Models Know About Local Culture?
Arboretum: A Large Multimodal Dataset Enabling AI for Biodiversity
RandNet-Parareal: a time-parallel PDE solver using Random Neural Networks
Bileve: Securing Text Provenance in Large Language Models Against Spoofing with Bi-level Signature
Is One GPU Enough? Pushing Image Generation at Higher-Resolutions with Foundation Models.
Practical Guide for Designing Cell-Type-Specific Promoter Sequences Using Conservative Model-Based Optimization
Achieving Domain-Independent Certified Robustness via Knowledge Continuity
Multi-modal Transfer Learning between Biological Foundation Models
CompBench: A Comparative Reasoning Benchmark for Multimodal LLMs
Conformal Prediction for Class-wise Coverage via Augmented Label Rank Calibration
No Free Lunch Theorem and Black-Box Complexity Analysis for Adversarial Optimisation
MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions
Quantum algorithm for large-scale market equilibrium computation
Lips Are Lying: Spotting the Temporal Inconsistency between Audio and Visual in Lip-Syncing DeepFakes
Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records
What makes unlearning hard and what to do about it
Reciprocal Learning
SolarCube: An Integrative Benchmark Dataset Harnessing Satellite and In-situ Observations for Large-scale Solar Energy Forecasting
Toward Reliable, Reproducible, and Practical Human Evaluation Protocol for Text-to-Video Models
WorldCoder, a Model-Based LLM Agent: Building World Models by Writing Code and Interacting with the Environment
Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
Efficient Contextual LLM Cascades through Budget-Constrained Policy Learning
IR-CM: The Fast and Universal Image Restoration Method Based on Consistency Model
Rethinking Transformer for Long Contextual Histopathology Whole Slide Image Analysis
CNCA: Toward Customizable and Natural Generation of Adversarial Camouflage for Vehicle Detectors
DACO: Towards Application-Driven and Comprehensive Data Analysis via Code Generation
On the Comparison between Multi-modal and Single-modal Contrastive Learning
NoisyGL: A Comprehensive Benchmark for Graph Neural Networks under Label Noise
Construction and Application of Materials Knowledge Graph in Multidisciplinary Materials Science via Large Language Model
Building Timeseries Dataset: Empowering Large-Scale Building Analytics
SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
A Framework for Bilevel Optimization on Riemannian Manifolds
Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
GraphCroc: Cross-Correlation Autoencoder for Graph Structural Reconstruction
Many-shot Jailbreaking
Approximated Orthogonal Projection Unit: Stabilizing Regression Network Training Using Natural Gradient
Geometry of naturalistic object representations in recurrent neural network models of working memory
Learning to Cooperate with Humans using Generative Agents
Rapid Plug-in Defenders
Pretrained Optimization Model for Zero-Shot Black Box Optimization
FreqBlender: Enhancing DeepFake Detection by Blending Frequency Knowledge
ChronoMagic: A Benchmark for Metamorphic Evaluation of Time-lapse Text-to-Video Generation
No-Regret Learning for Fair Multi-Agent Social Welfare Optimization
BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction
GAVEL: Generating Games via Evolution and Language Models
ENAT: Rethinking Spatial-temporal Interactions in Token-based Image Synthesis
SpreadsheetBench: Towards Challenging Real World Spreadsheet Manipulation
GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
The AlCHEmist: Automated Labeling 500x CHEaper than LLM Data Annotators
Vaccine: Perturbation-aware Alignment for Large Language Models Finetuning
Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning
Group-wise oracle-efficient algorithms for online multi-group learning
Codec Avatar Studio: Paired Human Captures for Complete, Driveable, and Generalizable Avatars
Learning in Markov Games with Adaptive Adversaries: Policy Regret, Fundamental Barriers, and Efficient Algorithms
Offline Multitask Representation Learning for Reinforcement Learning
Adversarially Robust Multi-task Representation Learning
Self-Taught Recognizer: Toward Unsupervised Adaptation for Speech Foundation Models
Optimal ablation for model internals
DreamMesh4D: Video-to-4D Generation with Sparse-Controlled Gaussian-Mesh Hybrid Representation
Mr.Bean: A Comprehensive Meta-Reasoning Benchmark for Analyzing Large Language Models
How Do Transformers Fill in the Blanks? A Case Study on Matrix Completion
Counterfactual PPO Enhanced Shared Reflector for LLM-based Multi-agent Collaboration
PLIP: Language-Image Pre-training for Person Representation Learning
COSMIC: Compress Satellite Image Efficiently via Diffusion Compensation
Noisy Dual Mirror Descent: A Near Optimal Algorithm for Jointly-DP Convex Resource Allocation
VidMan: Exploiting Intrinsic Dynamics from Video Diffusion Model for Effective Robot Manipulation
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
Identification and Estimation of the Bi-Directional MR with Some Invalid Instruments
Stochastic Optimization Schemes for Performative Prediction with Nonconvex Loss
LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS
Revisiting motion information for RGB-Event tracking with MOT philosophy
Advancing Video Anomaly Detection: A Concise Review and a New Dataset
Rethinking Weight Decay for Robust Fine-Tuning of Foundation Models
FLAME : Factuality-Aware Alignment for Large Language Models
Pretraining Codomain Attention Neural Operators for Solving Multiphysics PDEs
Probabilistic size-and-shape functional mixed models
Adjust Pearson's $r$ to Measure Nonlinear Monotone Dependence
PhyloGen: Language Model-Enhanced Phylogenetic Inference via Graph Structure Generation
RGFN: Synthesizable Molecular Generation Using GFlowNets
SCube: Instant Large-Scale Scene Reconstruction using VoxSplats
G-Retriever: Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
Computerized Adaptive Testing via Collaborative Ranking
Gene-Gene Relationship Modeling Based on Genetic Evidence for Single-Cell RNA-Seq Data Imputation
Vector Quantization Prompting for Continual Learning
SemCoder: Training Code Language Models with Comprehensive Semantics
Bag of Tricks: Benchmarking of Jailbreak Attacks on LLMs
MultiOrg: A Multi-rater Organoid-detection Dataset
Membership Inference Attacks against Large Language Models via Self-prompt Calibration
Stochastic Taylor Derivative Estimator: Efficient amortization for arbitrary differential operators
Amortized Eigendecomposition for Neural Networks
Kernel PCA for Out-of-Distribution Detection
Addressing Asynchronicity in Clinical Multimodal Fusion via Individualized Chest X-ray Generation
Information Re-Organization Improves Reasoning in Large Language Models
Cronos: Enhancing Deep Learning with Scalable GPU Accelerated Convex Neural Networks
EHRNoteQA: An LLM Benchmark for Real-World Clinical Practice Using Discharge Summaries
Mind's Eye of LLMs: Visualization-of-Thought Elicits Spatial Reasoning in Large Language Models
DrivingDojo Dataset: Advancing Interactive and Knowledge-Enriched Driving World Model
Beyond Accuracy: Tracking more like Human via Visual Search
Mining and Transferring Feature-Geometry Coherence for Unsupervised Point Cloud Registration
Cambrian-1: A Fully Open, Vision-Centric Exploration of Multimodal LLMs
The High Line: Exact Risk and Learning Rate Curves of Stochastic Adaptive Learning Rate Algorithms
Automating Dataset Updates Towards Reliable and Timely Evaluation of Large Language Models
Towards Multi-Domain Learning for Generalizable Video Anomaly Detection
MOTE-NAS: Multi-Objective Training-based Estimate for Efficient Neural Architecture Search
TARSS-Net: Temporal-Aware Radar Semantic Segmentation Network
ChatTracker: Enhancing Visual Tracking Performance via Chatting with Multimodal Large Language Model
Exact Gradients for Stochastic Spiking Neural Networks Driven by Rough Signals
GraphTrail: Translating GNN Predictions into Human-Interpretable Logical Rules
Con4m: Context-aware Consistency Learning Framework for Segmented Time Series Classification
DMNet: Self-comparison Driven Model for Subject-independent Seizure Detection
VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
Bridging Gaps: Federated Multi-View Clustering in Heterogeneous Hybrid Views
One-Step Effective Diffusion Network for Real-World Image Super-Resolution
LLM-based Skill Diffusion for Zero-shot Policy Adaptation
Incremental Learning of Retrievable Skills For Efficient Continual Task Adaptation
TinyLUT: Tiny Look-Up Table for Efficient Image Restoration at the Edge
SongCreator: Lyrics-based Universal Song Generation
Enriching Disentanglement: From Logical Definitions to Quantitative Metrics
AdaPKC: PeakConv with Adaptive Peak Receptive Field for Radar Semantic Segmentation
DiffTOP: Differentiable Trajectory Optimization for Deep Reinforcement and Imitation Learning
LaKD: Length-agnostic Knowledge Distillation for Trajectory Prediction with Any Length Observations
Boosting Text-to-Video Generative Model with MLLMs Feedback
Towards a Scalable Reference-Free Evaluation of Generative Models
Re-assembling the past: The RePAIR dataset and benchmark for real world 2D and 3D puzzle solving
StreamBench: Towards Benchmarking Continuous Improvement of Language Agents
OnlineTAS: An Online Baseline for Temporal Action Segmentation
Hybrid Global Causal Discovery with Local Search
From Chaos to Clarity: 3DGS in the Dark
ContextGS : Compact 3D Gaussian Splatting with Anchor Level Context Model
Universal Exact Compression of Differentially Private Mechanisms
The Poisson Midpoint Method for Langevin Dynamics: Provably Efficient Discretization for Diffusion Models
Near-Optimal Streaming Heavy-Tailed Statistical Estimation with Clipped SGD
A Decision-Language Model (DLM) for Dynamic Restless Multi-Armed Bandit Tasks in Public Health
An Autoencoder-Like Nonnegative Matrix Co-Factorization for Improved Student Cognitive Modeling
DoGaussian: Distributed-Oriented Gaussian Splatting for Large-Scale 3D Reconstruction Via Gaussian Consensus
Unchosen Experts Can Contribute Too: Unleashing MoE Models’ Power by Self-Contrast
An End-To-End Graph Attention Network Hash for Cross-Modal Retrieval
Wasserstein Distance Rivals Kullback-Leibler Divergence for Knowledge Distillation
PIVOT-R: Primitive-Driven Waypoint-Aware World Model for Robotic Manipulation
2DQuant: Low-bit Post-Training Quantization for Image Super-Resolution
SfPUEL: Shape from Polarization under Unknown Environment Light
Unlocking the Capabilities of Masked Generative Models for Image Synthesis via Self-Guidance
Peri-midFormer: Periodic Pyramid Transformer for Time Series Analysis
Self-supervised Transformation Learning for Equivariant Representations
FlexPlanner: Flexible 3D Floorplanning via Deep Reinforcement Learning in Hybrid Action Space with Multi-Modality Representation
Measuring Multimodal Mathematical Reasoning with MATH-Vision Dataset
Multi-Head Mixture-of-Experts
Multimodal Large Language Models Make Text-to-Image Generative Models Align Better
Mind the Gap Between Prototypes and Images in Cross-domain Few-shot Classification
Acceleration Exists! Optimization Problems When Oracle Can Only Compare Objective Function Values
TextCtrl: Diffusion-based Scene Text Editing with Prior Guidance Control
ProSST: Protein Language Modeling with Quantized Structure and Disentangled Attention
RAGChecker: A Fine-grained Framework for Diagnosing Retrieval-Augmented Generation
Concentrate Attention: Towards Domain-Generalizable Prompt Optimization for Language Models
GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages
DropEdge not Foolproof: Effective Augmentation Method for Signed Graph Neural Networks
Provably Safe Neural Network Controllers via Differential Dynamic Logic
Learning to Balance Altruism and Self-interest Based on Empathy in Mixed-Motive Games
AdaSociety: An Adaptive Environment with Social Structures for Multi-Agent Decision-Making
A Benchmark Dataset for Event-Guided Human Pose Estimation and Tracking in Extreme Conditions
Scalable Kernel Inverse Optimization
Taming Generative Diffusion Prior for Universal Blind Image Restoration
Cross-Device Collaborative Test-Time Adaptation
Q-Distribution guided Q-learning for offline reinforcement learning: Uncertainty penalized Q-value via consistency model
Personalized Federated Learning with Mixture of Models for Adaptive Prediction and Model Fine-Tuning
Croissant: A Metadata Format for ML-Ready Datasets
End-to-end Learnable Clustering for Intent Learning in Recommendation
Recursive PAC-Bayes: A Frequentist Approach to Sequential Prior Updates with No Information Loss
Breaking Determinism: Fuzzy Modeling of Sequential Recommendation Using Discrete State Space Diffusion Model
On the Expressivity and Sample Complexity of Node-Individualized Graph Neural Networks
Identify Then Recommend: Towards Unsupervised Group Recommendation
Activation Map Compression through Tensor Decomposition for Deep Learning
EEVR: A Virtual Reality-Based Emotion Dataset Featuring Paired Physiological Signals and Textual Descriptions
An exactly solvable model for emergence and scaling laws
InfiBench: Evaluating the Question-Answering Capabilities of Code Large Language Models
Advancing Cross-domain Discriminability in Continual Learning of Vison-Language Models
SHED: Shapley-Based Automated Dataset Refinement for Instruction Fine-Tuning
FLoRA: Federated Fine-Tuning Large Language Models with Heterogeneous Low-Rank Adaptations
$\texttt{Model-GLUE}$: Democratized LLM Scaling for A Large Model Zoo in the Wild
Non-Asymptotic Uncertainty Quantification in High-Dimensional Learning
Annealed Multiple Choice Learning: Overcoming limitations of Winner-takes-all with annealing
Graph Classification via Reference Distribution Learning: Theory and Practice
Functional Gradient Flows for Constrained Sampling
Learning via Surrogate PAC-Bayes
Towards Combating Frequency Simplicity-biased Learning for Domain Generalization
No-regret Learning in Harmonic Games: Extrapolation in the Face of Conflicting Interests
Dual Encoder GAN Inversion for High-Fidelity 3D Head Reconstruction from Single Images
Accelerating Non-Maximum Suppression: A Graph Theory Perspective
A scalable generative model for dynamical system reconstruction from neuroimaging data
CLIPAway: Harmonizing focused embeddings for removing objects via diffusion models
The Convergence of Variance Exploding Diffusion Models under the Manifold Hypothesis
Freya PAGE: First Optimal Time Complexity for Large-Scale Nonconvex Finite-Sum Optimization with Heterogeneous Asynchronous Computations
GOUDA: A General Graph Contrastive Learning Framework via Augmentation Unification
Task-Agnostic Machine Learning-Assisted Inference
Consensus Learning with Deep Sets for Essential Matrix Estimation
Improving the Worst-Case Bidirectional Communication Complexity for Nonconvex Distributed Optimization under Function Similarity
MoMu-Diffusion: On Learning Long-Term Motion-Music Synchronization and Correspondence
A robust inlier identification algorithm for point cloud registration via $\mathbf{\ell_0}$-minimization
Quantifying the Bitter Lesson: How Safety Benchmarks Measure Capabilities Instead of Safety
Language Without Borders: A Dataset and Benchmark for Code-Switching Lip Reading
Towards the Transferability of Rewards Recovered via Regularized Inverse Reinforcement Learning
Convergence Analysis of Split Federated Learning on Heterogeneous Data
Fully Transparent Self-Alignment for Code Generation
LG-VQ: Language-Guided Codebook Learning
One Token to Seg Them All: Language Instructed Reasoning Segmentation in Videos
DoFIT: Domain-aware Federated Instruction Tuning with Alleviated Catastrophic Forgetting
On Sampling Strategies for Spectral Model Sharding
EHRCon: Dataset for Checking Consistency between Unstructured Notes and Structured Tables in Electronic Health Records
ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images
MLLMGuard: A Multi-dimensional Safety Evaluation Suite for Multimodal Large Language Models
When to Act and When to Ask: Policy Learning With Deferral Under Hidden Confounding
Not Just Object, But State: Compositional Incremental Learning without Forgetting
$\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
SplitNeRF: Split Sum Approximation Neural Field for Joint Geometry, Illumination, and Material Estimation
SOI: Scaling Down Computational Complexity by Estimating Partial States of the Model
BAN: Detecting Backdoors Activated by Neuron Noise
A-FedPD: Aligning Dual-Drift is All Federated Primal-Dual Learning Need
Selective Generation for Language Models
Enhancing Multiple Dimensions of Trustworthiness in LLMs via Sparse Activation Control
CALE: Continuous Arcade Learning Environment
Scribbles for All: Benchmarking Scribble Supervised Segmentation Across Datasets
Multi-scale Consistency for Robust 3D Registration via Hierarchical Sinkhorn Tree
BEACON: Benchmark for Comprehensive RNA Tasks and Language Models
DDR: Exploiting Deep Degradation Response as Flexible Image Descriptor
SGLang: Efficient Execution of Structured Language Model Programs
Emergence of heavy tails in homogenized stochastic gradient descent
Online Bayesian Persuasion Without a Clue
Animal-Bench: Benchmarking Multimodal Video Models for Animal-centric Video Understanding
FOOGD: Federated Collaboration for Both Out-of-distribution Generalization and Detection
Drift-Resilient TabPFN: In-Context Learning Distribution Shifts on Tabular Data
GACL: Exemplar-Free Generalized Analytic Continual Learning
Sm: enhanced localization in Multiple Instance Learning for medical imaging classification
Self-Guiding Exploration for Combinatorial Problems
Key-Grid: Unsupervised 3D Keypoints Detection using Grid Heatmap Features
FastDrag: Manipulate Anything in One Step
AdvAD: Exploring Non-Parametric Diffusion for Imperceptible Adversarial Attacks
CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmark
Representation noising effectively prevents harmful fine-tuning on LLMs
Loss Symmetry and Noise Equilibrium of Stochastic Gradient Descent
Improving Generalization and Convergence by Enhancing Implicit Regularization
Membership Inference Attacks against Large Vision-Language Models
Marginalized Hamiltonian Monte Carlo for Linear Mixed-Effects Models
Variational Delayed Policy Optimization
End-to-End Video Semantic Segmentation in Adverse Weather using Fusion Blocks and Temporal-Spatial Teacher-Student Learning
DisenGCD: A Meta Multigraph-assisted Disentangled Graph Learning Framework for Cognitive Diagnosis
Globally Q-linear Gaussian-Newton Method for Overparameterized Non-convex Matrix Sensing
Towards Unified Multimodal Editing with Enhanced Knowledge Collaboration
Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
Thinking Forward: Memory-Efficient Federated Finetuning of Language Models
Approximately Pareto-optimal Solutions for Bi-Objective k-Clustering
No "Zero-Shot" Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance
A Practitioner's Guide to Real-World Continual Multimodal Pretraining
ColJailBreak: Collaborative Generation and Editing for Jailbreaking Text-to-Image Deep Generation
Enhancing vision-language models for medical imaging: bridging the 3D gap with innovative slice selection
SVFT: Parameter-Efficient Fine-Tuning with Singular Vectors
Feature-Level Adversarial Attacks and Ranking Disruption for Visible-Infrared Person Re-identification
WaveAttack: Asymmetric Frequency Obfuscation-based Backdoor Attacks Against Deep Neural Networks
Knowledge-Empowered Dynamic Graph Network for Irregularly Sampled Medical Time Series
SciInstruct: a Self-Reflective Instruction Annotated Dataset for Training Scientific Language Models
State-free Reinforcement Learning
ALS: Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment
4D Gaussian Splatting in the Wild with Uncertainty-Aware Regularization
Rethinking Imbalance in Image Super-Resolution for Efficient Inference
BetterDepth: Plug-and-Play Diffusion Refiner for Zero-Shot Monocular Depth Estimation
Optimal Top-Two Method for Best Arm Identification and Fluid Analysis
Can Large Language Model Agents Simulate Human Trust Behavior?
CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics
PowerPM: Foundation Model for Power Systems
FinBen: An Holistic Financial Benchmark for Large Language Models
HARMONIC: Harnessing LLMs for Tabular Data Synthesis and Privacy Protection
Be Confident in What You Know: Bayesian Parameter Efficient Fine-Tuning of Foundation Models
CALVIN: Improved Contextual Video Captioning via Instruction Tuning
Multi-turn Reinforcement Learning with Preference Human Feedback
Effective Exploration Based on the Structural Information Principles
D2R2: Diffusion-based Representation with Random Distance Matching for Tabular Few-shot Learning
Natural Counterfactuals With Necessary Backtracking
On Causal Discovery in the Presence of Deterministic Relations
Risk-sensitive control as inference with Rényi divergence
Bias in Motion: Theoretical Insights into the Dynamics of Bias in SGD Training
DC-Gaussian: Improving 3D Gaussian Splatting for Reflective Dash Cam Videos
Refusal in Language Models Is Mediated by a Single Direction
Sim-to-Real Transfer Can Make Naive Exploration Efficient in Reinforcement Learning
Sample Complexity Reduction through Policy Difference Estimation in RL
Humor in AI: Massive Scale Crowd-Sourced Preferences and Benchmarks for Cartoon Captioning
Randomized algorithms and PAC bounds for inverse reinforcement learning in continuous spaces
Safe Time-Varying Optimization based on Gaussian Processes with Spatio-Temporal Kernel
Real-Time Recurrent Learning using Trace Units in Reinforcement Learning
Aligning Model Properties via Conformal Risk Control
Higher-Order Causal Message Passing for Experimentation Under Unknown Interference
Prospective Representation Learning for Non-Exemplar Class-Incremental Learning
Exploring the Edges of Latent State Clusters for Goal-Conditioned Reinforcement Learning
From Transparent to Opaque: Rethinking Neural Implicit Surfaces with $\alpha$-NeuS
FuseFL: One-Shot Federated Learning through the Lens of Causality with Progressive Model Fusion
Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models
Mitigating Biases in Blackbox Feature Extractors for Image Classification Tasks
Touchstone Benchmark: Are We on the Right Way for Evaluating AI Algorithms for Medical Segmentation?
A benchmark for prediction of transcriptomic responses to chemical perturbations across cell types
Should We Really Edit Language Models? On the Evaluation of Edited Language Models
Active design of two-photon holographic stimulation for identifying neural population dynamics
Efficient Lifelong Model Evaluation in an Era of Rapid Progress
CiteME: Can Language Models Accurately Cite Scientific Claims?
Graph Diffusion Transformer for Multi-Conditional Molecular Generation
Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation
Adaptive Image Quality Assessment via Teaching Large Multimodal Models to Compare
Targeted Sequential Indirect Experiment Design
WikiDO: Evaluating Out-of-Distribution Generalization of Vision-Language Models in Cross-Modal Retrieval
Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
Learning World Models for Unconstrained Goal Navigation
AvaTaR: Optimizing LLM Agents for Tool-Assisted Knowledge Retrieval
STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases
Embodied Agent Interface: Benchmarking LLMs for Embodied Decision Making
MiSO: Optimizing brain stimulation to create neural activity states
Analytically Computing Partial Information Decomposition
Causal language modeling can elicit search and reasoning capabilities on sudoku puzzles
Unrolled denoising networks that provably learn to perform optimal Bayesian inference
A structure-aware framework for learning device placements on computation graphs
SDP4Bit: Toward 4-bit Communication Quantization in Sharded Data Parallelism for LLM Training
Scalable and Stable Parallelization of Nonlinear RNNs
Deep Graph Mating
Private Geometric Median
On Sparse Canonical Correlation Analysis
Depth Anything V2
Differentially Private Graph Diffusion with Applications in Personalized PageRanks
Self-Refining Diffusion Samplers: Enabling Parallelization via Parareal Iterations
Zipper: Addressing Degeneracy in Algorithm-Agnostic Inference
Quantifying and Optimizing Global Faithfulness in Persona-driven Role-playing
Bayesian Optimisation with Unknown Hyperparameters: Regret Bounds Logarithmically Closer to Optimal
No Regrets: Investigating and Improving Regret Approximations for Curriculum Discovery
Mind the Gap: A Causal Perspective on Bias Amplification in Prediction & Decision-Making
Decoupled Kullback-Leibler Divergence Loss
Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Prediction
Boosting Vision-Language Models with Transduction
Interpretable Lightweight Transformer via Unrolling of Learned Graph Smoothness Priors
Evaluating the World Model Implicit in a Generative Model
realSEUDO for real-time calcium imaging analysis
Detecting Bugs with Substantial Monetary Consequences by LLM and Rule-based Reasoning
SlimSAM: 0.1% Data Makes Segment Anything Slim
TPC: Test-time Procrustes Calibration for Diffusion-based Human Image Animation
Certified Machine Unlearning via Noisy Stochastic Gradient Descent
In-Context Learning with Representations: Contextual Generalization of Trained Transformers
Fight Back Against Jailbreaking via Prompt Adversarial Tuning
Identifying General Mechanism Shifts in Linear Causal Representations
Implicit Optimization Bias of Next-token Prediction in Linear Models
Kraken: Inherently Parallel Transformers For Efficient Multi-Device Inference
Full-Atom Peptide Design with Geometric Latent Diffusion
Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity
Is Cross-validation the Gold Standard to Evaluate Model Performance?
Adapting to Unknown Low-Dimensional Structures in Score-Based Diffusion Models
Toward Approaches to Scalability in 3D Human Pose Estimation
Certified Adversarial Robustness via Randomized $\alpha$-Smoothing for Regression Models
Relation-Driven Diffusion for Human-Object Interaction Detection
Personalized Adapter for Large Meteorology Model on Devices: Towards Weather Foundation Models
Compressing Large Language Models using Low Rank and Low Precision Decomposition
Exploring Behavior-Relevant and Disentangled Neural Dynamics with Generative Diffusion Models
Fast Rates in Stochastic Online Convex Optimization by Exploiting the Curvature of Feasible Sets
Variational Distillation of Diffusion Policies into Mixture of Experts
Clustering with Non-adaptive Subset Queries
In-Context Learning with Transformers: Softmax Attention Adapts to Function Lipschitzness
OPEL: Optimal Transport Guided ProcedurE Learning
Implicitly Guided Design with PropEn: Match your Data to Follow the Gradient
Exploring Consistency in Graph Representations: from Graph Kernels to Graph Neural Networks
Spiking Token Mixer: A event-driven friendly Former structure for spiking neural networks
GenRec: Unifying Video Generation and Recognition with Diffusion Models
Zipfian Whitening
Sparsity-Agnostic Linear Bandits with Adaptive Adversaries
Generalization Bound and Learning Methods for Data-Driven Projections in Linear Programming
On Weak Regret Analysis for Dueling Bandits
Unraveling the Gradient Descent Dynamics of Transformers
Can Learned Optimization Make Reinforcement Learning Less Difficult?
Towards Universal Mesh Movement Networks
Optimizing over Multiple Distributions under Generalized Quasar-Convexity Condition
Robust Sparse Regression with Non-Isotropic Designs
Diversity from the Void: Training Adaptive Agents in Open-Ended Simulators
A Unified Framework for 3D Scene Understanding
What If the Input is Expanded in OOD Detection?
SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering
The Selective $G$-Bispectrum and its Inversion: Applications to $G$-Invariant Networks
SPEAR: Exact Gradient Inversion of Batches in Federated Learning
Coarse-to-Fine Concept Bottleneck Models
A Simple yet Scalable Granger Causal Structural Learning from Topological Event Sequences
Learning Linear Causal Representations from General Environments: Identifiability and Intrinsic Ambiguity
SPO: Sequential Monte Carlo Policy Optimisation
FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
UDON: Universal Dynamic Online distillatioN for generic image representations
Long-tailed Object Detection Pretraining: Dynamic Rebalancing Contrastive Learning with Dual Reconstruction
Learning predictable and robust neural representations by straightening image sequences
Consistency Diffusion Bridge Models
INDICT: Code Generation with Internal Dialogues of Critiques for Both Security and Helpfulness
Bayesian Adaptive Calibration and Optimal Design
On the Role of Attention Masks and LayerNorm in Transformers
Label Delay in Online Continual Learning
Evaluating and Eliciting Lateral Thinking of Large Language Models with Situation Puzzles
If You Want to Be Robust, Be Wary of Initialization
Generalizable Person Re-identification via Balancing Alignment and Uniformity
End-To-End Causal Effect Estimation from Unstructured Text Data
Public-data Assisted Private Stochastic Optimization: Power and Limitations
Mitigating Covariate Shift in Behavioral Cloning via Robust Distribution Correction Estimation
3DET-Mamba: Causal Sequence Modelling for End-to-End 3D Object Detection
Are More LLM Calls All You Need? Towards the Scaling Properties of Compound AI Systems
Expectation Alignment: Handling Reward Misspecification in the Presence of Expectation Mismatch
Compositional Estimation of Lipschitz Constants for Deep Neural Networks
GLinSAT: The General Linear Satisfiability Neural Network Layer By Accelerated Gradient Descent
Is Value Function Learning Really the Main Bottleneck of Offline RL?
AV-Cloud: Spatial Audio Rendering Through Audio-Visual Cloud Splatting
Epipolar-Free 3D Gaussian Splatting for Generalizable Novel View Synthesis
Model Lego: Creating Models Like Disassembling and Assembling Building Blocks
Time Makes Space: Emergence of Place Fields in Networks Encoding Temporally Continuous Sensory Experiences
HyperLogic: Enhancing Diversity and Accuracy in Rule Learning with HyperNets
Guided Trajectory Generation with Diffusion Models for Offline Model-based Optimization
TurboHopp: Accelerated Molecule Scaffold Hopping with Consistency Models
SAM-Guided Masked Token Prediction for 3D Scene Understanding
Shared Autonomy with IDA: Interventional Diffusion Assistance
LoRA-GA: Low-Rank Adaptation with Gradient Approximation
On Feature Learning in Structured State Space Models
Reconstruction Attacks on Machine Unlearning: Simple Models are Vulnerable
Pretrained Large Language Models Use Fourier Features to Compute Addition
Exponential Quantum Communication Advantage in Distributed Inference and Learning
Metric Transforms and Low Rank Representations of Kernels
Understanding and Improving Adversarial Collaborative Filtering for Robust Recommendation
Off-Dynamics Reinforcement Learning via Domain Adaptation and Reward Augmented Imitation
Regularizing Hidden States Enables Learning Generalizable Reward Model for LLMs
Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
FastSurvival: Hidden Computational Blessings in Training Cox Proportional Hazards Models
Learning to Understand: Identifying Interactions via the Möbius Transform
Kronecker-Factored Approximate Curvature for Physics-Informed Neural Networks
Efficient Temporal Action Segmentation via Boundary-aware Query Voting
Invariant subspaces and PCA in nearly matrix multiplication time
Simple and Fast Distillation of Diffusion Models
Federated Fine-tuning of Large Language Models under Heterogeneous Tasks and Client Resources
Towards training digitally-tied analog blocks via hybrid gradient computation
Reinforcement Learning Policy as Macro Regulator Rather than Macro Placer
Generalized Protein Pocket Generation with Prior-Informed Flow Matching
MambaLLIE: Implicit Retinex-Aware Low Light Enhancement with Global-then-Local State Space
No Representation, No Trust: Connecting Representation, Collapse, and Trust Issues in PPO
Revisiting Score Propagation in Graph Out-of-Distribution Detection
Unsupervised Anomaly Detection in The Presence of Missing Values
GENOT: A Neural Optimal Transport Framework for Single Cell Genomics
Neural Flow Diffusion Models: Learnable Forward Process for Improved Diffusion Modelling
pcaGAN: Improving Posterior-Sampling cGANs via Principal Component Regularization
Aggregate-and-Adapt Natural Language Prompts for Downstream Generalization of CLIP
Bridge the Points: Graph-based Few-shot Segment Anything Semantically
Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
On the Scalability of GNNs for Molecular Graphs
Diffeomorphic interpolation for efficient persistence-based topological optimization
Q-VLM: Post-training Quantization for Large Vision-Language Models
Localize, Understand, Collaborate: Semantic-Aware Dragging via Intention Reasoner
GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning
Beyond Primal-Dual Methods in Bandits with Stochastic and Adversarial Constraints
Bayesian Nonparametrics Meets Data-Driven Distributionally Robust Optimization
Dimension-free Private Mean Estimation for Anisotropic Distributions
Advancing Spiking Neural Networks for Sequential Modeling through Central Pattern Generators
Is Behavior Cloning All You Need? Understanding Horizon in Imitation Learning
Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editing
Alias-Free Mamba Neural Operator
Fairness and Efficiency in Online Class Matching
Generate Universal Adversarial Perturbations for Few-Shot Learning
Personalizing Reinforcement Learning from Human Feedback with Variational Preference Learning
Distributed-Order Fractional Graph Operating Network
Plant-and-Steal: Truthful Fair Allocations via Predictions
Flatten Anything: Unsupervised Neural Surface Parameterization
Mission Impossible: A Statistical Perspective on Jailbreaking LLMs
An engine not a camera: Measuring performative power of online search
Parameter Disparities Dissection for Backdoor Defense in Heterogeneous Federated Learning
Masked Pre-training Enables Universal Zero-shot Denoiser
Low-Rank Optimal Transport through Factor Relaxation with Latent Coupling
Fully Explicit Dynamic Gaussian Splatting
Forgetting, Ignorance or Myopia: Revisiting Key Challenges in Online Continual Learning
Efficient Discrepancy Testing for Learning with Distribution Shift
Unleashing Multispectral Video's Potential in Semantic Segmentation: A Semi-supervised Viewpoint and New UAV-View Benchmark
Crafting Interpretable Embeddings by Asking LLMs Questions
MGF: Mixed Gaussian Flow for Diverse Trajectory Prediction
Infinite Limits of Multi-head Transformer Dynamics
Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE
One-Step Diffusion Distillation through Score Implicit Matching
A hierarchical decomposition for explaining ML performance discrepancies
Gradient-variation Online Learning under Generalized Smoothness
FreeSplat: Generalizable 3D Gaussian Splatting Towards Free View Synthesis of Indoor Scenes
Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms
DiffPO: A causal diffusion model for predicting potential outcomes of treatments
Sharing Key Semantics in Transformer Makes Efficient Image Restoration
Yo'LLaVA: Your Personalized Language and Vision Assistant
Online Relational Inference for Evolving Multi-agent Interacting System
Precise asymptotics of reweighted least-squares algorithms for linear diagonal networks
The Group Robustness is in the Details: Revisiting Finetuning under Spurious Correlations
ActAnywhere: Subject-Aware Video Background Generation
Wings: Learning Multimodal LLMs without Text-only Forgetting
The Representation Landscape of Few-Shot Learning and Fine-Tuning in Large Language Models
From an Image to a Scene: Learning to Imagine the World from a Million 360° Videos
AirSketch: Generative Motion to Sketch
NeuralFuse: Learning to Recover the Accuracy of Access-Limited Neural Network Inference in Low-Voltage Regimes
Long-range Meta-path Search on Large-scale Heterogeneous Graphs
HardCore Generation: Generating Hard UNSAT Problems for Data Augmentation
Discovering plasticity rules that organize and maintain neural circuits
A Geometric View of Data Complexity: Efficient Local Intrinsic Dimension Estimation with Diffusion Models
DECRL: A Deep Evolutionary Clustering Jointed Temporal Knowledge Graph Representation Learning Approach
Zero-Shot Tokenizer Transfer
Rad-NeRF: Ray-decoupled Training of Neural Radiance Field
Vision-Language Models are Strong Noisy Label Detectors
UNITS: A Unified Multi-Task Time Series Model
Neural P$^3$M: A Long-Range Interaction Modeling Enhancer for Geometric GNNs
Time-Reversal Provides Unsupervised Feedback to LLMs
Applying Guidance in a Limited Interval Improves Sample and Distribution Quality in Diffusion Models
Hyperbolic Embeddings of Supervised Models
Constrained Sampling with Primal-Dual Langevin Monte Carlo
Unlocking the Boundaries of Thought: A Reasoning Granularity Framework to Quantify and Optimize Chain-of-Thought
Mutli-Armed Bandits with Network Interference
Dual Risk Minimization: Towards Next-Level Robustness in Fine-tuning Zero-Shot Models
Learning to Solve Quadratic Unconstrained Binary Optimization in a Classification Way
Stress-Testing Capability Elicitation With Password-Locked Models
PERIA: Perceive, Reason, Imagine, Act via Holistic Language and Vision Planning for Manipulation
Toward Global Convergence of Gradient EM for Over-Paramterized Gaussian Mixture Models
IDGen: Item Discrimination Induced Prompt Generation for LLM Evaluation
Scalable Constrained Policy Optimization for Safe Multi-agent Reinforcement Learning
Generative Semi-supervised Graph Anomaly Detection
RashomonGB: Analyzing the Rashomon Effect and Mitigating Predictive Multiplicity in Gradient Boosting
Segment, Shuffle, and Stitch: A Simple Mechanism for Improving Time-Series Representations
Enhancing Robustness of Graph Neural Networks on Social Media with Explainable Inverse Reinforcement Learning
Rethinking Deep Thinking
Entrywise error bounds for low-rank approximations of kernel matrices
Learning the Optimal Policy for Balancing Multiple Short-Term and Long-Term Rewards
Bridging Geometric States via Generative Modeling
Semantic Feature Learning for Universal Unsupervised Cross-Domain Retrieval
Multimodal foundation world models for generalist embodied agents
Neural Gaffer: Relighting Any Object via Diffusion
Towards Understanding the Working Mechanism of Text-to-Image Diffusion Model
Deep Correlated Prompting for Visual Recognition with Missing Modalities
Continuous Spatiotemporal Events Decoupling through Spike-based Bayesian Computation
Efficient Combinatorial Optimization via Heat Diffusion
Logarithmic Smoothing for Pessimistic Off-Policy Evaluation, Selection and Learning
Improving Sparse Decomposition of Language Model Activations with Gated Sparse Autoencoders
Implicit regularization of multi-task learning and finetuning: multiple regimes of feature reuse
Multi-Label Learning with Stronger Consistency Guarantees
Marginal Causal Flows for Validation and Inference
Scala: Scalable Representation Learning for Vision Transformer
Conservative Fine-Tuning of Diffusion Models from Offline Data
FedNE: Surrogate-Assisted Federated Neighbor Embedding for Privacy-Preserving Dimensionality Reduction
Amortized Bayesian Experimental Design for Decision-Making
On Differentially Private U Statistics
PURE: Prompt Evolution with Graph ODE for Out-of-distribution Fluid Dynamics Modeling
Learning diverse causally emergent representations from time series data
ReGS: Reference-based Controllable Scene Stylization with Gaussian Splatting
Guiding Neural Collapse: Optimising Towards the Nearest Simplex Equiangular Tight Frame
Efficient Algorithm and Improved Regret for RL with Multinomial Logit Function Approximation
XMask3D: Cross-modal Mask Reasoning for Open Vocabulary 3D Semantic Segmentation
End-to-End Ontology Learning with Large Language Models
ReLIZO: Sample Reusable Linear Interpolation-based Zeroth-order Optimization
MutaPLM: Protein Language Modeling for Mutation Explanation and Engineering
GTBench: Uncovering the Strategic Reasoning Capabilities of LLMs via Game-Theoretic Evaluations
Neural Concept Binder
Hierarchical Uncertainty Exploration via Feedforward Posterior Trees
Decoupling Semantic Similarity from Spatial Alignment for Neural Networks.
PGN: The RNN's New Successor is Effective for Long-Range Time Series Forecasting
Controlled maximal variability along with reliable performance in recurrent neural networks
Information-theoretic Generalization Analysis for Expected Calibration Error
Fair Wasserstein Coresets
Towards Flexible 3D Perception: Object-Centric Occupancy Completion Augments 3D Object Detection in Long Sequence
CemiFace: Center-based Semi-hard Synthetic Face Generation for Face Recognition
From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models
Avoiding Undesired Future with Minimal Cost in Non-Stationary Environments
Color-Oriented Redundancy Reduction in Dataset Distillation
Learning 3D Garment Animation from Trajectories of A Piece of Cloth
Policy Aggregation
Auditing Local Explanations is Hard
Predicting Ground State Properties: Constant Sample Complexity and Deep Learning Algorithms
BiDM: Pushing the Limit of Quantization for Diffusion Models
User-Creator Feature Dynamics in Recommender Systems with Dual Influence
Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
Accelerating ERM for data-driven algorithm design using output-sensitive techniques
MAmmoTH2: Scaling Instructions from the Web
Learning Bregman Divergences with Application to Robustness
Permutation-Invariant Autoregressive Diffusion for Graph Generation
Generative Modeling of Molecular Dynamics Trajectories
Toward a Stable, Fair, and Comprehensive Evaluation of Object Hallucination in Large Vision-Language Models
Local Curvature Smoothing with Stein's Identity for Efficient Score Matching
AUC Maximization under Positive Distribution Shift
A Simple and Optimal Approach for Universal Online Learning with Gradient Variations
Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion
Transferable Adversarial Attacks on SAM and Its Downstream Models via Universal Meta Initialization and Gradient Robust Attacks
Text-DiFuse: An Interactive Multi-Modal Image Fusion Framework based on Text-modulated Diffusion Model
MomentumSMoE: Integrating Momentum into Sparse Mixture of Experts
Proving Theorems Recursively
Sketchy Moment Matching: Toward Fast and Provable Data Selection for Finetuning
Causal Discovery from Event Sequences by Local Cause-Effect Attribution
MC-DiT: Contextual Enhancement via Clean-to-Clean Reconstruction for Masked Diffusion Models
Continuously Learning, Adapting, and Improving: A Dual-Process Approach to Autonomous Driving
Parallelizing Linear Transformers with the Delta Rule over Sequence Length
Equivariant Machine Learning on Graphs with Nonlinear Spectral Filters
RobIR: Robust Inverse Rendering for High-Illumination Scenes
Encrypted Data Pruning for Confidential Training of Deep Neural Networks
Learning Diffusion at Lightspeed
Random Function Descent
Transformer Doctor: Diagnosing and Treating Vision Transformers
On the Use of Anchoring for Training Vision Models
ManiPose: Manifold-Constrained Multi-Hypothesis 3D Human Pose Estimation
Measuring Mutual Policy Divergence for Multi-Agent Sequential Exploration
RCDN: Towards Robust Camera-Insensitivity Collaborative Perception via Dynamic Feature-based 3D Neural Modeling
CIFD: Controlled Information Flow to Enhance Knowledge Distillation
Towards Human-AI Complementarity with Predictions Sets
Inverse Factorized Soft Q-Learning for Cooperative Multi-agent Imitation Learning
Is Programming by Example solved by LLMs?
Learning Scene-specific Descriptions via Adaptive Renormalization for Open-vocabulary Scene Graph Generation
Evaluate then Cooperate: Shapley-based View Cooperation Enhancement for Multi-view Clustering
Unified Lexical Representation for Interpretable Visual-Language Alignment
Take A Shortcut Back: Mitigating the Gradient Vanishing for Training Spiking Neural Networks
Optimization Can Learn Johnson Lindenstrauss Embeddings
Synthesize, Partition, then Adapt: Eliciting Diverse Samples from Foundation Models
Combining Statistical Depth and Fermat Distance for Uncertainty Quantification
Beyond Redundancy: Information-aware Unsupervised Multiplex Graph Structure Learning
Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization
Feedback control guides credit assignment in biological circuits
Co-occurrence is not Factual Association in Language Models
Causal vs. Anticausal merging of predictors
Learning on Large Graphs using Intersecting Communities
Interpreting Learned Feedback Patterns in Large Language Models
Towards Flexible Visual Relationship Segmentation
The Implicit Bias of Adam on Separable Data
Structural Inference of Dynamical Systems with Conjoined State Space Models
Large Stepsize Gradient Descent for Non-Homogeneous Two-Layer Networks: Margin Improvement and Fast Optimization
Faster Accelerated First-order Methods for Convex Optimization with Strongly Convex Function Constraints
Universal Online Convex Optimization with $1$ Projection per Round
Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates
Geometric Exploitation for Indoor Panoramic Semantic Segmentation
Communication-Efficient Federated Group Distributionally Robust Optimization
Can an AI Agent Safely Run a Government? Existence of Probably Approximately Aligned Policies
OptCM: The Optimization Consistency Models for Solving Combinatorial Problems in Few Shots
LoRANN: Low-Rank Matrix Factorization for Approximate Nearest Neighbor Search
How In-Context Learning Emerges from Training on Unstructured Data: The Role of Co-Occurrence, Positional Information, and Noise Structures
Multi-Reward Best Policy Identification
DropBP: Accelerating Fine-Tuning of Large Language Models by Dropping Backward Propagation
Unsupervised Object Detection with Theoretical Guarantees
A Polar Coordinate System Explicitly Represents Syntax in Language Models
Hierarchical Selective Classification
Focus On What Matters: Separated Models For Visual-Based RL Generalization
Corruption-Robust Linear Bandits: Minimax Optimality and Gap-Dependent Misspecification
On the Ability of Developers' Training Data Preservation of Learnware
The Feature Speed Formula: a flexible approach to scale hyper-parameters of deep neural networks
Quantum Algorithms for Non-smooth Non-convex Optimization
Human Expertise in Algorithmic Prediction
Advancing Training Efficiency of Deep Spiking Neural Networks through Rate-based Backpropagation
Toward a Theory of Tokenization in LLMs
Reinforcement Learning with Lookahead Information
Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level
Scaling White-Box Transformers for Vision
Data Selection for Task-Specific Model Finetuning
Implicit Bias of Mirror Flow on Separable Data
MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders
Sparse-view Pose Estimation and Reconstruction via Analysis by Generative Synthesis
Stochastic Optimal Control Matching
Linear Causal Representation Learning from Unknown Multi-node Interventions
LiT: Unifying LiDAR "Languages" with LiDAR Translator
Stabilize the Latent Space for Image Autoregressive Modeling: A Unified Perspective
Incentivizing Quality Text Generation via Statistical Contracts
KV Cache is 1 Bit Per Channel: Efficient Large Language Model Inference with Coupled Quantization
Do CLIP Models Always Generalize Better than ImageNet Models?
A theoretical design of concept sets: improving the predictability of Concept Bottleneck Models
Model Collapse Demystified: The Case of Regression
Neural Experts: Mixture of Experts for Implicit Neural Representations
Probabilistic Weather Forecasting with Hierarchical Graph Neural Networks
A Theoretical Perspective for Speculative Decoding Algorithm
Bandits with Preference Feedback: A Stackelberg Game Perspective
Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists
Diffusion Models are Certifiably Robust Classifiers
Communication Efficient Distributed Training with Distributed Lion
Energy-Based Modelling for Discrete and Mixed Data via Heat Equations on Structured Spaces
Training Dynamics of Transformers to Recognize Word Co-occurrence via Gradient Flow Analysis
Unified Generative and Discriminative Training for Multi-modal Large Language Models
Discovery of the Hidden World with Large Language Models
Rethinking Misalignment in Vision-Language Model Adaptation from a Causal Perspective
GREAT Score: Global Robustness Evaluation of Adversarial Perturbation using Generative Models
Average gradient outer product as a mechanism for deep neural collapse
Learning Segmentation from Point Trajectories
Remix-DiT: Mixing Diffusion Transformers for Multi-Expert Denoising
Fishers and Hessians of Continuous Relaxations
Template-free Articulated Gaussian Splatting for Real-time Reposable Dynamic View Synthesis
Improved off-policy training of diffusion samplers
Curriculum Fine-tuning of Vision Foundation Model for Medical Image Classification Under Label Noise
Unified Speech Recognition: A Single Model for Auditory, Visual, and Audiovisual Inputs
Learning Multimodal Behaviors from Scratch with Diffusion Policy Gradient
Supra-Laplacian Encoding for Transformer on Dynamic Graphs
Large Pre-trained time series models for cross-domain Time series analysis tasks
Improving Subgroup Robustness via Data Selection
Speaking Your Language: Spatial Relationships in Interpretable Emergent Communication
Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
The Space Complexity of Approximating Logistic Loss
Direct3D: Scalable Image-to-3D Generation via 3D Latent Diffusion Transformer
Optimal deep learning of holomorphic operators between Banach spaces
Conformalized Credal Set Predictors
HAWK: Learning to Understand Open-World Video Anomalies
Harnessing Heuristics for Deep Reinforcement Learning via Constrained Optimization
Visual Pinwheel Center Act as Geometric Saliency Detector
OccamLLM: Fast and Exact Language Model Arithmetic in a Single Step
Exact, Tractable Gauss-Newton Optimization in Deep Reversible Architectures Reveal Poor Generalization
Measuring Dejavu Memorization Efficiently
An Accelerated Algorithm for Stochastic Bilevel Optimization under Unbounded Smoothness
SPRINQL: Sub-optimal Demonstrations driven Offline Imitation Learning
Lumen: Unleashing Versatile Vision-Centric Capabilities of Large Multimodal Models
Vision-Language Navigation with Energy-Based Policy
Adam with model exponential moving average is effective for nonconvex optimization
GeoNLF: Geometry guided Pose-Free Neural LiDAR Fields
Skinned Motion Retargeting with Dense Geometric Interaction Perception
Test-Time Debiasing of Vision-Language Embeddings
$\text{Di}^2\text{Pose}$: Discrete Diffusion Model for Occluded 3D Human Pose Estimation
The Fine-Grained Complexity of Gradient Computation for Training Large Language Models
Learning to Reason Iteratively and Parallelly for Complex Visual Reasoning Scenarios
Mean-Field Analysis for Learning Subspace-Sparse Polynomials with Gaussian Input
AlterMOMA: Fusion Redundancy Pruning for Camera-LiDAR Fusion Models with Alternative Modality Masking
A Tractable Inference Perspective of Offline RL
JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models
Incorporating Test-Time Optimization into Training with Dual Networks for Human Mesh Recovery
AdaFlow
Sample-Efficient Agnostic Boosting
Calibrating Reasoning in Language Models with Internal Consistency
Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
Sample Complexity of Algorithm Selection Using Neural Networks and Its Applications to Branch-and-Cut
Efficient Sign-Based Optimization: Accelerating Convergence via Variance Reduction
A Primal-Dual-Assisted Penalty Approach to Bilevel Optimization with Coupled Constraints
MAC Advice for facility location mechanism design
The Minimax Regret of Sequential Probability Assignment, Contextual Shtarkov Sums, and Contextual Normalized Maximum Likelihood
Learning Formal Mathematics From Intrinsic Motivation
Partial Structure Discovery is Sufficient for No-regret Learning in Causal Bandits
Disentangled Representation Learning in Non-Markovian Causal Systems
Learning from higher-order correlations, efficiently: hypothesis tests, random features, and neural networks
Transformer Efficiently Learns Low-dimensional Target Functions In-context
BAKU: An Efficient Transformer for Multi-Task Policy Learning
Automatic Outlier Rectification via Optimal Transport
The Mamba in the Llama: Distilling and Accelerating Hybrid Models
Towards Estimating Bounds on the Effect of Policies under Unobserved Confounding
Protecting Your LLMs with Information Bottleneck
Graph Edit Distance with General Costs Using Neural Set Divergence
Online Convex Optimisation: The Optimal Switching Regret for all Segmentations Simultaneously
Explaining Text Datasets with Language Parameters
Lower Bounds of Uniform Stability in Gradient-Based Bilevel Algorithms for Hyperparameter Optimization
Revisiting the Integration of Convolution and Attention for Vision Backbone
Transformation-Invariant Learning and Theoretical Guarantees for OOD Generalization
RAMP: Boosting Adversarial Robustness Against Multiple $l_p$ Perturbations
Derandomizing Multi-Distribution Learning
Leveraging Tumor Heterogeneity: Heterogeneous Graph Representation Learning for Cancer Survival Prediction in Whole Slide Images
DisCEdit: Model Editing by Identifying Discriminative Components
TransAgent: Transfer Vision-Language Foundation Models with Heterogeneous Agent Collaboration
Evaluation of Text-to-Video Generation Models: A Dynamics Perspective
Adaptive Variance Reduction for Stochastic Optimization under Weaker Assumptions
EigenVI: score-based variational inference with orthogonal function expansions
Dynamical Conditional Optimal Transport through Simulation-Free Flows
Knowledgeable Agents by Offline Reinforcement Learning from Large Language Model Rollouts
UPS: Unified Projection Sharing for Lightweight Single-Image Super-resolution and Beyond
Distilling Costly Set Functions to Parametric Families
SyncVIS: Synchronized Video Instance Segmentation
Future Motion Estimation via Event Sequence Diffusion
Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
Improving Equivariant Model Training via Constraint Relaxation
Out-of-Distribution Detection with a Single Unconditional Diffusion Model
Efficient Recurrent Off-Policy RL Requires a Context-Encoder-Specific Learning Rate
Improved Distribution Matching Distillation for Fast Image Synthesis
Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing
An Image is Worth 32 Tokens for Reconstruction and Generation
Microstructures and Accuracy of Graph Recall by Large Language Models
Consistency Purification: Effective and Efficient Diffusion Purification towards Certified Robustness
What Matters in Graph Class Incremental Learning? An Information Preservation Perspective
One-to-Normal: Anomaly Personalization for Few-shot Anomaly Detection
Distributed Least Squares in Small Space via Sketching and Bias Reduction
DG-SLAM: Robust Dynamic Gaussian Splatting SLAM with Hybrid Pose Optimization
Verified Safe Reinforcement Learning for Neural Network Dynamic Models
Graph Neural Flows for Unveiling Systemic Interactions Among Irregularly Sampled Time Series
SEL-BALD: Deep Bayesian Active Learning for Selective Labeling with Instance Rejection
Physics-Informed Variational State-Space Gaussian Processes
Gorilla: Teaching LLMs to Use Tools
Interpolating Item and User Fairness in Multi-Sided Recommendations
SELMA: Learning and Merging Skill-Specific Text-to-Image Experts with Auto-Generated Data
Neural Persistence Dynamics
Self-Evolution Decoding for Improving Factuality in Large Language Models
Approximation-Aware Bayesian Optimization
UQE: A Query Engine for Unstructured Databases
Multi-LLM Debate: Framework, Principals, and Interventions
UniFL: Improve Stable Diffusion via Unified Feedback Learning
Off-Policy Selection for Initiating Human-Centric Experimental Design
On the Expressive Power of Tree-Structured Probabilistic Circuits
Verified Code Transpilation with LLMs
Learning-Augmented Dynamic Submodular Maximization
The Iterative Optimal Brain Surgeon: Faster Sparse Recovery by Leveraging Second-Order Information
On the Curses of Future and History in Future-dependent Value Functions for Off-policy Evaluation
The Impact of Initialization on the Finetuning Dynamics in LoRA
Online Estimation via Offline Estimation: An Information-Theoretic Framework
MiniCache: KV Cache Compression in Depth Dimension for Large Language Models
Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation
A Label is Worth A Thousand Images in Dataset Distillation
UniGAD: Unifying Multi-level Graph Anomaly Detection
Learning Human-like Representations to Enable Learning Human Values
Scaling Laws with Vocabulary: Larger Models Deserve Larger Vocabularies
HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach
Adversarial Generation of Hierarchical Gaussians for 3D Generative Model
Generalizablity of Memorization Neural Network
Understanding Information Storage and Transfer in Multi-Modal Large Language Models
Treatment of Statistical Estimation Problems in Randomized Smoothing for Adversarial Robustness
A Nearly Optimal and Low-Switching Algorithm for Reinforcement Learning with General Function Approximation
Minimizing Hyperspherical Energy for Diverse Deep Ensembling
Face2QR: A Unified Framework for Aesthetic, Face-Preserving, and Scannable QR Code Generation
Universality of AdaGrad Stepsizes for Stochastic Optimization: Inexact Oracle, Acceleration and Variance Reduction
OwMatch: Conditional Self-Labeling with Consistency for Open-world Semi-Supervised Learning
Sequoia: Scalable and Robust Speculative Decoding
Reranking Laws for Language Generation: A Communication-Theoretic Perspective
Super Consistency of Neural Network Landscapes and Learning Rate Transfer
Aligning to Thousands of Varying Preferences via System Message Generalization
MIDGArD: Modular Interpretable Diffusion over Graphs for Articulated Designs
DeMo: Decoupling Motion Forecasting into Directional Intentions and Dynamic States
EM Distillation for One-step Diffusion Models
Trace is the New AutoDiff: Unlocking Efficient Optimization of Computational Workflows
3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability
Uncertainty-based Offline Variational Bayesian Reinforcement Learning for Robustness under Diverse Data Corruptions
Learning from Highly Sparse Spatio-temporal Data
Monomial Matrix Group Equivariant Neural Functional Networks
Interaction-Force Transport Gradient Flows
Regret Minimization in Stackelberg Games with Side Information
No Free Lunch in LLM Watermarking: Trade-offs in Watermarking Design Choices
Graph Coarsening with Message-Passing Guarantees
Learning Successor Features the Simple Way
OmniJARVIS: Unified Vision-Language-Action Tokenization Enables Open-World Instruction Following Agents
DeTeCtive: Detecting AI-generated Text via Multi-Level Contrastive Learning
Learning Truncated Causal History Model for Video Restoration
F-OAL: Foward-only Online Analytic Learning with Fast Training and Low Memory Footprint in Class Incremental Learning
Improving Deep Learning Performance through Constrained Parameter Regularization
GSDF: 3DGS Meets SDF for Improved Neural Rendering and Reconstruction
Parametric model reduction of mean-field and stochastic systems via higher-order action matching
RG-SAN: Rule-Guided Spatial Awareness Network for End-to-End 3D Referring Expression Segmentation
From Causal to Concept-Based Representation Learning
How Control Information Influences Multilingual Text Image Generation and Editing?
AsCAN: Asymmetric Convolution-Attention Networks for Efficient Recognition and Generation
Fast samplers for Inverse Problems in Iterative Refinement models
Easy-to-Hard Generalization: Scalable Alignment Beyond Human Supervision
Symmetry Discovery Beyond Affine Transformations
Identifiable Object-Centric Representation Learning via Probabilistic Slot Attention
Reinforcement Learning Under Latent Dynamics: Toward Statistical and Algorithmic Modularity
MAGIS: LLM-Based Multi-Agent Framework for GitHub Issue Resolution
GRANOLA: Adaptive Normalization for Graph Neural Networks
Near-Optimal Distributed Minimax Optimization under the Second-Order Similarity
Tighter Convergence Bounds for Shuffled SGD via Primal-Dual Perspective
IODA: Instance-Guided One-shot Domain Adaptation for Super-Resolution
Protected Test-Time Domain Adaptation via Online Entropy Matching
The Evolution of Statistical Induction Heads: In-Context Learning Markov Chains
Towards Safe Concept Transfer of Multi-Modal Diffusion via Causal Representation Editing
Kaleido Diffusion: Improving Conditional Diffusion Models with Autoregressive Latent Modeling
Post-Robustness of Backdoor Purification
Expert-level protocol translation for self-driving labs
Most Influential Subset Selection: Challenges, Promises, and Beyond
Empowering Visible-Infrared Person Re-Identification with Large Foundation Models
Tell What You Hear From What You See - Video to Audio Generation Through Text
Continual learning with the neural tangent ensemble
Watermarking Makes Language Models Radioactive
Optimization Efficient Open-World Visual Region Recognition
Neural network learns low-dimensional polynomials with SGD near the information-theoretic limit
A Closer Look at the CLS Token for Cross-Domain Few-Shot Learning
HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning
Differentially Private Equivalence Testing for Continuous Distributions and Application
Dynamic Neural Regeneration: Enhancing Deep Learning Generalization on Small Datasets
Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
Enhancing LLM’s Cognition via Structurization
Self-Play Fine-tuning of Diffusion Models for Text-to-image Generation
NeuralClothSim: Neural Deformation Fields Meet the Thin Shell Theory
Achieving $\tilde{O}(1/\epsilon)$ Sample Complexity for Constrained Markov Decision Process
Apathetic or Empathetic? Evaluating LLMs' Emotional Alignments with Humans
Hallo3D: Multi-Modal Hallucination Detection and Mitigation for Consistent 3D Content Generation
Spectral Editing of Activations for Large Language Model Alignment
SuperDeepFool: a new fast and accurate minimal adversarial attack
Algorithmic Capabilities of Random Transformers
Sequence-Augmented SE(3)-Flow Matching For Conditional Protein Generation
Multi-Stage Predict+Optimize for (Mixed Integer) Linear Programs
Learning to Merge Tokens via Decoupled Embedding for Efficient Vision Transformers
Causal Dependence Plots
Learning Partitions from Context
Transformers as Game Players: Provable In-context Game-playing Capabilities of Pre-trained Models
Effective Sharpness Aware Minimization Requires Layerwise Perturbation Scaling
Smoothie: Label Free Language Model Routing
Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning
The Implicit Bias of Heterogeneity towards Invariance: A Study of Multi-Environment Matrix Sensing
OT4P: Unlocking Effective Orthogonal Group Path for Permutation Relaxation
BELM: Bidirectional Explicit Linear Multi-step Sampler for Exact Inversion in Diffusion Models
The Limits of Transfer Reinforcement Learning with Latent Low-rank Structure
Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models
Span-Based Optimal Sample Complexity for Weakly Communicating and General Average Reward MDPs
The Empirical Impact of Neural Parameter Symmetries, or Lack Thereof
Tetrahedron Splatting for 3D Generation
A Surprisingly Simple Approach to Generalized Few-Shot Semantic Segmentation
An Efficient Memory Module for Graph Few-Shot Class-Incremental Learning
Particle Semi-Implicit Variational Inference
Linear Transformers are Versatile In-Context Learners
Exploration by Learning Diverse Skills through Successor State Measures
Capability v.s. Behavior in Compositional Generalization: A Learning Dynamics Perspective
OctreeOcc: Efficient and Multi-Granularity Occupancy Prediction Using Octree Queries
Noether's Razor: Learning Conserved Quantities
Learning to Mitigate Externalities: the Coase Theorem with Hindsight Rationality
Policy Mirror Descent with Lookahead
Shaping the distribution of neural responses with interneurons in a recurrent circuit model
CSPG: Crossing Sparse Proximity Graphs for Approximate Nearest Neighbor Search
Carrot and Stick: Eliciting Comparison Data and Beyond
Recovering Complete Actions for Cross-dataset Skeleton Action Recognition
Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
On the Impacts of the Random Initialization in the Neural Tangent Kernel Theory
Private Stochastic Convex Optimization with Heavy Tails: Near-Optimality from Simple Reductions
Implicit Regularization of Sharpness-Aware Minimization for Scale-Invariant Problems
Penalty-based Methods for Simple Bilevel Optimization under Hölderian Error Bounds
Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Models
Weight decay induces low-rank attention layers
Provable Partially Observable Reinforcement Learning with Privileged Information
Attention Temperature Matters in ViT-Based Cross-Domain Few-Shot Learning
LookHere: Vision Transformers with Directed Attention Generalize and Extrapolate
Measuring Goal-Directedness
Sample-efficient Simulation-based Inference for Urban Travel Demand Calibration
Nonlinear dynamics of localization in neural receptive fields
3D Equivariant Pose Regression via Direct Wigner-D Harmonics Prediction
A Rank-Based Metric for Evaluating Large Language Models
VisionLLM v2: An End-to-End Generalist Multimodal Large Language Model for Hundreds of Vision-Language Tasks
Estimating Generalization Performance Along the Trajectory of Proximal SGD in Robust Regression
Preference Learning of Latent Decision Utilities with a Human-like Model of Preferential Choice
HaloScope: Harnessing Unlabeled LLM Generations for Hallucination Detection
One for All: Multi-Domain Joint Training for Point Cloud Based 3D Object Detection
Implicit Curriculum in Procgen Made Explicit
Calibrated Self-Rewarding Vision Language Models
SEEV: Synthesis with Efficient Exact Verification for ReLU Neural Barrier Functions
Toward Real Ultra Image Segmentation: Leveraging Surrounding Context to Cultivate General Segmentation Model
Text-Aware Diffusion for Policy Learning
Towards a "Universal Translator" for Neural Dynamics at Single-Cell, Single-Spike Resolution
UGC: Universal Graph Coarsening
Optimistic Verifiable Training by Controlling Hardware Nondeterminism
Learning the Latent Causal Structure for Modeling Label Noise
DiffSF: Diffusion Models for Scene Flow Estimation
Learning De-Biased Representations for Remote-Sensing Imagery
Analytic Nonlinear Dynamical System Identification with Non-asymptotic Guarantees
Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning
Recurrent Reinforcement Learning with Memoroids
Few-Shot Adversarial Prompt Learning on Vision-Language Models
Evidential Mixture Machines: Deciphering Multi-Label Correlations for Active Learning Sensitivity
Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledge
S2HPruner: Soft-to-Hard Distillation Bridges the Discretization Gap in Pruning
DuQuant: Distributing Outliers via Dual Transformation Makes Stronger Quantized LLMs
Learning-Augmented Approximation Algorithms for Maximization Problems
Tight Rates for Bandit Control Beyond Quadratics
Non-asymptotic Global Convergence Analysis of BFGS with the Armijo-Wolfe Line Search
Demystifying Encoding: Detecting Explanations that Hide Information in the Selection
Latent functional maps
RGMDT: Return-Gap-Minimizing Decision Tree Extraction in Non-Euclidean Metric Space
Learning Cooperative Trajectory Representations for Motion Forecasting
Once Read is Enough: Finetuning-free Language Models with Cluster-guided Sparse Experts for Long-tail Domain Knowledge
Polynomial-Time Computation of Exact $\Phi$-Equilibria in Polyhedral Games
SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling
Improving the Training of Rectified Flows
Quality-Improved and Property-Preserved Polarimetric Imaging via Complementarily Fusing
Bounds for the smallest eigenvalue of the NTK for arbitrary spherical data of arbitrary dimension
Learn Incrementally from An Ongoing Trajectory: A Provable In-Trajectory Inverse Reinforcement Learning Framework
MaNo: Exploiting Matrix Norm for Unsupervised Accuracy Estimation Under Distribution Shifts
Interventional Causal Discovery in a Mixture of DAGs
Directional Smoothness and Gradient Methods: Convergence and Adaptivity
Neglected Hessian component explains mysteries in sharpness regularization
How many classifiers do we need?
Practical Bayesian Algorithm Execution via Posterior Sampling
Entropy Coding of Large Unordered Data Structures
AR-Pro: Anomaly Explanation and Repair with Formal Properties
Predictive Attractor Models
Nonstationary Sparse Spectral Permanental Process
Controlling Multiple Errors Simultaneously with a PAC-Bayes Bound
Unifying Generation and Prediction on Graphs with Latent Graph Diffusion
MotionCraft: Physics-Based Zero-Shot Video Generation
Latent Intrinsics Emerge from Training to Relight
Fine-grained Analysis of In-context Linear Estimation
Diffusion Models With Learned Adaptive Noise
Maximum Entropy Reinforcement Learning via Energy-Based Normalizing Flow
Optimal Aggregation of Prediction Intervals under Unsupervised Domain Shift
Shuffling Gradient-Based Methods for Nonconvex-Concave Minimax Optimization
UDKAG: Augmenting Large Vision-Language Models with Up-to-Date Knowledge
Coherent 3D Scene Diffusion From a Single RGB Image
VISA: Variational Inference with Sequential Sample-Average Approximations
Accelerated Regularized Learning in Finite N-Person Games
Listenable Maps for Zero-Shot Audio Classifiers
Unitary Convolutions for Learning on Graphs and Groups
Quadratic Quantum Variational Monte Carlo
John Ellipsoids via Lazy Updates
Replicable Uniformity Testing
QUEST: Quadruple Multimodal Contrastive Learning with Constraints and Self-Penalization
Practical $0.385$-Approximation for Submodular Maximization Subject to a Cardinality Constraint
Improved Sample Complexity for Multiclass PAC Learning
Optimal Flow Matching: Learning Straight Trajectories in Just One Step
This Too Shall Pass: Removing Stale Observations in Dynamic Bayesian Optimization
Robust Conformal Prediction Using Privileged Information
A generalized neural tangent kernel for surrogate gradient learning
Operator World Models for Reinforcement Learning
How to Use Diffusion Priors under Sparse Views?
Rethinking Model-based, Policy-based, and Value-based Reinforcement Learning via the Lens of Representation Complexity
Input-to-State Stable Coupled Oscillator Networks for Closed-form Model-based Control in Latent Space
Multi-Scale Representation Learning for Protein Fitness Prediction
Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation
Repurposing Language Models into Embedding Models: Finding the Compute-Optimal Recipe
Data Attribution for Text-to-Image Models by Unlearning Synthesized Images
Identifying Latent State-Transition Processes for Individualized Reinforcement Learning
QGFN: Controllable Greediness with Action Values
Chain of Thoughtlessness? An Analysis of CoT in Planning
Lyapunov functions: a long-standing open problem in mathematics, with symbolic transformers
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging
Rethinking 3D Convolution in $\ell_p$-norm Space
An Analysis of Elo Rating Systems via Markov Chains
On the Saturation Effects of Spectral Algorithms in Large Dimensions
Large Language Models Play StarCraft II:Benchmarks and A Chain of Summarization Approach
UQ-Guided Hyperparameter Optimization for Iterative Learners
DRIP: Unleashing Diffusion Priors for Joint Foreground and Alpha Prediction in Image Matting
To Believe or Not to Believe Your LLM
RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
Towards Croppable Implicit Neural Representations
Symmetries in Overparametrized Neural Networks: A Mean Field View
Improved Bayes Regret Bounds for Multi-Task Hierarchical Bayesian Bandit Algorithms
A Canonization Perspective on Invariant and Equivariant Learning
Advection Augmented Convolutional Neural Networks
FuseMoE: Mixture-of-Experts Transformers for Fleximodal Fusion
Robust Prompt Optimization for Defending Language Models Against Jailbreaking Attacks
High-Resolution Image Harmonization with Adaptive-Interval Color Transformation
Stochastic Zeroth-Order Optimization under Strongly Convexity and Lipschitz Hessian: Minimax Sample Complexity
Towards Neuron Attributions in Multi-Modal Large Language Models
Autoregressive Image Diffusion: Generating Image Sequence and Application in MRI
Easy Regional Contrastive Learning of Expressive Visual Fashion Representations
Dynamic Multi-Object 3D Grounding with Language Informed Spatial Attention
MV2Cyl: Reconstructing 3D Extrusion Cylinders from Multi-View Images
Query-Based Adversarial Prompt Generation
Instructor-inspired Machine Learning for Robust Molecular Property Prediction
Agent Planning with World Knowledge Model
Does Worst-Performing Agent Lead the Pack? Analyzing Agent Dynamics in Unified Distributed SGD
Accurate and Steady Inertial Pose Estimation through Sequence Structure Learning and Modulation
Reinforcement Learning with LTL and $\omega$-Regular Objectives via Optimality-Preserving Translation to Average Rewards
Identifiable Shared Component Analysis of Unpaired Multimodal Mixtures
A Universal Growth Rate for Learning with Smooth Surrogate Losses
Customizing Language Models with Instance-wise LoRA for Sequential Recommendation
Transformers are Minimax Optimal Nonparametric In-Context Learners
Soft-Label Integration for Robust Toxicity Classification
Your contrastive learning problem is secretly a distribution alignment problem
Induced Model Matching: Restricted Models Help Train Full-Featured Models
Fast and Memory-Efficient Video Diffusion Using Streamlined Inference
Are Self-Attentions Effective for Time Series Forecasting?
Improved Algorithms for Contextual Dynamic Pricing
MaskFactory: Towards High-quality Synthetic Data Generation For Dichotomous Image Segmentation
A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings
Causal Effect Identification in a Sub-Population with Latent Variables
S-SOS: Stochastic Sum-Of-Squares for Parametric Polynomial Optimization
ProgressEditor: Simple Progression is All You Need for High-Quality 3D Scene Editing
Similarity-Navigated Conformal Prediction for Graph Neural Networks
Scaling Retrieval-Based Language Models with a Trillion-Token Datastore
SkiLD: Unsupervised Skill Discovery Guided by Local Dependencies
Policy-shaped prediction: avoiding distractions in model-based RL
Set-based Neural Network Encoding Without Weight Tying
Belief-State Query Policies for Planning With Preferences Under Partial Observability
Unlocking the Potential of Global Human Expertise
Flexible mapping of abstract domains by grid cells via self-supervised extraction and projection of generalized velocity signals
Convergence of $\log(1/\epsilon)$ for Gradient-Based Algorithms in Zero-Sum Games without the Condition Number: A Smoothed Analysis
Interpretable Image Classification with Adaptive Prototype-based Vision Transformers
Precipitation Downscaling with Spatiotemporal Video Diffusion
Inverse M-Kernels for Linear Universal Approximators of Non-Negative Functions
Propensity Score Alignment of Unpaired Multimodal Data
Happy: A Debiased Learning Framework for Continual Generalized Category Discovery
Piecewise-Stationary Bandits with Knapsacks
Near-Equivalence Between Bounded Regret and Delay Robustness in Interactive Decision Making
GraphMorph: Tubular Structure Extraction by Morphing Predicted Graphs
Optimizing Automatic Differentiation with Deep Reinforcement Learning
Autobidder's Dilemma: Why More Sophisticated Autobidders Lead to Worse Auction Efficiency
Attack-Aware Noise Calibration for Differential Privacy
Contrastive losses as generalized models of global epistasis
Rethinking Optimal Transport in Offline Reinforcement Learning
On the Target-kernel Alignment: a Unified Analysis with Kernel Complexity
Fast Last-Iterate Convergence of Learning in Games Requires Forgetful Algorithms
Fixed Confidence Best Arm Identification in the Bayesian Setting
Improving Logits-based Detector without Logits from Black-box LLMs
Surge Phenomenon in Optimal Learning Rate and Batch Size Scaling
An Equivalence Between Static and Dynamic Regret Minimization
The Price of Implicit Bias in Adversarially Robust Generalization
A Novel Approach to Loss Landscape Characterization without Over-Parametrization
Least Squares Regression Can Exhibit Under-Parameterized Double Descent
KptLLM: Unveiling the Power of Large Language Model for Keypoint Comprehension
Dual Cone Gradient Descent for Training Physics-Informed Neural Networks
Image Copy Detection for Diffusion Models
Nonparametric Classification on Low Dimensional Manifolds using Overparameterized Convolutional Residual Networks
Rough Transformers: Lightweight Continuous-Time Sequence Modelling with Path Signatures
Brain-JEPA: Brain Dynamics Foundation Model with Gradient Positioning and Spatiotemporal Masking
Metric Space Magnitude for Evaluating the Diversity of Latent Representations
CigTime: Corrective Instruction Generation Through Inverse Motion Editing
Conditional Synthesis of 3D Molecules with Time Correction Sampler
Test-Time Adaptation Induces Stronger Accuracy and Agreement-on-the-Line
Adaptive Important Region Selection with Reinforced Hierarchical Search for Dense Object Detection
Achieving Optimal Clustering in Gaussian Mixture Models with Anisotropic Covariance Structures
TALoS: Enhancing Semantic Scene Completion via Test-time Adaptation on the Line of Sight
Amortizing intractable inference in diffusion models for vision, language, and control
Automated Label Unification for Multi-Dataset Semantic Segmentation with GNNs
Optimal Multi-Fidelity Best-Arm Identification
Wormhole Loss for Partial Shape Matching
GOMAA-Geo: GOal Modality Agnostic Active Geo-localization
Panacea: Pareto Alignment via Preference Adaptation for LLMs
Dual Lagrangian Learning for Conic Optimization
TrAct: Making First-layer Pre-Activations Trainable
Understanding the Gains from Repeated Self-Distillation
Fine-Grained Dynamic Framework for Bias-Variance Joint Optimization on Data Missing Not at Random
An Information Theoretic Perspective on Conformal Prediction
Biologically-Motivated Learning Model for Instructed Visual Processing
Approximating the Top Eigenvector in Random Order Streams
DiffusionBlend: Learning 3D Image Prior through Position-aware Diffusion Score Blending for 3D Computed Tomography Reconstruction
Selective Explanations
Online Learning of Delayed Choices
DHA: Learning Decoupled-Head Attention from Transformer Checkpoints via Adaptive Heads Fusion
Decision-Focused Learning with Directional Gradients
To Learn or Not to Learn, That is the Question
Neur2BiLO: Neural Bilevel Optimization
Denoising Diffusion Path: Attribution Noise Reduction with An Auxiliary Diffusion Model
GFlowNet Assisted Biological Sequence Editing
HC-GAE: The Hierarchical Cluster-based Graph Auto-Encoder for Graph Representation Learning
Diffusion Twigs with Loop Guidance for Conditional Graph Generation
DEX: Data Channel Extension for Efficient CNN Inference on Tiny AI Accelerators
Private Online Learning via Lazy Algorithms
Long-range Brain Graph Transformer
Efficient Leverage Score Sampling for Tensor Train Decomposition
Persistent Test-time Adaptation in Recurring Testing Scenarios
Graph Convolutions Enrich the Self-Attention in Transformers!
Searching for Efficient Linear Layers over a Continuous Space of Structured Matrices
MatFormer: Nested Transformer for Elastic Inference
PrefPaint: Aligning Image Inpainting Diffusion Model with Human Preference
TrajCLIP: Pedestrian trajectory prediction method using contrastive learning and idempotent networks
Label Noise: Ignorance Is Bliss
Found in the Middle: How Language Models Use Long Contexts Better via Plug-and-Play Positional Encoding
Compositional Generalization Across Distributional Shifts with Sparse Tree Operations
Trajectory Flow Matching with Applications to Clinical Time Series Modelling
Expected Probabilistic Hierarchies
Diffusion Model-based Numerical Tabular Data Imputation: A Wasserstein Gradient Flow Perspective
AlphaPruning: Using Heavy-Tailed Self Regularization Theory for Improved Layer-wise Pruning of Large Language Models
Non-Stationary Learning of Neural Networks with Automatic Soft Parameter Reset
A PID Controller Approach for Adaptive Probability-dependent Gradient Decay in Model Calibration
Enhancing Chess Reinforcement Learning with Graph Representation
The Factorization Curse: Which Tokens You Predict Underlie the Reversal Curse and More
Self-Healing Machine Learning: A Framework for Autonomous Adaptation in Real-World Environments
On the Implicit Bias of Predicting in Latent Space in Self Supervised Learning
Symmetries In-Context: Universal Self-Supervised Learning through Contextual World Models
Overcoming Brittleness in Pareto-Optimal Learning Augmented Algorithms
A Simple Image Segmentation Framework via In-Context Examples
Discovering Preference Optimization Algorithms with and for Large Language Models
Frozen-DETR: Enhancing DETR with Image Understanding from Frozen Foundation Models
MKGL: Mastery of a Three-Word Language
Functional Bilevel Optimization for Machine Learning
Poisson Variational Autoencoder
Nuclear Norm Regularization for Deep Learning
Image-aware Evaluation of Generated Medical Reports
Active Learning of General Halfspaces: Label Queries vs Membership Queries
Exploring Token Pruning in Vision State Space Models
CountGD: Multi-Modal Open-World Counting
SpeAr: A Spectral Approach for Zero-Shot Node Classification
Lookback Prophet Inequalitites
Disentangled Unsupervised Skill Discovery for Efficient Hierarchical Reinforcement Learning
StreamingDialogue: Prolonged Dialogue Learning via Long Context Compression with Minimal Losses
Fully First-Order Methods for Linearly Constrained Bilevel Optimization
A Robust Mixed-Effects Bandit Algorithm for Assessing Mobile Health Interventions
Structure Consistent Gaussian Splatting with Matching Prior for Few-shot Novel View Synthesis
TrackIME: Enhanced Video Point Tracking via Instance Motion Estimation
Fairness-Aware Meta-Learning via Nash Bargaining
Transition Constrained Bayesian Optimization via Markov Decision Processes
Neural Assets: 3D-Aware Multi-Object Scene Synthesis with Image Diffusion Models
Fractal Patterns May Illuminate the Success of Next-Token Prediction
Is the MMI Criterion Necessary for Explanation? Degenerating Non-causal Features to Plain Noise
What Rotary Position Embedding Can Tell Us: Identifying Query and Key Weights Corresponding to Basic Syntactic or High-level Semantic Information
Exploring DCN-like architecture for fast image generation with arbitrary resolution
Fair Bilevel Neural Network (FairBiNN): On Balancing fairness and accuracy via Stackelberg Equilibrium
Robust Graph Neural Networks via Unbiased Aggregation
Introducing Spectral Attention for Long-Range Dependency in Time Series Forecasting
Fair Secretaries with Unfair Predictions
Not so griddy: Internal representations of RNNs path integrating more than one agent
Abstract Reward Processes: Leveraging State Abstraction for Consistent Off-Policy Evaluation
What matters when building vision-language models?
Generalization Analysis for Label-Specific Representation Learning
Approximately Equivariant Neural Processes
Scalable DBSCAN with Random Projections
Semi-Supervised Sparse Gaussian Classification: Provable Benefits of Unlabeled Data
Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models
Hardness of Learning Neural Networks under the Manifold Hypothesis
Bayesian Identification of the Hamiltonian Inductive Bias in Dynamical Systems
QuaRot: Outlier-Free 4-Bit Inference in Rotated LLMs
Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL
DeltaDock: A Unified Framework for Accurate, Efficient, and Physically Reliable Molecular Docking
Generalizing CNNs to graphs with learnable neighborhood quantization
Breaking the curse of dimensionality in structured density estimation
ReMAP: Neural Model Reprogramming with Network Inversion and Retrieval-Augmented Mapping for Adaptive Motion Forecasting
UMFC: Unsupervised Multi-Domain Feature Calibration for Vision-Language Models
Learning Optimal Lattice Vector Quantizers for End-to-end DNN Image Compression
Dissecting Query-Key Interaction in Vision Transformers
From Linear to Linearizable Optimization: A Novel Framework with Applications to Stationary and Non-stationary DR-submodular Optimization
UniDSeg: Unified Cross-Domain 3D Semantic Segmentation via Visual Foundation Models Prior
Towards Understanding How Transformers Learn In-context Through a Representation Learning Lens
One-Shot Safety Alignment for Large Language Models via Optimal Dualization
Classification Diffusion Models: Revitalizing Density Ratio Estimation
Context-aware testing: A new paradigm for tabular model testing
RankUp: Boosting Semi-Supervised Regression with an Auxiliary Ranking Classifier
Self-Consuming Generative Models with Curated Data Provably Optimize Human Preferences
Can neural operators always be continuously discretized?
Is A Picture Worth A Thousand Words? Delving Into Spatial Reasoning for Vision Language Models
On Differentially Private Subspace Estimation in a Distribution-Free Setting
Structured Matrix Basis for Multivariate Time Series Forecasting with Interpretable Dynamics
Online Weighted Paging with Unknown Weights
Neural Krylov Iteration for Accelerating Linear System Solving
Light Unbalanced Optimal Transport
Axioms for AI Alignment from Human Feedback
Oja's Algorithm for Sparse PCA
InversionView: A General-Purpose Method for Reading Information from Neural Activations
Learning Macroscopic Dynamics from Partial Microscopic Observations
IF-Font: Ideographic Description Sequence-Following Font Generation
On Statistical Rates and Provably Efficient Criteria of Latent Diffusion Transformers (DiTs)
Distributional regression: CRPS-error bounds for model fitting, model selection and convex aggregation
Robust Reinforcement Learning from Corrupted Human Feedback
Generative Forests
Credit Attribution and Stable Compression
Text-Guided Attention is All You Need for Zero-Shot Robustness in Vision-Language Models
One-to-Multiple: A Progressive Style Transfer Unsupervised Domain-Adaptive Framework for Kidney Tumor Segmentation
Stopping Bayesian Optimization with Probabilistic Regret Bounds
No-regret Bandit Exploration based on Soft Tree Ensemble Model
OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioning
Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation
Convolutions and More as Einsum: A Tensor Network Perspective with Advances for Second-Order Methods
ParallelEdits: Efficient Multi-Aspect Text-Driven Image Editing with Attention Grouping
A Unified Principle of Pessimism for Offline Reinforcement Learning under Model Mismatch
AnyFit: Controllable Virtual Try-on for Any Combination of Attire Across Any Scenario
Instruction-Guided Visual Masking
Sequential Decision Making with Expert Demonstrations under Unobserved Heterogeneity
UnSeg: One Universal Unlearnable Example Generator is Enough against All Image Segmentation
Test-time Aggregation for Collaborative Filtering
Efficient $\Phi$-Regret Minimization with Low-Degree Swap Deviations in Extensive-Form Games
FedGMKD: An Efficient Prototype Federated Learning Framework through Knowledge Distillation and Differential Aggregation
Estimating Heterogeneous Treatment Effects by Combining Weak Instruments and Observational Data
Splatter a Video: Video Gaussian Representation for Versatile Processing
Soft Superpixel Neighborhood Attention
A Non-parametric Direct Learning Approach to Heterogeneous Treatment Effect Estimation under Unmeasured Confounding
Fast Encoder-Based 3D from Casual Videos via Point Track Processing
POCA: Partially Observable Cost-Aware Active-Learning
Revealing Distribution Discrepancy by Sampling Transfer in Unlabeled Data
Secret Collusion among Generative AI Agents
ChatQA: Surpassing GPT-4 on Conversational QA and RAG
Linguistic Collapse: Neural Collapse in (Large) Language Models
Adam on Local Time: Addressing Nonstationarity in RL with Relative Adam Timesteps
LSH-MoE: Communication-efficient MoE Training via Locality-Sensitive Hashing
Robust Sleep Staging over Incomplete Multimodal Physiological Signals via Contrastive Imagination
Multistable Shape from Shading Emerges from Patch Diffusion
Guiding a Diffusion Model with a Bad Version of Itself
DeTikZify: Synthesizing Graphics Programs for Scientific Figures and Sketches with TikZ
Fast yet Safe: Early-Exiting with Risk Control
The Fairness-Quality Tradeoff in Clustering
InfLLM: Training-Free Long-Context Extrapolation for LLMs with an Efficient Context Memory
Hybrid Reinforcement Learning Breaks Sample Size Barriers In Linear MDPs
Vivid-ZOO: Multi-View Video Generation with Diffusion Model
VisMin: Visual Minimal-Change Understanding
Bridging Multicalibration and Out-of-distribution Generalization Beyond Covariate Shift
Learning Discrete Concepts in Latent Hierarchical Models
Efficient LLM Jailbreak via Adaptive Dense-to-sparse Constrained Optimization
Entropy testing and its application to testing Bayesian networks
Causal Contrastive Learning for Counterfactual Regression Over Time
Multilinear Mixture of Experts: Scalable Expert Specialization through Factorization
Discovering Creative Behaviours through DUPLEX: Diverse Universal Features for Policy Exploration
Stability and Generalization of Asynchronous SGD: Sharper Bounds Beyond Lipschitz and Smoothness
Opponent Modeling with In-context Search
VeLoRA: Memory Efficient Training using Rank-1 Sub-Token Projections
Fair Allocation in Dynamic Mechanism Design
Disentangling and mitigating the impact of task similarity for continual learning
MALT Powers Up Adversarial Attacks
A Recipe for Charge Density Prediction
Does Reasoning Emerge? Examining the Probabilities of Causation in Large Language Models
Historical Test-time Prompt Tuning for Vision Foundation Models
Text-Guided Image Editing in Around 7 Steps with Invertible Consistency Distillation
Using Noise to Infer Aspects of Simplicity Without Learning
VCR-GauS: View Consistent Depth-Normal Regularizer for Gaussian Surface Reconstruction
Collaborative Video Diffusion: Consistent Multi-video Generation with Camera Control
Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
Strategic Linear Contextual Bandits
Debiasing Synthetic Data Generated by Deep Generative Models
SARDet-100K: Towards Open-Source Benchmark and ToolKit for Large-Scale SAR Object Detection
Learning Elastic Costs to Shape Monge Displacements
Distributionally Robust Reinforcement Learning with Interactive Data Collection: Fundamental Hardness and Near-Optimal Algorithm
4+3 Phases of Compute-Optimal Neural Scaling Laws
Unified Covariate Adjustment for Causal Inference
Learning to grok: Emergence of in-context learning and skill composition in modular arithmetic tasks
Improved Regret for Bandit Convex Optimization with Delayed Feedback
SureMap: Simultaneous mean estimation for single-task and multi-task disaggregated evaluation
Towards Open-Vocabulary Semantic Segmentation Without Semantic Labels
Understanding Hallucinations in Diffusion Models through Mode Interpolation
In-and-Out: Algorithmic Diffusion for Sampling Convex Bodies
Symmetric Linear Bandits with Hidden Symmetry
Rethinking Parity Check Enhanced Symmetry-Preserving Ansatz
Minimum Entropy Coupling with Bottleneck
Enhancing Preference-based Linear Bandits via Human Response Time
An Accelerated Gradient Method for Convex Smooth Simple Bilevel Optimization
Learning Mixtures of Unknown Causal Interventions
Geometry-aware training of factorized layers in tensor Tucker format
Hamiltonian Monte Carlo on ReLU Neural Networks is Inefficient
Tri-Level Navigator: LLM-Empowered Tri-Level Learning for Time Series OOD Generalization
Scaling transformer neural networks for skillful and reliable medium-range weather forecasting
On the Sparsity of the Strong Lottery Ticket Hypothesis
Navigating Chemical Space with Latent Flows
Images that Sound: Composing Images and Sounds on a Single Canvas
Orchid: Flexible and Data-Dependent Convolution for Sequence Modeling
Amortized Fourier Neural Operators
Unelicitable Backdoors via Cryptographic Transformer Circuits
Fair GLASSO: Estimating Fair Graphical Models with Unbiased Statistical Behavior
Improving self-training under distribution shifts via anchored confidence with theoretical guarantees
Parameterized Approximation Schemes for Fair-Range Clustering
Learn more, but bother less: parameter efficient continual learning
MoEUT: Mixture-of-Experts Universal Transformers
Ctrl-X: Controlling Structure and Appearance for Text-To-Image Generation Without Guidance
Approximation Rate of the Transformer Architecture for Sequence Modeling
Video Diffusion Models are Training-free Motion Interpreter and Controller
Learning-to-Cache: Accelerating Diffusion Transformer via Layer Caching
Neural Pfaffians: Solving Many Many-Electron Schrödinger Equations
Constrained Adaptive Attack: Effective Adversarial Attack Against Deep Neural Networks for Tabular Data
CriticEval: Evaluating Large-scale Language Model as Critic
How to Scale Inverse RL to Large State Spaces? A Provably Efficient Approach
Is Score Matching Suitable for Estimating Point Processes?
Finding good policies in average-reward Markov Decision Processes without prior knowledge
Truthful High Dimensional Sparse Linear Regression
Generalizable Implicit Motion Modeling for Video Frame Interpolation
Contextual Active Model Selection
Analyzing & Reducing the Need for Learning Rate Warmup in Neural Network Optimization
TripletCLIP: Improving Compositional Reasoning of CLIP via Vision-Language Negatives
$\beta$-DPO: Direct Preference Optimization with Dynamic $\beta$
PureGen: Universal Data Purification for Train-Time Poison Defense via Generative Model Dynamics
Stochastic Amortization: A Unified Approach to Accelerate Feature and Data Attribution
Normalization and effective learning rates in reinforcement learning
Towards Next-Generation Logic Synthesis: A Scalable Neural Circuit Generation Framework
Latent Diffusion for Neural Spiking Data
NeoRL: Efficient Exploration for Nonepisodic RL
A Simple Remedy for Dataset Bias via Self-Influence: A Mislabeled Sample Perspective
DeTrack: In-model Latent Denoising Learning for Visual Object Tracking
Compositional PAC-Bayes: Generalization of GNNs with persistence and beyond
Learning the Expected Core of Strictly Convex Stochastic Cooperative Games
SDformer: Similarity-driven Discrete Transformer For Time Series Generation
DiffHammer: Rethinking the Robustness of Diffusion-Based Adversarial Purification
Advancing Tool-Augmented Large Language Models: Integrating Insights from Errors in Inference Trees
Recurrent Complex-Weighted Autoencoders for Unsupervised Object Discovery
Statistical Estimation in the Spiked Tensor Model via the Quantum Approximate Optimization Algorithm
Online Control in Population Dynamics
Unity by Diversity: Improved Representation Learning for Multimodal VAEs
Hierarchical data visualization via PCA trees
SE(3)-bi-equivariant Transformers for Point Cloud Assembly
Ferrari: Federated Feature Unlearning via Optimizing Feature Sensitivity
DISP-LLM: Dimension-Independent Structural Pruning for Large Language Models
PV-Tuning: Beyond Straight-Through Estimation for Extreme LLM Compression
Why Do We Need Weight Decay in Modern Deep Learning?
DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos
Preference Learning Algorithms Do Not Learn Preference Rankings
Reparameterizable Tree-structured Variational Inference for Instance-level Correlation Capturing
Graph-based Uncertainty Metrics for Long-form Language Model Generations
A Full-duplex Speech Dialogue Scheme Based On Large Language Model
Warm-starting Push-Relabel
SpatialPIN: Enhancing Spatial Reasoning Capabilities of Vision-Language Models through Prompting and Interacting 3D Priors
Reawakening knowledge: Anticipatory recovery from catastrophic interference via structured training
Deterministic Policies for Constrained Reinforcement Learning in Polynomial-Time
Provably Efficient Reinforcement Learning for Infinite-Horizon Average-Reward Linear MDPs
UNIT: Unifying Image and Text Recognition in One Vision Encoder
Transformers Represent Belief State Geometry in their Residual Stream
Towards Learning Group-Equivariant Features for Domain Adaptive 3D Detection
Finding NeMo: Localizing Neurons Responsible For Memorization in Diffusion Models
AgentPoison: Red-teaming LLM Agents via Memory or Knowledge Base Backdoor Poisoning
Reprogramming Pretrained Target-Specific Diffusion Models for Dual-Target Drug Design
SpeedLoader: An I/O efficient scheme for heterogeneous and distributed LLM operation
Theoretical Analysis of Weak-to-Strong Generalization
Online Feature Updates Improve Online (Generalized) Label Shift Adaptation
Harnessing small projectors and multiple views for efficient vision pretraining
A Simple yet Universal Framework for Depth Completion
Pure Message Passing Can Estimate Common Neighbor for Link Prediction
Tracing Hyperparameter Dependencies for Model Parsing via Learnable Graph Pooling Network
Soft ascent-descent as a stable and flexible alternative to flooding
Scaling Laws and Compute-Optimal Training without Fixed Training Duration
Hierarchical Hybrid Sliced Wasserstein: A Scalable Metric for Heterogeneous Joint Distributions
Disentangling Linear Quadratic Control with Untrusted ML Predictions
A Combinatorial Algorithm for the Semi-Discrete Optimal Transport Problem
E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation
Protein-Nucleic Acid Complex Modeling with Frame Averaging Transformer
A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds
Amortized Planning with Large-Scale Transformers: A Case Study on Chess
Megalodon: Efficient LLM Pretraining and Inference with Unlimited Context Length
Random Cycle Coding: Lossless Compression of Cluster Assignments via Bits-Back Coding
Continual Learning in the Frequency Domain
HippoRAG: Neurobiologically Inspired Long-Term Memory for Large Language Models
Learning Image Priors Through Patch-Based Diffusion Models for Solving Inverse Problems
When Your AIs Deceive You: Challenges of Partial Observability in Reinforcement Learning from Human Feedback
No Free Delivery Service: Epistemic limits of passive data collection in complex social systems
Semi-Random Matrix Completion via Flow-Based Adaptive Reweighting
Polyhedral Complex Derivation from Piecewise Trilinear Networks
How does Gradient Descent Learn Features --- A Local Analysis for Regularized Two-Layer Neural Networks
Training-Free Open-Ended Object Detection and Segmentation via Attention as Prompts
Gradient Rewiring for Editable Graph Neural Network Training
Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
Fine-Tuning is Fine, if Calibrated
Visual Data Diagnosis and Debiasing with Concept Graphs
High-probability complexity bounds for stochastic non-convex minimax optimization
Sample Complexity of Interventional Causal Representation Learning
Log-concave Sampling from a Convex Body with a Barrier: a Robust and Unified Dikin Walk
MVInpainter: Learning Multi-View Consistent Inpainting to Bridge 2D and 3D Editing
MMSite: A Multi-modal Framework for the Identification of Active Sites in Proteins
Absorb & Escape: Overcoming Single Model Limitations in Generating Heterogeneous Genomic Sequences
Detecting Brittle Decisions for Free: Leveraging Margin Consistency in Deep Robust Classifiers
Textual Training for the Hassle-Free Removal of Unwanted Visual Data
Prospective Learning: Learning for a Dynamic Future
Jointly Modeling Inter- & Intra-Modality Dependencies for Multi-modal Learning
FreeLong: Training-Free Long Video Generation with SpectralBlend Temporal Attention
Why Transformers Need Adam: A Hessian Perspective
Certified Robustness for Deep Equilibrium Models via Serialized Random Smoothing
Provable Acceleration of Nesterov's Accelerated Gradient for Asymmetric Matrix Factorization and Linear Neural Networks
Mixture of Link Predictors on Graphs
Steganalysis on Digital Watermarking: Is Your Robustness a Maginot Line?
Gradient Guidance for Diffusion Models: An Optimization Perspective
Building on Efficient Foundations: Effective Training of LLMs with Structured Feedforward Layers
PediatricsGPT: Large Language Models as Chinese Medical Assistants for Pediatric Applications
Fairness-Aware Estimation of Graphical Models
Stabilized Proximal Point Methods for Federated Optimization
Strategic Multi-Armed Bandit Problems Under Debt-Free Reporting
Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classification
Personalized Federated Learning via Feature Distribution Adaptation
CHASE: Learning Convex Hull Adaptive Shift for Skeleton-based Multi-Entity Action Recognition
Federated Learning under Periodic Client Participation and Heterogeneous Data: A New Communication-Efficient Algorithm and Analysis
Subwords as Skills: Tokenization for Sparse-Reward Reinforcement Learning
Learning to be Smooth: An End-to-End Differentiable Particle Smoother
I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token
Leveraging Visual Tokens for Extended Text Contexts in Multi-Modal Learning
Embedding-Aligned Language Models
General Articulated Objects Manipulation in Real Images via Part-Aware Diffusion Process
Large Scale Transfer Learning for Tabular Data via Language Modeling
Towards Understanding the Mechanisms of Associative Memory in Transformers
ALPINE: Unveiling The Planning Capability of Autoregressive Learning in Language Models
Energy-efficient Reinforcement Learning by Discovering Neural Pathways
Robust Fine-tuning of Zero-shot Models via Variance Reduction
One-Layer Transformer Provably Learns One-Nearest Neighbor In Context
Learning to Assist Humans without Inferring Rewards
Understanding Transformers via N-Gram Statistics
Fine-Tuning Personalization in Federated Learning to Mitigate Adversarial Clients
Cardinality-Aware Set Prediction and Top-$k$ Classification
Universal Neural Functionals
Precise Relational DNN Verification With Cross Executional Branching
MediQ: Question-Asking LLMs for Adaptive and Reliable Medical Reasoning
Bilevel Optimization with Lower-Level Contextual MDPs
Multimodal Task Vectors Enable Many-Shot Multimodal In-Context Learning
Depth Anywhere: Enhancing 360 Monocular Depth Estimation via Perspective Distillation and Unlabeled Data Augmentation
WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
Deep Graph Neural Networks via Posteriori-Sampling-based Node-Adaptative Residual Module
Kernel-Based Function Approximation for Average Reward Reinforcement Learning: An Optimist No-Regret Algorithm
Efficiency for Free: Ideal Data Are Transportable Representations
Online Budgeted Matching with General Bids
Stepwise Alignment for Constrained Language Model Policy Optimization
Nonparametric Instrumental Variable Regression through Stochastic Approximate Gradients
Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents
Nearly Minimax Optimal Submodular Maximization with Bandit Feedback
Web-Scale Visual Entity Recognition: An LLM-Driven Data Approach
Decomposing and Interpreting Image Representations via Text in ViTs Beyond CLIP
Direct Consistency Optimization for Robust Customization of Text-to-Image Diffusion models
Balancing Context Length and Mixing Times for Reinforcement Learning at Scale
Reproducibility of predictive networks for mouse visual cortex
Transforming Vision Transformer: Towards Efficient Multi-Task Asynchronous Learner
PrivCirNet: Efficient Private Inference via Block Circulant Transformation
Learning from Offline Foundation Features with Tensor Augmentations
FUG: Feature-Universal Graph Contrastive Pre-training for Graphs with Diverse Node Features
Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
PageRank Bandits for Link Prediction
NoiseGPT: Label Noise Detection and Rectification through Probability Curvature
Estimating Fréchet bounds for validating programmatic weak supervision
Aligning Audio-Visual Joint Representations with an Agentic Workflow
Prompt-Based Knowledge Graph Foundation Model for Universal In-Context Reasoning
Latent Neural Operator for Solving Forward and Inverse PDE Problems
Learning Better Representations From Less Data For Propositional Satisfiability
Energy-based Hopfield Boosting for Out-of-Distribution Detection
Single Image Reflection Separation via Interactive Dual-Stream Transformers
Learning Where to Edit Vision Transformers
WizardArena: Post-training Large Language Models via Simulated Offline Chatbot Arena
Slight Corruption in Pre-training Data Makes Better Diffusion Models
PRODuctive bandits: Importance Weighting No More
CodeRosetta: Pushing the Boundaries of Unsupervised Code Translation for Parallel Programming
QT-ViT: Improving Linear Attention in ViT with Quadratic Taylor Expansion
Stochastic Newton Proximal Extragradient Method
REBORN: Reinforcement-Learned Boundary Segmentation with Iterative Training for Unsupervised ASR
Text2NKG: Fine-Grained N-ary Relation Extraction for N-ary relational Knowledge Graph Construction
Maximum Entropy Inverse Reinforcement Learning of Diffusion Models with Energy-Based Models
FairWire: Fair Graph Generation
Dissecting the Interplay of Attention Paths in a Statistical Mechanics Theory of Transformers
Ad Auctions for LLMs via Retrieval Augmented Generation
Uncovering Safety Risks of Large Language Models through Concept Activation Vector
Self-Supervised Alignment with Mutual Information: Learning to Follow Principles without Preference Labels
Learning Group Actions on Latent Representations
Safe and Efficient: A Primal-Dual Method for Offline Convex CMDPs under Partial Data Coverage
Demographic parity fair regression in unaware setting
GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing
Randomized Truthful Auctions with Learning Agents
No Filter: Towards Cultural and Socioeconomic Diversity in Multimodal Systems
StrategyLLM: Large Language Models as Strategy Generators, Executors, Optimizers, and Evaluators for Problem Solving
Improving Adaptivity via Over-Parameterization in Sequence Models
DreamSteerer: Enhancing Source Image Conditioned Editability using Personalized Diffusion Models
Reinforcement Learning-Guided Semi-Supervised Learning
AverNet: All-in-one Video Restoration for Time-varying Unknown Degradations
Variational Flow Matching for Graph Generation
State Space Models on Temporal Graphs: A First-Principles Study
Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification
Toward a Well-Calibrated Discrimination via Survival Outcome-Aware Contrastive Learning
Gradient-Free Methods for Nonconvex Nonsmooth Stochastic Compositional Optimization
Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Images
HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion
The Value of Reward Lookahead in Reinforcement Learning
D-LLM: A Token Adaptive Computing Resource Allocation Strategy for Large Language Models
Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single Image
Distribution-Aware Data Expansion with Diffusion Models
Exocentric-to-Egocentric Video Generation
RaVL: Discovering and Mitigating Spurious Correlations in Fine-Tuned Vision-Language Models
Frequency-aware Generative Models for Multivariate Time-series Imputation
Federated Graph Learning for Cross-Domain Recommendation
Optimal Rates for Vector-Valued Spectral Regularization Learning Algorithms
Meta-DT: Offline Meta-RL as Conditional Sequence Modeling with World Model Disentanglement
An eye for an ear: zero-shot audio description leveraging an image captioner with audio-visual token distribution matching
MambaSCI: Efficient Mamba-UNet for Quad-Bayer Patterned Video Snapshot Compressive Imaging
Idiographic Personality Gaussian Process for Psychological Assessment
Do causal predictors generalize better to new domains?
What can Foundation Models’ Embeddings do?
Ordered Momentum for Asynchronous SGD
Dynamic Service Fee Pricing under Strategic Behavior: Actions as Instruments and Phase Transition
Neural Cover Selection for Image Steganography
Online Iterative Reinforcement Learning from Human Feedback with General Preference Model
Trajectory Data Suffices for Statistically Efficient Learning in Offline RL with Linear $q^\pi$-Realizability and Concentrability
A Huber Loss Minimization Approach to Mean Estimation under User-level Differential Privacy
FEEL-SNN: Robust Spiking Neural Networks with Frequency Encoding and Evolutionary Leak Factor
QuadMamba: Learning Quadtree-based Selective Scan for Visual State Space Model
High-dimensional (Group) Adversarial Training in Linear Regression
Robust Mixture Learning when Outliers Overwhelm Small Groups
Inversion-based Latent Bayesian Optimization
DiffAug: A Diffuse-and-Denoise Augmentation for Training Robust Classifiers
Improving Temporal Link Prediction via Temporal Walk Matrix Projection
In-Context Learning of a Linear Transformer Block: Benefits of the MLP Component and One-Step GD Initialization
DiffNorm: Self-Supervised Normalization for Non-autoregressive Speech-to-speech Translation
Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs
Fundamental Limits of Prompt Compression: A Rate-Distortion Framework for Black-Box Language Models
Hyper-opinion Evidential Deep Learning for Out-of-Distribution Detection
Simplifying Constraint Inference with Inverse Reinforcement Learning
MicroAdam: Accurate Adaptive Optimization with Low Space Overhead and Provable Convergence
Unveiling The Matthew Effect Across Channels: Assessing Layer Width Sufficiency via Weight Norm Variance
Beyond Euclidean: Dual-Space Representation Learning for Weakly Supervised Video Violence Detection
Universal Rates for Active Learning
What type of inference is planning?
Diffusion Tuning: Transferring Diffusion Models via Chain of Forgetting
SGD vs GD: Rank Deficiency in Linear Networks
Language Hierarchical Self-training for Detecting Twenty-thousand Classes using Image-level Supervision
Likelihood-based differentiable structure learning
Multi-times Monte Carlo Rendering for Inter-reflection Reconstruction
Improving Viewpoint-Independent Object-Centric Representations through Active Viewpoint Selection
From Biased to Unbiased Dynamics: An Infinitesimal Generator Approach
CAT3D: Create Anything in 3D with Multi-View Diffusion Models
Generated and Pseudo Content guided Prototype Refinement for Few-shot Point Cloud Segmentation
Deep Bayesian Active Learning for Preference Modeling in Large Language Models
B-cosification: Transforming Deep Neural Networks to be Inherently Interpretable
HHD-GP: Incorporating Helmholtz-Hodge Decomposition into Gaussian Processes for Learning Dynamical Systems
Latent Paraphrasing: Perturbation on Layers Improves Knowledge Injection in Language Models
OPERA: Automatic Offline Policy Evaluation with Re-weighted Aggregates of Multiple Estimators
Monte Carlo Tree Search based Space Transfer for Black Box Optimization
Heavy-Tailed Class Imbalance and Why Adam Outperforms Gradient Descent on Language Models
Frequency Adaptive Normalization For Non-stationary Time Series Forecasting
Differentially Private Reinforcement Learning with Self-Play
Prompt Tuning Strikes Back: Customizing Foundation Models with Low-Rank Prompt Adaptation
Are Graph Neural Networks Optimal Approximation Algorithms?
Learning Goal-Conditioned Representations in Reward Models for Aligning Language Models
Detecting and Measuring Confounding Using Causal Mechanism Shifts
Deep Equilibrium Algorithmic Reasoning
Diffusion Model with Cross Attention as an Inductive Bias for Disentanglement
Wild-GS: Real-Time Novel View Synthesis from Unconstrained Photo Collections
EnOF: Training Accurate Spiking Neural Networks via Enhancing the Output Feature Representation
Learning Hybrid Models for Digital Twins of Dynamical Systems
Tree of Attacks: Jailbreaking Black-Box LLMs Automatically
Optimal Hypothesis Selection in (Almost) Linear Time
Understanding Generalizability of Diffusion Models Requires Rethinking the Hidden Gaussian Structure
Inexact Augmented Lagrangian Methods for Conic Optimization: Quadratic Growth and Linear Convergence
Doob's Lagrangian: A Sample-Efficient Variational Approach to Transition Path Sampling
Time-Varying LoRA: Towards Effective Cross-Domain Fine-Tuning of Diffusion Models
Achieving Linear Convergence with Parameter-Free Algorithms in Decentralized Optimization
Bayesian Strategic Classification
GrounDiT: Grounding Diffusion Transformers via Noisy Image Patch Transplantation
QVAE-Mole: The Quantum VAE with Spherical Latent Variable Learning for 3-D Molecule Generation
U-DiTs: Downsample Tokens in U-Shaped Diffusion Transformers
4Real: Towards Photorealistic 4D Scene Generation via Video Diffusion Models
ID-to-3D: Expressive ID-guided 3D Heads via Score Distillation Sampling
Mixtures of Experts for Audio-Visual Learning
SpeechAlign: Speech Language Models Can Self-Improve via Preference Optimization
Achieving Tractable Minimax Optimal Regret in Average Reward MDPs
Provably Robust Score-Based Diffusion Posterior Sampling for Plug-and-Play Image Reconstruction
4Diffusion: Multi-view Video Diffusion Model for 4D Generation
Diffusing Differentiable Representations
The Intelligible and Effective Graph Neural Additive Network
Polyak Meets Parameter-free Clipped Gradient Descent
Scalable Optimization in the Modular Norm
Déjà Vu Memorization in Vision–Language Models
Stepping on the Edge: Curvature Aware Learning Rate Tuners
Measuring Progress in Dictionary Learning for Language Model Interpretability with Board Game Models
General bounds on the quality of Bayesian coresets
AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data
Normalization Layer Per-Example Gradients are Sufficient to Predict Gradient Noise Scale in Transformers
VeXKD: The Versatile Integration of Cross-Modal Fusion and Knowledge Distillation for 3D Perception
Spatio-Temporal Interactive Learning for Efficient Image Reconstruction of Spiking Cameras
Who Evaluates the Evaluations? Objectively Scoring Text-to-Image Prompt Coherence Metrics with T2IScoreScore (TS2)
A Closer Look at AUROC and AUPRC under Class Imbalance
RankRAG: Unifying Retrieval-Augmented Generation and Context Ranking in LLMs
Gaussian Approximation and Multiplier Bootstrap for Polyak-Ruppert Averaged Linear Stochastic Approximation with Applications to TD Learning
Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models
Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion
Computing the Bias of Constant-step Stochastic Approximation with Markovian Noise
Statistical and Geometrical properties of the Kernel Kullback-Leibler divergence
Reparameterized Multi-Resolution Convolutions for Long Sequence Modelling
Learning a Single Neuron Robustly to Distributional Shifts and Adversarial Label Noise
Shaving Weights with Occam's Razor: Bayesian Sparsification for Neural Networks using the Marginal Likelihood
ROBIN: Robust and Invisible Watermarks for Diffusion Models with Adversarial Optimization
SymILO: A Symmetry-Aware Learning Framework for Integer Linear Optimization
OTTER: Effortless Label Distribution Adaptation of Zero-shot Models
Neural Localization Fields for Continuous 3D Human Pose and Shape Estimation
Sample Efficient Bayesian Learning of Causal Graphs from Interventions
LACIE: Listener-Aware Finetuning for Calibration in Large Language Models
B'MOJO: Realizations of Hybrid State Space Models with Eidetic and Fading Memory
Optimal-state Dynamics Estimation for Physics-based Human Motion Capture from Videos
Scaling the Codebook Size of VQ-GAN to 100,000 with a Utilization Rate of 99%
Semantic and Spatial Adaptive Pixel-level Classifier for Semantic Segmentation
Ada-MSHyper: Adaptive Multi-Scale Hypergraph Transformer for Time Series Forecasting
Conditional Controllable Image Fusion
Collaborative Refining for Learning from Inaccurate Labels
Image Understanding Makes for A Good Tokenizer for Image Generation
Decentralized Noncooperative Games with Coupled Decision-Dependent Distributions
Gradients of Functions of Large Matrices
Improving Generalization of Dynamic Graph Learning via Environment Prompt
Neural Collapse to Multiple Centers For Imbalanced Data
Online Adaptation of Language Models with a Memory of Amortized Contexts
YouDream: Generating Anatomically Controllable Consistent Text-to-3D Animals
Sample-efficient Bayesian Optimisation Using Known Invariances
Trading Place for Space: Increasing Location Resolution Reduces Contextual Capacity in Hippocampal Codes
Adaptive Exploration for Data-Efficient General Value Function Evaluations
Your Diffusion Model is Secretly a Noise Classifier and Benefits from Contrastive Training
Qualitative Mechanism Independence
Quantifying Aleatoric Uncertainty of the Treatment Effect: A Novel Orthogonal Learner
Building Network Architectures for Continual Reinforcement Learning with Parseval Regularization
Navigating Extremes: Dynamic Sparsity in Large Output Spaces
Exploitation of a Latent Mechanism in Graph Contrastive Learning: Representation Scattering
Parallelizing Model-based Reinforcement Learning Over the Sequence Length
The Reliability of OKRidge Method in Solving Sparse Ridge Regression Problems
CoSy: Evaluating Textual Explanations of Neurons
Large Language Models Must Be Taught to Know What They Don’t Know
The motion planning neural circuit in goal-directed navigation as Lie group operator search
Faster Differentially Private Top-$k$ Selection: A Joint Exponential Mechanism with Pruning
Suppress Content Shift: Better Diffusion Features via Off-the-Shelf Generation Techniques
Cascade of phase transitions in the training of energy-based models
GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts
Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
Towards a Theoretical Understanding of the 'Reversal Curse' via Training Dynamics
Multi-Agent Imitation Learning: Value is Easy, Regret is Hard
Physics-Constrained Comprehensive Optical Neural Networks
Predicting Future Actions of Reinforcement Learning Agents
Almost Minimax Optimal Best Arm Identification in Piecewise Stationary Linear Bandits
On the Role of Information Structure in Reinforcement Learning for Partially-Observable Sequential Teams and Games
Hybrid Mamba for Few-Shot Segmentation
Selective Attention: Enhancing Transformer through Principled Context Control
Learning Distributions on Manifolds with Free-Form Flows
FedGTST: Boosting Global Transferability of Federated Models via Statistics Tuning
Grounded Answers for Multi-agent Decision-making Problem through Generative World Model
Rule Based Rewards for Fine-Grained Safety Behavior in LLMs
Accuracy is Not All You Need
SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
SSDiff: Spatial-spectral Integrated Diffusion Model for Remote Sensing Pansharpening
Dynamic Inference of Multimodal Large Language Models for Efficient Robot Execution
Understanding the expressivity and trainability of Fourier Neural Operator
Towards an Information Theoretic Framework of Context-Based Offline Meta-Reinforcement Learning
Pick up the PACE: A Parameter-Free Optimizer for Lifelong Reinforcement Learning
Learning rigid-body simulators over implicit shapes for large-scale scenes and vision
The surprising efficiency of temporal difference learning for rare event prediction
Learning Optimal Tax Design in Nonatomic Congestion Games
A Gradient Accumulation Method for Dense Retriever under Memory Constraint
Cherry on Top: Parameter Heterogeneity and Quantization in Large Language Models
MoE Jetpack: From Dense Checkpoints to Adaptive Mixture of Experts for Vision Tasks
Near-Optimality of Contrastive Divergence Algorithms
Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
Controlling Counterfactual Harm in Decision Support Systems Based on Prediction Sets
Density-based User Representation using Gaussian Process Regression for Multi-interest Personalized Retrieval
MADiff: Offline Multi-agent Learning with Diffusion Models
Learning and Transferring Sparse Contextual Bigrams with Linear Transformers
LoD-Loc: Aerial Visual Localization using LoD 3D Map with Neural Wireframe Alignment
Fundamental Convergence Analysis of Sharpness-Aware Minimization
Generative Hierarchical Materials Search
3DGS-Enhancer: Enhancing Unbounded 3D Gaussian Splatting with View-consistent 2D Diffusion Priors
Sharpness-Aware Minimization Activated Interactive Teaching Understanding and Optimization
Elo Uncovered: Robustness and Best Practices in Language Model Evaluation
A Closer Look at Deep Learning Phenomena Through A Telescoping Lens
Inference via Interpolation: Contrastive Representations Provably Enable Planning and Inference
Object segmentation from common fate: Motion energy processing enables human-like zero-shot generalization to random dot stimuli
LoQT: Low Rank Adapters for Quantized Training
Interpretable Mesomorphic Networks for Tabular Data
PSL: Rethinking and Improving Softmax Loss from Pairwise Perspective for Recommendation
Provable Posterior Sampling with Denoising Oracles Through Tilted Transport
Learning to Price Homogeneous Data
Generalization Beyond Data Imbalance: A Controlled Study on CLIP for Transferable Insights
Hollowed Net for On-Device Personalization of Text-to-Image Diffusion Models
Does Video-Text Pretraining Help Open-Vocabulary Online Action Detection?
Single Forward Video Generation Model
Mutual Information Estimation via $f$-Divergence and Data Derangements
Efficient Policy Evaluation Across Multiple Different Experimental Datasets
L4GM: Large 4D Gaussian Reconstruction Model
Active preference learning for ordering items in- and out-of-sample
FUNGI: Features From Unsupervised Gradients
Group Robust Preference Optimization in Reward-free RLHF
The Impact of Geometric Complexity on Neural Collapse in Transfer Learning
Transfer Learning for Latent Variable Network Models
Towards Efficient and Optimal Covariance-Adaptive Algorithms for Combinatorial Semi-Bandits
Scaling Laws in Linear Regression: Compute, Parameters, and Data
Thompson Sampling For Combinatorial Bandits: Polynomial Regret and Mismatched Sampling Paradox
Linear Causal Bandits: Unknown Graph and Soft Interventions
Memory-Efficient LLM Training with Online Subspace Descent
Monoculture in Matching Markets
FlexCap: Describe Anything in Images in Controllable Detail
QueST: Self-Supervised Skill Abstractions for Learning Continuous Control
DenoiseReID: Denoising Model for Representation Learning of Person Re-Identification
Improved Sample Complexity Bounds for Diffusion Model Training
Accelerating Relative Entropy Coding with Space Partitioning
A Theoretical Understanding of Self-Correction through In-context Alignment
Improved Guarantees for Fully Dynamic $k$-Center Clustering with Outliers in General Metric Spaces
Leveraging Separated World Model for Exploration in Visually Distracted Environments
Questioning the Survey Responses of Large Language Models
Mean-Field Langevin Dynamics for Signed Measures via a Bilevel Approach
Observational Scaling Laws and the Predictability of Langauge Model Performance
Clustering in Causal Attention Masking
Zero-Shot Transfer of Neural ODEs
Scalable Bayesian Optimization via Focalized Sparse Gaussian Processes
Decomposable Transformer Point Processes
ST$_k$: A Scalable Module for Solving Top-k problems
Realizable $H$-Consistent and Bayes-Consistent Loss Functions for Learning to Defer
Geometric Trajectory Diffusion Models
Local to Global: Learning Dynamics and Effect of Initialization for Transformers
Achieving Near-Optimal Convergence for Distributed Minimax Optimization with Adaptive Stepsizes
Sparse maximal update parameterization: A holistic approach to sparse training dynamics
Can large language models explore in-context?
CoMat: Aligning Text-to-Image Diffusion Model with Image-to-Text Concept Matching
Enhancing Data Quality via Training Dynamics from Private Domains for Collaborative Fine-Tuning of Large Language Models
Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
When is Multicalibration Post-Processing Necessary?
Ordering-Based Causal Discovery for Linear and Nonlinear Relations
DynaMITE-RL: A Dynamic Model for Improved Temporal Meta-Reinforcement Learning
Suitable is the Best: Task-oriented Knowledge Fusion in Vulnerability Detection
A Fast Convoluted Story: Scaling Probabilistic Inference for Integer Arithmetics
Identifying Causal Effects Under Functional Dependencies
Deterministic Uncertainty Propagation for Improved Model-Based Offline Reinforcement Learning
Towards Stable Representations for Protein Interface Prediction
$M^3$GPT: An Advanced Multimodal, Multitask Framework for Motion Comprehension and Generation
Honor Among Bandits: No-Regret Learning for Online Fair Division
Barely Random Algorithms for Metrical Task Systems
Shadowheart SGD: Distributed Asynchronous SGD with Optimal Time Complexity Under Arbitrary Computation and Communication Heterogeneity
Hyper-SD: Trajectory Segmented Consistency Model for Efficient Image Synthesis
Pseudo-Siamese Directional Transformers for Self-Supervised Real-World Denoising
How Diffusion Models Learn to Factorize and Compose
Graphcode: Learning from multiparameter persistent homology using graph neural networks
On scalable oversight with weak LLMs judging strong LLMs
UrbanKGent: A Unified Large Language Model Agent Framework for Urban Knowledge Graph Construction
Streaming Bayes GFlowNets
Seeing the Image: Prioritizing Visual Correlation by Contrastive Alignment
Motion Consistency Model: Accelerating Video Diffusion with Disentangled Motion-Appearance Distillation
GaussianCut: Interactive segmentation via graph cut for 3D Gaussian Splatting
ANAH-v2: Scaling Analytical Hallucination Annotation of Large Language Models
When does perceptual alignment benefit vision representations?
Occupancy-based Policy Gradient: Estimation, Convergence, and Optimality
No-Regret M${}^{\natural}$-Concave Function Maximization: Stochastic Bandit Algorithms and NP-Hardness of Adversarial Full-Information Setting
Safe and Sparse Newton Method for Entropic-Regularized Optimal Transport
Test-Time Dynamic Image Fusion
Why Warmup the Learning Rate? Underlying Mechanisms and Improvements
A Local Method for Satisfying Interventional Fairness with Partially Known Causal Graphs
Single-loop Stochastic Algorithms for Difference of Max-Structured Weakly Convex Functions
Understanding Visual Feature Reliance through the Lens of Complexity
Matrix Denoising with Doubly Heteroscedastic Noise: Fundamental Limits and Optimal Spectral Methods
Non-asymptotic Convergence of Training Transformers for Next-token Prediction
Towards a theory of how the structure of language is acquired by deep neural networks
MeLLoC: Lossless Compression with High-order Mechanism Learning
Adaptive and Optimal Second-order Optimistic Methods for Minimax Optimization
Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses
Robustly overfitting latents for flexible neural image compression
Adaptive Depth Networks with Skippable Sub-Paths
Smoothed Online Classification can be Harder than Batch Classification
ActFusion: a Unified Diffusion Model for Action Segmentation and Anticipation
Scaling laws for learning with real and surrogate data
PTQ4DiT: Post-training Quantization for Diffusion Transformers
Time-Constrained Robust MDPs
Discrete Dictionary-based Decomposition Layer for Structured Representation Learning
Enhancing LLM Reasoning via Vision-Augmented Prompting
Neural Residual Diffusion Models for Deep Scalable Vision Generation
SlimGPT: Layer-wise Structured Pruning for Large Language Models
Multivariate Stochastic Dominance via Optimal Transport and Applications to Models Benchmarking
The Power of Hard Attention Transformers on Data Sequences: A formal language theoretic perspective
TFG: Unified Training-Free Guidance for Diffusion Models
On Divergence Measures for Training GFlowNets
Predicting Scaling Laws with Statistical and Approximation Theory for Transformer Neural Networks on Intrinsically Low-dimensional Data
Mirror and Preconditioned Gradient Descent in Wasserstein Space
Zero-Shot Image Segmentation via Recursive Normalized Cut on Diffusion Features
OptEx: Expediting First-Order Optimization with Approximately Parallelized Iterations
Quantifying the Gain in Weak-to-Strong Generalization
Equivariant spatio-hemispherical networks for diffusion MRI deconvolution
Why are Visually-Grounded Language Models Bad at Image Classification?
Data-Efficient Operator Learning via Unsupervised Pretraining and In-Context Learning
A Unifying Post-Processing Framework for Multi-Objective Learn-to-Defer Problems
LRM-Zero: Training Large Reconstruction Models with Synthesized Data
A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
CLIPCEIL: Boosting Domain Generalization for CLIP by Channel rEfinement and Image-text aLignment
A Modular Conditional Diffusion Framework for Image Reconstruction
LG-CAV: Train Any Concept Activation Vector with Language Guidance
Intrinsic Robustness of Prophet Inequality to Strategic Reward Signaling
Understanding Preference Learning Through the Lens of Coverage
EDT: An Efficient Diffusion Transformer Framework Inspired by Human-like Sketching
On the Worst Prompt Performance of Large Language Models
Universality in Transfer Learning for Linear Models
Robust group and simultaneous inferences for high-dimensional single index model
Covariate Shift Corrected Conditional Randomization Test
Differential Privacy in Scalable General Kernel Learning via $K$-means Nystr{\"o}m Random Features
Online Composite Optimization Between Stochastic and Adversarial Environments
Theoretical Investigations and Practical Enhancements on Tail Task Risk Minimization in Meta Learning
Improving robustness to corruptions with multiplicative weight perturbations
BLoB: Bayesian Low-Rank Adaptation by Backpropagation for Large Language Models
Active Classification with Few Queries under Misspecification
TopoLogic: An Interpretable Pipeline for Lane Topology Reasoning on Driving Scenes
ReNO: Enhancing One-step Text-to-Image Models through Reward-based Noise Optimization
SAND: Smooth imputation of sparse and noisy functional data with Transformer networks
Structured Unrestricted-Rank Matrices for Parameter Efficient Finetuning
Marrying Causal Representation Learning with Dynamical Systems for Science
Analysis of Corrected Graph Convolutions
Transcoders find interpretable LLM feature circuits
Adversarially Robust Dense-Sparse Tradeoffs via Heavy-Hitters
Sample and Computationally Efficient Robust Learning of Gaussian Single-Index Models
Advancing Fine-Grained Classification by Structure and Subject Preserving Augmentation
RETR: Multi-View Radar Detection Transformer for Indoor Perception
How to Boost Any Loss Function
Memory-Efficient Gradient Unrolling for Large-Scale Bi-level Optimization
Estimating Ego-Body Pose from Doubly Sparse Egocentric Video Data
Robust Offline Active Learning on Graphs
From Text to Trajectory: Exploring Unified Complex Constraint Representation and Decomposition in Safe Reinforcement Learning
From Similarity to Superiority: Channel Clustering for Time Series Forecasting
A Unified Confidence Sequence for Generalized Linear Models, with Applications to Bandits
Online Classification with Predictions
Scaling Sign Language Translation
Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling
Building a stable classifier with the inflated argmax
Meta-Controller: Few-Shot Imitation of Unseen Embodiments and Tasks in Continuous Control
Perceptual Fairness in Image Restoration
FedAvP: Augment Local Data via Shared Policy in Federated Learning
Bridging The Gap between Low-rank and Orthogonal Adaptation via Householder Reflection Adaptation
Are Your Models Still Fair? Fairness Attacks on Graph Neural Networks via Node Injections
Spherical Frustum Sparse Convolution Network for LiDAR Point Cloud Semantic Segmentation
Two-way Deconfounder for Off-policy Evaluation under Unmeasured Confounding
Opponent Modeling based on Subgoal Inference
Probabilistic Graph Rewiring via Virtual Nodes
Exploratory Retrieval-Augmented Planning For Continual Embodied Instruction Following
Tolerant Algorithms for Learning with Arbitrary Covariate Shift
eXponential FAmily Dynamical Systems (XFADS): Large-scale nonlinear Gaussian state-space modeling
An Improved Empirical Fisher Approximation for Natural Gradient Descent
MaskLLM: Learnable Semi-Structured Sparsity for Large Language Models
Rule Extrapolation in Language Modeling: A Study of Compositional Generalization on OOD Prompts
Enhancing Protein Mutation Effect Prediction through a Retrieval-Augmented Framework
Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs?
The Secretary Problem with Predicted Additive Gap
Animate3D: Animating Any 3D Model with Multi-view Video Diffusion
STL: Still Tricky Logic (for System Validation, Even When Showing Your Work)
Talking Heads: Understanding Inter-Layer Communication in Transformer Language Models
On provable privacy vulnerabilities of graph representations
Mind the Graph When Balancing Data for Fairness or Robustness
How Molecules Impact Cells: Unlocking Contrastive PhenoMolecular Retrieval
Near-Optimal Dynamic Regret for Adversarial Linear Mixture MDPs
Where does In-context Learning \\ Happen in Large Language Models?
Neural Fluidic System Design and Control with Differentiable Simulation
NeuroGauss4D-PCI: 4D Neural Fields and Gaussian Deformation Fields for Point Cloud Interpolation
Efficient and Sharp Off-Policy Evaluation in Robust Markov Decision Processes
Robot Policy Learning with Temporal Optiaml Transport Reward
Warped Diffusion: Solving Video Inverse Problems with Image Diffusion Models
Unveiling the Power of Diffusion Features For Personalized Segmentation and Retrieval
A Best-of-both-worlds Algorithm for Bandits with Delayed Feedback with Robustness to Excessive Delays
Partial observation can induce mechanistic mismatches in data-constrained models of neural dynamics
EfficientCAPER: An End-to-End Framework for Fast and Robust Category-Level Articulated Object Pose Estimation
LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning
Transformers Learn Higher-Order Optimization Methods for In-Context Learning: A Study with Linear Models
Pessimistic Backward Policy for GFlowNets
Distribution Learning with Valid Outputs Beyond the Worst-Case
Simple and Effective Masked Diffusion Language Models
Adversarial Schrödinger Bridge Matching
Injecting Undetectable Backdoors in Deep Learning and Language Models
Why the Metric Backbone Preserves Community Structure
Noise Contrastive Alignment of Language Models with Explicit Rewards
QBB: Quantization with Binary Bases for LLMs
Learning to Handle Complex Constraints for Vehicle Routing Problems
GUIDE: Real-Time Human-Shaped Agents
DiMSUM: Diffusion Mamba - A Scalable and Unified Spatial-Frequency Method for Image Generation
Fast Sampling via Discrete Non-Markov Diffusion Models
Turning Indirect Knowledge into Direct Demonstrations for Computer Agents at Scale
SOAP: Enhancing Efficiency of generated Code via Self-Optimization
Information-theoretic Limits of Online Classification with Noisy Labels
Conformalized Time Series with Semantic Features
PointMamba: A Simple State Space Model for Point Cloud Analysis
Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control
Banded Square Root Matrix Factorization for Differentially Private Model Training
Deep Homomorphism Networks
TopoFR: A Closer Look at Topology Alignment on Face Recognition
Exploring & Improving Multi-token Prediction (Block Draft) in Language Modeling
Superposed Decoding: Multiple Generations from a Single Autoregressive Inference Pass
Goal-Conditioned On-Policy Reinforcement Learning
Towards Fast Exact Conformalization of Generalized Parametric Estimation
Uniform Last-Iterate Guarantee for Bandits and Reinforcement Learning
KOALA: Empirical Lessons Toward Memory-Efficient and Fast Diffusion Models for Text-to-Image Synthesis
Model-Based Transfer Learning for Contextual Reinforcement Learning
Oracle-Efficient Reinforcement Learning for Max Value Ensembles
RectifID: Personalizing Rectified Flow with Anchored Classifier Guidance
Data-Driven Discovery of Dynamical Systems in Pharmacology using Large Language Models
Causal Imitation for Markov Decision Processes: a Partial Identification Approach
Rethinking LLM Memorization through the Lens of Adversarial Compression
SpaceByte: Towards Deleting Tokenization from Large Language Modeling
BrainBits: How Much of the Brain are Generative Reconstruction Methods Using?
SmallToLarge (S2L): Scalable Data Selection for Fine-tuning Large Language Models by Summarizing Training Trajectories of Small Models
ProvNeRF: Modeling per Point Provenance in NeRFs as a Stochastic Process
Even Sparser Graph Transformers
An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning
Progressive Exploration-Conformal Learning for Sparsely Annotated Object Detection in Aerial Images
Fair Online Bilateral Trade
REDUCR: Robust Data Downsampling using Class Priority Reweighting
Fine Tuning Out-of-Vocabulary Item Recommendation with User Sequence Imagination
Collaborative Cognitive Diagnosis with Disentangled Representation Learning
RoboMamba: Multimodal State Space Model for Efficient Robot Reasoning and Manipulation
Semantic Routing via Autoregressive Modeling
Connecting Joint-Embedding Predictive Architecture with Contrastive Self-supervised Learning
Online Control with Adversarial Disturbance for Continuous-time Linear Systems
The Implicit Bias of Gradient Descent on Separable Multiclass Data
LiveScene: Language Embedding Interactive Radiance Fields for Physical Scene Control and Rendering
Unravelling in Collaborative Learning
Energy-Guided Continuous Entropic Barycenter Estimation for General Costs
Near-Minimax-Optimal Distributional Reinforcement Learning with a Generative Model
A Foundation Model for Zero-shot Logical Query Reasoning
NVRC: Neural Video Representation Compression
Binding in hippocampal-entorhinal circuits enables compositionality in cognitive maps
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
Unpacking DPO and PPO: Disentangling Best Practices for Learning from Preference Feedback
SpatialRGPT: Grounded Spatial Reasoning in Vision-Language Models
Hamiltonian Score Matching and Generative Flows
Explicit Eigenvalue Reguralization Improves Sharpness-Aware Minimization
What Makes Safety Fine-tuning Methods Safe? A Mechanistic Study
Binary Search Tree with Distributional Predictions
Non-convolutional graph neural networks.
Large language model validity via enhanced conformal prediction methods
SimGen: Simulator-conditioned Driving Scene Generation
Causal Temporal Representation Learning with Nonstationary Sparse Transition
SpecExec: Massively Parallel Speculative Decoding For Interactive LLM Inference on Consumer Devices
On the Stability and Generalization of Meta-Learning
State Chrono Representation for Enhancing Generalization in Reinforcement Learning
DiffuBox: Refining 3D Object Detection with Point Diffusion
ChatCam: Empowering Camera Control through Conversational AI
DMesh: A Differentiable Mesh Representation
LM-HT SNN: Enhancing the Performance of SNN to ANN Counterpart through Learnable Multi-hierarchical Threshold Model
GAMap: Zero-Shot Object Goal Navigation with Multi-Scale Geometric-Affordance Guidance
Training GNNs in Balance by Dynamic Rescaling
Improving Alignment and Robustness with Short Circuiting
Probablistic Emulation of a Global Climate Model with Spherical DYffusion
On the Optimal Time Complexities in Decentralized Stochastic Asynchronous Optimization
Lower Bounds and Optimal Algorithms for Non-Smooth Convex Decentralized Optimization over Time-Varying Networks
Sigmoid Gating is More Sample Efficient than Softmax Gating in Mixture of Experts
TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables
Inflationary Flows: Calibrated Bayesian Inference with Diffusion-Based Models
A Comprehensive Analysis on the Learning Curve in Kernel Ridge Regression
Piecewise deterministic generative models
Rethinking Decoders for Transformer-based Semantic Segmentation: Compression is All You Need
SAMPa: Sharpness-aware Minimization Parallelized
Provable Editing of Deep Neural Networks using Parametric Linear Relaxation
Mechanism Design Through Exploration Control: Optimizing the Trade-Off Between User and Creator Engagement
Principled Bayesian Optimization in Collaboration with Human Experts
Rethinking Score Distillation as a Bridge Between Image Distributions
Revisiting Self-Supervised Heterogeneous Graph Learning from Spectral Clustering Perspective
FedLPA: One-shot Federated Learning with Layer-Wise Posterior Aggregation
Reinforcing Language Agents via Policy Optimization with Action Decomposition
Blind Image Restoration via Fast Diffusion Inversion
Communication Bounds for the Distributed Experts Problem
Mixture of Adversarial LoRAs: Boosting Robust Generalization in Meta-tuning
Variance estimation for compound decisions
1-bit quanta video reconstruction via self-supervised photon prediction
Periodic agent-state based Q-learning for POMDPs
SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigation
HDR-GS: Efficient High Dynamic Range Novel View Synthesis at 1000x Speed via Gaussian Splatting
WaterMax: breaking the LLM watermark detectability-robustness-quality trade-off
Heterogeneity-Guided Client Sampling: Towards Fast and Efficient Non-IID Federated Learning
Efficient Multi-task LLM Quantization and Serving for Multiple LoRA Adapters
Asymptotics of Alpha-Divergence Variational Inference Algorithms with Exponential Families
BiScope: AI-generated Text Detection by Checking Memorization of Preceding Tokens
Classification Done Right for Vision-Language Pre-Training
Mixture of Nested Experts: Adaptive Processing of Visual Tokens
Model-free Low-Rank Reinforcement Learning via Leveraged Entry-wise Matrix Estimation
Structured flexibility in recurrent neural networks via neuromodulation
MVSDet: Multi-View Indoor 3D Object Detection via Efficient Plane Sweeps
Noisy Label Learning with Instance-Dependent Outliers: Identifiability via Crowd Wisdom
HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data
Local and Adaptive Mirror Descents in Extensive-Form Games
LLM Processes: Numerical Predictive Distributions Conditioned on Natural Language
Schur Nets: exploiting local structure for equivariance in higher order graph neural networks
Learning the Infinitesimal Generator of Stochastic Diffusion Processes
OmniTokenizer: A Joint Image-Video Tokenizer for Visual Generation
Physics-informed Neural Networks for Functional Differential Equations: Cylindrical Approximation and Its Convergence Guarantees
Universal In-Context Approximation By Prompting Fully Recurrent Models
Embedding Dimension of Contrastive Learning and $k$-Nearest Neighbors
Learning from Snapshots of Discrete and Continuous Data Streams
Preference-based Pure Exploration
Value-Based Deep Multi-Agent Reinforcement Learning with Dynamic Sparse Training
Skill-aware Mutual Information Optimisation for Zero-shot Generalisation in Reinforcement Learning
Achievable Fairness on Your Data With Utility Guarantees
Bayesian Domain Adaptation with Gaussian Mixture Domain-Indexing
Humanoid Locomotion as Next Token Prediction
Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
Towards Calibrated Robust Fine-Tuning of Vision-Language Models
Simulated Humanoid Grasping on Diverse Objects
Learning Low-Rank Feature for Thorax Disease Classification
HOI-Swap: Swapping Objects in Videos with Hand-Object Interaction Awareness
Active Set Ordering
CorDA: Context-Oriented Decomposition Adaptation of Large Language Models
Continuous Heatmap Regression for Pose Estimation via Implicit Neural Representation
MeshXL: Neural Coordinate Field for Generative 3D Foundation Models
Instruction Tuning With Loss Over Instructions
First-Order Minimax Bilevel Optimization
Navigating the Safety Landscape: Measuring Risks in Finetuning Large Language Models
Nonparametric Evaluation of Noisy ICA Solutions
FRHOzen: Loss-Based Data Selection for Targeted Language Model Pre-training
Trap-MID: Trapdoor-based Defense against Model Inversion Attacks
Visual Sketchpad: Sketching as a Visual Chain of Thought for Multimodal Language Models
Antigen-Specific Antibody Design via Direct Energy-based Preference Optimization
On the Convergence of Loss and Uncertainty-based Active Learning Algorithms
Consistency of Neural Causal Partial Identification
Erasing Undesirable Concepts in Diffusion Models with Adversarial Preservation
GL-NeRF: Gauss-Laguerre Quadrature Enables Training-Free NeRF Acceleration
Lightweight Frequency Masker for Cross-Domain Few-Shot Semantic Segmentation
Confusion-Resistant Federated Learning via Diffusion-Based Data Harmonization on Non-IID Data
Achievable distributional robustness when the robust risk is only partially identified
Byzantine Robustness and Partial Participation Can Be Achieved at Once: Just Clip Gradient Differences
An effective framework for estimating individualized treatment rule with multi-category treatments
Transferability Bound Theory: Exploring Relationship between Adversarial Transferability and Flatness
Where Do Large Learning Rates Lead Us?
Hybrid Generative AI for De Novo Design of Co-Crystals with Enhanced Tabletability
Continuous Temporal Domain Generalization
Generative Modelling of Structurally Constrained Graphs
Neural Network Reparametrization for Accelerated Optimization in Molecular Simulations
Diffusion of Thought: Chain-of-Thought Reasoning in Diffusion Language Models
Learning Plaintext-Ciphertext Cryptographic Problems via ANF-based SAT Instance Representation
The Power of Extrapolation in Federated Learning
Structured Learning of Compositional Sequential Interventions
LLM Dataset Inference: Detect Datasets, not Strings
How Far Can Transformers Reason? The Locality Barrier and Inductive Scratchpad
TabEBM: A Tabular Data Augmentation Method with Class-Specific Energy-Based Models
When LLM Meets DRL: Advancing Jailbreaking Efficiency via DRL-guided Search
Target-Guided Adversarial Point Cloud Transformer Towards Recognition Against Real-world Corruptions
Benchmarking the Reasoning Robustness against Noisy Rationales in Chain-of-thought Prompting
Probing the Decision Boundaries of In-context Learning in Large Language Models
Euclidean distance compression via deep random features
Enhancing Large Vision Language Models with Self-Training on Image Comprehension
A Critical Evaluation of AI Feedback for Aligning Large Language Models
Edit Distance Robust Watermarks via Indexing Pseudorandom Codes
A Metalearned Neural Circuit for Nonparametric Bayesian Inference
Speeding up non-parametric regression via distribution compression
CLIP in Mirror: Disentangling text from visual images through reflection
Replay-and-Forget-Free Graph Class-Incremental Learning: A Task Profiling and Prompting Approach
Policy Improvement using Language Feedback Models
On Affine Homotopy between Language Encoders
Generalized Linear Bandits with Limited Adaptivity
AutoTimes: Autoregressive Time Series Forecasters via Large Language Models
SlowFocus: Enhancing Fine-grained Temporal Understanding in Video LLM
TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks
DiffusionFake: Enhancing Generalization in Deepfake Detection via Guided Stable Diffusion
Pruning neural network models for gene regulatory dynamics using data and domain knowledge
Stabilizing Linear Passive-Aggressive Online Learning with Weighted Reservoir Sampling
Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
ProxyFusion: Face Feature Aggregation Through Sparse Experts
Language Generation in the Limit
Analysing Multi-Task Regression via Random Matrix Theory with Application to Time Series Forecasting
AutoSurvey: Large Language Models Can Automatically Write Surveys
Masked Hard-Attention Transformers Recognize Exactly the Star-Free Languages
Robust and Faster Zeroth-order Minimax Optimization: Complexity and Applications
Toxicity Detection for Free
Predicting Label Distribution from Ternary Labels
LLaNA: Large Language and NeRF Assistant
Understanding and Improving Training-free Loss-based Diffusion Guidance
Leveraging an ECG Beat Diffusion Model for Morphological Reconstruction from Indirect Signals
Constrained Diffusion Models via Dual Training
3D Structure Prediction of Atomic Systems with Flow-based Direct Preference Optimization
Fast Tree-Field Integrators: From Low Displacement Rank to Topological Transformers
Last-Iterate Convergence for Generalized Frank-Wolfe in Monotone Variational Inequalities
Revisiting K-mer Profile for Effective and Scalable Genome Representation Learning
QuanTA: Efficient High-Rank Fine-Tuning of LLMs with Quantum-Informed Tensor Adaptation
Learning from Noisy Labels via Conditional Distributionally Robust Optimization
CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for Bird's Eye View Object Detection
Remove that Square Root: A New Efficient Scale-Invariant Version of AdaGrad
Matching the Statistical Query Lower Bound for $k$-Sparse Parity Problems with Stochastic Gradient Descent
DiChaViT: Diverse Representations Boosts Channel-Adaptive Vision Transformers
Rethinking Out-of-Distribution Detection on Imbalanced Data Distribution
Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
Dual Defense: Enhancing Privacy and Mitigating Poisoning Attacks in Federated Learning
Data Mixture Inference Attack: BPE Tokenizers Reveal Training Data Compositions
On the Parameter Identifiability of Partially Observed Linear Causal Models
On Socially Fair Low-Rank Approximation and Column Subset Selection
Learning Noisy Halfspaces with a Margin: Massart is No Harder than Random
Novel Object Synthesis via Adaptive Text-Image Harmony
Spectral Graph Pruning Against Over-Squashing and Over-Smoothing
Unsupervised Hierarchy-Agnostic Segmentation: Parsing Semantic Image Structure
Diffusion-DICE: In-Sample Diffusion Guidance for Offline Reinforcement Learning
Training an Open-Vocabulary Monocular 3D Detection Model without 3D Data
A Theory of Optimistically Universal Online Learnability for General Concept Classes
Distributionally Robust Performative Prediction
Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain
Bayesian Online Natural Gradient (BONG)
PuLID: Pure and Lightning ID Customization via Contrastive Alignment
Multi-hypotheses Conditioned Point Cloud Diffusion for 3D Human Reconstruction from Occluded Images
On the Benefits of Public Representations for Private Transfer Learning under Distribution Shift
Membership Inference on Text-to-Image Diffusion Models via Conditional Likelihood Discrepancy
EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer
GPT as Visual Explainer
Online Non-convex Learning in Dynamic Environments
UniMTS: Unified Pre-training for Motion Time Series
Make Continual Learning Stronger via C-Flat
Neural Combinatorial Optimization for Robust Routing Problem with Uncertain Travel Times
Is Knowledge Power? Dissecting Information Asymmetry In Repeated Games
Aligning LLM Agents by Learning Latent Preference from User Edits
Understanding, Rehearsing, and Introspecting: Learn a Policy from Textual Tutorial Books in Football Games
Deep Policy Gradient Without Batch Updates or a Replay Buffer
Language Grounded Multi-Agent Communication for Ad-hoc Teamwork
Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning
Tensor-Based Synchronization and the Low-Rankness of the Block Trifocal Tensor
Recursive Introspection: Teaching Foundation Model Agents How to Self-Improve
Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability
Multiple Physics Pretraining for Spatiotemporal Surrogate Models
Pre-Trained Multi-Goal Transformers with Prompt Optimization for Efficient Online Adaptation
GaussianCube: A Structured and Explicit Radiance Representation for 3D Generative Modeling
Intervention and Conditioning in Causal Bayesian Networks
Learning Distinguishable Trajectory Representation with Contrastive Loss
DAGER: Exact Gradient Inversion for Large Language Models
Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization
Metacognitive Capabilities of LLMs: An Exploration in Mathematical Problem Solving
CosAE: Learnable Fourier Series for Image Restoration
MSA Generation with Seqs2Seqs Pretraining: Advancing Protein Structure Predictions
Don't Compress Gradients in Random Reshuffling: Compress Gradient Differences
PAC-Bayes-Chernoff bounds for unbounded losses
TAPTRv2: Tracking Any Point with Transformers as Detection
Simplifying Latent Dynamics with Softly State-Invariant World Models
Fourier-enhanced Implicit Neural Fusion Network for Multispectral and Hyperspectral Image Fusion
The Limits of Differential Privacy in Online Learning
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
Fast Proxy Experiment Design for Causal Effect Identification
Enhancing Robustness of Last Layer Two-Stage Fair Model Corrections
Exploring and Exploiting the Asymmetric Valley of Deep Neural Networks
Ex Uno Pluria: Insights on Ensembling in Low Precision Number Systems
Taming "data-hungry" reinforcement learning? Stability in continuous state-action spaces
Spatio-Spectral Graph Neural Networks
OccFusion: Rendering Occluded Humans with Generative Diffusion Priors
Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs
UV-free Texture Generation with Denoising and Heat Diffusion
Bidirectional Recurrence for Cardiac Motion Tracking with Gaussian Process Latent Coding
Optimal Private and Communication Constraint Distributed Goodness-of-Fit Testing for Discrete Distributions in the Large Sample Regime
HYDRA: Model Factorization Framework for Black-Box LLM Personalization
Progressive Cross-Scale Self-Supervised Blind Image Deconvolution via Implicit Neural Representation
Swap Regret, Symmetry, and Nash Convergence in Games
Improving Linear System Solvers for Hyperparameter Optimisation in Iterative Gaussian Processes
Multistep Distillation of Diffusion Models via Moment Matching
Stabilizing Zero-Shot Prediction: A Novel Antidote to Forgetting in Continual Vision-Language Tasks
VLMimic: Vision Language Models are Visual Imitation Learner for Fine-grained Actions
Testing Calibration in Nearly-Linear Time
Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
AdanCA: Neural Cellular Automata As Adaptors For More Robust Vision Transformer
Out-Of-Distribution Detection with Diversification (Provably)
Inferring stochastic low-rank recurrent neural networks from neural data
Learning Interaction-aware 3D Gaussian Splatting for One-shot Hand Avatars
Fully Unconstrained Online Learning
Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem
SequentialAttention++ for Block Sparsification: Differentiable Pruning Meets Combinatorial Optimization
QWO: Speeding Up Permutation-Based Causal Discovery in LiGAMs
Clustering then Propagation: Select Better Anchors for Knowledge Graph Embedding
FERERO: A Flexible Framework for Preference-Guided Multi-Objective Learning
Contracting with a Learning Agent
CausalDiff: Causality-Inspired Disentanglement via Diffusion Model for Adversarial Defense
Addressing bias in online selection with limited budget of comparisons
InterDreamer: Less Supervision for More Generalizable Text-Driven 3D Human-Object Interaction Synthesis
Bias Amplification in Language Model Evolution: An Iterated Learning Perspective
A Unifying Normative Framework of Decision Confidence
Multi-Group Proportional Representation
SELF-DISCOVER: Large Language Models Self-Compose Reasoning Structures
Efficient Adaptation of Pre-trained Vision Transformer via Householder Transformation
Divide-and-Conquer Posterior Sampling for Denoising Diffusion priors
Provably Faster Algorithms for Bilevel Optimization via Without-Replacement Sampling
Slot State Space Models
Self-Calibrating Conformal Prediction
BERTs are Generative In-Context Learners
Rethinking Fourier Transform for Long-term Time Series Forecasting: A Basis Functions Perspective
Symbolic Regression with a Learned Concept Library
Generative Fractional Diffusion Models
Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits
Model Sensitivity Aware Continual Learning
Genetic-guided GFlowNets for Sample Efficient Molecular Optimization
SLowcalSGD : Slow Query Points Improve Local-SGD for Stochastic Convex Optimization
Great Minds Think Alike: The Universal Convergence Trend of Input Salience
MQT-LLaVA: Matryoshka Query Transformer for Large Vision-Language Models
MVSplat360: Benchmarking 360$\textdegree$ Generalizable 3D Novel View Synthesis from Sparse Views
$\textit{NeuroPath}$: A Neural Pathway Transformer for Joining the Dots of Human Connectomes
Instance-Optimal Private Density Estimation in the Wasserstein Distance
On the Minimax Regret for Contextual Linear Bandits and Multi-Armed Bandits with Expert Advice
AROMA: Preserving Spatial Structure for Latent PDE Modeling with Local Neural Fields
Contrastive-Equivariant Self-Supervised Learning Improves Alignment with Primate Visual Area IT
Understanding Transformer Reasoning Capabilities via Graph Algorithms
What does guidance do? A fine-grained analysis in a simple setting
SpelsNet: Surface Primitive Elements Segmentation by B-Rep Graph Structure Supervision
Proportional Fairness in Non-Centroid Clustering
Expanding Sparse Tuning for Low Memory Usage
Transferable Boltzmann Generators
Causal Context Adjustment Loss for Learned Image Compression
Optimal Transport-based Labor-free Text Prompt Modeling for Sketch Re-identification
One Sample Fits All: Approximating All Probabilistic Values Simultaneously and Efficiently
Persistent Homology for High-dimensional Data Based on Spectral Methods
Improving Neural ODE Training with Temporal Adaptive Batch Normalization
xLSTM: Extended Long Short-Term Memory
A New Neural Kernel Regime: The Inductive Bias of Multi-Task Training
Buffer of Thoughts: Thought-Augmented Reasoning with Large Language Models
Disentangling Interpretable Factors of Variations with Supervised Independent Subspace Principal Component Analysis
Learning Transferable Features for Implicit Neural Representations
Ensuring Right Prediction With Right Rationale
Feint Behaviors and Strategies: Formalization, Implementation and Evaluation
Many-Shot In-Context Learning
DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data
MultiOOD: Scaling Out-of-Distribution Detection for Multiple Modalities
Learning to Embed Distributions via Maximum Kernel Entropy
I Bet You Did Not Mean That: Semantic Importance of Any Classifier via Betting
Global Convergence in Training Large-Scale Transformers
Attention boosted Individualized Regression
Model Reconstruction Using Counterfactual Explanations: A Perspective From Polytope Theory
Disentangling the Roles of Distinct Cell Classes with Cell-Type Dynamical Systems
When and How Does Synthetic Data Improve Reasoning Capabilities of Language Models?
Score-based 3D molecule generation with neural fields
A Bayesian Approach to Data Point Selection
A Flexible, Equivariant Framework for Subgraph GNNs via Graph Products and Graph Coarsening
IPM-LSTM: A Learning-Based Interior Point Method for Solving Nonlinear Programs
Coded Computing: A Learning-Theoretic Framework
Compact Language Models via Pruning and Knowledge Distillation
Minimax Optimal and Computationally Efficient Algorithms for Distributionally Robust Offline Reinforcement Learning
MSPE: Multi-Scale Patch Embedding Prompts Vision Transformers to Any Resolution
Weisfeiler and Leman Go Loopy: A New Hierarchy for Graph Representational Learning
Stability and Generalization of Adversarial Training for Shallow Neural Networks with Smooth Activation
Optimization Algorithm Design via Electric Circuits
Spectral-Risk Safe Reinforcement Learning with Convergence Guarantees
Articulate your NeRF: Unsupervised articulated object modeling via conditional view synthesis
Noise-Aware Differentially Private Regression via Meta-Learning
Computational Aspects of Bayesian Persuasion under Approximate Best Response
Pearls from Pebbles: Improved Confidence Functions for Auto-labeling
Implicit Multimodal Alignment: On the Generalization of Frozen LLMs to Multimodal Inputs
Transformers need glasses! Information over-squashing in language tasks
Globally Convergent Variational Inference
GO4Align: Group Optimization for Multi-Task Alignment
Private Algorithms for Stochastic Saddle Points and Variational Inequalities: Beyond Euclidean Geometry
NeuroClips: Towards High-fidelity and Smooth fMRI-to-Video Reconstruction
Visual Prompt Tuning in Null Space for Continual Learning
Graph Diffusion Policy Optimization
Finding Transformer Circuits With Edge Pruning
Learning Cut Generating Functions for Integer Programming
Any2Policy: Learning Visuomotor Policy with Any-Modality
BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO
Improving Neural Network Surface Processing with Principal Curvatures
Efficient Sketches for Training Data Attribution and Studying the Loss Landscape
Efficient Adversarial Training in LLMs with Continuous Attacks
Improved Generation of Adversarial Examples Against Safety-aligned LLMs
S-STE: Continuous Pruning Function for Efficient 2:4 Sparse Pre-training
Extensive-Form Game Solving via Blackwell Approachability on Treeplexes
Optimal and Approximate Adaptive Stochastic Quantization
Learning high-dimensional targets by two-parameter models and gradient flow
Robust Reinforcement Learning with General Utility
Contrasting with Symile: Simple Model-Agnostic Representation Learning for Unlimited Modalities
Unified Insights: Harnessing Multi-modal Data for Phenotype Imputation via View Decoupling
WeiPer: OOD Detection using Weight Perturbations of Class Projections
ReplaceAnything3D: Text-Guided Object Replacement in 3D Scenes with Compositional Scene Representations
Scale Equivariant Graph Meta Networks
Identifying spatio-temporal relations between anomalies and extreme events
Learning Social Welfare Functions
Stratified Prediction-Powered Inference for Effective Hybrid Evaluation of Language Models
Offline Behavior Distillation
SOFTS: Efficient Multivariate Time Series Forecasting with Series-Core Fusion
Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials
Benign overfitting in leaky ReLU networks with moderate input dimension
Looks Too Good To Be True: An Information-Theoretic Analysis of Hallucinations in Generative Restoration Models
Pin-Tuning: Parameter-Efficient In-Context Tuning for Few-shot Molecular Property Prediction
FSP-Laplace: Function-Space Priors for the Laplace Approximation in Bayesian Deep Learning
Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
Identifiability Analysis of Linear ODE Systems with Hidden Confounders
The Power of Resets in Online Reinforcement Learning
Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging
DMPlug: A Plug-in Method for Solving Inverse Problems with Diffusion Models
SwitchHead: Accelerating Transformers with Mixture-of-Experts Attention
Learning Diffusion Priors from Observations by Expectation Maximization
Not All Diffusion Model Activations Have Been Evaluated as Discriminative Features
Identifying Functionally Important Features with End-to-End Sparse Dictionary Learning
QTIP: Quantization with Trellises and Incoherence Processing
Revisiting Ensembling in One-Shot Federated Learning
DeltaDEQ: Exploiting Heterogeneous Convergence for Accelerating Deep Equilibrium Iterations
Vidu4D: Single Generated Video to High-Fidelity 4D Reconstruction with Dynamic Gaussian Surfels
Ensemble Learning for Heterogeneous Large Language Models with Deep Parallel Collaboration
Untrained Neural Nets for Snapshot Compressive Imaging: Theory and Algorithms
Asynchronous Perception Machine for Test Time Training
Provably and Practically Efficient Adversarial Imitation Learning with General Function Approximation
Progressive Entropic Optimal Transport Solvers
Utilizing Human Behavior Modeling to Manipulate Explanations in AI-Assisted Decision Making: The Good, the Bad, and the Ugly
Do's and Don'ts: Learning Desirable Skills with Instruction Videos
Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
Prediction-Powered Ranking of Large Language Models
Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)
Stable Minima Cannot Overfit in Univariate ReLU Networks: Generalization by Large Step Sizes
You Don't Need Data-Augmentations in Self-Supervised Learning
RouterDC: Query-Based Router by Dual Contrastive Learning for Assembling Large Language Models
Doubly Mild Generalization for Offline Reinforcement Learning
Uncovering the Redundancy in Graph Self-supervised Learning Models
Error Analysis of Spherically Constrained Least Squares Reformulation in Solving the Stackelberg Prediction Game
A Boosting-Type Convergence Result for AdaBoost.MH with Factorized Multi-Class Classifiers
Richelieu: Self-Evolving LLM-Based Agents for AI Diplomacy
Slot-VLM: Object-Event Slots for Video-Language Modeling
ReLU Characteristic Activation Analysis
Factorized Diffusion Architectures for Unsupervised Image Generation and Segmentation
Connecting the Dots: LLMs can Infer and Verbalize Latent Structure from Disparate Training Data
Learning with Fitzpatrick Losses
ContextCite: Attributing Model Generation to Context
Amortized Active Causal Induction with Deep Reinforcement Learning
Right this way: Can VLMs Guide Us to See More to Answer Questions?
Language Models as Zero-shot Lossless Gradient Compressors: Towards General Neural Parameter Prior Models
Zero-Shot Reinforcement Learning from Low Quality Data
Diffusion Policies creating a Trust Region for Offline Reinforcement Learning
Improved Particle Approximation Error for Mean Field Neural Networks
Universal Rates of Empirical Risk Minimization
Sample-Efficient Private Learning of Mixtures of Gaussians
Team-Fictitious Play for Reaching Team-Nash Equilibrium in Multi-team Games
Fast Rates for Bandit PAC Multiclass Classification
Energy-based Epistemic Uncertainty for Graph Neural Networks
Linear Time Approximation Algorithm for Column Subset Selection with Local Search
Prompt Optimization with EASE? Efficient Ordering-aware Automated Selection of Exemplars
Memorize What Matters: Emergent Scene Decomposition from Multitraverse
xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token
Using Time-Aware Graph Neural Networks to Predict Temporal Centralities in Dynamic Graphs
Adaptive Visual Scene Understanding: Incremental Scene Graph Generation
Scalable DP-SGD: Shuffling vs. Poisson Subsampling
Classifier Clustering and Feature Alignment for Federated Learning under Distributed Concept Drift
CogVLM: Visual Expert for Pretrained Language Models
Diffusion Imitation from Observation
Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
The Sample-Communication Complexity Trade-off in Federated Q-Learning
Inevitable Trade-off between Watermark Strength and Speculative Sampling Efficiency for Language Models
Robust Neural Contextual Bandit against Adversarial Corruptions
Topological Generalization Bounds for Discrete-Time Stochastic Optimization Algorithms
On the Optimality of Dilated Entropy and Lower Bounds for Online Learning in Extensive-Form Games
Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
Separations in the Representational Capabilities of Transformers and Recurrent Architectures
Fair and Welfare-Efficient Constrained Multi-Matchings under Uncertainty
Open-Book Neural Algorithmic Reasoning
Active Perception for Grasp Detection via Neural Graspness Field
Addressing Hidden Confounding with Heterogeneous Observational Datasets for Recommendation
Policy Optimization for Robust Average Reward MDPs
Learning Discrete Latent Variable Structures with Tensor Rank Conditions
Rethinking the Dynamics of Spiking Neural Networks
How does Architecture Influence the Base Capabilities of Pre-trained Language Models? A Case Study Based on FFN-Wider and MoE Transformers
Locating What You Need: Towards Adapting Diffusion Models to OOD Concepts In-the-Wild
One-shot Federated Learning via Synthetic Distiller-Distillate Communication
Perceiving Longer Sequences With Bi-Directional Cross-Attention Transformers
Exploring Molecular Pretraining Model at Scale
Fine-grained Image-to-LiDAR Contrastive Distillation with Visual Foundation Models
Worst-Case Offline Reinforcement Learning with Arbitrary Data Support
Transformers on Markov data: Constant depth suffices
LION: Linear Group RNN for 3D Object Detection in Point Clouds
ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification
Scalable and Effective Arithmetic Tree Generation for RL-Driven Adder and Multiplier Designs
Reinforcement Learning Gradients as Vitamin for Online Finetuning Decision Transformers
On the Efficiency of ERM in Feature Learning
Text2CAD: Generating Sequential CAD Designs from Beginner-to-Expert Level Text Prompts
Hierarchical and Density-based Causal Clustering
Unlocking Tokens as Data Points for Generalization Bounds on Larger Language Models
Categorical Flow Matching on Statistical Manifolds
Imitating Language via Scalable Inverse Reinforcement Learning
SIRIUS : Contexual Sparisty with Correction for Efficient LLMs
Deep Support Vectors
Conditional Density Estimation with Histogram Trees
TOPA: Extend Large Language Models for Video Understanding via Text-Only Pre-Alignment
e-COP : Episodic Constrained Optimization of Policies
DARG: Dynamic Evaluation of Large Language Models via Adaptive Reasoning Graph
Towards Exact Gradient-based Training on Analog In-memory Computing
Minimizing UCB: a Better Local Search Strategy in Local Bayesian Optimization
Robust Gaussian Processes via Relevance Pursuit
Who Needs Features? On the Surprising Effectiveness of Attention Transfer for Vision Transformers
Motion Forecasting in Continuous Driving
Unsupervised Modality Adaptation with Text-to-Image Diffusion Models for Semantic Segmentation
CausalStock: Deep End-to-end Causal Discovery for News-driven Multi-stock Movement Prediction
Relating Hopfield Networks to Episodic Control
Molecule Generation with Fragment Retrieval Augmentation
T2V-Turbo: Breaking the Quality Bottleneck of Video Consistency Model with Mixed Reward Feedback
Improving Context-Aware Preference Modeling for Language Models
Bootstrapping Top-down Information for Self-modulating Slot Attention
DiTFastAtten: Accelerate Diffusion Transformers Through Efficient Attention Computation
Gaussian Process Bandits for Top-k Recommendations
Exploring Low-Dimensional Subspace in Diffusion Models for Controllable Image Editing
Motion Graph Unleashed: A Novel Approach to Video Prediction
NoMAD-Attention: Efficient LLM Inference on CPUs Through Multiply-add-free Attention
Continual Learning with Global Alignment
On Learning Physical Neural Representations of Dynamical Data
Gradient-based Discrete Sampling with Automatic Cyclical Scheduling
Regularized Q-Learning
Do Finetti: On Causal Effects for Exchangeable Data
Seek Commonality but Preserve Differences: Dissected Dynamics Modeling for Multi-modal Visual RL
Alleviate Anchor-Shift: Explore Blind Spots with Cross-View Reconstruction for Incomplete Multi-View Clustering
Improving Robustness of 3D Point Cloud Recognition from a Fourier Perspective
MetaUAS: Universal Anomaly Segmentation with One-Prompt Meta-Learning
Resolving Discrepancies in Compute-Optimal Scaling of Language Models
Unveiling Induction Heads: Provable Training Dynamics and Feature Learning in Transformers
What is my quantum computer good for? Quantum capability learning with physics-aware neural networks
Convolutional Differentiable Logic Gate Networks
Active, anytime-valid risk controlling prediction sets
A Near-optimal Algorithm for Learning Margin Halfspaces with Massart Noise
Chain-of-Thought Reasoning Without Prompting
Taming Heavy-Tailed Losses in Adversarial Bandits and the Best-of-Both-Worlds Setting
DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning
BAdam: A Memory Efficient Full Parameter Optimization Method for Large Language Models
Iterative Reasoning Preference Optimization
FlexSBDD: Structure-Based Drug Design with Flexible Protein Modeling
Disentangled Style Domain for Implicit $z$-Watermark Towards Copyright Protection
Aligning Embeddings and Geometric Random Graphs: Informational Results and Computational Approaches for the Procrustes-Wasserstein Problem
Provably Optimal Memory Capacity for Modern Hopfield Models
Introspective Planning: Aligning Robots' Uncertainty with Inherent Task Ambiguity
On Complexity of Teaching a Family of Linear Behavior Cloning Learners
A Method for Evaluating Hyperparameter Sensitivity in Reinforcement Learning
Private Edge Density Estimation for Random Graphs: Optimal, Efficient and Robust
The Dormant Neuron Phenomenon in Multi-Agent Reinforcement Learning Value Factorization
Strategic Littlestone Dimension: Improved Bounds on Online Strategic Classification
Linear Regression using Heterogeneous Data Batches
Differentially Private Optimization with Sparse Gradients
Treeffuser: probabilistic prediction via conditional diffusions with gradient-boosted trees
Instance-Specific Asymmetric Sensitivity in Differential Privacy
Score Distillation via Reparametrized DDIM
Efficiency of the First-Price Auction in the Autobidding World
Expectile Regularization for Fast and Accurate Training of Neural Optimal Transport
Bias Detection via Signaling
Towards Dynamic Message Passing on Graphs
How Does Black-Box Impact the Learning Guarantee of Stochastic Compositional Optimization?
Human-Assisted Out-of-Distribution Generalization and Detection
Optimal Classification under Performative Distribution Shift
AsyncDiff: Parallelizing Diffusion Models by Asynchronous Denoising
AP-Adapter: Improving Generalization of Automatic Prompts on Unseen Text-to-Image Diffusion Models
Recurrent neural networks: vanishing and exploding gradients are not the end of the story
DCDepth: Progressive Monocular Depth Estimation in Discrete Cosine Domain
Boundary Matters: A Bi-Level Active Finetuning Method
ETO:Efficient Transformer-based Local Feature Matching by Organizing Multiple Homography Hypotheses
Equivariant Neural Diffusion for Molecule Generation
A theoretical case-study of Scalable Oversight in Hierarchical Reinforcement Learning
Efficient Multi-task Reinforcement Learning with Cross-Task Policy Guidance
Conformal Classification with Equalized Coverage for Adaptively Selected Groups
Multidimensional Fractional Programming for Normalized Cuts
D-MiSo: Editing Dynamic 3D Scenes using Multi-Gaussians Soup
Improving the Learning Capability of Small-size Image Restoration Network by Deep Fourier Shifting Operator over Resource-limited Scene
Learning to Decouple the Lights for 3D Face Texture Modeling
Cluster-wise Graph Transformer with Dual-granularity Kernelized Attention
Multi-Agent Coordination via Multi-Level Communication
Fearless Stochasticity in Expectation Propagation
Low Degree Hardness for Broadcasting on Trees
SEA: State-Exchange Attention for High-Fidelity Physics-Based Transformers
The Edge-of-Reach Problem in Offline Model-Based Reinforcement Learning
Decoding-Time Language Model Alignment with Multiple Objectives
EGonc : Energy-based Open-Set Node Classification with substitute Unknowns
On the Inductive Bias of Stacking Towards Improving Reasoning
A Swiss Army Knife for Heterogeneous Federated Learning: Flexible Coupling via Trace Norm
Theoretical Foundations of Deep Selective State-Space Models
Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation
Generative Adversarial Bayesian Optimization for Surrogate Objectives
Post-Hoc Reversal: Are We Selecting Models Prematurely?
Stylus: Automatic Adapter Selection for Diffusion Models
Training Data Attribution via Approximate Unrolling
B-ary Tree Push-Pull Method is Provably Efficient for Distributed Learning on Heterogeneous Data
FairQueue: Rethinking Prompt Learning for Fair Text-to-Image Generation
Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning
Alleviating Distortion in Image Generation via Multi-Resolution Diffusion Models
Geometric-Averaged Preference Optimization for Soft Preference Labels
Enhancing Large Language Models through Adaptive Tokenizers
Graph Structure Inference with BAM: Introducing the Bilinear Attention Mechanism
Multiclass Transductive Online Learning
LLM Circuit Analyses Are Consistent Across Training and Scale
On Tractable $\Phi$-Equilibria in Non-Concave Games
Better by default: Strong pre-tuned MLPs and boosted trees on tabular data
Unleashing the Potential of the Diffusion Model in Few-shot Semantic Segmentation
Exploiting Activation Sparsity with Dense to Dynamic-k Mixture-of-Experts Conversion
Understanding Emergent Abilities of Language Models from the Loss Perspective
Accelerating Best-of-N via Speculative Rejection
Geometry Awakening: Cross-Geometry Learning Exhibits Superiority over Individual Structures
Retrieval & Fine-Tuning for In-Context Tabular Models
LLMs as Zero-shot Graph Learners: Alignment of GNN Represetantions with LLM Token Embeddings
Bridging semantics and pragmatics in information-theoretic emergent communication
How Does Variance Shape the Regret in Contextual Bandits?
Optimal Scalarizations for Sublinear Hypervolume Regret
Automated Efficient Estimation using Monte Carlo Efficient Influence Functions
Last-Iterate Global Convergence of Policy Gradients for Constrained Reinforcement Learning
Towards Understanding Extrapolation: a Causal Lens
Externally Valid Policy Evaluation from Randomized Trials Using Additional Observational Data
RadarOcc: Robust 3D Occupancy Prediction with 4D Imaging Radar
Meta-Exploiting Frequency Prior for Cross-Domain Few-Shot Learning
Adaptive Experimentation When You Can't Experiment
Replicability in Learning: Geometric Partitions and KKM-Sperner Lemma
Multi-language Diversity Benefits Autoformalization
Quantitative Convergences of Lie Group Momentum Optimizers
Gaussian Graph Network: Learning Efficient and Generalizable Gaussian Representations from Multi-view Images
Provably Mitigating Overoptimization in RLHF: Your SFT Loss is Implicitly an Adversarial Regularizer
Weight Diffusion for Future: Learn to Generalize in Non-Stationary Environments
When Is Inductive Inference Possible?
Aligning Individual and Collective Objectives in Multi-Agent Cooperation
Dendritic Integration Inspired Artificial Neural Networks Enhance Data Correlation
Partial Transportability for Domain Generalization
Automating Data Annotation under Strategic Human Agents: Risks and Potential Solutions
DiffuserLite: Towards Real-time Diffusion Planning
Stochastic Optimization Algorithms for Instrumental Variable Regression with Streaming Data
On the cohesion and separability of average-link for hierarchical agglomerative clustering
Distributional Preference Alignment of LLMs via Optimal Transport
MINI-SEQUENCE TRANSFORMER: Optimizing Intermediate Memory for Long Sequences Training
The Sample Complexity of Gradient Descent in Stochastic Convex Optimization
EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models
Temporal Graph Neural Tangent Kernel with Graphon-Guaranteed
Compute-efficient LLM Training via Online Batch Selection
Reparameterization invariance in approximate Bayesian inference
HOPE: Shape Matching Via Aligning Different K-hop Neighbourhoods
Delving into the Reversal Curse: How Far Can Large Language Models Generalize?
Sketched Lanczos uncertainty score: a low-memory summary of the Fisher information
Understanding Linear Probing then Fine-tuning Language Models from NTK Perspective
Generalized Tensor Decomposition for Understanding Multi-Output Regression under Combinatorial Shifts
Language-Driven Interactive Traffic Trajectory Generation
Can Models Learn Skill Composition from Examples?
Closed-Loop Visuomotor Control with Generative Expectation for Robotic Manipulation
Theoretical and Empirical Insights into the Origins of Degree Bias in Graph Neural Networks
FlowTurbo: Towards Real-time Flow-Based Image Generation with Velocity Refiner
I2EBench: A Comprehensive Benchmark for Instruction-based Image Editing
An Adaptive Approach for Infinitely Many-armed Bandits under Generalized Rotting Constraints
Warm-up Free Policy Optimization: Improved Regret in Linear Markov Decision Processes
Wide Two-Layer Networks can Learn from Adversarial Perturbations
Multilingual Diversity Improves Vision-Language Representations
Evidential Stochastic Differential Equations for Time-Aware Sequential Recommendation
Mitigating Fine-tuning based Jailbreak Attack with Backdoor Enhanced Safety Alignment
On the Computational Landscape of Replicable Learning
Improving Ab-Initio Cryo-EM Reconstruction with Semi-Amortized Pose Inference
Multi-view Masked Contrastive Representation Learning for Endoscopic Video Analysis
Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?
Trajectory Diffusion for ObjectGoal Navigation
A Global Depth-Range-Free Multi-View Stereo Transformer Network with Pose Embedding
Truth is Universal: Robust Detection of Lies in LLMs
Schrodinger Bridge Flow for Unpaired Data Translation
Learning-Augmented Priority Queues
Dense Associative Memory Through the Lens of Random Features
Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
Bayesian-Guided Label Mapping for Visual Reprogramming
Are Large-scale Soft Labels Necessary for Large-scale Dataset Distillation?
Data Distribution Valuation
Cooperate or Collapse: Emergence of Sustainability in a Society of LLM Agents
Mixture of Tokens: Continuous MoE through Cross-Example Aggregation
Maximizing utility in multi-agent environments by anticipating the behavior of other learners
Score-Optimal Diffusion Schedules
Confidence Regulation Neurons in Language Models
DarkSAM: Fooling Segment Anything Model to Segment Nothing
Understanding the Expressive Power and Mechanisms of Transformer for Sequence Modeling
Private and Personalized Frequency Estimation in a Federated Setting
BitsFusion: 1.99 bits Weight Quantization of Diffusion Model
ALPS: Improved Optimization for Highly Sparse One-Shot Pruning for Large Language Models
Near-Optimal Distributionally Robust RL with General $L_p$ Norms
Neural collapse vs. low-rank bias: Is deep neural collapse really optimal?
DeNetDM: Debiasing by Network Depth Modulation
Non-parametric classification via expand-and-sparsify representation
Sourcerer: Sample-based Maximum Entropy Source Distribution Estimation
Generalization of Hamiltonian algorithms
FlowLLM: Flow Matching for Material Generation with Learned Base Distributions
Can LLMs Learn by Teaching? A Preliminary Study
The Road Less Scheduled
Learning-Augmented Algorithms with Explicit Predictors
ScaleKD: Strong Vision Transformers Could Be Excellent Teachers
Queueing Matching Bandits with Preference Feedback
Not All Tokens Are What You Need for Pretraining
Reliable Learning of Halfspaces under Gaussian Marginals
KVQuant: Towards 10 Million Context Length LLM Inference with KV Cache Quantization
CoFie: Learning Compact Neural Surface Representations with Coordinate Fields
A General Protocol to Probe Large Vision Models for 3D Physical Understanding
Grounding Multimodal Large Language Models in Actions
Promoting Fairness Among Dynamic Agents in Online-Matching Markets under Known Stationary Arrival Distributions
Test-time Adaptation in Non-stationary Environments via Adaptive Representation Alignment
RefDrop: Controllable Consistency in Image or Video Generation via Reference Feature Guidance
Fast Iterative Hard Thresholding Methods with Pruning Gradient Computations
Learning Versatile Skills with Curriculum Masking
Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games
SyncTweedies: A General Generative Framework Based on Synchronized Diffusions
Achieving Constant Regret in Linear Markov Decision Processes
Bridge the Modality and Capacity Gaps in Vision-Language Model Selection
Voxel Proposal Network via Multi-Frame Knowledge Distillation for Semantic Scene Completion
PointAD: Comprehending 3D Anomalies from Points and Pixels for Zero-shot 3D Anomaly Detection
FreqMark: Invisible Image Watermarking via Frequency Based Optimization in Latent Space
Layer-Adaptive $\mathcal{H}_\infty$ State Pruning for Deep Diagonal State Space Model Compression
Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
DiGRAF: Diffeomorphic Graph-Adaptive Activation Function
Zero-to-Hero: Enhancing Zero-Shot Novel View Synthesis via Attention Map Filtering
Meta-Learning Universal Priors Using Non-Injective Change of Variables
Abstracted Shapes as Tokens - A Generalizable and Interpretable Model for Time-series Classification
Probabilistic Federated Prompt-Tuning in Data Imbalance Settings
$SE(3)$ Equivariant Ray Embeddings for Implicit Multi-View Depth Estimation
Dynamic 3D Gaussian Fields for Urban Areas
Class Distribution Shifts in Zero-Shot Learning: Learning Robust Representations
PACE: Pacing Operator Learning to Accurate Optical Field Simulation for Complicated Photonic Devices
A teacher-teacher framework for clinical language representation learning
Visual Fourier Prompt Tuning
Self-playing Adversarial Language Game Enhances LLM Reasoning
P$^2$C$^2$Net: PDE-Preserved Coarse Correction Network for efficient prediction of spatiotemporal dynamics
Segment Anything without Supervision
Code Agents are State of the Art Software Testers
Statistical Efficiency of Distributional Temporal Difference
Safety through feedback in Constrained RL
SCRREAM : SCan, Register, REnder And Map: A Framework for Annotating Accurate and Dense 3D Indoor Scenes with a Benchmark
IKEA Manuals at Work: 4D Grounding of Assembly Instructions on Internet Videos
LibAMM: Empirical Insights into Approximate Computing for Accelerating Matrix Multiplication
HEMM: Holistic Evaluation of Multimodal Foundation Models
VidProM: A Million-scale Real Prompt-Gallery Dataset for Text-to-Video Diffusion Models
OpenSatMap: A Fine-grained High-resolution Satellite Dataset for Large-scale Map Construction
OpenCDA-Loop: A Closed-loop Benchmarking Platform for End-to-end Evaluation of Cooperative Perception
UKnow: A Unified Knowledge Protocol with Multimodal Knowledge Graph Datasets for Reasoning and Vision-Language Pre-Training
ConceptMix: A Compositional Image Generation Benchmark with Controllable Difficulty
ImageNet3D: Towards General-Purpose Object-Level 3D Understanding
SciFIBench: Benchmarking Large Multimodal Models for Scientific Figure Interpretation
Bench2Drive: Towards Multi-Ability Benchmarking of Closed-Loop End-To-End Autonomous Driving
Infusing Synthetic Data with Real-World Patterns for Zero-Shot Material State Segmentation
Benchmarking Uncertainty Disentanglement: Specialized Uncertainties for Specialized Tasks
NanoBaseLib: A Multi-Task Benchmark Dataset for Nanopore Sequencing
UnlearnCanvas: Stylized Image Dataset for Enhanced Machine Unlearning Evaluation in Diffusion Models
GC-Bench: An Open and Unified Benchmark for Graph Condensation
CharXiv: Charting Gaps in Realistic Chart Understanding in Multimodal LLMs
ConMe: Rethinking Evaluation of Compositional Reasoning for Modern VLMs
FUSU: A Multi-temporal-source Land Use Change Segmentation Dataset for Fine-grained Urban Semantic Understanding
Streaming Detection of Queried Event Start
SeafloorGenAI: A Large-scale Vision-Language Dataset for Seafloor Geological Survey
MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations
A Simulation Benchmark for Autonomous Racing with Large-Scale Human Data
FindingEmo: An Image Dataset for Emotion Recognition in the Wild
LucidAction: A Hierarchical and Multi-model Dataset for Comprehensive Action Quality Assessment
BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays
FiVA: Fine-grained Visual Attribute Dataset for Text-to-Image Diffusion Models
LongVideoBench: A Benchmark for Long-context Interleaved Video-Language Understanding
Expecting The Unexpected: Towards Broad Out-Of-Distribution Detection
DART-Eval: A Comprehensive DNA Language Model Evaluation Benchmark on Regulatory DNA
Scalable Early Childhood Reading Performance Prediction
Infer Induced Sentiment of Comment Response to Video: A New Task, Dataset and Baseline
IncomeSCM: From tabular data set to time-series simulator and causal estimation benchmark
APEBench: A Benchmark for Autoregressive Neural Emulators of PDEs
NeuralPlane: An Efficiently Parallelizable Platform for Fixed-wing Aircraft Control with Reinforcement Learning
UltraMedical: Building Specialized Generalists in Biomedicine
Task Me Anything
VastTrack: Vast Category Visual Object Tracking
WildVision: Evaluating Vision-Language Models in the Wild with Human Preferences
Visual CoT: Advancing Multi-Modal Language Models with a Comprehensive Dataset and Benchmark for Chain-of-Thought Reasoning
FVEL: Interactive Formal Verification Environment with Large Language Models via Theorem Proving
HEST-1k: A Dataset For Spatial Transcriptomics and Histology Image Analysis
VideoGUI: A Benchmark for GUI Automation from Instructional Videos
Benchmarking the Attribution Quality of Vision Models
PEACE: A Dataset of Pharmaceutical Care for Cancer Pain Analgesia Evaluation and Medication Decision
BetterBench: Assessing AI Benchmarks, Uncovering Issues, and Establishing Best Practices
On the Effects of Data Scale on Computer Control Agents
Norms for Managing Datasets: A Systematic Review of NeurIPS Datasets
TorchSpatial: A Location Encoding Framework and Benchmark for Spatial Representation Learning
GeSS: Benchmarking Geometric Deep Learning under Scientific Applications with Distribution Shifts
EffiBench: Benchmarking the Efficiency of Automatically Generated Code
Human-Aware Vision-and-Language Navigation: Bridging Simulation to Reality with Dynamic Human Interactions
Indoor Air Quality Dataset with Activities of Daily Living in Low to Middle-income Communities
Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models
Benchmarking Estimators for Natural Experiments: A Novel Dataset and a Doubly Robust Algorithm
Terra: A Multimodal Spatio-Temporal Dataset Spanning the Earth
NN4SysBench: Characterizing Neural Network Verification for Computer Systems
Evaluating Large Vision-and-Language Models on Children's Mathematical Olympiads
MMM-RS: A Multi-modal, Multi-GSD, Multi-scene Remote Sensing Dataset and Benchmark for Text-to-Image Generation
A Benchmark Suite for Evaluating Neural Mutual Information Estimators on Unstructured Datasets
Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
A Novel Benchmark for Decision-Making in Uncertain and Competitive Games
Needle In A Multimodal Haystack
GTA: A Benchmark for General Tool Agents
Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming
Revisiting Few-Shot Object Detection with Vision-Language Models
PertEval: Unveiling Real Knowledge Capacity of LLMs with Knowledge-Invariant Perturbations
DetectEval: Benchmarking LLM-Generated Text Detection in Real-World Scenarios
WFCRL: A Multi-Agent Reinforcement Learning Benchmark for Wind Farm Control
A SARS-CoV-2 Interaction Dataset and VHH Sequence Corpus for Antibody Language Models
Brain Treebank: Large-scale intracranial recordings from naturalistic language stimuli
A Retrospective on the Robot Air Hockey Challenge: Benchmarking Robust, Reliable, and Safe Learning Techniques for Real-world Robotics
WikiDBs: A Large-Scale Corpus Of Relational Databases From Wikidata
OVT-B: A New Large-Scale Benchmark for Open-Vocabulary Multi-Object Tracking
Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation
SHDocs: A dataset, benchmark, and method to efficiently generate high-quality, real-world specular highlight data with near-perfect alignment
ViLCo-Bench: VIdeo Language COntinual learning Benchmark
FEDMEKI: A Benchmark for Scaling Medical Foundation Models via Federated Knowledge Injection
The Fragility of Fairness: Causal Sensitivity Analysis for Fair Machine Learning
STimage-1K4M: A histopathology image-gene expression dataset for spatial transcriptomics
Comprehensive Framework for Curating Speech Datasets and Evaluating ASR Systems: A Case Study for the Polish Language
Towards Visual Text Design Transfer Across Languages
ActionAtlas: A VideoQA Benchmark for Fine-grained Action Recognition
CableInspect-AD: An Expert-Annotated Anomaly Detection Dataset
Is Function Similarity Over-Engineered? Building a Benchmark
Implicit Zoo: A Large-Scale Dataset of Neural Implicit Functions for 2D Images and 3D Scenes
Reactzyme: A Benchmark for Enzyme-Reaction Prediction
BIOSCAN-5M: A Multimodal Dataset for Insect Biodiversity
IMDL-BenCo: A Comprehensive Benchmark and Codebase for Image Manipulation Detection & Localization
$\texttt{pfl-research}$: simulation framework for accelerating research in Private Federated Learning
Benchmark Repositories for Better Benchmarking
Prejudice and Volatility: A Statistical Framework for Measuring Social Discrimination in Large Language Models
Can LLMs Solve Molecule Puzzles? A Multimodal Benchmark for Molecular Structure Elucidation
Evaluating Copyright Takedown Methods for Language Models
Towards Comprehensive Detection of Chinese Harmful Memes: Dataset and Detector
Instruction Tuning Large Language Models to Understand Electronic Health Records
Assemblage: Automatic Binary Dataset Construction for Machine Learning
Job-SDF: A Multi-Granularity Dataset for Job Skill Demand Forecasting and Benchmarking
TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs
SUGARCREPE++ Dataset: Vision-Language Model Sensitivity to Semantic and Lexical Alterations
Vript: A Video Is Worth Thousands of Words
AudioMarkBench: Benchmarking Robustness of Audio Watermarking
EvoCodeBench: An Evolving Code Generation Benchmark with Domain-Specific Evaluations
E.T. Bench: Towards Open-Ended Event-Level Video-Language Understanding
WildPPG: A Real-World PPG Dataset of Long Continuous Recordings
Benchmarking LLMs via Uncertainty Quantification
XLand-MiniGrid: Scalable Meta-Reinforcement Learning Environments in JAX
TACT: Advancing Complex Aggregative Reasoning with Information Extraction Tools
MARVEL: Multidimensional Abstraction and Reasoning through Visual Evaluation and Learning
$\texttt{dopanim}$: A Dataset of Doppelganger Animals with Noisy Annotations from Multiple Humans
$\nabla^2$DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials
AMBROSIA: A Benchmark for Parsing Ambiguous Questions into Database Queries
Fit for our purpose, not yours: Benchmark for a low-resource, Indigenous language
A Data-Centric Perspective on Evaluating Machine Learning Models for Tabular Data
CURE4Rec: A Benchmark for Recommendation Unlearning with Deeper Influence
Noisy Ostracods: A Fine-Grained, Imbalanced Real-World Dataset for Benchmarking Robust Machine Learning and Label Correction Methods
MathPile: A Billion-Token-Scale Pretraining Corpus for Math
Revisiting, Benchmarking and Understanding Unsupervised Graph Domain Adaptation
WindsorML - High-Fidelity Computational Fluid Dynamics Dataset For Automotive Aerodynamics
PowerGraph: A power grid benchmark dataset for graph neural networks
ClashEval: Quantifying the tug-of-war between an LLM’s internal prior and external evidence
TAPVid-3D: A Benchmark for Tracking Any Point in 3D
UniTox: Leveraging LLMs to Curate a Unified Dataset of Drug-Induced Toxicity from FDA Labels
FT-AED: Benchmark Dataset for Early Freeway Traffic Anomalous Event Detection
ABCFair: an Adaptable Benchmark approach for Comparing Fairness Methods
$\texttt{dattri}$: A Library for Efficient Data Attribution
DECO-Bench: Unified Benchmark for Decoupled Task-Agnostic Synthetic Data Release
What to Say and When to Say it: Live Fitness Coaching as a Testbed for Situated Interaction
cPAPERS: A Dataset of Situated and Multimodal Interactive Conversations in Scientific Papers
StackEval: Benchmarking LLMs in Coding Assistance
Kuro Siwo: 33 billion $m^2$ under the water. A global multi-temporal satellite dataset for rapid flood mapping
shapiq: Shapley Interactions for Machine Learning
Evaluate calibration of language models with folktexts
M3LEO: A Multi-Modal, Multi-Label Earth Observation Dataset Integrating Interferometric SAR and RGB Data
RepLiQA: A Question-Answering Dataset for Benchmarking LLMs on Unseen Reference Content
TabularBench: Benchmarking Adversarial Robustness for Tabular Deep Learning in Real-world Use-cases
Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
WorkArena++: Towards Compositional Planning and Reasoning-based Common Knowledge Work Tasks
WildGuard: Open One-stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs
Stronger Than You Think: Benchmarking Weak Supervision on Realistic Tasks
Time-MMD: A New Multi-Domain Multimodal Dataset for Time Series Analysis
RedPajama: an Open Dataset for Training Large Language Models
ClevrSkills: Compositional Language And Visual Understanding in Robotics
DiscoveryWorld: A Virtual Environment for Developing and Evaluating Automated Scientific Discovery Agents
Benchmarking Out-of-Distribution Generalization Capabilities of DNN-based Encoding Models for the Ventral Visual Cortex.
The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale
CryoBench: Datasets and Benchmarks for Heterogeneous Cryo-EM Reconstruction
Topic-Conversation Relevance (TCR) Dataset and Benchmarks
HelpSteer 2: Open-source dataset for training top-performing reward models
UniBench: Visual Reasoning Requires Rethinking Vision-Language Beyond Scaling
MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens
BLURD: Benchmarking and Learning using a Unified Rendering and Diffusion Model
DevBench: A multimodal developmental benchmark for language learning
QGym: Scalable Simulation and Benchmarking of Queuing Network Controllers
μBench: A Microscopy Benchmark for Vision-Language Understanding
Melting Pot Contest: Charting the Future of Generalized Cooperative Intelligence
Towards Reliable Model Selection for Unsupervised Domain Adaptation: An Empirical Study and A Certified Baseline
Benchmarking Out-of-Distribution Generalization and Adaptation for Electromyography
Newswire: A Large-Scale Structured Database of a Century of Historical News
Human-level shape inferences: A benchmark for evaluating the 3D understanding of vision models
Using Unity to Help Solve Reinforcement Learning
DivSafe: Evaluating the Generalization of LLM Safety Training Across Diverse Tasks and Prompt Types
CLAVE: An Adaptive Framework for Evaluating Values of LLM Generated Responses
OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments
Beyond Prompts: Dynamic Conversational Benchmarking of Large Language Models
Unraveling Molecular Structure: A Multimodal Spectroscopic Dataset for Chemistry
SRFUND: A Multi-Granularity Hierarchical Structure Reconstruction Benchmark in Form Understanding
TSGM: A Flexible Framework for Generative Modeling of Synthetic Time Series
BABILong: Testing the Limits of LLMs with Long Context Reasoning-in-a-Haystack
FairJob: A Real-World Dataset for Fairness in Online Systems
Multi-Chain Graphs of Graphs: A New Paradigm in Blockchain Dataset
Proving Olympiad Algebraic Inequalities without Human Demonstrations
FlashAttention-3: Fast and Accurate Attention with Asynchrony and Low-precision
Muharaf: Manuscripts of Handwritten Arabic Dataset for Cursive Text Recognition
Through the Looking-Glass: Tracing Shifts in AI Data Consent across the Web
Simplified and Generalized Masked Diffusion for Discrete Data
Sparse High Rank Adapters
FouRA: Fourier Low-Rank Adaptation
pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning
Reward Learning from Human Demonstration Improves Supervised Fine-tuning for LLM Alignment
Aligner Encoders: Self-Attention Transformers Can Be Self-Transducers
OpenDebateEvidence: A Massive-Scale Argument Mining and Summarization Dataset
SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers
Nonlocal Attention Operator: Materializing Hidden Knowledge Towards Interpretable Physics Discovery
PACE: marrying the generalization of PArameter-efficient fine-tuning with Consistency rEgularization
CARE: a Benchmark Suite for the Classification and Retrieval of Enzymes
LINGOLY: A Benchmark of Olympiad-Level Linguistic Reasoning Puzzles in Low Resource and Extinct Languages
Einsum Benchmark: Enabling the Development of Next-Generation Tensor Execution Engines
Real-time Core-Periphery Guided ViT with Smart Data Layout Selection on Mobile Devices
xMIL: Insightful Explanations for Multiple Instance Learning in Histopathology
MambaLRP: Explaining Selective State Space Sequence Models
Learning to Edit Visual Programs with Self-Supervision
EnsIR: An Ensemble Algorithm for Image Restoration via Gaussian Mixture Models
SustainDC: Benchmarking for Sustainable Data Center Control
ReFT: Representation Finetuning for Language Models
RMLR: Extending Multinomial Logistic Regression into General Geometries
Federated Ensemble-Directed Offline Reinforcement Learning
Stress-Testing Long-Context Language Models with Lifelong ICL and Task Haystack
User-item fairness tradeoffs in recommendations
Medformer: A Multi-Granularity Patching Transformer for Medical Time-Series Classification
StepbaQ: Stepping backward as Correction for Quantized Diffusion Models
Temporally Consistent Atmospheric Turbulence Mitigation with Neural Representations
Large Language Model Unlearning via Embedding-Corrupted Prompts
The Unmet Promise of Synthetic Training Images: Using Retrieved Real Images Performs Better
SparseLLM: Towards Global Pruning of Pre-trained Language Models
SceneDiffuser: Efficient and Controllable Driving Simulation Initialization and Rollout
Flaws can be Applause: Unleashing Potential of Segmenting Ambiguous Objects in SAM
CONTRAST: Continual Multi-source Adaptation to Dynamic Distributions
Gated Slot Attention for Efficient Linear-Time Sequence Modeling
Toward Robust Incomplete Multimodal Sentiment Analysis via Representation Factorization and Alignment
FedGMark: Certifiably Robust Watermarking for Federated Graph Learning
Improving optimal control and estimation methods adapted to the noise characteristics of the sensorimotor system
When LLMs Meet Cunning Texts: A Fallacy Understanding Benchmark for Large Language Models
CLIPLoss and Norm-Based Data Selection Methods for Multimodal Contrastive Learning
GenAI Arena: An Open Evaluation Platform for Generative Models
GV-Rep: A Large-Scale Dataset for Genetic Variant Representation Learning
MARPLE: A Benchmark for Long-Horizon Inference
FinCon: A Synthesized LLM Multi-Agent System with Conceptual Verbal Reinforcement for Enhanced Financial Decision Making
SR-CACO-2: A Dataset for Confocal Fluorescence Microscopy Image Super-Resolution
Learn To be Efficient: Build Structured Sparsity in Large Language Models
When to Sense and Control? A Time-adaptive Approach for Continuous-Time RL
Transductive Active Learning: Theory and Applications
The iNaturalist Sounds Dataset
Towards General Conceptual Model Editing via Adversarial Representation Engineering
Video Token Merging for Long Video Understanding
Voxel Mamba: Group-Free State Space Models for Point Cloud based 3D Object Detection
Task-oriented Time Series Imputation Evaluation via Generalized Representers
FactorizePhys: Effective Spatial-Temporal Attention in Remote Photo-plethysmography through Factorization of Voxel Embeddings
A Prompt Learning based Regulation Framework for Generalizable Point Cloud Analysis
Zero-Shot Scene Reconstruction from Single Images with Deep Prior Assembly
Neural Signed Distance Function Inference through Splatting 3D Gaussians Pulled on Zero-Level Set
Binocular-Guided 3D Gaussian Splatting with View Consistency for Sparse View Synthesis
Enhancing Large Language Models via Additional Pre-Training on Principled Synthetic Logic Corpus
Attack-Resilient Image Watermarking Using Stable Diffusion
Physics-Informed Regularization for Domain-Agnostic Dynamical System Modeling
Domain Adaptation for Large-Vocabulary Object Detectors
Decision-Making Behavior Evaluation Framework for LLMs under Uncertain Context
Do Multimodal Foundation Models Understand Enterprise Workflows? A Benchmark for Business Process Management Tasks
DreamScene: Layout-Guided 3D Scene Generation
Value Imprint: A Technique for Auditing the Human Values Embedded in RLHF Datasets
Source Code Foundation Models are Transferable Binary Analysis Knowledge Bases
Towards Effective Planning Strategies for Dynamic Opinion Networks
PaGoDA: Progressive Growing of a One-Step Generator from a Low-Resolution Diffusion Teacher
Dataset Decomposition: Faster LLM Training with Variable Sequence Length Curriculum
Mixture of Demonstrations for In-Context Learning
Efficient Prompt Optimization Through the Lens of Best Arm Identification
FASTopic: A Fast, Adaptive, Stable, and Transferable Topic Modeling Paradigm
Taming the Long Tail in Human Mobility Prediction
Adaptable Logical Control for Large Language Models
Alignment for Honesty
Lexicon3D: Probing Visual Encoding Models for Complex 3D Scene Understanding
Base of RoPE Bounds Context Length
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
KFNN: K-Free Nearest Neighbor For Crowdsourcing
IWBVT: Instance Weighting-based Bias-Variance Trade-off for Crowdsourcing
MedSafetyBench: Evaluating and Improving the Medical Safety of Large Language Models
An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations
Discrete-state Continuous-time Diffusion for Graph Generation
BackTime: Backdoor Attacks on Multivariate Time Series Forecasting
Learning to Shape In-distribution Feature Space for Out-of-distribution Detection
Prototypical Hash Encoding for On-the-Fly Fine-Grained Category Discovery
Causal Inference in the Closed-Loop: Marginal Structural Models for Sequential Excursion Effects
Optical Diffusion Models for Image Generation
Dual-frame Fluid Motion Estimation with Test-time Optimization and Zero-divergence Loss
SCaR: Refining Skill Chaining for Long-Horizon Robotic Manipulation via Dual Regularization
Segment Any Change
Enhancing Zero-Shot Vision Models by Label-Free Prompt Distribution Learning and Bias Correcting
Exclusively Penalized Q-learning for Offline Reinforcement Learning
Approximating mutual information of high-dimensional variables using learned representations
Make the Most of Your Data: Changing the Training Data Distribution to Improve Generalization
Diffusion Representation for Reinforcement Learning
Architect: Generating Vivid and Interactive 3D Scenes with Hierarchical 2D Inpainting
Learning to Reason via Program Generation, Emulation, and Search
Faster Neighborhood Attention: Reducing the O(n^2) Cost of Self Attention at the Threadblock Level
Biomedical Visual Instruction Tuning with Clinician Preference Alignment
Model Fusion through Bayesian Optimization in Language Model Fine-Tuning
TFGDA: Exploring Topology and Feature Alignment in Semi-supervised Graph Domain Adaptation through Robust Clustering
Implicit Precursor Extraction with Expert Retriever for Inorganic Retrosynthesis
Capturing the denoising effect of PCA via compression ratio
Dense Connector for MLLMs
Flexible Context-Driven Sensory Processing in Dynamical Vision Models
Are Language Models Actually Useful for Time Series Forecasting?
Inference of Neural Dynamics Using Switching Recurrent Neural Networks
Cost-aware Bayesian optimization via the Pandora's box Gittins index
Cell ontology guided transcriptome foundation model
The Effectiveness of Surprisingly Popular Voting with Partial Preferences
Aligning Diffusion Models by Optimizing Human Utility
BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
OASIS: Conditional Distribution Shaping for Offline Safe Reinforcement Learning
Risk-Averse Finetuning of Large Language Models
Exploiting Representation Curvature for Boundary Detection in Time Series
From News to Forecast: Integrating Event Analysis in LLM-Based Time Series Forecasting with Reflection
ReFIR: Grounding Large Restoration Models with Retrieval Augmentation
BoostAdapter: Improving Test-Time Adaptation via regional boostraping
Diffusion Unlearning Optimization for Robust and Safe Text-to-Image Models
Understanding Model Selection for Learning in Strategic Environments
Safe Exploitative Play in Stochastic Bayesian Games with Untrusted Type Beliefs
DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation
Dual-Perspective Activation: Efficient Channel Denoising via Joint Forward-Backward Criterion for Artificial Neural Networks
CLAP4CLIP: Continual Learning with Probabilistic Finetuning for Vision-Language Models
A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysis
GraphVis: Boosting LLMs with Visual Knowledge Graph Integration
RA-PbRL: Provably Efficient Risk-Aware Preference-Based Reinforcement Learning
QUEEN: QUantized Efficient ENcoding for Streaming Free-viewpoint Videos
First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
OSLO: One-Shot Label-Only Membership Inference Attacks
RedCode: Multi-dimensional Safety Benchmark for Code Agents
A Separation in Heavy-Tailed Sampling: Gaussian vs. Stable Oracles for Proximal Samplers
Zeroth-Order Sampling Methods for Non-Log-Concave Distributions: Alleviating Metastability by Denoising Diffusion
Evaluating the design space of diffusion-based generative models
Fast Graph Sharpness-Aware Minimization for Enhancing and Accelerating Few-Shot Node Classification
Scientific Consistency Improves upon Multi-Task Learning in Molecular Science
Fine-grained Control of Generative Data Augmentation in IoT Sensing
Understanding the Limits of Vision Language Models Through the Lens of the Binding Problem
Ultrafast classical phylogenetic method beats large protein language models on variant effect prediction
EMR-Merging: Tuning-Free High-Performance Model Merging
NeuRodin: A Two-stage Framework for High-Fidelity Neural Surface Reconstruction
DiffPano: Scalable and Consistent Text to Panorama Generation with Spherical Epipolar-Aware Diffusion
Rethinking the Capacity of Graph Neural Networks for Branching Strategy
Length Optimization in Conformal Prediction
Reward Machines for Deep RL in Noisy and Uncertain Environments
Invariant Tokenization for Language Model Enabled Crystal Materials Generation
Adaptive Randomized Smoothing: Certifying Multi-Step Defences against Adversarial Examples
DiPEx: Dispersing Prompt Expansion for Class-Agnostic Object Detection
HyperDDPM: Estimating Epistemic and Aleatoric Uncertainty with a Single Model
DiffusionPDE: Generative PDE-Solving under Partial Observation
Near-Optimal Approximation of Matrix Functions by the Lanczos Method
Ensemble sampling for linear bandits: small ensembles suffice
Block Transformer: Global-to-Local Language Modeling for Fast Inference
A Neural Network Approach for Efficiently Answering Most Probable Explanation Queries in Probabilistic Models
Temporal-Difference Learning Using Distributed Error Signals
STONE: A Submodular Optimization Framework for Active 3D Object Detection
Validating Climate Models with Spherical Convolutional Wasserstein Distance
3D Gaussian Can Be Sparser Than You Thought: Efficient Rendering via Learned Fragment Pruning
Truncated Variance Reduced Value Iteration
Expressive Gaussian Human Avatars from Monocular RGB Video
On the Impact of Feature Heterophily on Link Prediction with Graph Neural Networks
2D-OOB: Attributing Data Contribution through Joint Valuation Framework
Immiscible Diffusion: Accelerating Diffusion Training with Noise Assignment
Grammar-Aligned Decoding
Principled Probabilistic Imaging using Diffusion Models as Plug-and-Play Priors
A Generative Approach to Control Complex Physical Systems
Deep Learning in Medical Image Registration: Magic or Mirage?
Transferable Reinforcement Learning via Generalized Occupancy Models
Who’s asking? User personas and the mechanics of latent misalignment
Score-based generative models are provably robust: an uncertainty quantification perspective
Privacy Backdoors: Enhancing Membership Inference through Poisoning Pre-trained Models
Real-time Stereo-based 3D Object Detection for Streaming Perception
Incorporating Surrogate Gradient Norm to Improve Offline Optimization Techniques
On the Power of Decision Trees in Auto-Regressive Language Modeling
LuSh-NeRF: Lighting up and Sharpening NeRFs for Low-light Scenes
Newton Informed Neural Operator for Computing Multiple Solutions of Nonlinear Partials Differential Equations
Optimal Multiclass U-Calibration Error and Beyond
Quantum Deep Equilibrium Models
DeepDRK: Deep Dependency Regularized Knockoff for Feature Selection
DistillNeRF: Perceiving 3D Scenes from Single-Glance Images by Distilling Neural Fields and Foundation Model Features
Subject-driven Text-to-Image Generation via Preference-based Reinforcement Learning
Text-Infused Attention and Foreground-Aware Modeling for Zero-Shot Temporal Action Detection
Training-Free Adaptive Diffusion with Bounded Difference Approximation Strategy
Approaching Human-Level Forecasting with Language Models
From Dictionary to Tensor: A Scalable Multi-View Subspace Clustering Framework with Triple Information Enhancement
Robust Contrastive Multi-view Clustering against Dual Noisy Correspondence
Renovating Names in Open-Vocabulary Segmentation Benchmarks
WildGaussians: 3D Gaussian Splatting In the Wild
Conformalized Multiple Testing after Data-dependent Selection
In-N-Out: Lifting 2D Diffusion Prior for 3D Object Removal via Tuning-Free Latents Alignment
MeMo: Meaningful, Modular Controllers via Noise Injection
Aggregating Quantitative Relative Judgments: From Social Choice to Ranking Prediction
Towards Understanding Evolving Patterns in Sequential Data
MVGamba: Unify 3D Content Generation as State Space Sequence Modeling
VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidance
OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
Efficient and Private Marginal Reconstruction with Local Non-Negativity
FFAM: Feature Factorization Activation Map for Explanation of 3D Detectors
Sketching for Distributed Deep Learning: A Sharper Analysis
HourVideo: 1-Hour Video-Language Understanding
Large Language Models as Urban Residents: An LLM Agent Framework for Personal Mobility Generation
Solving Minimum-Cost Reach Avoid using Reinforcement Learning
Fast Channel Simulation via Error-Correcting Codes
Accelerating Inference with Fast and Expressive Sketch Structured Transform
PANORAMIA: Efficient Privacy Auditing of Machine Learning Models without Retraining
Combining Observational Data and Language for Species Range Estimation
Style Adaptation and Uncertainty Estimation for Multi-source Blended-Target Domain Adaptation
Exactly Minimax-Optimal Locally Differentially Private Sampling
The PRISM Alignment Dataset: What Participatory, Representative and Individualised Human Feedback Reveals About the Subjective and Multicultural Alignment of Large Language Models
ReMI: A Dataset for Reasoning with Multiple Images
ACES: Generating a Diversity of Challenging Programming Puzzles with Autotelic Generative Models
Latent Learning Progress Drives Autonomous Goal Selection in Human Reinforcement Learning
PaCE: Parsimonious Concept Engineering for Large Language Models
DAVED: Data Acquisition via Experimental Design for Data Markets
AutoMix: Automatically Mixing Language Models
TFS-NeRF: Template-Free NeRF for Semantic 3D Reconstruction of Dynamic Scene
SeeClear: Semantic Distillation Enhances Pixel Condensation for Video Super-Resolution
Evidence of Learned Look-Ahead in a Chess-Playing Neural Network
FINALLY: fast and universal speech enhancement with studio-like quality
Everyday Object Meets Vision-and-Language Navigation Agent via Backdoor
Identifying Equivalent Training Dynamics
UAV3D: A Large-scale 3D Perception Benchmark for Unmanned Aerial Vehicles
A Walsh Hadamard Derived Linear Vector Symbolic Architecture
Efficient Minimum Bayes Risk Decoding using Low-Rank Matrix Completion Algorithms
Continual Audio-Visual Sound Separation
Nearly Tight Black-Box Auditing of Differentially Private Machine Learning
Return of Unconditional Generation: A Self-supervised Representation Generation Method
Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformers
Autoregressive Image Generation without Vector Quantization
Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
Training-Free Visual Prompt Learning for Multimodal Large Language Models
Nimbus: Secure and Efficient Two-Party Inference for Transformers
Enhancing In-Context Learning Performance with just SVD-Based Weight Pruning: A Theoretical Perspective
Set-Based Prompting: Provably Solving the Language Model Order Dependency Problem
Human-AI Alignment in Chess with Skill-Aware Attention
Data-faithful Feature Attribution: Mitigating Unobservable Confounders via Instrumental Variables
Stochastic contextual bandits with graph feedback: from independence number to MAS number
The Elephant in the Room: Towards A Reliable Time-Series Anomaly Detection Benchmark
Harnessing Multiple Correlated Networks for Exact Community Recovery
An Any-to-Any Vision Model for Tens of Tasks and Modalities
Transcendence: Generative Models Can Outperform The Experts That Train Them
Identity Decoupling for Multi-Subject Personalization of Text-to-Image Models
Knowledge Graph Fine-Tuning Upon Open-World Knowledge from Large Language Models
Stochastic Extragradient with Flip-Flop Shuffling & Anchoring: Provable Improvements
Position Coupling: Leveraging Task Structure for Improved Length Generalization of Transformers
Provable Benefit of Cutout and CutMix for Feature Learning
DASH: Warm-Starting Neural Network Training Without Loss of Plasticity Under Stationarity
Optimal Algorithms for Augmented Testing of Discrete Distributions
Statistical-Computational Trade-offs for Density Estimation
Improving Gloss-free Sign Language Translation by Reducing Representation Density
Diffusion4D: Fast Spatial-temporal Consistent 4D generation via Video Diffusion Models
Adapting Diffusion Models for Improved Prompt Compliance and Controllable Image Synthesis
LT-Defense: Searching-free Backdoor Defense via Exploiting Long-Tailed Effect
Does Egalitarian Fairness Lead to Instability? The Fairness Bounds in Stable Federated Learning Under Altruistic Behaviors
Seeing is NOT Always Believing! Unveiling the True Symmetric Moral Consistency of Large Language Models
SurgicAI: A Fine-grained Platform for Data Collection and Benchmarking in Surgical Policy Learning
Using Surrogates in Covariate-adjusted Response-adaptive Randomization Experiments with Delayed Outcomes
Random Representations Outperform Online Continually Learned Representations
Equivariant Blurring Diffusion for Hierarchical Molecular Conformer Generation
Diffusion Actor-Critic with Entropy Regulator
MemVLT: Vision-Language Tracking with Adaptive Memory-based Prompts
Efficient Centroid-Linkage Clustering
Black-Box Forgetting
Integrating GNN and Neural ODEs for Estimating Two-Body Interactions in Mixed-Species Collective Motion
Synergistic Dual Spatial-aware Generation of Image-to-text and Text-to-image
Boosting Graph Pooling with Persistent Homology
Referring Human Pose and Mask Estimation In the Wild
Adaptive Labeling for Efficient Out-of-distribution Model Evaluation
Recurrent neural network dynamical systems for biological vision
Physics-Guided Neural Impulse Response Field via Implicit Wave Propagation Modeling
Do Counterfactually Fair Image Classifiers Satisfy Group Fairness? -- A Theoretical and Empirical Study
On Neural Networks as Infinite Tree-Structured Probabilistic Graphical Models
ComBack: A Versatile Dataset for Enhancing Compiler Backend Development Efficiency
LCM: Locally Constrained Compact Point Cloud Model for Masked Point Modeling
DDN: Dual-domain Dynamic Normalization for Non-stationary Time Series Forecasting
FACT or Fiction: Can Truthful Mechanisms Eliminate Federated Free Riding?
Molecule Design by Latent Prompt Transformer
Cost-efficient Knowledge-based Question Answering with Large Language Models
KnowGPT: Knowledge Graph based Prompting for Large Language Models
Nuclear Fusion Diamond Polishing Dataset
Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
Easy2Hard-Bench: Standardized Difficulty Labels for Profiling LLM Performance and Generalization
Scalable Neural Network Verification with Branch-and-bound Inferred Cutting Planes
GITA: Graph to Visual and Textual Integration for Vision-Language Graph Reasoning
Sample-Efficient Geometry Reconstruction from Euclidean Distances using Non-Convex Optimization
Generalizing Consistency Policy to Visual RL with Prioritized Proximal Experience Regularization
Iteratively Refined Behavior Regularization for Offline Reinforcement Learning
Unlock the Intermittent Control Ability of Model Free Reinforcement Learning
CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making
MemoryFormer : Minimize Transformer Computation by Removing Fully-Connected Layers
YOLOv10: Real-Time End-to-End Object Detection
Alleviating Hallucinations in Large Vision-Language Models through Hallucination-Induced Optimization
CoIN: A Benchmark of Continual Instruction Tuning for Multimodel Large Language Models
Neuro-Symbolic Data Generation for Math Reasoning
Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency
Transformers Can Do Arithmetic with the Right Embeddings
Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs
Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators
Diffusion Priors for Variational Image Denoising
Autonomous Driving with Spiking Neural Networks
Coupled Mamba: Enhanced Multimodal Fusion with Coupled State Space Model
All-in-One Image Coding for Joint Human-Machine Vision with Multi-Path Aggregation
DA-Ada: Learning Domain-Aware Adapter for Domain Adaptive Object Detection
Jailbreaking Large Language Models Against Moderation Guardrails via Cipher Characters
Beyond the Doors of Perception: Vision Transformers Represent Relations Between Objects
AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents
Understanding Bias in Visual Datasets
Continuous Contrastive Learning for Long-Tailed Semi-Supervised Recognition
Constant Acceleration Flow
The Importance of Being Scalable: Efficient Architectures for Neural Network Potentials
EEGPT: Pretrained Transformer for Universal and Reliable Representation of EEG Signals
RSA: Resolving Scale Ambiguities in Monocular Depth Estimators through Language Descriptions
Diffusion-Reward Adversarial Imitation Learning
DN-4DGS: Denoised Deformable Network with Temporal-Spatial Aggregation for Dynamic Scene Rendering
MotionGS: Exploring Explicit Motion Guidance for Deformable 3D Gaussian Splatting
Towards Next-Level Post-Training Quantization of Hyper-Scale Transformers
ReVideo: Remake a Video with Motion and Content Control
Diffusion PID: Interpreting Diffusion via Partial Information Decomposition
S-MolSearch: 3D Semi-supervised Contrastive Learning for Bioactive Molecule Search
Localized Zeroth-Order Prompt Optimization
Learning Representations for Hierarchies with Minimal Support
Accelerating Self-supervised Learning Pretraining
Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
ARC: A Generalist Graph Anomaly Detector with In-Context Learning
The Best of Both Worlds: Toward an Honest and Helpful Large Language Model
DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control
A Pairwise Pseudo-likelihood Approach for Matrix Completion with Informative Missingness
Interactive Deep Clustering via Value Mining
Referencing Where to Focus: Improving Visual Grounding with Referential Query
Accelerating Pre-training of Multimodal LLMs via Chain-of-Sight
Visual Anchors Are Strong Information Aggregators For Multimodal Large Language Model
Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective
Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models
Beyond Efficiency: Molecular Data Pruning for Enhanced Generalization
Self-Guided Masked Autoencoder
CV-VAE: A Compatible Video VAE for Latent Generative Video Models
Graph-enhanced Optimizers for Structure-aware Recommendation Embedding Evolution
A Simple Framework for Generalization in Visual RL under Dynamic Scene Perturbations
Efficient Zero-Shot HOI Detection: Enhancing VLM Adaptation with Innovative Prompt Learning
Revisiting Adversarial Patches for Designing Camera-Agnostic Attacks against Person Detection
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
HENASY: Learning to Assemble Scene-Entities for Interpretable Egocentric Video-Language Model
DDGS-CT: Direction-Disentangled Gaussian Splatting for Realistic Volume Rendering
Long-Range Feedback Spiking Network Captures Dynamic and Static Representations of the Visual Cortex under Movie Stimuli
QKFormer: Hierarchical Spiking Transformer using Q-K Attention
Tangent Space Causal Inference: Leveraging Vector Fields for Causal Discovery in Dynamical Systems
GenWarp: Single Image to Novel Views with Semantic-Preserving Generative Warping
Activating Self-Attention for Multi-Scene Absolute Pose Regression
FlexMol: A Flexible Toolkit for Benchmarking Molecular Relational Learning
ProtGO: Function-Guided Protein Modeling for Unified Representation Learning
Learning Complete Protein Representation by Dynamically Coupling of Sequence and Structure
UniIF: Unified Molecule Inverse Folding
DTGB: A Comprehensive Benchmark for Dynamic Text-Attributed Graphs
Beyond task diversity: provable representation transfer for sequential multitask linear bandits
DP-SGD with Fixed-Size Minibatches: Tighter Guarantees with or without Replacement
Unveiling the Potential of Robustness in Selecting Conditional Average Treatment Effect Estimators
MergeMinds: Boosting Multilingual Reasoning with the Built-in Capabilities of LLMs
Localizing Memorization in SSL Vision Encoders
Open LLMs are Necessary for Private Adaptations and Outperform their Closed Alternatives
Class-wise Transformation Is All You Need
Large Language Models-guided Dynamic Adaptation for Temporal Knowledge Graph Reasoning
FineStyle: Fine-grained Controllable Style Personalization for Text-to-image Models
Learnable In-Context Vector for Visual Question Answering
Probabilistic Decomposed Linear Dynamical Systems for Robust Discovery of Latent Neural Dynamics
UrbanDataLayer: A Unified Data Pipeline for Urban Science
Non-asymptotic Approximation Error Bounds of Parameterized Quantum Circuits
SpGesture: Source-Free Domain-adaptive sEMG-based Gesture Recognition with Jaccard Attentive Spiking Neural Network
Plan-on-Graph: Self-Correcting Adaptive Planning of Large Language Model on Knowledge Graphs
VRSBench: A Versatile Vision-Language Benchmark Dataset for Remote Sensing Image Understanding
3DCoMPaT200: Language Grounded Large-Scale 3D Vision Dataset for Compositional Recognition
Alleviating Attention Bias for Visual-Informed Text Generation
Unveiling LoRA Intrinsic Ranks via Salience Analysis
SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models
LLMCBench: Benchmarking Large Language Model Compression for Efficient Deployment
Almost Surely Asymptotically Constant Graph Neural Networks
In Pursuit of Causal Label Correlations for Multi-label Image Recognition
DataComp-LM: In search of the next generation of training sets for language models
CoSW: Conditional Sample Weighting for Smoke Segmentation with Label Noise
Spectral Adapter: Fine-Tuning in Spectral Space
Reinforced Cross-Domain Knowledge Distillation on Time Series Data
Schedule Your Edit: A Simple yet Effective Diffusion Noise Schedule for Image Editing
Flipped Classroom: Aligning Teacher Attention with Student in Generalized Category Discovery
Boosting Alignment for Post-Unlearning Text-to-Image Generative Models
Nearest Neighbor Speculative Decoding for LLM Generation and Attribution
PCP-MAE: Learning to Predict Centers for Point Masked Autoencoders
VMamba: Visual State Space Model
Exploring Structured Semantic Priors Underlying Diffusion Score for Test-time Adaptation
Counterfactual Fairness by Combining Factual and Counterfactual Predictions
Magnet: We Never Know How Text-to-Image Diffusion Models Work, Until We Learn How Vision-Language Models Function
Data Augmentation with Diffusion for Open-Set Semi-Supervised Learning
Diversify, Contextualize, and Adapt: Efficient Entropy Modeling for Neural Image Codec
SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition
TPR: Topology-Preserving Reservoirs for Generalized Zero-Shot Learning
MM-WLAuslan: Multi-View Multi-Modal Word-Level Australian Sign Language Recognition Dataset
Conjugate Bayesian Two-step Change Point Detection for Hawkes Process
Hierarchical Object-Aware Dual-Level Contrastive Learning for Domain Generalized Stereo Matching
Abductive Reasoning in Logical Credal Networks
ESPACE: Dimensionality Reduction of Activations for Model Compression
Provable Guarantees for Model Performance via Mechanistic Intepretability
ReST-MCTS*: LLM Self-Training via Process Reward Guided Tree Search
Taming Cross-Domain Representation Variance in Federated Prototype Learning with Heterogeneous Data Domains
Towards Global Optimal Visual In-Context Learning Prompt Selection
NeuralSteiner: Learning Steiner Tree for Overflow-avoiding Global Routing in Chip Design
Is Your HD Map Constructor Reliable under Sensor Corruptions?
IPO: Interpretable Prompt Optimization for Vision-Language Models
Boosting Semi-Supervised Scene Text Recognition via Viewing and Summarizing
WenMind: A Comprehensive Benchmark for Evaluating Large Language Models in Chinese Classical Literature and Language Arts
DomainGallery: Few-shot Domain-driven Image Generation by Attribute-centric Finetuning
Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllability
DFA-GNN: Forward Learning of Graph Neural Networks by Direct Feedback Alignment
Parameter Efficient Adaptation for Image Restoration with Heterogeneous Mixture-of-Experts
Map It Anywhere: Empowering BEV Map Prediction using Large-scale Public Datasets
Meta-Diffu$B$: A Contextualized Sequence-to-Sequence Text Diffusion Model with Meta-Exploration
PeRFlow: Piecewise Rectified Flow as Universal Plug-and-Play Accelerator
Neuro-Vision to Language: Enhancing Visual Reconstruction and Language Interaction through Brain Recordings
Real-Time Selection Under General Constraints via Predictive Inference
Conformal Inverse Optimization
4-bit Shampoo for Memory-Efficient Network Training
DETAIL: Task DEmonsTration Attribution for Interpretable In-context Learning
ZSC-Eval: An Evaluation Toolkit and Benchmark for Multi-agent Zero-shot Coordination
Vocal Call Locator Benchmark (VCL'24) for localizing rodent vocalizations from multi-channel audio
MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs
Streaming Long Video Understanding with Large Language Models
Are We on the Right Way for Evaluating Large Vision-Language Models?
ShareGPT4Video: Improving Video Understanding and Generation with Better Captions
ResAD: A Simple Framework for Class Generalizable Anomaly Detection
A provable control of sensitivity of neural networks through a direct parameterization of the overall bi-Lipschitzness
ART: Automatic Red-teaming for Text-to-Image Models to Protect Benign Users
Infinite-Dimensional Feature Interaction
SimPO: Simple Preference Optimization with a Reference-Free Reward
How to Solve Contextual Goal-Oriented Problems with Offline Datasets?
Adversarial Environment Design via Regret-Guided Diffusion Models
GeoLRM: Geometry-Aware Large Reconstruction Model for High-Quality 3D Gaussian Generation
Towards Robust Multimodal Sentiment Analysis with Incomplete Data
Dynamics of Supervised and Reinforcement Learning in the Non-Linear Perceptron
Unifying Homophily and Heterophily for Spectral Graph Neural Networks via Triple Filter Ensembles
FIARSE: Model-Heterogeneity Federated Learning via Importance-Aware Submodel Extraction
On the Identifiability of Hybrid Physics-Neural Models: Meta-Learning as a Solution
MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map
DeformableTST: Transformer for Time Series Forecasting without Over-reliance on Patching
What Makes Partial-Label Learning Algorithms Effective?
Initializing Variable-sized Vision Transformers from Learngene with Learnable Transformations
Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration
LESS: Label-Efficient and Single-Stage Referring 3D Instance Segmentation
Compositional 3D-aware Video Generation with LLM Director
Crafting Hierarchical Strand-based Hair Geometry with Frequency-decomposed Representative Guide Curves
PhyRecon: Physically Plausible Neural Scene Reconstruction
LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D
Exploring Adversarial Robustness of Deep State Space Models
Improving Generalization in Federated Learning with Model-Data Mutual Information Regularization: A Posterior Inference Approach
Can Large Language Models Analyze Graphs like Professionals? A Benchmark and Dataset
Knowledge Circuit in Transformers
WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
A Trajectory-aware Spatio-temporal Graph for Video Salient Object Ranking
Prune and Repaint: Content-Aware Image Retargeting for any Ratio
$\text{ID}^3$: Identity-Preserving-yet-Diversified Diffusion Models for Synthetic Face Recognition
Motion Generation based on Spatial-Temporal Joint Modeling
MILP-StuDio: MILP Instance Generation via Block Structure Decomposition
Boundary Decomposition for Nadir Objective Vector Estimation
Meteor: Mamba-based Traversal of Rationale for Large Language and Vision Models
Improving Decision Sparsity
Optimal Batched Best Arm Identification
Meaningful Learning: Enhancing Abstract Reasoning in Large Language Models via Generic Fact Guidance
Pricing and Competition for Generative AI
On Convergence of Adam for Stochastic Optimization under Relaxed Assumptions
Training Compute-Optimal Protein Language Models
Learning Disentangled Representations for Perceptual Point Cloud Quality Assessment via Mutual Information Minimization
Episodic Future Thinking Reinforcement Learning for Social Decision-making
MSAGPT: Neural Prompting Protein Structure Prediction via MSA Generative Pre-Training
Don't Just String Tokens, Stack Them! Improving Multimodal Transformers with Layer Stack
A New Multi-Source Light Detection Benchmark and Semi-Supervised Focal Light Detection
Double-Ended Synthesis Planning with Goal-Constrained Bidirectional Search
Train-Attention: Meta-Learning Where to Focus in Continual Knowledge Learning
Improved Regret of Linear Ensemble Sampling
Prior-itizing Privacy: A Bayesian Approach to Setting the Privacy Budget in Differential Privacy
Dual Critic Reinforcement Learning under Partial Observability
Eye-gaze Guided Multi-modal Alignment for Medical Representation Learning
Mixed Dynamics In Linear Networks: Unifying the Lazy and Active Regimes
L-TTA: Lightweight Test-Time Adaptation Using a Versatile Stem Layer
Segmenting Watermarked Texts From Language Models
Bridge-IF: Learning Inverse Protein Folding with Markov Bridges
HYSYNTH: Context-Free LLM Approximation for Guiding Program Synthesis
Doing Experiments and Revising Rules with Natural Language and Probabilistic Reasoning
Nesterov acceleration despite very noisy gradients
Mixture of neural fields for heterogeneous reconstruction in cryo-EM
MedJourney: Benchmark and Evaluation of Large Language Models over Patient Clinical Journey
Low Precision Local Training is Enough for Federated Learning
Diffusion Policy Attacker: Crafting Adversarial Attacks for Diffusion-based Policies
Exploring the Precise Dynamics of Single-Layer GAN Models: Leveraging Multi-Feature Discriminators for High-Dimensional Subspace Learning
DFBA: Data Free Backdoor Attacks
RoPINN: Region Optimized Physics-Informed Neural Networks
Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness
Breaking Semantic Artifacts for Generalized AI-generated Image Detection
A Careful Examination of Large Language Model Performance on Grade School Arithmetic
SubgDiff: A Subgraph Diffusion Model to Improve Molecular Representation Learning
A Layer-Wise Natural Gradient Optimizer for Training Deep Neural Networks
A Single-Step, Sharpness-Aware Minimization is All You Need to Achieve Efficient and Accurate Sparse Training
Simulation-Free Training of Neural ODEs on Paired Data
CoLLaM: A Comprehensive Chinese Legal Benchmark for Evaluating Large Language Models
Gaussian-Informed Continuum for Physical Property Identification and Simulation
G3: An Effective and Adaptive Framework for Worldwide Geolocalization Using Large Multi-Modality Models
ECMamba: Consolidating Selective State Space Model with Retinex Guidance for Efficient Multiple Exposure Correction
LAM3D: Large Image-Point Clouds Alignment Model for 3D Reconstruction from Single Image
Binarized Diffusion Model for Image Super-Resolution
Few-Shot Diffusion Models Escape the Curse of Dimensionality
CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework
Zero-shot Generalizable Incremental Learning for Vision-Language Object Detection
DiReCT: Diagnostic Reasoning for Clinical Notes via Large Language Models
ProTransformer: Robustify Transformers via Plug-and-Play Paradigm
Interpreting the Weight Space of Customized Diffusion Models
Unified Gradient-Based Machine Unlearning with Remain Geometry Enhancement
InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
Towards Robust \emph{De Novo} Peptide Sequencing in Proteomics against Data Biases
NovoBench: Benchmarking Deep Learning-based \emph{De Novo} Sequencing Methods in Proteomics
Kaleidoscope: Learnable Masks for Heterogeneous Multi-agent Reinforcement Learning
Infusing Self-Consistency into Quantum Hamiltonian Prediction via Deep Equilibrium Models
Accelerating Diffusion Models with Parallel Sampling: Inference at Sub-Linear Time Complexity
Dual-Diffusion for Binocular 3D Human Pose Estimation
There is No Silver Bullet: Benchmarking Methods in Predictive Combinatorial Optimization
MMLONGBENCH-DOC: Benchmarking Long-context Document Understanding with Visualizations
Linear Uncertainty Quantification of Graphical Model Inference
Training for Stable Explanation for Free
Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning
Beyond Aesthetics: Cultural Competence in Text-to-Image Models
On the Identifiability of Poisson Branching Structural Causal Model Using Probability Generating Function
The Bayesian sampling in a canonical recurrent circuit with a diversity of inhibitory interneurons
SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset
Facilitating Multimodal Classification via Dynamically Learning Modality Gap
Identifying Selections for Unsupervised Subtask Discovery
Spike-based Neuromorphic Model for Sound Source Localization
Bridging OOD Generalization and Detection: A Graph-Theoretic View
ALI-Agent: Assessing LLMs' Alignment with Human Values via Agent-based Evaluation
Enhancing Graph Transformers with Hierarchical Distance Structural Encoding
Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification
Spec-Gaussian: Anisotropic View-Dependent Appearance for 3D Gaussian Splatting
Pre-training Differentially Private Models with Limited Public Data
DOPPLER: Differentially Private Optimizers with Low-pass Filter for Privacy Noise Reduction
AFBench: A Large-scale Benchmark for Airfoil Design
Generalizable and Animatable Gaussian Head Avatar
Rethinking Memory and Communication Costs for Efficient Large Language Model Training
You Only Cache Once: Decoder-Decoder Architectures for Language Models
Preference Alignment with Flow Matching
ADOPT: Modified Adam Can Converge with Any $\beta_2$ with the Optimal Rate
Few-Shot Task Learning Through Inverse Generative Modeling
Constrained Human-AI Cooperation: An Inclusive Embodied Social Intelligence Challenge
Distribution Guidance Network for Weakly Supervised Point Cloud Semantic Segmentation
Automated Multi-level Preference for MLLMs
Octopus: A Multi-modal LLM with Parallel Recognition and Sequential Understanding
Attractor Memory for Long-Term Time Series Forecasting: A Chaos Perspective
Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models
$\textit{Read-ME}$: Refactorizing LLMs as Router-Decoupled Mixture of Experts with System Co-Design
Conformal Alignment: Knowing When to Trust Foundation Models with Guarantees
Diversity Is Not All You Need: Training A Robust Cooperative Agent Needs Specialist Partners
Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models
IMPACT: A Large-scale Integrated Multimodal Patent Analysis and Creation Dataset for Design Patents
AmoebaLLM: Constructing Any-Shape Large Language Models for Efficient and Instant Deployment
Stepping Forward on the Last Mile
Towards the Dynamics of a DNN Learning Symbolic Interactions
Contextual Decision-Making with Knapsacks beyond the Worst Case
Navigating the Effect of Parametrization for Dimensionality Reduction
Multi-modal Situated Reasoning in 3D Scenes
Dynamic Subgroup Identification in Covariate-adjusted Response-adaptive Randomization Experiments
Tackling Uncertain Correspondences for Multi-Modal Entity Alignment
Unconditional stability of a recurrent neural circuit implementing divisive normalization
Spiking Graph Neural Network on Riemannian Manifolds
Drones Help Drones: A Collaborative Framework for Multi-Drone Object Trajectory Prediction and Beyond
RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
A Siamese Transformer with Hierarchical Refinement for Lane Detection
Prediction with Action: Visual Policy Learning via Joint Denoising Process
HORSE: Hierarchical Representation for Large-Scale Neural Subset Selection
Contextual Linear Optimization with Bandit Feedback
Learning Frequency-aware Vision Foundation Model for Domain Generalized Semantic Segmentation
Samba: Severity-aware Recurrent Modeling for Cross-domain Medical Image Grading
Adaptive Domain Learning for Cross-domain Image Denoising
Counter-Current Learning: A Biologically Plausible Dual Network Approach for Deep Learning
Exploring the Role of Large Language Models in Prompt Encoding for Diffusion Models
Neural Embedding Ranks: Aligning 3D latent dynamics with movement for long-term and cross-area decoding
MoVA: Adapting Mixture of Vision Experts to Multimodal Context
Smoothed Energy Guidance: Guiding Diffusion Models by Attenuating Energy Curvature of Attention
GS-Hider: Hiding Messages into 3D Gaussian Splatting
HiCoM: Hierarchical Coherent Motion for Dynamic Streamable Scenes with 3D Gaussian Splatting
MambaTalk: Co-Speech Gesture Generation with Selective State Space Models
Effective Rank Analysis and Regularization for Enhanced 3D Gaussian Splatting
SeTAR: Out-of-Distribution Detection with Selective Low-Rank Approximation
Putting Gale & Shapley to Work: Guaranteeing Stability Through Learning
3D Gaussian Splatting as Markov Chain Monte Carlo
DeepITE: Designing Variational Graph Autoencoders for Intervention Target Estimation
Make Fashion Real: Texture-preserving Rendered-to-Real Translation with Diffusion Models
RAW: A Robust and Agile Plug-and-Play Watermark Framework for AI-Generated Images with Provable Guarantees
Virtual Scanning: Unsupervised Non-line-of-sight Imaging from Irregularly Undersampled Transients
Semi-Open 3D Object Retrieval via Hypergraph-Based Hierarchical Equilibrium Representation
Hypergraph-Based Fuzzy Assembled Representation for Open-Set 3D Object Retrieval
Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
Conditional Generative Models are Sufficient to Sample from Any Causal Effect Estimand
ShowMaker: Creating High-Fidelity 2D Human Video via Fine-Grained Diffusion Modeling
Elliptical Attention
Solving Intricate Problems with Human-like Decomposition and Rethinking
Revisiting Differentially Private ReLU Regression
Separation and Bias of Deep Equilibrium Models on Expressivity and Learning Dynamics
Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning
Unleash Region Understanding in Intermediate Layers for MLLM-based Referring Expression Generation
Automated Generation and Selection of Context-Aware Guidelines for Large Language Model Agents
Grasp as You Say: Language-guided Dexterous Grasp Generation
Improving Environment Novelty Quantification for Effective Unsupervised Environment Design
On the Computational Complexity of Private High-dimensional Model Selection
Entity Alignment with Noisy Annotations from Large Language Models
Parameter-Inverted Image Pyramid Networks
Large Language Model-Driven Audio Codec is a Few-Shot Audio Task Learner
ShopBench: A Massive Multi-Task Online Shopping Benchmark for Large Language Models
Conjugated Semantic Pool Improves OOD Detection with Pre-trained Vision-Language Models
Identifiability Guarantees for Causal Disentanglement from Purely Observational Data
Provably Efficient Interactive-Grounded Learning with Personalized Reward
Contextual Multinomial Logit Bandits with General Value Functions
Reducing Transformer Key-Value Cache Size with Cross-Layer Attention
NeuMA: Neural Material Adaptor for Visual Grounding of Intrinsic Dynamics
Proportional Fairness in Clustering: A Social Choice Perspective
DiP-GO: A Diffusion Pruner via Few-step Gradient Optimization
EAGLE: Efficient Adaptive Geometry-based Learning in Cross-view Understanding
Weakly Supervised Referring Image Segmentation via Progressive Comprehension
ActSort: An active-learning accelerated cell sorting algorithm for large-scale calcium imaging datasets
Towards Evaluation of Adversarial Robustness and Privacy on Label Mapping Visual Prompting Models
Harmony4D: A Video Dataset for In-The-Wild Close Human Interactions
Typicalness-Aware Learning for Failure Detection
How to Continually Adapt Text-to-Image Diffusion Models for Flexible Customization?
Implicit Regularization of Decentralized Gradient Descent for Sparse Regression
RealMAN: A Real-Recorded and Annotated Microphone Array Dataset for Dynamic Speech Enhancement and Localization
Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf
ODRL: A Benchmark for Off-Dynamics Reinforcement Learning
Gated Inference Network: Inferencing and Learning State-Space Models
Rethinking No-reference Image Exposure Assessment from Holism to Pixel: Models, Datasets and Benchmarks
Distributional Reinforcement Learning with Regularized Wasserstein Loss
Learning Structured Representations with Hyperbolic Embeddings
Cryptographic Hardness of Score Estimation
An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
Time-FFM: Towards LM-Empowered Federated Foundation Model for Time Series Forecasting
Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments
Dynamic Non-Line-of-Sight Imaging with Mamba Enforced Temporal Consistency
GarmentLab: A Unified Simulation and Benchmark for Garment Manipulation
Multi-Task Prompt Decision Transformer for Efficient Unseen Task Generalization
SpeechForensics: Audio-Visual Speech Representation Learning for Face Forgery Detection
ArkVale: Efficient Generative LLM Inference with Recallable Key-Value Eviction
TabPedia: Towards Comprehensive Visual Table Understanding with Concept Synergy
Privacy without Noisy Gradients: Slicing Mechanism for Generative Model Training
LoCo: Learning 3D Location-Consistent Image Features with a Memory-Efficient Ranking Loss
C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory
Diffusion for World Modeling: Visual Details Matter in Atari
GoMatching: A Simple Baseline for Video Text Spotting via Long and Short Term Matching
Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
Goal Reduction with Loop-Removal Accelerates RL and Models Human Brain Activity in Goal-Directed Learning
A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks
Revive Re-weighting in Imbalanced Learning by Density Ratio Estimation
Towards Unsupervised Model Selection for Domain Adaptive Object Detection
CondTSF: One-line Plugin of Dataset Condensation for Time Series Forecasting
Improving Deep Reinforcement Learning by Reducing the Chain Effect of Value and Policy Churn
The Ladder in Chaos: Improving Policy Learning by Harnessing the Parameter Evolving Path in A Low-dimensional Space
Calibrated Preference Optimization for Direct Language Model Alignment
Small coresets via negative dependence: DPPs, linear statistics, and concentration
Phased Consistency Model
Lumina-Next : Making Lumina-T2X Stronger and Faster with Next-DiT
BLAST: Block-Level Adaptive Structured Matrices for Efficient Deep Neural Network Inference
Pedestrian-Centric 3D Pre-collision Pose and Shape Estimation from Dashcam Perspective
Unleashing the Denoising Capability of Diffusion Prior for Solving Inverse Problems
Latent Plan Transformer: Planning as Latent Variable Inference
Differentiable Quantum Computing for Large-scale Linear Control
FedLLM-Bench: Realistic Benchmarks for Federated Learning of Large Language Models
Just Add $100 More: Augmenting Pseudo-LiDAR Point Cloud for Resolving Class-imbalance Problem
Excluding the Irrelevant: Focusing Reinforcement Learning through Continuous Action Masking
Large Language Model Unlearning
FIFO-Diffusion: Generating Infinite Videos from Text without Training
SpikeReveal: Unlocking Temporal Sequences from Real Blurry Inputs with Spike Streams
Accelerating Greedy Coordinate Gradient and General Prompt Optimization via Probe Sampling
SnapKV: LLM Knows What You are Looking for Before Generation
Ask, Attend, Attack: A Effective Decision-Based Black-Box Targeted Attack for Image-to-Text Models
DePLM: Denoising Protein Language Models for Property Optimization
Pedestrian Trajectory Prediction with Missing Data: Datasets, Imputation, and Benchmarking
FilterNet: Harnessing Frequency Filters for Time Series Forecasting
AdaNeg: Adaptive Negative Proxy Guided OOD Detection with Vision-Language Models
Is Your LiDAR Placement Optimized for 3D Scene Understanding?
AUCSeg: AUC-oriented Pixel-level Long-tail Semantic Segmentation
AutoCV: Empowering Reasoning with Automated Process Labeling via Confidence Variation
Dissect Black Box: Interpreting for Rule-Based Explanations in Unsupervised Anomaly Detection
Optimized Feature Generation for Tabular Data via LLMs with Decision Tree Reasoning
Connectivity-Driven Pseudo-Labeling Makes Stronger Cross-Domain Segmenters
MambaAD: Exploring State Space Models for Multi-class Unsupervised Anomaly Detection
Graph-based Unsupervised Disentangled Representation Learning via Multimodal Large Language Models
Diversity-Driven Synthesis: Enhancing Dataset Distillation through Directed Weight Adjustment
AID: Attention Interpolation of Text-to-Image Diffusion
Regularized Adaptive Momentum Dual Averaging with an Efficient Inexact Subproblem Solver for Training Structured Neural Network
CultureLLM: Incorporating Cultural Differences into Large Language Models
CulturePark: Boosting Cross-cultural Understanding in Large Language Models
Mitigating Reward Overoptimization via Lightweight Uncertainty Estimation
CALANet: Cheap All-Layer Aggregation for Human Activity Recognition
Towards Editing Time Series
AutoManual: Generating Instruction Manuals by LLM Agents via Interactive Environmental Learning
FAST: A Dual-tier Few-Shot Learning Paradigm for Whole Slide Image Classification
Resolving Partial Observability in Decision Processes via the Lambda Discrepancy
CoBo: Collaborative Learning via Bilevel Optimization
The Star Geometry of Critic-Based Regularizer Learning
Flow Priors for Linear Inverse Problems via Iterative Corrupted Trajectory Matching
BitDelta: Your Fine-Tune May Only Be Worth One Bit
MagR: Weight Magnitude Reduction for Enhancing Post-Training Quantization
Boosting Transferability and Discriminability for Time Series Domain Adaptation
V-PETL Bench: A Unified Visual Parameter-Efficient Transfer Learning Benchmark
SemFlow: Binding Semantic Segmentation and Image Synthesis via Rectified Flow
Do LLMs Build World Representations? Probing Through the Lens of State Abstraction
When is an Embedding Model More Promising than Another?
VideoTetris: Towards Compositional Text-to-Video Generation
A StrongREJECT for Empty Jailbreaks
LLMDFA: Analyzing Dataflow in Code with Large Language Models
Benchmarking Complex Instruction-Following with Multiple Constraints Composition
Active Learning for Derivative-Based Global Sensitivity Analysis with Gaussian Processes
GLBench: A Comprehensive Benchmark for Graph with Large Language Models
A Comprehensive Investigation of Sparse Rate Reduction in Transformer-like Models
Sample Selection via Contrastive Fragmentation for Noisy Label Regression
APDDv2: Aesthetics of Paintings and Drawings Dataset with Artist Labeled Scores and Comments
DrivAerNet++: A Large-Scale Multimodal Car Dataset with Computational Fluid Dynamics Simulations and Deep Learning Benchmarks
Chain of Preference Optimization: Improving Chain-of-Thought Reasoning in LLMs
From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
Algorithmic progress in language models
TransVIP: Speech to Speech Translation System with Voice and Isochrony Preservation
Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
EgoChoir: Capturing 3D Human-Object Interaction Regions from Egocentric Views
CoVoMix: Advancing Zero-Shot Speech Generation for Human-like Multi-talker Conversations
Generalized Eigenvalue Problems with Generative Priors
ANT: Adaptive Noise Schedule for Time Series Diffusion Models
Web2Code: A Large-scale Webpage-to-Code Dataset and Evaluation Framework for Multimodal LLMs
UltraEdit: Instruction-based Fine-Grained Image Editing at Scale
DataStealing: Steal Data from Diffusion Models in Federated Learning with Multiple Trojans
On the Noise Robustness of In-Context Learning for Text Generation
Can We Leave Deepfake Data Behind in Training Deepfake Detector?
Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text
A versatile informative diffusion model for single-cell ATAC-seq data generation and analysis
SMART: Scalable Multi-agent Real-time Motion Generation via Next-token Prediction
Generalize or Detect? Towards Robust Semantic Segmentation Under Multiple Distribution Shifts
SS3DM: Benchmarking Street-View Surface Reconstruction with a Synthetic 3D Mesh Dataset
AlphaTablets: A Generic Plane Representation for 3D Planar Reconstruction from Monocular Videos
CARES: A Comprehensive Benchmark of Trustworthiness in Medical Vision Language Models
Fairness without Harm: An Influence-Guided Active Sampling Approach
Vision Model Pre-training on Interleaved Image-Text Data via Latent Compression Learning
PEAC: Unsupervised Pre-training for Cross-Embodiment Reinforcement Learning
CAT: Coordinating Anatomical-Textual Prompts for Multi-Organ and Tumor Segmentation
Large Scene Model: Real-time Unposed Images to Semantic 3D
Visual Perception by Large Language Model’s Weights
N-agent Ad Hoc Teamwork
Enhancing Domain Adaptation through Prompt Gradient Alignment
Long-Tailed Out-of-Distribution Detection via Normalized Outlier Distribution Adaptation
Invisible Image Watermarks Are Provably Removable Using Generative AI
Cloud Object Detector Adaptation by Integrating Different Source Knowledge
D-CPT Law: Domain-specific Continual Pre-Training Scaling Law for Large Language Models
A Compositional Atlas for Algebraic Circuits
SpikedAttention: Training-Free and Fully Spike-Driven Transformer-to-SNN Conversion with Winner-Oriented Spike Shift for Softmax Operation
SimVG: A Simple Framework for Visual Grounding with Decoupled Multi-modal Fusion
Symmetry-Informed Governing Equation Discovery
Lighting Every Darkness with 3DGS: Fast Training and Real-Time Rendering for HDR View Synthesis
PrivacyLens: Evaluating Privacy Norm Awareness of Language Models in Action
MDAgents: An Adaptive Collaboration of LLMs for Medical Decision Making
LoFiT: Localized Fine-tuning on LLM Representations
Paths to Equilibrium in Games
Instruction Embedding: Latent Representations of Instructions Towards Task Identification
Era3D: High-Resolution Multiview Diffusion using Efficient Row-wise Attention
T2Vs Meet VLMs: A Scalable Multimodal Dataset for Visual Harmfulness Recognition
Shadowcast: Stealthy Data Poisoning Attacks Against Vision-Language Models
Trajectory Volatility for Out-of-Distribution Detection in Mathematical Reasoning
Towards Multi-dimensional Explanation Alignment for Medical Classification
Initializing Services in Interactive ML Systems for Diverse Users
OneBit: Towards Extremely Low-bit Large Language Models
Delta-CoMe: Training-Free Delta-Compression with Mixed-Precision for Large Language Models
Hierarchical Visual Feature Aggregation for OCR-Free Document Understanding
UniBias: Unveiling and Mitigating LLM Bias through Internal Attention and FFN Manipulation
DiffuPac: Contextual Mimicry in Adversarial Packets Generation via Diffusion Model
Free Lunch in Pathology Foundation Model: Task-specific Model Adaptation with Concept-Guided Feature Enhancement
Pretraining with Random Noise for Fast and Robust Learning without Weight Transport
Gradient-free Decoder Inversion in Latent Diffusion Models
Collaboration! Towards Robust Neural Methods for Routing Problems
Are Uncertainty Quantification Capabilities of Evidential Deep Learning a Mirage?
Geodesic Optimization for Predictive Shift Adaptation on EEG data
Mixture of In-Context Experts Enhance LLMs' Long Context Awareness
CaptainCook4D: A Dataset for Understanding Errors in Procedural Activities
Online Posterior Sampling with a Diffusion Prior
Optimal Design for Human Feedback
WhodunitBench: Evaluating Large Multimodal Agents via Murder Mystery Games
SampDetox: Black-box Backdoor Defense via Perturbation-based Sample Detoxification
Learning-Augmented Algorithms for the Bahncard Problem
ConceptFactory: Facilitate 3D Object Knowledge Annotation with Object Conceptualization
Lean Workbook: A large-scale Lean problem set formalized from natural language math problems
WelQrate: Defining the Gold Standard in Small Molecule Drug Discovery Benchmarking
Efficient Streaming Algorithms for Graphlet Sampling
Probabilistic Conformal Distillation for Enhancing Missing Modality Robustness
RFLPA: A Robust Federated Learning Framework against Poisoning Attacks with Secure Aggregation
BonBon Alignment for Large Language Models: on the Sweetness of Best-of-n Sampling
Bridging the Divide: Reconsidering Softmax and Linear Attention
ICAL: Continual Learning of Multimodal Agents by Transforming Trajectories into Actionable Insights
Breaking the False Sense of Security in Backdoor Defense through Re-Activation Attack
Mitigating Backdoor Attack by Injecting Proactive Defensive Backdoor
Discrete Modeling via Boundary Conditional Diffusion Processes
Cluster-Learngene: Inheriting Adaptive Clusters for Vision Transformers
S$^{2}$FT: Efficient, Scalable and Generalizable LLM Fine-tuning by Structured Sparsity
LLM-AutoDA: Large Language Model-Driven Automatic Data Augmentation for Long-tailed Problems
Breaking Long-Tailed Learning Bottlenecks: A Controllable Paradigm with Hypernetwork-Generated Diverse Experts
Customized Multiple Clustering via Multi-Modal Subspace Proxy Learning
Swift Sampler: Efficient Learning of Sampler by 10 parameters
Unveiling the Tapestry of Consistency in Large Vision-Language Models
Online Consistency of the Nearest Neighbor Rule
Mars: Situated Inductive Reasoning in an Open-World Environment
Semantic Density: Uncertainty Quantification in Semantic Space for Large Language Models
Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration
HLM-Cite: Hybrid Language Model Workflow for Text-based Scientific Citation Prediction
TaskBench: Benchmarking Large Language Models for Task Automation
Self-Calibrated Tuning of Vision-Language Models for Out-of-Distribution Detection
Make Your LLM Fully Utilize the Context
Long-form factuality in large language models
Text to Blind Motion
Pandora's Box: Towards Building Universal Attackers against Real-World Large Vision-Language Models
Temporal Sentence Grounding with Relevance Feedback in Videos
Advantage-Aware Policy Optimization for Offline Reinforcement Learning
LOVA3: Learning to Visual Question Answering, Asking and Assessment
DARNet: Dual Attention Refinement Network with Spatiotemporal Construction for Auditory Attention Detection
Addressing Spatial-Temporal Heterogeneity: General Mixed Time Series Analysis via Latent Continuity Recovery and Alignment
FuseAnyPart: Diffusion-Driven Facial Parts Swapping via Multiple Reference Images
Boosting the Potential of Large Language Models with an Intelligent Information Assistant
Customized Subgraph Selection and Encoding for Drug-drug Interaction Prediction
A Cat Is A Cat (Not A Dog!): Unraveling Information Mix-ups in Text-to-Image Encoders through Causal Analysis and Embedding Optimization
PCoTTA: Continual Test-Time Adaptation for Multi-Task Point Cloud Understanding
Integrating Suboptimal Human Knowledge with Hierarchical Reinforcement Learning for Large-Scale Multiagent Systems
Sharpness-diversity tradeoff: improving flat ensembles with SharpBalance
Kangaroo: Lossless Self-Speculative Decoding for Accelerating LLMs via Double Early Exiting
Weight for Robustness: A Comprehensive Approach towards Optimal Fault-Tolerant Asynchronous ML
Search for Efficient Large Language Models
Transfer Q-star : Principled Decoding for LLM Alignment
Discrete Flow Matching
Solving Sparse \& High-Dimensional-Output Regression via Compression
DeepLag: Discovering Deep Lagrangian Dynamics for Intuitive Fluid Prediction
Universal Physics Transformers: A Framework For Efficiently Scaling Neural Operators
ELSA: Exploiting Layer-wise N:M Sparsity for Vision Transformer Acceleration
LotCLIP: Improving Language-Image Pre-training for Long Text Understanding
CuMo: Scaling Multimodal LLM with Co-Upcycled Mixture-of-Experts
GS-Blur: A 3D Scene-Based Dataset for Realistic Image Deblurring
SynRS3D: A Synthetic Dataset for Global 3D Semantic Understanding from Monocular Remote Sensing Imagery
Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
Understanding the Role of Equivariance in Self-supervised Learning
Efficient Multi-modal Models via Stage-wise Visual Context Compression
Understanding Multi-Granularity for Open-Vocabulary Part Segmentation
VHELM: A Holistic Evaluation of Vision Language Models
Image2Struct: A Benchmark for Evaluating Vision-Language Models in Extracting Structured Information from Images
ERBench: An Entity-Relationship based Automatically Verifiable Hallucination Benchmark for Large Language Models
Training LLMs to Better Self-Debug and Explain Code
Procedure-Aware Surgical Video-language Pretraining with Hierarchical Knowledge Augmentation
You May Better Reconstruct Anomalous over Normal Graphs: Analysis and a Simple Method for Reconstruction-based Graph-Level Anomaly Detection
UDA: A Benchmark Suite for Retrieval Augmented Generation in Real-World Document Analysis
Accelerating Nash Equilibrium Convergence in Monte Carlo Settings Through Counterfactual Value Based Fictitious Play
MetaCURL: Non-stationary Concave Utility Reinforcement Learning
MO-DDN: A Coarse-to-Fine Attribute-based Exploration Agent for Multi-Object Demand-driven Navigation
R$^2$-Gaussian: Rectifying Radiative Gaussian Splatting for Tomographic Reconstruction
Scene Graph Disentanglement and Composition for Generalizable Complex Image Generation
Unsupervised Homography Estimation on Multimodal Image Pair via Alternating Optimization
PPLNs: Parametric Piecewise Linear Networks for Event-Based Temporal Modeling and Beyond
AMOR: A Recipe for Building Adaptable Modular Knowledge Agents Through Process Feedback
Navigable Graphs for High-Dimensional Nearest Neighbor Search: Constructions and Limits
A Consistency-Aware Spot-Guided Transformer for Versatile and Hierarchical Point Cloud Registration
CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
Meta-Reinforcement Learning with Universal Policy Adaptation: Provable Near-Optimality under All-task Optimum Comparator
On Giant's Shoulders: Effortless Weak to Strong by Dynamic Logits Fusion
LibMOON: A Gradient-based MultiObjective OptimizatioN Library in PyTorch
Gliding over the Pareto Front with Uniform Designs
Generalizing Weather Forecast to Fine-grained Temporal Scales via Physics-AI Hybrid Modeling
Knowledge Composition using Task Vectors with Learned Anisotropic Scaling
Dual-Personalizing Adapter for Federated Foundation Models
Integrating Deep Metric Learning with Coreset for Active Learning in 3D Segmentation
Road Network Representation Learning with the Third Law of Geography
Autonomous Agent for Collaborative Task under Information Asymmetry
Adaptive Sampling for Efficient Softmax Approximation
Solving Zero-Sum Markov Games with Continous State via Spectral Dynamic Embedding
AWT: Transferring Vision-Language Models via Augmentation, Weighting, and Transportation
Cross-Modality Perturbation Synergy Attack for Person Re-identification
Towards Unified One-tower Expression Grounding and Segmentation with Mask Referring Modeling
Knowledge Graph Completion by Intermediate Variables Regularization
RelBench: A Benchmark for Deep Learning on Relational Databases
To Err like Human: Affective Bias-Inspired Measures for Visual Emotion Recognition Evaluation
Association Pattern-aware Fusion for Biological Entity Relationship Prediction
Vision Mamba Mender
Preferential Normalizing Flows
Dynamic Model Predictive Shielding for Provably Safe Reinforcement Learning
Exogenous Matching: Learning Good Proposals for Tractable Counterfactual Estimation
Unveiling Encoder-Free Vision-Language Models
DenseFusion-1M: Merging Vision Experts for Comprehensive Multimodal Perception
Paloma: A Benchmark for Evaluating Language Model Fit
OPS: Occupancy Prediction as A Sparse Set
Parsimony or Capability? Decomposition Delivers Both in Long-term Time Series Forecasting
Adaptive Passive-Aggressive Framework for Online Regression with Side Information
HumanVLA: Towards Vision-Language Directed Object Rearrangement by Physical Humanoid
$\texttt{ConflictBank}$: A Benchmark for Evaluating the Influence of Knowledge Conflicts in LLMs
Learning 1D Causal Visual Representation with De-focus Attention Networks
CODA: A Correlation-Oriented Disentanglement and Augmentation Modeling Scheme for Better Resisting Subpopulation Shifts
Learning symmetries via weight-sharing with doubly stochastic tensors
FairMedFM: Fairness Benchmarking for Medical Imaging Foundation Models
Zero-shot Image Editing with Reference Imitation
Flipping-based Policy for Chance-Constrained Markov Decision Processes
Slack-Free Spiking Neural Network Formulation for Hypergraph Minimum Vertex Cover
Federated Model Heterogeneous Matryoshka Representation Learning
Free-Rider and Conflict Aware Collaboration Formation for Cross-Silo Federated Learning
Almost Free: Self-concordance in Natural Exponential Families and an Application to Bandits
IQA-EVAL: Automatic Evaluation of Human-Model Interactive Question Answering
MEQA: A Benchmark for Multi-hop Event-centric Question Answering with Explanations
DeiSAM: Segment Anything with Deictic Prompting
Graph Neural Networks Need Cluster-Normalize-Activate Modules
FUGAL: Feature-fortified Unrestricted Graph Alignment
AlphaMath Almost Zero: Process Supervision Without Process
Muscles in Time: Learning to Understand Human Motion In-Depth by Simulating Muscle Activations
Large Language Models as Hyper-Heuristics for Combinatorial Optimization
Hybrid Mamba: An Promising In-Context RL for Long-Term Decision
HumanSplat: Generalizable Single-Image Human Gaussian Splatting with Structure Priors
Context and Geometry Aware Voxel Transformer for Semantic Scene Completion
You Only Look Around: Learning Illumination-Invariant Feature for Low-light Object Detection
Predictor-Corrector Enhanced Transformers with Exponential Moving Average Coefficient Learning
Make-An-Agent: A Generalizable Policy Network Generator with Behavior-Prompted Diffusion
GMAI-MMBench: A Comprehensive Multimodal Evaluation Benchmark Towards General Medical AI
Hamba: Single-view 3D Hand Reconstruction with Graph-guided Bi-Scanning Mamba
Cross-modal Representation Flattening for Multi-modal Domain Generalization
AdaptiveISP: Learning an Adaptive Image Signal Processor for Object Detection
PhoCoLens: Photorealistic and Consistent Reconstruction in Lensless Imaging
Never Miss A Beat: An Efficient Recipe for Context Window Extension of Large Language Models with Consistent “Middle” Enhancement
LAVIB: A Large-scale Video Interpolation Benchmark
Model Based Inference of Synaptic Plasticity Rules
Scaling Continuous Latent Variable Models as Probabilistic Integral Circuits
FUSE: Fast Unified Simulation and Estimation for PDEs
Parameter Competition Balancing for Model Merging
United We Stand, Divided We Fall: Fingerprinting Deep Neural Networks via Adversarial Trajectories
Can Language Models Learn to Skip Steps?
Sample Complexity of Posted Pricing for a Single Item
Learning Commonality, Divergence and Variety for Unsupervised Visible-Infrared Person Re-identification
Harmonizing Visual Text Comprehension and Generation
Are nuclear masks all you need for improved out-of-domain generalization? A closer look at cancer classification in histopathology.
SAFE: Slow and Fast Parameter-Efficient Tuning for Continual Learning with Pre-Trained Models
PromptFix: You Prompt and We Fix the Photo
Rethinking the Evaluation of Out-of-Distribution Detection: A Sorites Paradox
What Is Missing For Graph Homophily? Disentangling Graph Homophily For Graph Neural Networks
Reasoning Multi-Agent Behavioral Topology for Interactive Autonomous Driving
ODGEN: Domain-specific Object Detection Data Generation with Diffusion Models
Leveraging Contrastive Learning for Enhanced Node Representations in Tokenized Graph Transformers
PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models
Reconstructing the Image Stitching Pipeline: Integrating Fusion and Rectangling into a Unified Inpainting Model
Learning Infinitesimal Generators of Continuous Symmetries from Data
On the Power of Small-size Graph Neural Networks for Linear Programming
MixEval: Fast and Dynamic Human Preference Approximation with LLM Benchmark Mixtures
Stochastic Optimal Control for Diffusion Bridges in Function Spaces
Taming Diffusion Prior for Image Super-Resolution with Domain Shift SDEs
EGSST: Event-based Graph Spatiotemporal Sensitive Transformer for Object Detection
We use cookies to store which papers have been visited.
I agree
Successful Page Load
NeurIPS 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