ICLR 2023 Papers

Skip to yearly menu bar Skip to main content

mini compact topic detail

Contrastive Audio-Visual Masked Autoencoder

Fairness-aware Contrastive Learning with Partially Annotated Sensitive Attributes

Approximation and non-parametric estimation of functions over high-dimensional spheres via deep ReLU networks

Statistical Guarantees for Consensus Clustering

Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective

Seeing Differently, Acting Similarly: Heterogeneously Observable Imitation Learning

Humanly Certifying Superhuman Classifiers

Write and Paint: Generative Vision-Language Models are Unified Modal Learners

A law of adversarial risk, interpolation, and label noise

Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets

Unsupervised 3D Object Learning through Neuron Activity aware Plasticity

Amortised Invariance Learning for Contrastive Self-Supervision

Expressive Monotonic Neural Networks

In-sample Actor Critic for Offline Reinforcement Learning

The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks

Fake It Until You Make It : Towards Accurate Near-Distribution Novelty Detection

CktGNN: Circuit Graph Neural Network for Electronic Design Automation

Jointly Learning Visual and Auditory Speech Representations from Raw Data

Collaborative Pure Exploration in Kernel Bandit

Beyond Lipschitz: Sharp Generalization and Excess Risk Bounds for Full-Batch GD

DELTA: DEGRADATION-FREE FULLY TEST-TIME ADAPTATION

Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning

Provable Sim-to-real Transfer in Continuous Domain with Partial Observations

Diagnosing and Rectifying Vision Models using Language

Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path

Nearly Minimax Optimal Offline Reinforcement Learning with Linear Function Approximation: Single-Agent MDP and Markov Game

DensePure: Understanding Diffusion Models for Adversarial Robustness

Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling

Learning ReLU networks to high uniform accuracy is intractable

DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models

Budgeted Training for Vision Transformer

Hyperbolic Deep Reinforcement Learning

Interpretable Debiasing of Vectorized Language Representations with Iterative Orthogonalization

Rethinking Symbolic Regression: Morphology and Adaptability in the Context of Evolutionary Algorithms

Sequential Gradient Coding For Straggler Mitigation

How gradient estimator variance and bias impact learning in neural networks

TempCLR: Temporal Alignment Representation with Contrastive Learning

Optimal Conservative Offline RL with General Function Approximation via Augmented Lagrangian

Distilling Model Failures as Directions in Latent Space

Equivariant Hypergraph Diffusion Neural Operators

Learning to Grow Pretrained Models for Efficient Transformer Training

Is Attention All That NeRF Needs?

NeRF-SOS: Any-View Self-supervised Object Segmentation on Complex Scenes

Function-space regularized Rényi divergences

Finding the Global Semantic Representation in GAN through Fréchet Mean

DexDeform: Dexterous Deformable Object Manipulation with Human Demonstrations and Differentiable Physics

Effective passive membership inference attacks in federated learning against overparameterized models

CoRTX: Contrastive Framework for Real-time Explanation

Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning

A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games

Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions

Moderate Coreset: A Universal Method of Data Selection for Real-world Data-efficient Deep Learning

Harnessing Out-Of-Distribution Examples via Augmenting Content and Style

Using Language to Extend to Unseen Domains

A Holistic View of Label Noise Transition Matrix in Deep Learning and Beyond

Softened Symbol Grounding for Neuro-symbolic Systems

Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions

Logical Message Passing Networks with One-hop Inference on Atomic Formulas

Transformers Learn Shortcuts to Automata

Noise-Robust De-Duplication at Scale

Guiding Energy-based Models via Contrastive Latent Variables

Equivariance-aware Architectural Optimization of Neural Networks

Information Plane Analysis for Dropout Neural Networks

UniMax: Fairer and More Effective Language Sampling for Large-Scale Multilingual Pretraining

Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning

STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables

HiT-MDP: Learning the SMDP option framework on MDPs with Hidden Temporal Embeddings

Improved Learning-augmented Algorithms for k-means and k-medians Clustering

Progressive Mix-Up for Few-Shot Supervised Multi-Source Domain Transfer

Does Deep Learning Learn to Abstract? A Systematic Probing Framework

RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates

GOGGLE: Generative Modelling for Tabular Data by Learning Relational Structure

Quantized Compressed Sensing with Score-Based Generative Models

Latent Neural ODEs with Sparse Bayesian Multiple Shooting

$\mathcal{O}$-GNN: incorporating ring priors into molecular modeling

Characterizing the spectrum of the NTK via a power series expansion

Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability

FIFA: Making Fairness More Generalizable in Classifiers Trained on Imbalanced Data

Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design

VIPeR: Provably Efficient Algorithm for Offline RL with Neural Function Approximation

$\rm A^2Q$: Aggregation-Aware Quantization for Graph Neural Networks

Exponential Generalization Bounds with Near-Optimal Rates for $L_q$-Stable Algorithms

Learning to Induce Causal Structure

FoSR: First-order spectral rewiring for addressing oversquashing in GNNs

Achieving Near-Optimal Individual Regret & Low Communications in Multi-Agent Bandits

Online Boundary-Free Continual Learning by Scheduled Data Prior

A Higher Precision Algorithm for Computing the $1$-Wasserstein Distance

Bidirectional Language Models Are Also Few-shot Learners

Delving into Semantic Scale Imbalance

On the Trade-Off between Actionable Explanations and the Right to be Forgotten

Over-parameterized Model Optimization with Polyak-{\L}ojasiewicz Condition

Continuous-time identification of dynamic state-space models by deep subspace encoding

AE-FLOW: Autoencoders with Normalizing Flows for Medical Images Anomaly Detection

SpeedyZero: Mastering Atari with Limited Data and Time

Probabilistically Robust Recourse: Navigating the Trade-offs between Costs and Robustness in Algorithmic Recourse

Sampling-based inference for large linear models, with application to linearised Laplace

Constructive TT-representation of the tensors given as index interaction functions with applications

Adaptive Robust Evidential Optimization For Open Set Detection from Imbalanced Data

Is Model Ensemble Necessary? Model-based RL via a Single Model with Lipschitz Regularized Value Function

Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation

Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors

CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning

Learning to Estimate Single-View Volumetric Flow Motions without 3D Supervision

Variational Information Pursuit for Interpretable Predictions

DiffusER: Diffusion via Edit-based Reconstruction

Synthetic Data Generation of Many-to-Many Datasets via Random Graph Generation

One-Pixel Shortcut: On the Learning Preference of Deep Neural Networks

Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization

Boosting Causal Discovery via Adaptive Sample Reweighting

Inequality phenomenon in $l_{\infty}$-adversarial training, and its unrealized threats

Understanding weight-magnitude hyperparameters in training binary networks

GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis

Copy is All You Need

Grounding Graph Network Simulators using Physical Sensor Observations

Predictive Inference with Feature Conformal Prediction

The Curious Case of Benign Memorization

Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference

Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection

Guiding continuous operator learning through Physics-based boundary constraints

Preference Transformer: Modeling Human Preferences using Transformers for RL

LexMAE: Lexicon-Bottlenecked Pretraining for Large-Scale Retrieval

SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication

An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation

A GNN-Guided Predict-and-Search Framework for Mixed-Integer Linear Programming

On Explaining Neural Network Robustness with Activation Path

Liquid Structural State-Space Models

Approximate Vanishing Ideal Computations at Scale

Multi-task Self-supervised Graph Neural Networks Enable Stronger Task Generalization

Empowering Graph Representation Learning with Test-Time Graph Transformation

A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy

DeCap: Decoding CLIP Latents for Zero-Shot Captioning via Text-Only Training

Personalized Reward Learning with Interaction-Grounded Learning (IGL)

Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing

Defending against Adversarial Audio via Diffusion Model

Unsupervised Learning for Combinatorial Optimization Needs Meta Learning

Revisit Finetuning strategy for Few-Shot Learning to Transfer the Emdeddings

The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image

A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks

LDMIC: Learning-based Distributed Multi-view Image Coding

Riemannian Metric Learning via Optimal Transport

Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning

$\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks

Learning Input-agnostic Manipulation Directions in StyleGAN with Text Guidance

DAVA: Disentangling Adversarial Variational Autoencoder

Test-Time Adaptation via Self-Training with Nearest Neighbor Information

InCoder: A Generative Model for Code Infilling and Synthesis

Artificial Neuronal Ensembles with Learned Context Dependent Gating

A General Rank Preserving Framework for Asymmetric Image Retrieval

Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models

Can discrete information extraction prompts generalize across language models?

Score-based Continuous-time Discrete Diffusion Models

Any-scale Balanced Samplers for Discrete Space

Statistical Theory of Differentially Private Marginal-based Data Synthesis Algorithms

Reliability of CKA as a Similarity Measure in Deep Learning

When and Why Vision-Language Models Behave like Bags-Of-Words, and What to Do About It?

Order Matters: Agent-by-agent Policy Optimization

FastFill: Efficient Compatible Model Update

Mind the Pool: Convolutional Neural Networks Can Overfit Input Size

DFlow: Learning to Synthesize Better Optical Flow Datasets via a Differentiable Pipeline

Transformer-based World Models Are Happy With 100k Interactions

Differentiable Mathematical Programming for Object-Centric Representation Learning

MAST: Masked Augmentation Subspace Training for Generalizable Self-Supervised Priors

Scalable Subset Sampling with Neural Conditional Poisson Networks

Benchmarking Offline Reinforcement Learning on Real-Robot Hardware

A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis

Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization

Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolution

LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence

Neural-based classification rule learning for sequential data

ODAM: Gradient-based Instance-Specific Visual Explanations for Object Detection

Learning with Auxiliary Activation for Memory-Efficient Training

Policy-Based Self-Competition for Planning Problems

Out-of-Distribution Detection based on In-Distribution Data Patterns Memorization with Modern Hopfield Energy

Kernel Neural Optimal Transport

Neural Optimal Transport

Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small

Discovering Generalizable Multi-agent Coordination Skills from Multi-task Offline Data

Teacher Guided Training: An Efficient Framework for Knowledge Transfer

Measure the Predictive Heterogeneity

Provable Defense Against Geometric Transformations

Tensor-Based Sketching Method for the Low-Rank Approximation of Data Streams.

Data augmentation alone can improve adversarial training

CUTS: Neural Causal Discovery from Irregular Time-Series Data

LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification

Valid P-Value for Deep Learning-driven Salient Region

Pitfalls of Gaussians as a noise distribution in NCE

Broken Neural Scaling Laws

Bridging the Gap between ANNs and SNNs by Calibrating Offset Spikes

Visually-Augmented Language Modeling

A VAE for Transformers with Nonparametric Variational Information Bottleneck

A theoretical study of inductive biases in contrastive learning

Minimum Variance Unbiased N:M Sparsity for the Neural Gradients

Incremental Learning of Structured Memory via Closed-Loop Transcription

Explaining Temporal Graph Models through an Explorer-Navigator Framework

Backpropagation at the Infinitesimal Inference Limit of Energy-Based Models: Unifying Predictive Coding, Equilibrium Propagation, and Contrastive Hebbian Learning

Knowledge-in-Context: Towards Knowledgeable Semi-Parametric Language Models

What Do Self-Supervised Vision Transformers Learn?

Benchmarking Constraint Inference in Inverse Reinforcement Learning

Enhancing the Inductive Biases of Graph Neural ODE for Modeling Physical Systems

ESCHER: Eschewing Importance Sampling in Games by Computing a History Value Function to Estimate Regret

Sampling-free Inference for Ab-Initio Potential Energy Surface Networks

That Label's got Style: Handling Label Style Bias for Uncertain Image Segmentation

On The Relative Error of Random Fourier Features for Preserving Kernel Distance

Towards Inferential Reproducibility of Machine Learning Research

Beyond calibration: estimating the grouping loss of modern neural networks

DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing

Weighted Clock Logic Point Process

Squeeze Training for Adversarial Robustness

Asymptotic Instance-Optimal Algorithms for Interactive Decision Making

Is Forgetting Less a Good Inductive Bias for Forward Transfer?

Near-Optimal Deployment Efficiency in Reward-Free Reinforcement Learning with Linear Function Approximation

Where to Begin? On the Impact of Pre-Training and Initialization in Federated Learning

Long-Tailed Partial Label Learning via Dynamic Rebalancing

Global Explainability of GNNs via Logic Combination of Learned Concepts

Task Ambiguity in Humans and Language Models

Discrete Predictor-Corrector Diffusion Models for Image Synthesis

Recon: Reducing Conflicting Gradients From the Root For Multi-Task Learning

More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization

PerFedMask: Personalized Federated Learning with Optimized Masking Vectors

Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks

Imbalanced Semi-supervised Learning with Bias Adaptive Classifier

On Compositional Uncertainty Quantification for Seq2seq Graph Parsing

Free Lunch for Domain Adversarial Training: Environment Label Smoothing

Mastering the Game of No-Press Diplomacy via Human-Regularized Reinforcement Learning and Planning

Brain-like representational straightening of natural movies in robust feedforward neural networks

A Simple Approach for Visual Room Rearrangement: 3D Mapping and Semantic Search

Generative Modeling Helps Weak Supervision (and Vice Versa)

Federated Learning from Small Datasets

Multi-level Protein Structure Pre-training via Prompt Learning

PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithm

A Mixture-of-Expert Approach to RL-based Dialogue Management

M-L2O: Towards Generalizable Learning-to-Optimize by Test-Time Fast Self-Adaptation

Dichotomy of Control: Separating What You Can Control from What You Cannot

Re-calibrating Feature Attributions for Model Interpretation

Revisiting Populations in multi-agent Communication

Learning multi-scale local conditional probability models of images

Characterizing the Influence of Graph Elements

Disentangling Learning Representations with Density Estimation

Simple and Scalable Nearest Neighbor Machine Translation

Language Models Can Teach Themselves to Program Better

What Is Missing in IRM Training and Evaluation? Challenges and Solutions

A Differential Geometric View and Explainability of GNN on Evolving Graphs

TextGrad: Advancing Robustness Evaluation in NLP by Gradient-Driven Optimization

Consolidator: Mergable Adapter with Group Connections for Visual Adaptation

Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification

Continuous PDE Dynamics Forecasting with Implicit Neural Representations

Transfer NAS with Meta-learned Bayesian Surrogates

Hierarchical Sliced Wasserstein Distance

Supervision Complexity and its Role in Knowledge Distillation

LipsFormer: Introducing Lipschitz Continuity to Vision Transformers

Automatic Chain of Thought Prompting in Large Language Models

Near-Optimal Adversarial Reinforcement Learning with Switching Costs

Federated Nearest Neighbor Machine Translation

Language Models are Realistic Tabular Data Generators

Logical Entity Representation in Knowledge-Graphs for Differentiable Rule Learning

MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization

Data Valuation Without Training of a Model

Words are all you need? Language as an approximation for human similarity judgments

Link Prediction with Non-Contrastive Learning

Impossibly Good Experts and How to Follow Them

Scaling Laws For Deep Learning Based Image Reconstruction

Equal Improvability: A New Fairness Notion Considering the Long-term Impact

Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication

Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent

Hyperparameter Optimization through Neural Network Partitioning

Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks

Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction

NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis

Sequential Attention for Feature Selection

Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts

Improved Sample Complexity for Reward-free Reinforcement Learning under Low-rank MDPs

Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning

ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor

Re-Imagen: Retrieval-Augmented Text-to-Image Generator

Towards Robustness Certification Against Universal Perturbations

Sparse Upcycling: Training Mixture-of-Experts from Dense Checkpoints

Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets

Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?

HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetwork

Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance

PiFold: Toward effective and efficient protein inverse folding

Capturing the Motion of Every Joint: 3D Human Pose and Shape Estimation with Independent Tokens

Mind the Gap: Offline Policy Optimization for Imperfect Rewards

Autoregressive Conditional Neural Processes

CASR: Generating Complex Sequences with Autoregressive Self-Boost Refinement

Bias Propagation in Federated Learning

Make-A-Video: Text-to-Video Generation without Text-Video Data

kNN-Diffusion: Image Generation via Large-Scale Retrieval

AudioGen: Textually Guided Audio Generation

DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability

Is a Caption Worth a Thousand Images? A Study on Representation Learning

Almost Linear Constant-Factor Sketching for $\ell_1$ and Logistic Regression

Concept Gradient: Concept-based Interpretation Without Linear Assumption

Neural Networks Efficiently Learn Low-Dimensional Representations with SGD

Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication

Complexity-Based Prompting for Multi-step Reasoning

Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees

Human-Guided Fair Classification for Natural Language Processing

An Adaptive Policy to Employ Sharpness-Aware Minimization

NTK-SAP: Improving neural network pruning by aligning training dynamics

Revisiting the Assumption of Latent Separability for Backdoor Defenses

Holistic Adversarially Robust Pruning

Restricted Strong Convexity of Deep Learning Models with Smooth Activations

TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning

DFPC: Data flow driven pruning of coupled channels without data.

Graph Neural Network-Inspired Kernels for Gaussian Processes in Semi-Supervised Learning

Minimum Description Length Control

RGI: robust GAN-inversion for mask-free image inpainting and unsupervised pixel-wise anomaly detection

Part-Based Models Improve Adversarial Robustness

Basic Binary Convolution Unit for Binarized Image Restoration Network

Knowledge Distillation based Degradation Estimation for Blind Super-Resolution

Scale-invariant Bayesian Neural Networks with Connectivity Tangent Kernel

Hybrid RL: Using both offline and online data can make RL efficient

Become a Proficient Player with Limited Data through Watching Pure Videos

Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis

Masked Frequency Modeling for Self-Supervised Visual Pre-Training

On the Convergence of AdaGrad(Norm) on $\mathbb{R}^d$: Beyond Convexity, Non-Asymptotic Rate and Acceleration

Curriculum-based Co-design of Morphology and Control of Voxel-based Soft Robots

Instance-wise Batch Label Restoration via Gradients in Federated Learning

Truthful Self-Play

Zeroth-Order Optimization with Trajectory-Informed Derivative Estimation

Matching receptor to odorant with protein language and graph neural networks

Decompositional Generation Process for Instance-Dependent Partial Label Learning

A Graph Neural Network Approach to Automated Model Building in Cryo-EM Maps

Investigating Multi-task Pretraining and Generalization in Reinforcement Learning

Adversarial Imitation Learning with Preferences

Simple Emergent Action Representations from Multi-Task Policy Training

From $t$-SNE to UMAP with contrastive learning

On the Importance and Applicability of Pre-Training for Federated Learning

When to Make and Break Commitments?

Gromov-Wasserstein Autoencoders

3D UX-Net: A Large Kernel Volumetric ConvNet Modernizing Hierarchical Transformer for Medical Image Segmentation

Neural Episodic Control with State Abstraction

The Surprising Computational Power of Nondeterministic Stack RNNs

Feature Reconstruction From Outputs Can Mitigate Simplicity Bias in Neural Networks

Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting

Soft Neighbors are Positive Supporters in Contrastive Visual Representation Learning

FedFA: Federated Feature Augmentation

Efficient Planning in a Compact Latent Action Space

SketchKnitter: Vectorized Sketch Generation with Diffusion Models

Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning

MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning

On the Perils of Cascading Robust Classifiers

Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization

FairGBM: Gradient Boosting with Fairness Constraints

Efficient Model Updates for Approximate Unlearning of Graph-Structured Data

Does Learning from Decentralized Non-IID Unlabeled Data Benefit from Self Supervision?

Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification

How I Learned to Stop Worrying and Love Retraining

Malign Overfitting: Interpolation and Invariance are Fundamentally at Odds

AGRO: Adversarial discovery of error-prone Groups for Robust Optimization

Discovering Latent Knowledge in Language Models Without Supervision

Tier Balancing: Towards Dynamic Fairness over Underlying Causal Factors

RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch

Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths

PGrad: Learning Principal Gradients For Domain Generalization

Representational Dissimilarity Metric Spaces for Stochastic Neural Networks

Anamnesic Neural Differential Equations with Orthogonal Polynomial Projections

Neural Design for Genetic Perturbation Experiments

Topology-aware Robust Optimization for Out-of-Distribution Generalization

simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing

DecAF: Joint Decoding of Answers and Logical Forms for Question Answering over Knowledge Bases

Dr.Spider: A Diagnostic Evaluation Benchmark towards Text-to-SQL Robustness

Disentangling the Mechanisms Behind Implicit Regularization in SGD

GLM-130B: An Open Bilingual Pre-trained Model

DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems

The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes

Min-Max Multi-objective Bilevel Optimization with Applications in Robust Machine Learning

Vision Transformer Adapter for Dense Predictions

Learning Simultaneous Navigation and Construction in Grid Worlds

GAIN: On the Generalization of Instructional Action Understanding

Text Summarization with Oracle Expectation

Learning Sparse Group Models Through Boolean Relaxation

Combinatorial-Probabilistic Trade-Off: P-Values of Community Properties Test in the Stochastic Block Models

TEMPERA: Test-Time Prompt Editing via Reinforcement Learning

How to Train your HIPPO: State Space Models with Generalized Orthogonal Basis Projections

Sample Complexity of Nonparametric Off-Policy Evaluation on Low-Dimensional Manifolds using Deep Networks

Learning Kernelized Contextual Bandits in a Distributed and Asynchronous Environment

Representation Learning for Low-rank General-sum Markov Games

Deep Reinforcement Learning for Cost-Effective Medical Diagnosis

Layer Grafted Pre-training: Bridging Contrastive Learning And Masked Image Modeling For Label-Efficient Representations

Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow

Noise Injection Node Regularization for Robust Learning

Differentially Private $L_2$-Heavy Hitters in the Sliding Window Model

Temporal Domain Generalization with Drift-Aware Dynamic Neural Networks

Disparate Impact in Differential Privacy from Gradient Misalignment

Few-Shot Domain Adaptation For End-to-End Communication

Planckian Jitter: countering the color-crippling effects of color jitter on self-supervised training

Calibrating Transformers via Sparse Gaussian Processes

Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception

ViewCo: Discovering Text-Supervised Segmentation Masks via Multi-View Semantic Consistency

SAM as an Optimal Relaxation of Bayes

The Dark Side of AutoML: Towards Architectural Backdoor Search

ISS: Image as Stepping Stone for Text-Guided 3D Shape Generation

BrainBERT: Self-supervised representation learning for intracranial recordings

Flow Matching for Generative Modeling

Guiding Safe Exploration with Weakest Preconditions

Accelerating Hamiltonian Monte Carlo via Chebyshev Integration Time

Causal Estimation for Text Data with (Apparent) Overlap Violations

Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions

TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization

Hungry Hungry Hippos: Towards Language Modeling with State Space Models

Understanding new tasks through the lens of training data via exponential tilting

Perfectly Secure Steganography Using Minimum Entropy Coupling

Predictor-corrector algorithms for stochastic optimization under gradual distribution shift

A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification

FunkNN: Neural Interpolation for Functional Generation

Continual Pre-training of Language Models

Accelerated Single-Call Methods for Constrained Min-Max Optimization

MOAT: Alternating Mobile Convolution and Attention Brings Strong Vision Models

Lower Bounds on the Depth of Integral ReLU Neural Networks via Lattice Polytopes

Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions

Learning to CROSS exchange to solve min-max vehicle routing problems

Evolving Populations of Diverse RL Agents with MAP-Elites

Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning

PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs

Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation

Learning Adversarial Linear Mixture Markov Decision Processes with Bandit Feedback and Unknown Transition

The In-Sample Softmax for Offline Reinforcement Learning

Compositional Law Parsing with Latent Random Functions

Reversible Column Networks

Robust Algorithms on Adaptive Inputs from Bounded Adversaries

Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning

Transformers are Sample-Efficient World Models

Towards Minimax Optimal Reward-free Reinforcement Learning in Linear MDPs

Robust Explanation Constraints for Neural Networks

Domain Generalization via Heckman-type Selection Models

Quasi-optimal Reinforcement Learning with Continuous Actions

Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses

Agree to Disagree: Diversity through Disagreement for Better Transferability

Which Layer is Learning Faster? A Systematic Exploration of Layer-wise Convergence Rate for Deep Neural Networks

Strong inductive biases provably prevent harmless interpolation

Parametrizing Product Shape Manifolds by Composite Networks

Quantifying and Mitigating the Impact of Label Errors on Model Disparity Metrics

Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework

Hidden Markov Transformer for Simultaneous Machine Translation

Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting

Minimax Optimal Kernel Operator Learning via Multilevel Training

MeshDiffusion: Score-based Generative 3D Mesh Modeling

ChordMixer: A Scalable Neural Attention Model for Sequences with Different Length

FaiREE: fair classification with finite-sample and distribution-free guarantee

On the duality between contrastive and non-contrastive self-supervised learning

ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations

Emergence of Maps in the Memories of Blind Navigation Agents

Molecular Geometry Pretraining with SE(3)-Invariant Denoising Distance Matching

Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting

Simplicial Hopfield networks

Adversarial Training of Self-supervised Monocular Depth Estimation against Physical-World Attacks

Turning the Curse of Heterogeneity in Federated Learning into a Blessing for Out-of-Distribution Detection

D4AM: A General Denoising Framework for Downstream Acoustic Models

Finding Actual Descent Directions for Adversarial Training

Interpretations of Domain Adaptations via Layer Variational Analysis

Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer

MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

Policy Expansion for Bridging Offline-to-Online Reinforcement Learning

Mitigating Memorization of Noisy Labels via Regularization between Representations

ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning

Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model

Planning Goals for Exploration

DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity

Self-Guided Noise-Free Data Generation for Efficient Zero-Shot Learning

AutoGT: Automated Graph Transformer Architecture Search

Progress measures for grokking via mechanistic interpretability

Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle

Variance-Aware Sparse Linear Bandits

Label-free Concept Bottleneck Models

The Role of ImageNet Classes in Fréchet Inception Distance

Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement

Optimal Transport for Offline Imitation Learning

Does Zero-Shot Reinforcement Learning Exist?

A Self-Attention Ansatz for Ab-initio Quantum Chemistry

A Neural Mean Embedding Approach for Back-door and Front-door Adjustment

TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation

Certified Training: Small Boxes are All You Need

CLIP-ViP: Adapting Pre-trained Image-Text Model to Video-Language Alignment

BSTT: A Bayesian Spatial-Temporal Transformer for Sleep Staging

Optimizing Bi-Encoder for Named Entity Recognition via Contrastive Learning

Pre-training via Denoising for Molecular Property Prediction

AANG : Automating Auxiliary Learning

Dual Algorithmic Reasoning

SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning

Equivariant Energy-Guided SDE for Inverse Molecular Design

Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions

Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching

On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning

Learning Continuous Normalizing Flows For Faster Convergence To Target Distribution via Ascent Regularizations

A Simple Yet Powerful Deep Active Learning With Snapshots Ensembles

Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes

The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning

Simplicial Embeddings in Self-Supervised Learning and Downstream Classification

Learning Label Encodings for Deep Regression

Offline Congestion Games: How Feedback Type Affects Data Coverage Requirement

Neural Implicit Shape Editing using Boundary Sensitivity

Multifactor Sequential Disentanglement via Structured Koopman Autoencoders

Asynchronous Distributed Bilevel Optimization

Towards Open Temporal Graph Neural Networks

VA-DepthNet: A Variational Approach to Single Image Depth Prediction

Graph Contrastive Learning for Skeleton-based Action Recognition

Strategic Classification with Graph Neural Networks

Memory Gym: Partially Observable Challenges to Memory-Based Agents

What learning algorithm is in-context learning? Investigations with linear models

Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality

Learning to Extrapolate: A Transductive Approach

Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward

How Sharpness-Aware Minimization Minimizes Sharpness?

Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models

DreamFusion: Text-to-3D using 2D Diffusion

The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation

What Can we Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers?

The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium

Integrating Symmetry into Differentiable Planning with Steerable Convolutions

Deep Generative Symbolic Regression

Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation

Correlative Information Maximization Based Biologically Plausible Neural Networks for Correlated Source Separation

Batch Multivalid Conformal Prediction

Neural Networks and the Chomsky Hierarchy

SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments

A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation

This Looks Like It Rather Than That: ProtoKNN For Similarity-Based Classifiers

DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion

Towards Understanding GD with Hard and Conjugate Pseudo-labels for Test-Time Adaptation

Context-enriched molecule representations improve few-shot drug discovery

Boosting Adversarial Transferability using Dynamic Cues

Scalable and Equivariant Spherical CNNs by Discrete-Continuous (DISCO) Convolutions

When Source-Free Domain Adaptation Meets Learning with Noisy Labels

Training-Free Structured Diffusion Guidance for Compositional Text-to-Image Synthesis

CrAM: A Compression-Aware Minimizer

Semi-Implicit Variational Inference via Score Matching

Generative Augmented Flow Networks

Accurate Neural Training with 4-bit Matrix Multiplications at Standard Formats

Multiple sequence alignment as a sequence-to-sequence learning problem

A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation

A Primal-Dual Framework for Transformers and Neural Networks

Solving Constrained Variational Inequalities via a First-order Interior Point-based Method

Spectral Augmentation for Self-Supervised Learning on Graphs

Neural Causal Models for Counterfactual Identification and Estimation

The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks

Uni-Mol: A Universal 3D Molecular Representation Learning Framework

PASHA: Efficient HPO and NAS with Progressive Resource Allocation

Sign and Basis Invariant Networks for Spectral Graph Representation Learning

Betty: An Automatic Differentiation Library for Multilevel Optimization

EA-HAS-Bench: Energy-aware Hyperparameter and Architecture Search Benchmark

Structure by Architecture: Structured Representations without Regularization

A Non-monotonic Self-terminating Language Model

Learning topology-preserving data representations

Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach

Quantifying Memorization Across Neural Language Models

Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts

KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP

Scaffolding a Student to Instill Knowledge

Efficient Edge Inference by Selective Query

Graph Signal Sampling for Inductive One-Bit Matrix Completion: a Closed-form Solution

Faster Gradient-Free Methods for Escaping Saddle Points

Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories

Semi-Parametric Inducing Point Networks and Neural Processes

Taking a Step Back with KCal: Multi-Class Kernel-Based Calibration for Deep Neural Networks

Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task

Progressive Prompts: Continual Learning for Language Models

Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action Representations

Iterative Patch Selection for High-Resolution Image Recognition

ReAct: Synergizing Reasoning and Acting in Language Models

Efficient Offline Policy Optimization with a Learned Model

Learning to Solve Constraint Satisfaction Problems with Recurrent Transformer

Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints

New Insights for the Stability-Plasticity Dilemma in Online Continual Learning

Temporal Dependencies in Feature Importance for Time Series Prediction

Video Scene Graph Generation from Single-Frame Weak Supervision

Versatile Neural Processes for Learning Implicit Neural Representations

Human Motion Diffusion Model

Compressing multidimensional weather and climate data into neural networks

SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization

Simplified State Space Layers for Sequence Modeling

Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform

SQA3D: Situated Question Answering in 3D Scenes

A Minimalist Dataset for Systematic Generalization of Perception, Syntax, and Semantics

Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!

Rethinking the Expressive Power of GNNs via Graph Biconnectivity

BAYES RISK CTC: CONTROLLABLE CTC ALIGNMENT IN SEQUENCE-TO-SEQUENCE TASKS

Efficiently Computing Nash Equilibria in Adversarial Team Markov Games

Unsupervised Model Selection for Time Series Anomaly Detection

Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning

Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning

NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning

Backpropagation through Combinatorial Algorithms: Identity with Projection Works

DiffEdit: Diffusion-based semantic image editing with mask guidance

Towards Stable Test-time Adaptation in Dynamic Wild World

Denoising Masked Autoencoders Help Robust Classification

EquiMod: An Equivariance Module to Improve Visual Instance Discrimination

One Transformer Can Understand Both 2D & 3D Molecular Data

Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning

FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning

Learning with Logical Constraints but without Shortcut Satisfaction

Robust and Controllable Object-Centric Learning through Energy-based Models

Do We Really Need Complicated Model Architectures For Temporal Networks?

DepthFL : Depthwise Federated Learning for Heterogeneous Clients

Over-Training with Mixup May Hurt Generalization

Self-supervised learning with rotation-invariant kernels

Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning

Causal Balancing for Domain Generalization

Multitask Prompt Tuning Enables Parameter-Efficient Transfer Learning

Why (and When) does Local SGD Generalize Better than SGD?

Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization

Imitating Human Behaviour with Diffusion Models

Better Generative Replay for Continual Federated Learning

WikiWhy: Answering and Explaining Cause-and-Effect Questions

Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders

EVC: Towards Real-Time Neural Image Compression with Mask Decay

Sparse Token Transformer with Attention Back Tracking

Short-Term Memory Convolutions

MaskViT: Masked Visual Pre-Training for Video Prediction

REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH

Sharper Bounds for Uniformly Stable Algorithms with Stationary Mixing Process

Analogy-Forming Transformers for Few-Shot 3D Parsing

FluidLab: A Differentiable Environment for Benchmarking Complex Fluid Manipulation

Meta Temporal Point Processes

Images as Weight Matrices: Sequential Image Generation Through Synaptic Learning Rules

How to prepare your task head for finetuning

Dataset Pruning: Reducing Training Data by Examining Generalization Influence

Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs

KwikBucks: Correlation Clustering with Cheap-Weak and Expensive-Strong Signals

Automated Data Augmentations for Graph Classification

Population-size-Aware Policy Optimization for Mean-Field Games

Learning Soft Constraints From Constrained Expert Demonstrations

Energy-based Out-of-Distribution Detection for Graph Neural Networks

Learning Fast and Slow for Online Time Series Forecasting

Towards Lightweight, Model-Agnostic and Diversity-Aware Active Anomaly Detection

An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion

Neural Compositional Rule Learning for Knowledge Graph Reasoning

How robust is unsupervised representation learning to distribution shift?

Distilling Cognitive Backdoor Patterns within an Image

Iterative Circuit Repair Against Formal Specifications

MocoSFL: enabling cross-client collaborative self-supervised learning

Better Teacher Better Student: Dynamic Prior Knowledge for Knowledge Distillation

MECTA: Memory-Economic Continual Test-Time Model Adaptation

Continuous pseudo-labeling from the start

IDEAL: Query-Efficient Data-Free Learning from Black-Box Models

Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes

DiGress: Discrete Denoising diffusion for graph generation

Deja Vu: Continual Model Generalization for Unseen Domains

Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots

Adversarial Diversity in Hanabi

Statistical Efficiency of Score Matching: The View from Isoperimetry

Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction

LMSeg: Language-guided Multi-dataset Segmentation

RoPAWS: Robust Semi-supervised Representation Learning from Uncurated Data

Toward Adversarial Training on Contextualized Language Representation

BC-IRL: Learning Generalizable Reward Functions from Demonstrations

Omnigrok: Grokking Beyond Algorithmic Data

GRACE-C: Generalized Rate Agnostic Causal Estimation via Constraints

Actionable Neural Representations: Grid Cells from Minimal Constraints

Optimal Activation Functions for the Random Features Regression Model

EUCLID: Towards Efficient Unsupervised Reinforcement Learning with Multi-choice Dynamics Model

Sparse tree-based Initialization for Neural Networks

A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias

Cycle to Clique (Cy2C) Graph Neural Network: A Sight to See beyond Neighborhood Aggregation

MaskFusion: Feature Augmentation for Click-Through Rate Prediction via Input-adaptive Mask Fusion

Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation

Learned Index with Dynamic $\epsilon$

Boosting Multiagent Reinforcement Learning via Permutation Invariant and Permutation Equivariant Networks

DAG Learning on the Permutahedron

UNICORN: A Unified Backdoor Trigger Inversion Framework

PV3D: A 3D Generative Model for Portrait Video Generation

UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks

On The Specialization of Neural Modules

Learning What and Where: Disentangling Location and Identity Tracking Without Supervision

Mass-Editing Memory in a Transformer

Few-shot Backdoor Attacks via Neural Tangent Kernels

NERDS: A General Framework to Train Camera Denoisers from Raw-RGB Noisy Image Pairs

Programmatically Grounded, Compositionally Generalizable Robotic Manipulation

Truncated Diffusion Probabilistic Models and Diffusion-based Adversarial Auto-Encoders

ILA-DA: Improving Transferability of Intermediate Level Attack with Data Augmentation

Contrastive Alignment of Vision to Language Through Parameter-Efficient Transfer Learning

Diffusion-GAN: Training GANs with Diffusion

BEEF: Bi-Compatible Class-Incremental Learning via Energy-Based Expansion and Fusion

QuAnt: Quantum Annealing with Learnt Couplings

MACTA: A Multi-agent Reinforcement Learning Approach for Cache Timing Attacks and Detection

Schema Inference for Interpretable Image Classification

Relative representations enable zero-shot latent space communication

On Achieving Optimal Adversarial Test Error

Self-Consistency Improves Chain of Thought Reasoning in Language Models

Spiking Convolutional Neural Networks for Text Classification

A Kernel Perspective of Skip Connections in Convolutional Networks

In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations

Confidence-Conditioned Value Functions for Offline Reinforcement Learning

Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations

Analyzing Tree Architectures in Ensembles via Neural Tangent Kernel

Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness

Progressive Voronoi Diagram Subdivision Enables Accurate Data-free Class-Incremental Learning

Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation

Explicitly Minimizing the Blur Error of Variational Autoencoders

Learning to Estimate Shapley Values with Vision Transformers

HotProtein: A Novel Framework for Protein Thermostability Prediction and Editing

Hyper-Decision Transformer for Efficient Online Policy Adaptation

Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent

Sparsity-Constrained Optimal Transport

Real-Time Image Demoir$\acute{e}$ing on Mobile Devices

RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning

MEDICAL IMAGE UNDERSTANDING WITH PRETRAINED VISION LANGUAGE MODELS: A COMPREHENSIVE STUDY

Understanding Influence Functions and Datamodels via Harmonic Analysis

Stochastic No-regret Learning for General Games with Variance Reduction

When Data Geometry Meets Deep Function: Generalizing Offline Reinforcement Learning

MIMT: Masked Image Modeling Transformer for Video Compression

Graph-based Deterministic Policy Gradient for Repetitive Combinatorial Optimization Problems

Efficient Discrete Multi Marginal Optimal Transport Regularization

Evaluating Representations with Readout Model Switching

Sequential Learning of Neural Networks for Prequential MDL

Explaining RL Decisions with Trajectories

Efficient Conditionally Invariant Representation Learning

Stable Target Field for Reduced Variance Score Estimation in Diffusion Models

Relative Behavioral Attributes: Filling the Gap between Symbolic Goal Specification and Reward Learning from Human Preferences

ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs

DINO as a von Mises-Fisher mixture model

The Lie Derivative for Measuring Learned Equivariance

Continuized Acceleration for Quasar Convex Functions in Non-Convex Optimization

Meta-Learning in Games

Universal Approximation Theorems for Differentiable Geometric Deep Learning

Provable Memorization Capacity of Transformers

Bridge the Inference Gaps of Neural Processes via Expectation Maximization

Masked Vision and Language Modeling for Multi-modal Representation Learning

Massively Scaling Heteroscedastic Classifiers

CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations

Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation

Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations

Decision Transformer under Random Frame Dropping

Visual Classification via Description from Large Language Models

De Novo Molecular Generation via Connection-aware Motif Mining

Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives

Towards Smooth Video Composition

Revisiting Graph Adversarial Attack and Defense From a Data Distribution Perspective

How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?

How Much Space Has Been Explored? Measuring the Chemical Space Covered by Databases and Machine-Generated Molecules

E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation

Online Bias Correction for Task-Free Continual Learning

Arbitrary Virtual Try-on Network: Characteristics Representation and Trade-off between Body and Clothing

Behind the Scenes of Gradient Descent: A Trajectory Analysis via Basis Function Decomposition

Don’t fear the unlabelled: safe semi-supervised learning via debiasing

Learning differentiable solvers for systems with hard constraints

DM-NeRF: 3D Scene Geometry Decomposition and Manipulation from 2D Images

SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models

A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet

Token Merging: Your ViT But Faster

NAGphormer: A Tokenized Graph Transformer for Node Classification in Large Graphs

Ensuring DNN Solution Feasibility for Optimization Problems with Linear Constraints

Retrieval-based Controllable Molecule Generation

Prompt-to-Prompt Image Editing with Cross-Attention Control

Localized Randomized Smoothing for Collective Robustness Certification

Hebbian Deep Learning Without Feedback

Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs

Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap

Distributionally Robust Post-hoc Classifiers under Prior Shifts

More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity

Stochastic Multi-Person 3D Motion Forecasting

TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second

Learning Structured Representations by Embedding Class Hierarchy

Multi-Objective Reinforcement Learning: Convexity, Stationarity and Pareto Optimality

Asynchronous Gradient Play in Zero-Sum Multi-agent Games

Novel View Synthesis with Diffusion Models

Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting

Behavior Prior Representation learning for Offline Reinforcement Learning

Trading Information between Latents in Hierarchical Variational Autoencoders

MEDFAIR: Benchmarking Fairness for Medical Imaging

Decoupled Training for Long-Tailed Classification With Stochastic Representations

Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translation

Building a Subspace of Policies for Scalable Continual Learning

Unbiased Stochastic Proximal Solver for Graph Neural Networks with Equilibrium States

3D Segmenter: 3D Transformer based Semantic Segmentation via 2D Panoramic Distillation

TabCaps: A Capsule Neural Network for Tabular Data Classification with BoW Routing

GOOD: Exploring geometric cues for detecting objects in an open world

Average Sensitivity of Decision Tree Learning

Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism

Tailoring Language Generation Models under Total Variation Distance

H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection

The KFIoU Loss for Rotated Object Detection

Systematic Rectification of Language Models via Dead-end Analysis

Anisotropic Message Passing: Graph Neural Networks with Directional and Long-Range Interactions

SYNC: SAFETY-AWARE NEURAL CONTROL FOR STABILIZING STOCHASTIC DELAY-DIFFERENTIAL EQUATIONS

PatchDCT: Patch Refinement for High Quality Instance Segmentation

A Message Passing Perspective on Learning Dynamics of Contrastive Learning

A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learning

Improved Convergence of Differential Private SGD with Gradient Clipping

Toeplitz Neural Network for Sequence Modeling

Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks

On the Word Boundaries of Emergent Languages Based on Harris's Articulation Scheme

Effective Self-supervised Pre-training on Low-compute Networks without Distillation

On the Soft-Subnetwork for Few-Shot Class Incremental Learning

TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization

Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding

Approximate Nearest Neighbor Search through Modern Error-Correcting Codes

Boosting the Cycle Counting Power of Graph Neural Networks with I$^2$-GNNs

Offline Reinforcement Learning with Differentiable Function Approximation is Provably Efficient

DENSE RGB SLAM WITH NEURAL IMPLICIT MAPS

Monocular Scene Reconstruction with 3D SDF Transformers

Learning Heterogeneous Interaction Strengths by Trajectory Prediction with Graph Neural Network

Online Low Rank Matrix Completion

Robust Fair Clustering: A Novel Fairness Attack and Defense Framework

Adaptive Budget Allocation for Parameter-Efficient Fine-Tuning

Generalize Learned Heuristics to Solve Large-scale Vehicle Routing Problems in Real-time

On the complexity of nonsmooth automatic differentiation

DaxBench: Benchmarking Deformable Object Manipulation with Differentiable Physics

Exploring perceptual straightness in learned visual representations

CO3: Cooperative Unsupervised 3D Representation Learning for Autonomous Driving

Understanding the Role of Nonlinearity in Training Dynamics of Contrastive Learning

Bag of Tricks for Unsupervised Text-to-Speech

Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning

Composing Task Knowledge With Modular Successor Feature Approximators

Advancing Radiograph Representation Learning with Masked Record Modeling

Verifying the Union of Manifolds Hypothesis for Image Data

GAMR: A Guided Attention Model for (visual) Reasoning

Simple initialization and parametrization of sinusoidal networks via their kernel bandwidth

Energy-Based Test Sample Adaptation for Domain Generalization

On the Saturation Effect of Kernel Ridge Regression

Re-parameterizing Your Optimizers rather than Architectures

PLOT: Prompt Learning with Optimal Transport for Vision-Language Models

Linearly Mapping from Image to Text Space

Protein Representation Learning via Knowledge Enhanced Primary Structure Reasoning

The Provable Benefit of Unsupervised Data Sharing for Offline Reinforcement Learning

HomoDistil: Homotopic Task-Agnostic Distillation of Pre-trained Transformers

Exploring Active 3D Object Detection from a Generalization Perspective

Gradient Gating for Deep Multi-Rate Learning on Graphs

Diffusion Models Already Have A Semantic Latent Space

Masked Image Modeling with Denoising Contrast

GoBigger: A Scalable Platform for Cooperative-Competitive Multi-Agent Interactive Simulation

Contrastive Learning for Unsupervised Domain Adaptation of Time Series

TILP: Differentiable Learning of Temporal Logical Rules on Knowledge Graphs

Masked Unsupervised Self-training for Label-free Image Classification

Learning the Positions in CountSketch

Deep Ensembles for Graphs with Higher-order Dependencies

Globally Optimal Training of Neural Networks with Threshold Activation Functions

Sound Randomized Smoothing in Floating-Point Arithmetic

Partially Observable RL with B-Stability: Unified Structural Condition and Sharp Sample-Efficient Algorithms

Out-of-distribution Representation Learning for Time Series Classification

AnyDA: Anytime Domain Adaptation

Koopman Neural Operator Forecaster for Time-series with Temporal Distributional Shifts

Deep Generative Modeling on Limited Data with Regularization by Nontransferable Pre-trained Models

Sampling with Mollified Interaction Energy Descent

Multimodal Federated Learning via Contrastive Representation Ensemble

Leveraging Importance Weights in Subset Selection

Can CNNs Be More Robust Than Transformers?

Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics

Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions

Causal Imitation Learning via Inverse Reinforcement Learning

FIT: A Metric for Model Sensitivity

Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play

Progressively Compressed Auto-Encoder for Self-supervised Representation Learning

Understanding Edge-of-Stability Training Dynamics with a Minimalist Example

Learning to Decompose Visual Features with Latent Textual Prompts

Dual Diffusion Implicit Bridges for Image-to-Image Translation

Calibrating Sequence likelihood Improves Conditional Language Generation

Learning Proximal Operators to Discover Multiple Optima

REPAIR: REnormalizing Permuted Activations for Interpolation Repair

Neural Radiance Field Codebooks

Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation

Diffusion Probabilistic Modeling of Protein Backbones in 3D for the motif-scaffolding problem

ISAAC Newton: Input-based Approximate Curvature for Newton's Method

Revisiting adapters with adversarial training

Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles

Rethinking Graph Lottery Tickets: Graph Sparsity Matters

Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses

Unicom: Universal and Compact Representation Learning for Image Retrieval

Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model

Symbolic Physics Learner: Discovering governing equations via Monte Carlo tree search

Flow Annealed Importance Sampling Bootstrap

Calibration Matters: Tackling Maximization Bias in Large-scale Advertising Recommendation Systems

Replicable Bandits

Eva: Practical Second-order Optimization with Kronecker-vectorized Approximation

On the Robustness of Safe Reinforcement Learning under Observational Perturbations

Image as Set of Points

Trainability Preserving Neural Pruning

Graph Neural Networks for Link Prediction with Subgraph Sketching

Learning Locality and Isotropy in Dialogue Modeling

A Unified Algebraic Perspective on Lipschitz Neural Networks

Information-Theoretic Diffusion

Evaluating Long-Term Memory in 3D Mazes

Contrastive Meta-Learning for Partially Observable Few-Shot Learning

Hebbian and Gradient-based Plasticity Enables Robust Memory and Rapid Learning in RNNs

Proactive Multi-Camera Collaboration for 3D Human Pose Estimation

Promptagator: Few-shot Dense Retrieval From 8 Examples

Backstepping Temporal Difference Learning

Human MotionFormer: Transferring Human Motions with Vision Transformers

Memorization-Dilation: Modeling Neural Collapse Under Noise

On Representing Mixed-Integer Linear Programs by Graph Neural Networks

Revisiting Robustness in Graph Machine Learning

Parallel Deep Neural Networks Have Zero Duality Gap

Reward Design with Language Models

Contrastive Corpus Attribution for Explaining Representations

Multi-domain image generation and translation with identifiability guarantees

Continual evaluation for lifelong learning: Identifying the stability gap

Can We Faithfully Represent Absence States to Compute Shapley Values on a DNN?

Dataless Knowledge Fusion by Merging Weights of Language Models

Long Range Language Modeling via Gated State Spaces

Transformer Meets Boundary Value Inverse Problems

Masked Distillation with Receptive Tokens

Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval

TextShield: Beyond Successfully Detecting Adversarial Sentences in text classification

Meta-learning Adaptive Deep Kernel Gaussian Processes for Molecular Property Prediction

Sparse Random Networks for Communication-Efficient Federated Learning

MetaGL: Evaluation-Free Selection of Graph Learning Models via Meta-Learning

Scalable Batch-Mode Deep Bayesian Active Learning via Equivalence Class Annealing

Spatial Attention Kinetic Networks with E(n)-Equivariance

Distributed Differential Privacy in Multi-Armed Bandits

Coverage-centric Coreset Selection for High Pruning Rates

Achieving Sub-linear Regret in Infinite Horizon Average Reward Constrained MDP with Linear Function Approximation

Encoding Recurrence into Transformers

Learning Hyper Label Model for Programmatic Weak Supervision

FedSpeed: Larger Local Interval, Less Communication Round, and Higher Generalization Accuracy

CLARE: Conservative Model-Based Reward Learning for Offline Inverse Reinforcement Learning

Generalized Precision Matrix for Scalable Estimation of Nonparametric Markov Networks

Learning to Jointly Share and Prune Weights for Grounding Based Vision and Language Models

Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach

GReTo: Remedying dynamic graph topology-task discordance via target homophily

Everybody Needs Good Neighbours: An Unsupervised Locality-based Method for Bias Mitigation

Combating Exacerbated Heterogeneity for Robust Models in Federated Learning

Improving Deep Regression with Ordinal Entropy

Language Modelling with Pixels

Bitrate-Constrained DRO: Beyond Worst Case Robustness To Unknown Group Shifts

Neural Architecture Design and Robustness: A Dataset

Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?

Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling

AutoTransfer: AutoML with Knowledge Transfer - An Application to Graph Neural Networks

The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks

Decentralized Optimistic Hyperpolicy Mirror Descent: Provably No-Regret Learning in Markov Games

Exploring the Limits of Differentially Private Deep Learning with Group-wise Clipping

HypeR: Multitask Hyper-Prompted Training Enables Large-Scale Retrieval Generalization

Learning without Prejudices: Continual Unbiased Learning via Benign and Malignant Forgetting

Selective Annotation Makes Language Models Better Few-Shot Learners

Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance Fields

Scaling Forward Gradient With Local Losses

NORM: Knowledge Distillation via N-to-One Representation Matching

Critic Sequential Monte Carlo

(Certified!!) Adversarial Robustness for Free!

Measuring Forgetting of Memorized Training Examples

Multi-lingual Evaluation of Code Generation Models

wav2tok: Deep Sequence Tokenizer for Audio Retrieval

Deep Learning meets Nonparametric Regression: Are Weight-Decayed DNNs Locally Adaptive?

Robust Active Distillation

SeaFormer: Squeeze-enhanced Axial Transformer for Mobile Semantic Segmentation

Joint Edge-Model Sparse Learning is Provably Efficient for Graph Neural Networks

Near-optimal Policy Identification in Active Reinforcement Learning

Spherical Sliced-Wasserstein

InPL: Pseudo-labeling the Inliers First for Imbalanced Semi-supervised Learning

Subquadratic Algorithms for Kernel Matrices via Kernel Density Estimation

MixPro: Data Augmentation with MaskMix and Progressive Attention Labeling for Vision Transformer

Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies

SP2 : A Second Order Stochastic Polyak Method

CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks

Continual Transformers: Redundancy-Free Attention for Online Inference

Dirichlet-based Uncertainty Calibration for Active Domain Adaptation

Accurate Image Restoration with Attention Retractable Transformer

Predicting Cellular Responses with Variational Causal Inference and Refined Relational Information

Self-Supervised Set Representation Learning for Unsupervised Meta-Learning

Causal Representation Learning for Instantaneous and Temporal Effects in Interactive Systems

Visual Imitation Learning with Patch Rewards

CodeT: Code Generation with Generated Tests

Learning to Generate Columns with Application to Vertex Coloring

Interaction-Based Disentanglement of Entities for Object-Centric World Models

Learning where and when to reason in neuro-symbolic inference

On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation

StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training

Plateau in Monotonic Linear Interpolation --- A "Biased" View of Loss Landscape for Deep Networks

Improving Deep Policy Gradients with Value Function Search

Depth Separation with Multilayer Mean-Field Networks

Crossformer: Transformer Utilizing Cross-Dimension Dependency for Multivariate Time Series Forecasting

Individual Privacy Accounting with Gaussian Differential Privacy

Non-parametric Outlier Synthesis

General Neural Gauge Fields

Generate rather than Retrieve: Large Language Models are Strong Context Generators

Discovering Informative and Robust Positives for Video Domain Adaptation

Understanding Why Generalized Reweighting Does Not Improve Over ERM

Gradient-Guided Importance Sampling for Learning Binary Energy-Based Models

Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics

Is Conditional Generative Modeling all you need for Decision Making?

Fair Attribute Completion on Graph with Missing Attributes

Planning with Sequence Models through Iterative Energy Minimization

Composing Ensembles of Pre-trained Models via Iterative Consensus

Deep Ranking Ensembles for Hyperparameter Optimization

Robustness to corruption in pre-trained Bayesian neural networks

Neural Groundplans: Persistent Neural Scene Representations from a Single Image

Improved Training of Physics-Informed Neural Networks Using Energy-Based Priors: a Study on Electrical Impedance Tomography

Disentanglement with Biological Constraints: A Theory of Functional Cell Types

ERL-Re$^2$: Efficient Evolutionary Reinforcement Learning with Shared State Representation and Individual Policy Representation

Towards Understanding Why Mask Reconstruction Pretraining Helps in Downstream Tasks

Continual Unsupervised Disentangling of Self-Organizing Representations

Accelerating Guided Diffusion Sampling with Splitting Numerical Methods

Thalamus: a brain-inspired algorithm for biologically-plausible continual learning and disentangled representations

LiftedCL: Lifting Contrastive Learning for Human-Centric Perception

SIMPLE: A Gradient Estimator for k-Subset Sampling

Modeling content creator incentives on algorithm-curated platforms

Deep Variational Implicit Processes

Estimating individual treatment effects under unobserved confounding using binary instruments

Approximate Bayesian Inference with Stein Functional Variational Gradient Descent

Distributional Meta-Gradient Reinforcement Learning

Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference

Denoising Diffusion Error Correction Codes

Temperature Schedules for self-supervised contrastive methods on long-tail data

Meta Knowledge Condensation for Federated Learning

ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills

Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning

Neuro-Symbolic Procedural Planning with Commonsense Prompting

Learning Object-Language Alignments for Open-Vocabulary Object Detection

Time to augment self-supervised visual representation learning

Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization

Chasing All-Round Graph Representation Robustness: Model, Training, and Optimization

Personalized Federated Learning with Feature Alignment and Classifier Collaboration

Adversarial Attacks on Adversarial Bandits

Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling

Improving Object-centric Learning with Query Optimization

Phase transition for detecting a small community in a large network

Bi-level Physics-Informed Neural Networks for PDE Constrained Optimization using Broyden's Hypergradients

DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection

Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might Be

Transformer-Patcher: One Mistake Worth One Neuron

Are More Layers Beneficial to Graph Transformers?

Searching Lottery Tickets in Graph Neural Networks: A Dual Perspective

Improving Out-of-distribution Generalization with Indirection Representations

Bort: Towards Explainable Neural Networks with Bounded Orthogonal Constraint

The Power of Regularization in Solving Extensive-Form Games

S-NeRF: Neural Radiance Fields for Street Views

Cycle-consistent Masked AutoEncoder for Unsupervised Domain Generalization

CFlowNets: Continuous Control with Generative Flow Networks

Limitless Stability for Graph Convolutional Networks

DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection

Differentiable Gaussianization Layers for Inverse Problems Regularized by Deep Generative Models

Exploring Low-Rank Property in Multiple Instance Learning for Whole Slide Image Classification

Breaking Correlation Shift via Conditional Invariant Regularizer

Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case

In-context Reinforcement Learning with Algorithm Distillation

Your Contrastive Learning Is Secretly Doing Stochastic Neighbor Embedding

Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors

Block and Subword-Scaling Floating-Point (BSFP) : An Efficient Non-Uniform Quantization For Low Precision Inference

Semi-supervised Community Detection via Structural Similarity Metrics

Learning Symbolic Models for Graph-structured Physical Mechanism

DDM$^2$: Self-Supervised Diffusion MRI Denoising with Generative Diffusion Models

FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification

Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks

Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased

Multivariate Time-series Imputation with Disentangled Temporal Representations

Evidential Uncertainty and Diversity Guided Active Learning for Scene Graph Generation

Automating Nearest Neighbor Search Configuration with Constrained Optimization

OTOv2: Automatic, Generic, User-Friendly

Unified Discrete Diffusion for Simultaneous Vision-Language Generation

Win: Weight-Decay-Integrated Nesterov Acceleration for Adaptive Gradient Algorithms

Self-Distillation for Further Pre-training of Transformers

Statistical Inference for Fisher Market Equilibrium

Visual Recognition with Deep Nearest Centroids

LPT: Long-tailed Prompt Tuning for Image Classification

DamoFD: Digging into Backbone Design on Face Detection

Prompting GPT-3 To Be Reliable

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

Spikformer: When Spiking Neural Network Meets Transformer

Multimodal Analogical Reasoning over Knowledge Graphs

Voxurf: Voxel-based Efficient and Accurate Neural Surface Reconstruction

Conditional Positional Encodings for Vision Transformers

Guarded Policy Optimization with Imperfect Online Demonstrations

Contrastive Learning Can Find An Optimal Basis For Approximately View-Invariant Functions

Revisiting the Entropy Semiring for Neural Speech Recognition

Rethinking skip connection model as a learnable Markov chain

Measuring axiomatic soundness of counterfactual image models

Alternating Differentiation for Optimization Layers

Out-of-distribution Detection with Implicit Outlier Transformation

Extracting Robust Models with Uncertain Examples

Stochastic Differentially Private and Fair Learning

Volumetric Optimal Transportation by Fast Fourier Transform

Hierarchical Relational Learning for Few-Shot Knowledge Graph Completion

The Devil is in the Wrongly-classified Samples: Towards Unified Open-set Recognition

MCAL: Minimum Cost Human-Machine Active Labeling

Learnable Topological Features For Phylogenetic Inference via Graph Neural Networks

Rotamer Density Estimator is an Unsupervised Learner of the Effect of Mutations on Protein-Protein Interaction

Bit-Pruning: A Sparse Multiplication-Less Dot-Product

A Stable and Scalable Method for Solving Initial Value PDEs with Neural Networks

IS SYNTHETIC DATA FROM GENERATIVE MODELS READY FOR IMAGE RECOGNITION?

Learning Domain-Agnostic Representation for Disease Diagnosis

BEVDistill: Cross-Modal BEV Distillation for Multi-View 3D Object Detection

A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification

Suppressing the Heterogeneity: A Strong Feature Extractor for Few-shot Segmentation

Achieve the Minimum Width of Neural Networks for Universal Approximation

UniKGQA: Unified Retrieval and Reasoning for Solving Multi-hop Question Answering Over Knowledge Graph

On amortizing convex conjugates for optimal transport

Discovering Evolution Strategies via Meta-Black-Box Optimization

DualAfford: Learning Collaborative Visual Affordance for Dual-gripper Manipulation

SIMPLE: Specialized Model-Sample Matching for Domain Generalization

Contextual Image Masking Modeling via Synergized Contrasting without View Augmentation for Faster and Better Visual Pretraining

TDR-CL: Targeted Doubly Robust Collaborative Learning for Debiased Recommendations

Patch-Level Contrasting without Patch Correspondence for Accurate and Dense Contrastive Representation Learning

Continuous-Discrete Convolution for Geometry-Sequence Modeling in Proteins

Phenaki: Variable Length Video Generation from Open Domain Textual Descriptions

Human-level Atari 200x faster

Least-to-Most Prompting Enables Complex Reasoning in Large Language Models

Molecule Generation For Target Protein Binding with Structural Motifs

Neural Collapse Inspired Feature-Classifier Alignment for Few-Shot Class-Incremental Learning

Towards Robust Object Detection Invariant to Real-World Domain Shifts

Generating Diverse Cooperative Agents by Learning Incompatible Policies

Information-Theoretic Analysis of Unsupervised Domain Adaptation

Effects of Graph Convolutions in Multi-layer Networks

Diffusion Posterior Sampling for General Noisy Inverse Problems

Ask Me Anything: A simple strategy for prompting language models

Multi-skill Mobile Manipulation for Object Rearrangement

Post-hoc Concept Bottleneck Models

Neural Image-based Avatars: Generalizable Radiance Fields for Human Avatar Modeling

Corrupted Image Modeling for Self-Supervised Visual Pre-Training

Deep Learning on Implicit Neural Representations of Shapes

Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language

Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only

Neural DAG Scheduling via One-Shot Priority Sampling

Efficient recurrent architectures through activity sparsity and sparse back-propagation through time

Provably Auditing Ordinary Least Squares in Low Dimensions

On Accelerated Perceptrons and Beyond

EVA3D: Compositional 3D Human Generation from 2D Image Collections

Single-shot General Hyper-parameter Optimization for Federated Learning

DocPrompting: Generating Code by Retrieving the Docs

The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry

Fooling SHAP with Stealthily Biased Sampling

View Synthesis with Sculpted Neural Points

On Pre-training Language Model for Antibody

Represent to Control Partially Observed Systems: Representation Learning with Provable Sample Efficiency

Efficient Attention via Control Variates

CUDA: Curriculum of Data Augmentation for Long-tailed Recognition

Spacetime Representation Learning

Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation

DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking

Mind's Eye: Grounded Language Model Reasoning through Simulation

Code Translation with Compiler Representations

Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection

Phase2vec: dynamical systems embedding with a physics-informed convolutional network

GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation

Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow

Learning on Large-scale Text-attributed Graphs via Variational Inference

Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics

Theoretical Characterization of the Generalization Performance of Overfitted Meta-Learning

StableDR: Stabilized Doubly Robust Learning for Recommendation on Data Missing Not at Random

ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks

Fundamental Limits in Formal Verification of Message-Passing Neural Networks

Generative Modelling with Inverse Heat Dissipation

Improving the imputation of missing data with Markov Blanket discovery

Classically Approximating Variational Quantum Machine Learning with Random Fourier Features

Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems

Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?

Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching

Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization

Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier

Recitation-Augmented Language Models

PowerQuant: Automorphism Search for Non-Uniform Quantization

Powderworld: A Platform for Understanding Generalization via Rich Task Distributions

Fisher-Legendre (FishLeg) optimization of deep neural networks

Pseudo-label Training and Model Inertia in Neural Machine Translation

Choreographer: Learning and Adapting Skills in Imagination

Blurring Diffusion Models

MultiViz: Towards Visualizing and Understanding Multimodal Models

LAVA: Data Valuation without Pre-Specified Learning Algorithms

Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization

Neuromechanical Autoencoders: Learning to Couple Elastic and Neural Network Nonlinearity

NeRN: Learning Neural Representations for Neural Networks

Proposal-Contrastive Pretraining for Object Detection from Fewer Data

PAC Reinforcement Learning for Predictive State Representations

Unsupervised Manifold Alignment with Joint Multidimensional Scaling

Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions

Conditional Antibody Design as 3D Equivariant Graph Translation

From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data

A CMDP-within-online framework for Meta-Safe Reinforcement Learning

Relational Attention: Generalizing Transformers for Graph-Structured Tasks

Making Better Decision by Directly Planning in Continuous Control

Training language models to summarize narratives improves brain alignment

Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images

Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery

MARS: Meta-learning as Score Matching in the Function Space

BALTO: fast tensor program optimization with diversity-based active learning

Pseudoinverse-Guided Diffusion Models for Inverse Problems

Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers

HiViT: A Simpler and More Efficient Design of Hierarchical Vision Transformer

Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics

Spatio-temporal point processes with deep non-stationary kernels

Modeling Sequential Sentence Relation to Improve Cross-lingual Dense Retrieval

Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering

$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games

Towards the Generalization of Contrastive Self-Supervised Learning

Deterministic training of generative autoencoders using invertible layers

Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries

Learning rigid dynamics with face interaction graph networks

Few-shot Cross-domain Image Generation via Inference-time Latent-code Learning

On the Sensitivity of Reward Inference to Misspecified Human Models

ArCL: Enhancing Contrastive Learning with Augmentation-Robust Representations

Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning

Understanding and Adopting Rational Behavior by Bellman Score Estimation

SMART: Self-supervised Multi-task pretrAining with contRol Transformers

Learning with Stochastic Orders

LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation

Extremely Simple Activation Shaping for Out-of-Distribution Detection

Extreme Q-Learning: MaxEnt RL without Entropy

Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs

Learning About Progress From Experts

Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities

Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search

Git Re-Basin: Merging Models modulo Permutation Symmetries

SimPer: Simple Self-Supervised Learning of Periodic Targets

No Reason for No Supervision: Improved Generalization in Supervised Models

Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective

EV-GAN: Simulation of extreme events with ReLU neural networks

Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training

Topologically penalized regression on manifolds

Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks

Composite Slice Transformer: An Efficient Transformer with Composition of Multi-Scale Multi-Range Attentions

OPTQ: Accurate Quantization for Generative Pre-trained Transformers

Faster Last-iterate Convergence of Policy Optimization in Zero-Sum Markov Games

Learning Controllable Adaptive Simulation for Multi-resolution Physics

The Tilted Variational Autoencoder: Improving Out-of-Distribution Detection

Constraining Representations Yields Models That Know What They Don't Know

Faster federated optimization under second-order similarity

Diffusion Models for Causal Discovery via Topological Ordering

Deconstructing Distributions: A Pointwise Framework of Learning

Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs

Gray-Box Gaussian Processes for Automated Reinforcement Learning

Machine Unlearning of Federated Clusters

Making Substitute Models More Bayesian Can Enhance Transferability of Adversarial Examples

MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations

Understanding Embodied Reference with Touch-Line Transformer

Semi-supervised learning with a principled likelihood from a generative model of data curation

The hidden uniform cluster prior in self-supervised learning

STaSy: Score-based Tabular data Synthesis

Near-optimal Coresets for Robust Clustering

Learning Diffusion Bridges on Constrained Domains

Bayesian Oracle for bounding information gain in neural encoding models

Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RL

On Representing Linear Programs by Graph Neural Networks

SLTUNET: A Simple Unified Model for Sign Language Translation

Confidential-PROFITT: Confidential PROof of FaIr Training of Trees

A Convergent Single-Loop Algorithm for Relaxation of Gromov-Wasserstein in Graph Data

Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners

Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles

Model-based Causal Bayesian Optimization

Multi-objective optimization via equivariant deep hypervolume approximation

ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion

Why adversarial training can hurt robust accuracy

Planning with Large Language Models for Code Generation

Where to Diffuse, How to Diffuse, and How to Get Back: Automated Learning for Multivariate Diffusions

EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data

VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training

How Does Semi-supervised Learning with Pseudo-labelers Work? A Case Study

Robust Scheduling with GFlowNets

Generating Sequences by Learning to Self-Correct

Feature selection and low test error in shallow low-rotation ReLU networks

A probabilistic framework for task-aligned intra- and inter-area neural manifold estimation

Behavior Proximal Policy Optimization

Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images

Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs

Distributed Extra-gradient with Optimal Complexity and Communication Guarantees

Characteristic Neural Ordinary Differential Equation

Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise

Can We Find Nash Equilibria at a Linear Rate in Markov Games?

Causal Reasoning in the Presence of Latent Confounders via Neural ADMG Learning

Understanding DDPM Latent Codes Through Optimal Transport

Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation

A Theory of Dynamic Benchmarks

Language models are multilingual chain-of-thought reasoners

FIGARO: Controllable Music Generation using Learned and Expert Features

Real-time variational method for learning neural trajectory and its dynamics

Label Propagation with Weak Supervision

MICN: Multi-scale Local and Global Context Modeling for Long-term Series Forecasting

f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation

Interpretable Geometric Deep Learning via Learnable Randomness Injection

Denoising Diffusion Samplers

Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation

Model ensemble instead of prompt fusion: a sample-specific knowledge transfer method for few-shot prompt tuning

Learning Iterative Neural Optimizers for Image Steganography

Decomposed Prompting: A Modular Approach for Solving Complex Tasks

A Control-Centric Benchmark for Video Prediction

Enhancing Meta Learning via Multi-Objective Soft Improvement Functions

Pessimism in the Face of Confounders: Provably Efficient Offline Reinforcement Learning in Partially Observable Markov Decision Processes

Memorization Capacity of Neural Networks with Conditional Computation

Graph Domain Adaptation via Theory-Grounded Spectral Regularization

Characterizing intrinsic compositionality in transformers with Tree Projections

Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning

Recursive Time Series Data Augmentation

Fast Nonlinear Vector Quantile Regression

Unveiling the sampling density in non-uniform geometric graphs

Test-Time Robust Personalization for Federated Learning

Solving stochastic weak Minty variational inequalities without increasing batch size

QAID: Question Answering Inspired Few-shot Intent Detection

Towards Addressing Label Skews in One-Shot Federated Learning

Contextual Convolutional Networks

Scenario-based Question Answering with Interacting Contextual Properties

EAGLE: Large-scale Learning of Turbulent Fluid Dynamics with Mesh Transformers

Neural ePDOs: Spatially Adaptive Equivariant Partial Differential Operator Based Networks

Learning Fair Graph Representations via Automated Data Augmentations

Learning Hierarchical Protein Representations via Complete 3D Graph Networks

Computing all Optimal Partial Transports

Learning Vortex Dynamics for Fluid Inference and Prediction

Analog Bits: Generating Discrete Data using Diffusion Models with Self-Conditioning

Filter-Recovery Network for Multi-Speaker Audio-Visual Speech Separation

Function-Consistent Feature Distillation

Decompose to Generalize: Species-Generalized Animal Pose Estimation

Scaling Up Probabilistic Circuits by Latent Variable Distillation

What shapes the loss landscape of self supervised learning?

Efficient approximation of neural population structure and correlations with probabilistic circuits

TypeT5: Seq2seq Type Inference using Static Analysis

Stay Moral and Explore: Learn to Behave Morally in Text-based Games

Improving Differentiable Neural Architecture Search by Encouraging Transferability

Auto-Encoding Goodness of Fit

Particle-based Variational Inference with Preconditioned Functional Gradient Flow

Markup-to-Image Diffusion Models with Scheduled Sampling

An Extensible Multi-modal Multi-task Object Dataset with Materials

DySR: Adaptive Super-Resolution via Algorithm and System Co-design

Can Neural Networks Learn Implicit Logic from Physical Reasoning?

ManyDG: Many-domain Generalization for Healthcare Applications

StyleMorph: Disentangled 3D-Aware Image Synthesis with a 3D Morphable StyleGAN

Packed Ensembles for efficient uncertainty estimation

Generalization and Estimation Error Bounds for Model-based Neural Networks

Towards convergence to Nash equilibria in two-team zero-sum games

Exploring Temporally Dynamic Data Augmentation for Video Recognition

Understanding Train-Validation Split in Meta-Learning with Neural Networks

Bispectral Neural Networks

A Learning Based Hypothesis Test for Harmful Covariate Shift

$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference

Selective Frequency Network for Image Restoration

ImaginaryNet: Learning Object Detectors without Real Images and Annotations

Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation

Understanding the Generalization of Adam in Learning Neural Networks with Proper Regularization

FINDE: Neural Differential Equations for Finding and Preserving Invariant Quantities

Offline RL for Natural Language Generation with Implicit Language Q Learning

Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems

Human alignment of neural network representations

Risk-Aware Reinforcement Learning with Coherent Risk Measures and Non-linear Function Approximation

Self-supervision through Random Segments with Autoregressive Coding (RandSAC)

Efficiently Controlling Multiple Risks with Pareto Testing

DiffMimic: Efficient Motion Mimicking with Differentiable Physics

Causality Compensated Attention for Contextual Biased Visual Recognition

Sparse Mixture-of-Experts are Domain Generalizable Learners

Towards Better Selective Classification

Latent Bottlenecked Attentive Neural Processes

How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?

Latent Graph Inference using Product Manifolds

Light Sampling Field and BRDF Representation for Physically-based Neural Rendering

FedExP: Speeding Up Federated Averaging via Extrapolation

Compositionality with Variation Reliably Emerges in Neural Networks

gDDIM: Generalized denoising diffusion implicit models

Fast Sampling of Diffusion Models with Exponential Integrator

Understanding The Robustness of Self-supervised Learning Through Topic Modeling

Interactive Portrait Harmonization

AIM: Adapting Image Models for Efficient Video Action Recognition

Parameter-Efficient Fine-Tuning Design Spaces

Not All Tasks Are Born Equal: Understanding Zero-Shot Generalization

Learning in temporally structured environments

Dilated convolution with learnable spacings

PEER: A Collaborative Language Model

Maximizing Spatio-Temporal Entropy of Deep 3D CNNs for Efficient Video Recognition

Formal Mathematics Statement Curriculum Learning

D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory

Subsampling in Large Graphs Using Ricci Curvature

$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells

UL2: Unifying Language Learning Paradigms

STREET: A MULTI-TASK STRUCTURED REASONING AND EXPLANATION BENCHMARK

Efficient Certified Training and Robustness Verification of Neural ODEs

Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation

Diffusion Probabilistic Fields

Globally Injective ReLU Networks

SCALE-UP: An Efficient Black-box Input-level Backdoor Detection via Analyzing Scaled Prediction Consistency

Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences

Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement

SemPPL: Predicting Pseudo-Labels for Better Contrastive Representations

Distributionally Robust Recourse Action

Bidirectional Propagation for Cross-Modal 3D Object Detection

On the Effectiveness of Out-of-Distribution Data in Self-Supervised Long-Tail Learning.

Efficient Deep Reinforcement Learning Requires Regulating Overfitting

Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks

Learning to Segment from Noisy Annotations: A Spatial Correction Approach

Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation

DynaMS: Dyanmic Margin Selection for Efficient Deep Learning

CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers

Mid-Vision Feedback

HiCLIP: Contrastive Language-Image Pretraining with Hierarchy-aware Attention

Learning Rationalizable Equilibria in Multiplayer Games

Revisiting Intrinsic Reward for Exploration in Procedurally Generated Environments

Deep Learning From Crowdsourced Labels: Coupled Cross-Entropy Minimization, Identifiability, and Regularization

Efficient Federated Domain Translation

Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement

Agnostic Learning of General ReLU Activation Using Gradient Descent

Latent Variable Representation for Reinforcement Learning

Learning Probabilistic Topological Representations Using Discrete Morse Theory

Spectral Decomposition Representation for Reinforcement Learning

Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning

Robust Multivariate Time-Series Forecasting: Adversarial Attacks and Defense Mechanisms

MMVAE+: Enhancing the Generative Quality of Multimodal VAEs without Compromises

Causal Confusion and Reward Misidentification in Preference-Based Reward Learning

TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding

Open-Vocabulary Object Detection upon Frozen Vision and Language Models

Solving Continuous Control via Q-learning

Mutual Partial Label Learning with Competitive Label Noise

Partial Label Unsupervised Domain Adaptation with Class-Prototype Alignment

Max-Margin Works while Large Margin Fails: Generalization without Uniform Convergence

Implicit Regularization for Group Sparsity

A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning

Martingale Posterior Neural Processes

ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure

Red PANDA: Disambiguating Image Anomaly Detection by Removing Nuisance Factors

Identifiability Results for Multimodal Contrastive Learning

Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection

Learning Group Importance using the Differentiable Hypergeometric Distribution

PAC-NeRF: Physics Augmented Continuum Neural Radiance Fields for Geometry-Agnostic System Identification

A View From Somewhere: Human-Centric Face Representations

PaLI: A Jointly-Scaled Multilingual Language-Image Model

Learning Uncertainty for Unknown Domains with Zero-Target-Assumption

Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic

Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild

Federated Learning as Variational Inference: A Scalable Expectation Propagation Approach

MPCFORMER: FAST, PERFORMANT AND PRIVATE TRANSFORMER INFERENCE WITH MPC

Building Normalizing Flows with Stochastic Interpolants

Clifford Neural Layers for PDE Modeling

Learning to Compose Soft Prompts for Compositional Zero-Shot Learning

LogicDP: Creating Labels for Graph Data via Inductive Logic Programming

Maximizing Communication Efficiency for Large-scale Training via 0/1 Adam

Temporal Coherent Test Time Optimization for Robust Video Classification

Multi-Objective Online Learning

Provable Robustness against Wasserstein Distribution Shifts via Input Randomization

CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos

On the Performance of Temporal Difference Learning With Neural Networks

Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness

Scaling Laws for a Multi-Agent Reinforcement Learning Model

Transfer Learning with Deep Tabular Models

Anti-Symmetric DGN: a stable architecture for Deep Graph Networks

Protein Sequence and Structure Co-Design with Equivariant Translation

Differentially Private Adaptive Optimization with Delayed Preconditioners

SMART: Sentences as Basic Units for Text Evaluation

Fairness and Accuracy under Domain Generalization

Mitigating Dataset Bias by Using Per-Sample Gradient

Gradient Boosting Performs Gaussian Process Inference

A critical look at the evaluation of GNNs under heterophily: Are we really making progress?

Provably Efficient Lifelong Reinforcement Learning with Linear Representation

Confidence Estimation Using Unlabeled Data

Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve

Diffusion-based Image Translation using disentangled style and content representation

Competitive Physics Informed Networks

Learnable Graph Convolutional Attention Networks

On the Data-Efficiency with Contrastive Image Transformation in Reinforcement Learning

Unbiased Supervised Contrastive Learning

Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation

Bridging the Gap to Real-World Object-Centric Learning

Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning

Understanding Zero-shot Adversarial Robustness for Large-Scale Models

TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis

3D generation on ImageNet

TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation

Winning Both the Accuracy of Floating Point Activation and the Simplicity of Integer Arithmetic

Sparse Distributed Memory is a Continual Learner

Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation

Symmetric Pruning in Quantum Neural Networks

On The Inadequacy of Optimizing Alignment and Uniformity in Contrastive Learning of Sentence Representations

GNNDelete: A General Strategy for Unlearning in Graph Neural Networks

Fundamental limits on the robustness of image classifiers

CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code

Leveraging Unlabeled Data to Track Memorization

Learning to reason over visual objects

Weighted Ensemble Self-Supervised Learning

Agent-based Graph Neural Networks

Tuning Frequency Bias in Neural Network Training with Nonuniform Data

Treeformer: Dense Gradient Trees for Efficient Attention Computation

The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers

Augmentation with Projection: Towards an Effective and Efficient Data Augmentation Paradigm for Distillation

Protein Representation Learning by Geometric Structure Pretraining

DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks

Don’t forget the nullspace! Nullspace occupancy as a mechanism for out of distribution failure

Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics

Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods

Confidence-Based Feature Imputation for Graphs with Partially Known Features

Imitating Graph-Based Planning with Goal-Conditioned Policies

Long-Tailed Learning Requires Feature Learning

FedDAR: Federated Domain-Aware Representation Learning

FLIP: A Provable Defense Framework for Backdoor Mitigation in Federated Learning

Factorized Fourier Neural Operators

Variational Latent Branching Model for Off-Policy Evaluation

3D Equivariant Diffusion for Target-Aware Molecule Generation and Affinity Prediction

Transformer-based model for symbolic regression via joint supervised learning

LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning

Share Your Representation Only: Guaranteed Improvement of the Privacy-Utility Tradeoff in Federated Learning

Mini-batch $k$-means terminates within $O(d/\epsilon)$ iterations

Disentanglement of Correlated Factors via Hausdorff Factorized Support

An efficient encoder-decoder architecture with top-down attention for speech separation

Specformer: Spectral Graph Neural Networks Meet Transformers

BigVGAN: A Universal Neural Vocoder with Large-Scale Training

ZiCo: Zero-shot NAS via inverse Coefficient of Variation on Gradients

Cross-Layer Retrospective Retrieving via Layer Attention

Decision S4: Efficient Sequence-Based RL via State Spaces Layers

Easy Differentially Private Linear Regression

Contextual bandits with concave rewards, and an application to fair ranking

Can BERT Refrain from Forgetting on Sequential Tasks? A Probing Study

A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning

Mole-BERT: Rethinking Pre-training Graph Neural Networks for Molecules

DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training

Latent State Marginalization as a Low-cost Approach for Improving Exploration

Implicit Bias in Leaky ReLU Networks Trained on High-Dimensional Data

GFlowNets and variational inference

Leveraging Large Language Models for Multiple Choice Question Answering

Understanding the Covariance Structure of Convolutional Filters

Regression with Label Differential Privacy

E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking

WiNeRT: Towards Neural Ray Tracing for Wireless Channel Modelling and Differentiable Simulations

MA-BERT: Towards Matrix Arithmetic-only BERT Inference by Eliminating Complex Non-Linear Functions

An Exact Poly-Time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Network

On the Robustness to Misspecification of α-posteriors and Their Variational Approximations

Binding Language Models in Symbolic Languages

ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond

Compositional Semantic Parsing with Large Language Models

Coupled Multiwavelet Operator Learning for Coupled Differential Equations

POPGym: Benchmarking Partially Observable Reinforcement Learning

Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning

TrojText: Test-time Invisible Textual Trojan Insertion

Transferable Unlearnable Examples

Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning

Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN

Task-Aware Information Routing from Common Representation Space in Lifelong Learning

GNNInterpreter: A Probabilistic Generative Model-Level Explanation for Graph Neural Networks

Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore

Combinatorial Pure Exploration of Causal Bandits

Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization

What Makes Convolutional Models Great on Long Sequence Modeling?

Learning Multimodal Data Augmentation in Feature Space

Neural Systematic Binder

Active Image Indexing

How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization

Learning Human-Compatible Representations for Case-Based Decision Support

Optimizing Spca-based Continual Learning: A Theoretical Approach

Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models

The Best of Both Worlds: Accurate Global and Personalized Models through Federated Learning with Data-Free Hyper-Knowledge Distillation

Linear Connectivity Reveals Generalization Strategies

SCoMoE: Efficient Mixtures of Experts with Structured Communication

A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta.

The Role of Coverage in Online Reinforcement Learning

PINTO: Faithful Language Reasoning Using Prompt-Generated Rationales

GEASS: Neural causal feature selection for high-dimensional biological data

SmartFRZ: An Efficient Training Framework using Attention-Based Layer Freezing

Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement

Augmentation Component Analysis: Modeling Similarity via the Augmentation Overlaps

Neural Bregman Divergences for Distance Learning

Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks

A Theoretical Understanding of Shallow Vision Transformers: Learning, Generalization, and Sample Complexity

ChiroDiff: Modelling chirographic data with Diffusion Models

Out-of-Distribution Detection and Selective Generation for Conditional Language Models

A Unified Framework for Soft Threshold Pruning

Federated Neural Bandits

Compositional Task Representations for Large Language Models

An Additive Instance-Wise Approach to Multi-class Model Interpretation

Editing models with task arithmetic

Reparameterization through Spatial Gradient Scaling

Quality-Similar Diversity via Population Based Reinforcement Learning

Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learning

Adaptive Optimization in the $\infty$-Width Limit

Surgical Fine-Tuning Improves Adaptation to Distribution Shifts

Avoiding spurious correlations via logit correction

Interpretability with full complexity by constraining feature information

User-Interactive Offline Reinforcement Learning

Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RL

Large Language Models are Human-Level Prompt Engineers

Pruning Deep Neural Networks from a Sparsity Perspective

Spotlight: Mobile UI Understanding using Vision-Language Models with a Focus

Dual Student Networks for Data-Free Model Stealing

Data-Free One-Shot Federated Learning Under Very High Statistical Heterogeneity

Mosaic Representation Learning for Self-supervised Visual Pre-training

A Theoretical Framework for Inference and Learning in Predictive Coding Networks

Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top

Energy-Inspired Self-Supervised Pretraining for Vision Models

Effectively Modeling Time Series with Simple Discrete State Spaces

A Time Series is Worth 64 Words: Long-term Forecasting with Transformers

Random Laplacian Features for Learning with Hyperbolic Space

Replay Memory as An Empirical MDP: Combining Conservative Estimation with Experience Replay

$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space

Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought

Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport

Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection

CircNet: Meshing 3D Point Clouds with Circumcenter Detection

Robust Graph Dictionary Learning

Unsupervised visualization of image datasets using contrastive learning

Learning Harmonic Molecular Representations on Riemannian Manifold

Learning Language Representations with Logical Inductive Bias

First Steps Toward Understanding the Extrapolation of Nonlinear Models to Unseen Domains

Concept-level Debugging of Part-Prototype Networks

CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis

Computational Language Acquisition with Theory of Mind

Projective Proximal Gradient Descent for Nonconvex Nonsmooth Optimization: Fast Convergence Without Kurdyka-Lojasiewicz (KL) Property

Mega: Moving Average Equipped Gated Attention

Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees

Prototypical Calibration for Few-shot Learning of Language Models

Serving Graph Compression for Graph Neural Networks

Learning MLPs on Graphs: A Unified View of Effectiveness, Robustness, and Efficiency

Geometrically regularized autoencoders for non-Euclidean data

Calibrating the Rigged Lottery: Making All Tickets Reliable

A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution

VoGE: A Differentiable Volume Renderer using Gaussian Ellipsoids for Analysis-by-Synthesis