The schedule for 2023 is still being finalized. Recheck this page again closer to the conference start date.


Show Detail »
Schedule Mon Tue Wed Thu Fri
Timezone:
America/Los_Angeles
Filter Events:  
Filter Rooms:  

 

MON 1 MAY
1 a.m.
Oral Session 1 Track 1 [1:00-2:30]
Oral s 1:00-2:10
[1:00] A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet
[1:10] Token Merging: Your ViT But Faster
[1:20] TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
[1:30] Learning Group Importance using the Differentiable Hypergeometric Distribution
[1:40] Neural Networks and the Chomsky Hierarchy
[1:50] Learning on Large-scale Text-attributed Graphs via Variational Inference
[2:00] Image as Set of Points
(ends 2:30 AM)
Oral Session 1 Track 2 [1:00-2:30]
Oral s 1:00-2:30
[1:00] Flow Annealed Importance Sampling Bootstrap
[1:10] Dynamical systems embedding with a physics-informed convolutional network
[1:20] Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems
[1:30] Compressing multidimensional weather and climate data into neural networks
[1:40] D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory
[1:50] Conditional Antibody Design as 3D Equivariant Graph Translation
[2:00] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
[2:10] CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations
[2:20] Continuous PDE Dynamics Forecasting with Implicit Neural Representations
(ends 2:30 AM)
Oral Session 1 Track 3 [1:00-2:30]
A probabilistic framework for task-aligned intra- and inter-area neural manifold estimation
Disentangling with Biological Constraints: A Theory of Functional Cell Types
Hebbian Deep Learning Without Feedback
(ends 2:30 AM)
Oral Session 1 Track 4 [1:00-2:30]
Oral s 1:00-2:30
[1:00] Localized Randomized Smoothing for Collective Robustness Certification
[1:10] Quantifying Memorization Across Neural Language Models
[1:20] Generating Intuitive Fairness Specifications for Natural Language Processing
[1:30] Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
[1:40] Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
[1:50] UNICORN: A Unified Backdoor Trigger Inversion Framework
[2:00] Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
[2:10] Learning to Estimate Shapley Values with Vision Transformers
[2:20] Provable Defense Against Geometric Transformations
(ends 2:30 AM)
Oral Session 1 Track 5 [1:00-2:30]
Oral s 1:00-2:20
[1:00] Hyperbolic Deep Reinforcement Learning
[1:10] DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
[1:20] The In-Sample Softmax for Offline Reinforcement Learning
[1:30] Emergence of Maps in the Memories of Blind Navigation Agents
[1:40] Does Zero-Shot Reinforcement Learning Exist?
[1:50] Learning Soft Constraints From Constrained Expert Demonstrations
[2:00] Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes
[2:10] Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
(ends 2:30 AM)
Oral Session 1 Track 6 [1:00-2:30]
Oral s 1:00-2:20
[1:00] Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
[1:10] Fisher-Legendre (FishLeg) optimization of deep neural networks
[1:20] Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
[1:30] Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets
[1:40] NeRN: Learning Neural Representations for Neural Networks
[1:50] Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
[2:00] Continual Unsupervised Disentangling of Self-Organizing Representations
[2:10] Optimal Transport for Offline Imitation Learning
(ends 2:30 AM)
2:30 a.m.
Poster Session 1 [2:30-4:30]
TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding
Softened Symbol Grounding for Neuro-symbolic Systems
Weighted Clock Logic Point Process
On The Relative Error of Random Fourier Features for Preserving Kernel Distance
Characterizing intrinsic compositionality in transformers with Tree Projections
Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles
Test-Time Adaptation via Self-Training with Nearest Neighbor Information
Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
On the Soft-Subnetwork for Few-Shot Class Incremental Learning
Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation
Neural-based classification rule learning for sequential data
Light Sampling Field and BRDF Representation for Physically-based Neural Rendering
Continual Unsupervised Disentangling of Self-Organizing Representations
Valid P-Value for Deep Learning-driven Salient Region
Towards Better Selective Classification
A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
The In-Sample Softmax for Offline Reinforcement Learning
DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks
Optimal Transport for Offline Imitation Learning
Compressing multidimensional weather and climate data into neural networks
Does Zero-Shot Reinforcement Learning Exist?
LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
Real-time variational method for learning neural trajectory and its dynamics
Trainability Preserving Neural Pruning
Causal Balancing for Domain Generalization
Learning on Large-scale Text-attributed Graphs via Variational Inference
Deconstructing Distributions: A Pointwise Framework of Learning
wav2tok: Deep Sequence Tokenizer for Audio Retrieval
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs
Localized Randomized Smoothing for Collective Robustness Certification
A VAE for Transformers with Nonparametric Variational Information Bottleneck
Why (and When) does Local SGD Generalize Better than SGD?
Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model
Emergence of Maps in the Memories of Blind Navigation Agents
GLM-130B: An Open Bilingual Pre-trained Model
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
Why adversarial training can hurt robust accuracy
Neural Networks and the Chomsky Hierarchy
Diffusion-based Image Translation using disentangled style and content representation
LPT: Long-tailed Prompt Tuning for Image Classification
Mega: Moving Average Equipped Gated Attention
Learning Group Importance using the Differentiable Hypergeometric Distribution
Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
Equal Improvability: A New Fairness Notion Considering the Long-term Impact
Rethinking skip connection model as a learnable Markov chain
3D Segmenter: 3D Transformer based Semantic Segmentation via 2D Panoramic Distillation
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
Contrastive Meta-Learning for Partially Observable Few-Shot Learning
MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet
UNICORN: A Unified Backdoor Trigger Inversion Framework
Provable Defense Against Geometric Transformations
Editing models with task arithmetic
Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory
Preference Transformer: Modeling Human Preferences using Transformers for RL
Multi-objective optimization via equivariant deep hypervolume approximation
Conditional Antibody Design as 3D Equivariant Graph Translation
Quantifying Memorization Across Neural Language Models
Learning Soft Constraints From Constrained Expert Demonstrations
Finding the Global Semantic Representation in GAN through Fréchet Mean
Token Merging: Your ViT But Faster
Can discrete information extraction prompts generalize across language models?
Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data
CktGNN: Circuit Graph Neural Network for Electronic Design Automation
Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
Masked Vision and Language Modeling for Multi-modal Representation Learning
Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees
Generating Intuitive Fairness Specifications for Natural Language Processing
Unsupervised Manifold Alignment with Joint Multidimensional Scaling
Identifiability Results for Multimodal Contrastive Learning
How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?
Neural Groundplans: Persistent Neural Scene Representations from a Single Image
Machine Unlearning of Federated Clusters
Image as Set of Points
Generating Sequences by Learning to Self-Correct
Fooling SHAP with Stealthily Biased Sampling
A Control-Centric Benchmark for Video Prediction
Disentangling with Biological Constraints: A Theory of Functional Cell Types
Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems
Learning to Induce Causal Structure
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
Multimodal Federated Learning via Contrastive Representation Ensemble
Hebbian Deep Learning Without Feedback
An efficient encoder-decoder architecture with top-down attention for speech separation
Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts
CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations
Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots
Hyperbolic Deep Reinforcement Learning
Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication
Broken Neural Scaling Laws
Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action Representations
Fisher-Legendre (FishLeg) optimization of deep neural networks
Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets
NeRN: Learning Neural Representations for Neural Networks
TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
Explaining Temporal Graph Models through an Explorer-Navigator Framework
Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation
Matching receptor to odorant with protein language and graph neural networks
Denoising Diffusion Samplers
Protein Sequence and Structure Co-Design with Equivariant Translation
Contextual bandits with concave rewards, and an application to fair ranking
Continuous-time identification of dynamic state-space models by deep subspace encoding
Pareto-Efficient Decision Agents for Offline Multi-Objective Reinforcement Learning
Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference
Mitigating Dataset Bias by Using Per-Sample Gradient
Distributed Extra-gradient with Optimal Complexity and Communication Guarantees
Learning to reason over visual objects
Dynamical systems embedding with a physics-informed convolutional network
A probabilistic framework for task-aligned intra- and inter-area neural manifold estimation
Cross-Layer Retrospective Retrieving via Layer Attention
RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning
Avoiding spurious correlations via logit correction
Guiding Safe Exploration with Weakest Preconditions
Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths
Learning topology-preserving data representations
A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution
A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification
Interpretable Geometric Deep Learning via Learnable Randomness Injection
Sound Randomized Smoothing in Floating-Point Arithmetic
Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport
Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes
Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore
Interaction-Based Disentanglement of Entities for Object-Centric World Models
Sparse Random Networks for Communication-Efficient Federated Learning
Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs
Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
Unified Discrete Diffusion for Simultaneous Vision-Language Generation
Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints
Certified Defences Against Adversarial Patch Attacks on Semantic Segmentation
On the Perils of Cascading Robust Classifiers
Structure by Architecture: Structured Representations without Regularization
Continuous PDE Dynamics Forecasting with Implicit Neural Representations
How gradient estimator variance and bias impact learning in neural networks
Countinuous pseudo-labeling from the start
Learning to Estimate Shapley Values with Vision Transformers
QAID: Question Answering Inspired Few-shot Intent Detection
Flow Annealed Importance Sampling Bootstrap
Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward
(ends 4:30 AM)
6 a.m.
Oral Session 2 Track 1 [6:00-7:30]
Oral s 6:00-7:30
[6:00] GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
[6:10] ReAct: Synergizing Reasoning and Acting in Language Models
[6:20] Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
[6:30] Human Motion Diffusion Model
[6:40] NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning
[6:50] PEER: A Collaborative Language Model
[7:00] UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks
[7:10] Mass-Editing Memory in a Transformer
[7:20] On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation
(ends 7:30 AM)
Oral Session 2 Track 2 [6:00-7:30]
Oral s 6:00-7:30
[6:00] The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation
[6:10] The Generalized Eigenvalue Problem as a Nash Equilibrium
[6:20] Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
[6:30] Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives
[6:40] Unsupervised Model Selection for Time Series Anomaly Detection
[6:50] LAVA: Data Valuation without Pre-Specified Learning Algorithms
[7:00] Packed Ensembles for efficient uncertainty estimation
[7:10] Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering
[7:20] Learning where and when to reason in neuro-symbolic inference
(ends 7:30 AM)
Oral Session 2 Track 3 [6:00-7:30]
Oral s 6:00-7:00
[6:00] Diffusion Posterior Sampling for General Noisy Inverse Problems
[6:10] Prompt-to-Prompt Image Editing with Cross-Attention Control
[6:20] Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting
[6:30] Diffusion Models Already Have A Semantic Latent Space
[6:40] DreamFusion: Text-to-3D using 2D Diffusion
[6:50] Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
(ends 7:30 AM)
Oral Session 2 Track 4 [6:00-7:30]
Oral s 6:00-7:30
[6:00] Planning Goals for Exploration
[6:10] Multi-skill Mobile Manipulation for Object Rearrangement
[6:20] The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
[6:30] A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
[6:40] Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
[6:50] Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
[7:00] Near-optimal Policy Identification in Active Reinforcement Learning
[7:10] BC-IRL: Learning Generalizable Reward Functions from Demonstrations
[7:20] Learning About Progress From Experts
(ends 7:30 AM)
Oral Session 2 Track 5 [6:00-7:30]
Oral s 6:00-6:50
[6:00] Neural Optimal Transport
[6:10] Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
[6:20] Effects of Graph Convolutions in Multi-layer Networks
[6:30] A Kernel Perspective of Skip Connections in Convolutional Networks
[6:40] Modeling content creator incentives on algorithm-curated platforms
(ends 7:30 AM)
Oral Session 2 Track 6 [6:00-7:30]
Oral s 6:00-7:20
[6:00] A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
[6:10] Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception
[6:20] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
[6:30] ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
[6:40] Ask Me Anything: A simple strategy for prompting language models
[6:50] Code Translation with Compiler Representations
[7:00] Hidden Markov Transformer for Simultaneous Machine Translation
[7:10] Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
(ends 7:30 AM)
7:30 a.m.
Poster Session 2 [7:30-9:30]
The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation
$\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks
Leveraging Large Language Models for Multiple Choice Question Answering
Code Translation with Compiler Representations
An Exact Poly-Time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Network
On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation
Iterative Patch Selection for High-Resolution Image Recognition
On the Importance and Applicability of Pre-Training for Federated Learning
Can CNNs Be More Robust Than Transformers?
Modeling content creator incentives on algorithm-curated platforms
PASHA: Efficient HPO and NAS with Progressive Resource Allocation
Amortised Invariance Learning for Contrastive Self-Supervision
Temporal Coherent Test Time Optimization for Robust Video Classification
Linear Mode Connectivity of Deep Neural Networks via Permutation Invariance and Renormalization
The Generalized Eigenvalue Problem as a Nash Equilibrium
Learning Symbolic Models for Graph-structured Physical Mechanism
Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning
An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation
Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives
Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
Scaffolding a Student to Instill Knowledge
MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization
A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
Relaxed Combinatorial Optimization Networks with Self-Supervision: Theoretical and Empirical Notes on the Cardinality-Constrained Case
Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization
FIGARO: Controllable Music Generation using Learned and Expert Features
Language Models Can (kind of) Reason: A Systematic Formal Analysis of Chain-of-Thought
Discrete Predictor-Corrector Diffusion Models for Image Synthesis
Prompting GPT-3 To Be Reliable
Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
A Universal 3D Molecular Representation Learning Framework
Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception
Improved Training of Physics-Informed Neural Networks Using Energy-Based Priors: a Study on Electrical Impedance Tomography
Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions
Planning Goals for Exploration
CUTS: Neural Causal Discovery from Irregular Time-Series Data
A Kernel Perspective of Skip Connections in Convolutional Networks
ChordMixer: A Scalable Neural Attention Model for Sequences with Different Length
Strategic Classification on Graphs
POPGym: Benchmarking Partially Observable Reinforcement Learning
Trading Information between Latents in Hierarchical Variational Autoencoders
GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation
Mass-Editing Memory in a Transformer
In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations
Quantifying and Mitigating the Impact of Label Errors on Model Disparity Metrics
Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization
Effects of Graph Convolutions in Multi-layer Networks
Learning an Invertible Output Mapping Can Mitigate Simplicity Bias in Neural Networks
Open-Vocabulary Object Detection upon Frozen Vision and Language Models
Neural Causal Models for Counterfactual Identification and Estimation
Prompt-to-Prompt Image Editing with Cross-Attention Control
Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning
DreamFusion: Text-to-3D using 2D Diffusion
Optimizing Spca-based Continual Learning: A Theoretical Approach
Generative Modelling with Inverse Heat Dissipation
ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks
General Neural Gauge Fields
Gradient Boosting Performs Gaussian Process Inference
Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks
Bit-Pruning: A Sparse Multiplication-Less Dot-Product
Temperature Schedules for self-supervised contrastive methods on long-tail data
Is Reinforcement Learning (Not) for Natural Language Processing?: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
Gradient Gating for Deep Multi-Rate Learning on Graphs
PEER: A Collaborative Language Model
On the Edge of Benign Overfitting: Label Noise and Overparameterization Level
Explicitly Minimizing the Blur Error of Variational Autoencoders
TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning
Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
ReAct: Synergizing Reasoning and Acting in Language Models
MultiViz: Towards Visualizing and Understanding Multimodal Models
Over-Training with Mixup May Hurt Generalization
Unsupervised Model Selection for Time Series Anomaly Detection
LAVA: Data Valuation without Pre-Specified Learning Algorithms
Competitive Physics Informed Networks
Memorization Capacity of Neural Networks with Conditional Computation
Become a Proficient Player with Limited Data through Watching Pure Videos
Multi-skill Mobile Manipulation for Object Rearrangement
(Certified!!) Adversarial Robustness for Free!
Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication
Learning where and when to reason in neuro-symbolic inference
A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
Factorized Fourier Neural Operators
Diffusion Probabilistic Modeling of Protein Backbones in 3D for the motif-scaffolding problem
Complexity-Based Prompting for Multi-step Reasoning
Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection
DFlow: Learning to Synthesize Better Optical Flow Datasets via a Differentiable Pipeline
Information-Theoretic Analysis of Unsupervised Domain Adaptation
Human Motion Diffusion Model
Hidden Markov Transformer for Simultaneous Machine Translation
Learning Iterative Neural Optimizers for Image Steganography
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
Revisiting Graph Adversarial Attack and Defense From a Data Distribution Perspective
Grounding Graph Network Simulators using Physical Sensor Observations
NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
Constraining Representations Yields Models That Know What They Don't Know
Self-Supervised Set Representation Learning for Unsupervised Meta-Learning
Packed Ensembles for efficient uncertainty estimation
Fairness and Accuracy under Domain Generalization
The hidden uniform cluster prior in self-supervised learning
Protein Representation Learning by Geometric Structure Pretraining
Diffusion Models Already Have A Semantic Latent Space
Minimum Description Length Control
Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness
Iterative Circuit Repair Against Formal Specifications
Neural Optimal Transport
The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
Causal Reasoning in the Presence of Latent Confounders via Neural ADMG Learning
Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference
Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection
Measure the Predictive Heterogeneity
MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
Learning About Progress From Experts
Diffusion Posterior Sampling for General Noisy Inverse Problems
TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation
Uniform-in-time propagation of chaos for the mean field gradient Langevin dynamics
Near-optimal Policy Identification in Active Reinforcement Learning
Diffusion Models for Causal Discovery via Topological Ordering
BC-IRL: Learning Generalizable Reward Functions from Demonstrations
Variational Information Pursuit for Interpretable Predictions
Decoupled Training for Long-Tailed Classification With Stochastic Representations
Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering
Constructive TT-representation of the tensors given as index interaction functions with applications
Spatial Attention Kinetic Networks with E(n)-Equivariance
Decomposed Prompting: A Modular Approach for Solving Complex Tasks
Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models
Exploring perceptual straightness in learned visual representations
Ask Me Anything: A simple strategy for prompting language models
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation
Global Explainability of GNNs via Logic Combination of Learned Concepts
Unsupervised visualization of image datasets using contrastive learning
Robust Scheduling with GFlowNets
SpeedyZero: Mastering Atari with Limited Data and Time
Rethinking Symbolic Regression: Morphology and Adaptability in the Context of Evolutionary Algorithms
Computational Language Acquisition with Theory of Mind
Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting
(ends 9:30 AM)
TUE 2 MAY
1 a.m.
Oral Session 3 Track 1 [1:00-2:30]
Oral s 1:00-2:30
[1:00] Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
[1:10] Adversarial Diversity in Hanabi
[1:20] Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
[1:30] Programmatically Grounded, Compositionally Generalizable Robotic Manipulation
[1:40] On the Sensitivity of Reward Inference to Misspecified Human Models
[1:50] Understanding and Adopting Rational Behavior by Bellman Score Estimation
[2:00] SMART: Self-supervised Multi-task pretrAining with contRol Transformers
[2:10] Dichotomy of Control: Separating What You Can Control from What You Cannot
[2:20] Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
(ends 2:30 AM)
Oral Session 3 Track 2 [1:00-2:30]
Oral s 1:00-2:30
[1:00] AutoGT: Automated Graph Transformer Architecture Search
[1:10] Efficient Conditionally Invariant Representation Learning
[1:20] Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
[1:30] Omnigrok: Grokking Beyond Algorithmic Data
[1:40] Sparse MoE with Random Routing as the New Dropout: Training Bigger and Self-Scalable Models
[1:50] Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve
[2:00] Multi-lingual Evaluation of Code Generation Models
[2:10] Rethinking the Expressive Power of GNNs via Graph Biconnectivity
[2:20] When and why Vision-Language Models behave like Bags-of-Words, and what to do about it?
(ends 2:30 AM)
Oral Session 3 Track 3 [1:00-2:30]
Oral s 1:00-2:30
[1:00] Score-based Generative 3D Mesh Modeling
[1:10] The Role of ImageNet Classes in Fréchet Inception Distance
[1:20] Learning Diffusion Bridges on Constrained Domains
[1:30] Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
[1:40] Learning multi-scale local conditional probability models of images
[1:50] An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
[2:00] Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
[2:10] Closing the gap: Exact maximum likelihood training of generative autoencoders using invertible layers
[2:20] 3D generation on ImageNet
(ends 2:30 AM)
Oral Session 3 Track 4 [1:00-2:30]
Oral s 1:00-2:30
[1:00] On the duality between contrastive and non-contrastive self-supervised learning
[1:10] Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning
[1:20] The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
[1:30] Self-supervised learning with rotation-invariant kernels
[1:40] DINO as a von Mises-Fisher mixture model
[1:50] Domain Generalization via Heckman-type Selection Models
[2:00] Gradient-based optimization is not necessary for generalization in neural networks
[2:10] Efficient Discrete Multi Marginal Optimal Transport Regularization
[2:20] Sparsity-Constrained Optimal Transport
(ends 2:30 AM)
Oral Session 3 Track 5 [1:00-2:30]
Oral s 1:00-2:20
[1:00] Sign and Basis Invariant Networks for Spectral Graph Representation Learning
[1:10] ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks
[1:20] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
[1:30] QuAnt: Quantum Annealing with Learnt Couplings
[1:40] Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
[1:50] The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
[2:00] The Lie Derivative for Measuring Learned Equivariance
[2:10] Training language models to summarize narratives improves brain alignment
(ends 2:30 AM)
2:30 a.m.
Poster Session 3 [2:30-4:30]
Easy Differentially Private Linear Regression
Multi-lingual Evaluation of Code Generation Models
Bridge the Inference Gaps of Neural Processes via Expectation Maximization
Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
Topology-aware robust optimization
Learning to Extrapolate: A Transductive Approach
ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure
Scaling Forward Gradient With Local Losses
Treeformer: Dense Gradient Trees for Efficient Attention Computation
Diffusion Probabilistic Fields
LDMIC: Learning-based Distributed Multi-view Image Coding
Mid-Vision Feedback for Convolutional Neural Networks
Limitless Stability for Graph Convolutional Networks
Long-Tailed Learning Requires Feature Learning
Active Image Indexing
Language models are multilingual chain-of-thought reasoners
Self-supervised learning with rotation-invariant kernels
When and why Vision-Language Models behave like Bags-of-Words, and what to do about it?
Agent-based Graph Neural Networks
Classically Approximating Variational Quantum Machine Learning with Random Fourier Features
Transformer-based World Models Are Happy With 100k Interactions
TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
Holistic Adversarially Robust Pruning
Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
Efficient Certified Training and Robustness Verification of Neural ODEs
Empirical Study of Pre-training a Backbone for 3D Human Pose and Shape Estimation
Understanding and Adopting Rational Behavior by Bellman Score Estimation
FedFA: Federated Feature Augmentation
Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
Efficient Planning in a Compact Latent Action Space
The Curious Case of Benign Memorization
3D generation on ImageNet
Fundamental limits on the robustness of image classifiers
Sampling-free Inference for Ab-Initio Potential Energy Surface Networks
Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
Rethinking the Expressive Power of GNNs via Graph Biconnectivity
Learning multi-scale local conditional probability models of images
Backpropagation through Combinatorial Algorithms: Identity with Projection Works
ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
Adversarial Imitation Learning with Preferences
Efficient Conditionally Invariant Representation Learning
Efficient Discrete Multi Marginal Optimal Transport Regularization
A Mixture-of-Expert Approach to RL-based Dialogue Management
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking
ODAM: Gradient-based Instance-Specific Visual Explanations for Object Detection
Autoregressive Conditional Neural Processes
On the Sensitivity of Reward Inference to Misspecified Human Models
SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning
Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve
Interpretations of Domain Adaptations via Layer Variational Analysis
SMART: Self-supervised Multi-task pretrAining with contRol Transformers
LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification
DFPC: Data flow driven pruning of coupled channels without data.
Robust Fair Clustering: A Novel Fairness Attack and Defense Framework
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis
Domain Generalization via Heckman-type Selection Models
Understanding Embodied Reference with Touch-Line Transformer
The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes
Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding
Actionable Neural Representations: Grid Cells from Minimal Constraints
Leveraging Unlabeled Data to Track Memorization
Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism
ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks
DINO as a von Mises-Fisher mixture model
Make-A-Video: Text-to-Video Generation without Text-Video Data
Unicom: Universal and Compact Representation Learning for Image Retrieval
Learning Diffusion Bridges on Constrained Domains
Link Prediction with Non-Contrastive Learning
StyleMorph: Disentangling Shape, Pose and Appearance through 3D Morphable Image and Geometry Generation
The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
FaiREE: fair classification with finite-sample and distribution-free guarantee
Multivariate Time-series Imputation with Disentangled Temporal Representations
Dual Diffusion Implicit Bridges for Image-to-Image Translation
Revisiting Robustness in Graph Machine Learning
Sparse Distributed Memory is a Continual Learner
Sampling-based inference for large linear models, with application to linearised Laplace
Offline Congestion Games: How Feedback Type Affects Data Coverage Requirement
On the duality between contrastive and non-contrastive self-supervised learning
Learning to CROSS exchange to solve min-max vehicle routing problems
This Looks Like It Rather Than That: ProtoKNN For Similarity-Based Classifiers
Heavy-tailed Noise Does Not Explain the Gap Between SGD and Adam, but Sign Descent Might
A critical look at evaluation of GNNs under heterophily: Are we really making progress?
Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses
Neural Radiance Field Codebooks
Sign and Basis Invariant Networks for Spectral Graph Representation Learning
Adaptive Optimization in the $\infty$-Width Limit
QuAnt: Quantum Annealing with Learnt Couplings
The Lie Derivative for Measuring Learned Equivariance
Imitating Human Behaviour with Diffusion Models
DiffusER: Diffusion via Edit-based Reconstruction
Provable Sim-to-real Transfer in Continuous Domain with Partial Observations
Adversarial Diversity in Hanabi
DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
Large Language Models are Human-Level Prompt Engineers
FIT: A Metric for Model Sensitivity
Score-based Generative 3D Mesh Modeling
Closing the gap: Exact maximum likelihood training of generative autoencoders using invertible layers
GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis
Efficient Deep Reinforcement Learning Requires Regulating Statistical Overfitting
Label Propagation with Weak Supervision
Dichotomy of Control: Separating What You Can Control from What You Cannot
How Sharpness-Aware Minimization Minimizes Sharpness?
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
Latent Bottlenecked Attentive Neural Processes
Markup-to-Image Diffusion Models with Scheduled Sampling
Tuning Frequency Bias in Neural Network Training with Nonuniform Data
Omnigrok: Grokking Beyond Algorithmic Data
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification
The Role of ImageNet Classes in Fréchet Inception Distance
Data Valuation Without Training of a Model
Training language models to summarize narratives improves brain alignment
Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
Continual Learning of Language Models
Sparsity-Constrained Optimal Transport
KwikBucks: Correlation Clustering with Cheap-Weak and Expensive-Strong Signals
Language Models Can Teach Themselves to Program Better
Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
Sparse MoE with Random Routing as the New Dropout: Training Bigger and Self-Scalable Models
FunkNN: Neural Interpolation for Functional Generation
A Non-monotonic Self-terminating Language Model
Gradient-based optimization is not necessary for generalization in neural networks
Integrating Symmetry into Differentiable Planning with Steerable Convolutions
Estimating individual treatment effects under unobserved confounding using binary instruments
Programmatically Grounded, Compositionally Generalizable Robotic Manipulation
Mini-batch $k$-means terminates within $O(d/\epsilon)$ iterations
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
AutoGT: Automated Graph Transformer Architecture Search
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training
Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
Online Boundary-Free Continual Learning by Scheduled Data Prior
How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?
(ends 4:30 AM)
6 a.m.
Oral Session 4 Track 1 [6:00-7:30]
Oral s 6:00-7:20
[6:00] Minimalistic Unsupervised Learning with the Sparse Manifold Transform
[6:10] AANG : Automating Auxiliary Learning
[6:20] STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
[6:30] Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts
[6:40] When Source-Free Domain Adaptation Meets Learning with Noisy Labels
[6:50] Towards Stable Test-time Adaptation in Dynamic Wild World
[7:00] Proposal-Contrastive Pretraining for Object Detection from Fewer Data
[7:10] Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations
(ends 7:30 AM)
Oral Session 4 Track 2 [6:00-7:30]
Oral s 6:00-7:20
[6:00] Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle
[6:10] SAM as an Optimal Relaxation of Bayes
[6:20] Generative Augmented Flow Networks
[6:30] A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation
[6:40] Domain-Indexing Variational Bayes for Domain Adaptation
[6:50] GRACE-C: Generalized Rate Agnostic Causal Estimation via Constraints
[7:00] Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise
[7:10] Martingale Posterior Neural Processes
(ends 7:30 AM)
Oral Session 4 Track 3 [6:00-7:30]
Oral s 6:00-7:10
[6:00] Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation
[6:10] Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning
[6:20] Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
[6:30] Choreographer: Learning and Adapting Skills in Imagination
[6:40] A CMDP-within-online framework for Meta-Safe Reinforcement Learning
[6:50] Confidence-Conditioned Value Functions for Offline Reinforcement Learning
[7:00] Extreme Q-Learning: MaxEnt RL without Entropy
(ends 7:30 AM)
Oral Session 4 Track 4 [6:00-7:30]
Oral s 6:00-7:20
[6:00] Transformers are Sample-Efficient World Models
[6:10] Building a Subspace of Policies for Scalable Continual Learning
[6:20] Neural Episodic Control with State Abstraction
[6:30] Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
[6:40] Sparse Q-Learning: Offline Reinforcement Learning with Implicit Value Regularization
[6:50] Is Conditional Generative Modeling all you need for Decision Making?
[7:00] RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
[7:10] Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
(ends 7:30 AM)
Oral Session 4 Track 5 [6:00-7:30]
Oral s 6:00-7:00
[6:00] Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
[6:10] Learning Controllable Adaptive Simulation for Multi-resolution Physics
[6:20] Minimax Optimal Kernel Operator Learning via Multilevel Training
[6:30] Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics
[6:40] Pre-training via Denoising for Molecular Property Prediction
[6:50] MARS: Meta-learning as Score Matching in the Function Space
(ends 7:30 AM)
Oral Session 4 Track 6 [6:00-7:30]
Oral s 6:00-7:20
[6:00] CUDA: Curriculum of Data Augmentation for Long-tailed Recognition
[6:10] One-Pixel Shortcut: On the Learning Preference of Deep Neural Networks
[6:20] Learning Label Encodings for Deep Regression
[6:30] Multifactor Sequential Disentanglement via Structured Koopman Autoencoders
[6:40] A Unified Algebraic Perspective on Lipschitz Neural Networks
[6:50] From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data
[7:00] Git Re-Basin: Merging Models modulo Permutation Symmetries
[7:10] In-context Reinforcement Learning with Algorithm Distillation
(ends 7:30 AM)
7:30 a.m.
Poster Session 4 [7:30-9:30]
CUDA: Curriculum of Data Augmentation for Long-tailed Recognition
Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning
On Emergence of Activation Sparsity in Trained Transformers
Investigating Multi-task Pretraining and Generalization in Reinforcement Learning
Learning Controllable Adaptive Simulation for Multi-resolution Physics
Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning
De Novo Molecular Generation via Connection-aware Motif Mining
Revisiting Populations in multi-agent Communication
A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation
Pre-training via Denoising for Molecular Property Prediction
DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
AudioGen: Textually Guided Audio Generation
Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis
Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics
D4AM: A General Denoising Framework for Downstream Acoustic Models
Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework
MARS: Meta-learning as Score Matching in the Function Space
Don’t forget the nullspace! Nullspace occupancy as a mechanism for out of distribution failure
Minimax Optimal Kernel Operator Learning via Multilevel Training
Is Conditional Generative Modeling all you need for Decision Making?
Exact Group Fairness Regularization via Classwise Robust Optimization
Leveraging Incompatibility to Defend Against Backdoor Poisoning
Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks
Towards Robust Object Detection Invariant to Real-World Domain Shifts
Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning
Massively Scaling Heteroscedastic Classifiers
Meta-Learning in Games
Faster federated optimization under second-order similarity
The Continuous CNN: from Task-Specific to Unified CNN Architecture
What Can we Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers?
Contrastive Learning for Unsupervised Domain Adaptation of Time Series
Sparse Token Transformer with Attention Back Tracking
Empowering Networks With Scale and Rotation Equivariance Using A Similarity Convolution
Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
Domain-Indexing Variational Bayes for Domain Adaptation
AANG : Automating Auxiliary Learning
On the Word Boundaries of Emergent Languages Based on Harris's Articulation Scheme
Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks
Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Networks
Jointly Learning Visual and Auditory Speech Representations from Raw Data
Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations
Neural Episodic Control with State Abstraction
Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation
Energy-Based Test Sample Adaptation for Domain Generalization
The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks
From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data
Compositional Semantic Parsing with Large Language Models
Symmetries, Flat Minima and the Conserved Quantities of Gradient Flow
Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle
Reliability of CKA as a Similarity Measure in Deep Learning
A Graph Neural Network Approach to Automated Model Building in Cryo-EM Maps
Imitating Graph-Based Planning with Goal-Conditioned Policies
GRACE-C: Generalized Rate Agnostic Causal Estimation via Constraints
Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts
simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing
Generative Augmented Flow Networks
Decision Transformer under Random Frame Dropping
Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning
Git Re-Basin: Merging Models modulo Permutation Symmetries
Personalized Reward Learning with Interaction-Grounded Learning (IGL)
Learning with Auxiliary Activation for Memory-Efficient Training
DELTA: DEGRADATION-FREE FULLY TEST-TIME ADAPTATION
Planning with Language Models through Iterative Energy Minimization
Reproducible Bandits
Weighted Ensemble Self-Supervised Learning
Enhancing Meta Learning via Multi-Objective Soft Improvement Functions
On Achieving Optimal Adversarial Test Error
Don’t fear the unlabelled: safe semi-supervised learning via debiasing
Long Range Language Modeling via Gated State Spaces
Martingale Posterior Neural Processes
Scaling Laws For Deep Learning Based Image Reconstruction
Extreme Q-Learning: MaxEnt RL without Entropy
A Unified Algebraic Perspective on Lipschitz Neural Networks
Versatile Neural Processes for Learning Implicit Neural Representations
Self-Distillation for Further Pre-training of Transformers
Specformer: Spectral Graph Neural Networks Meet Transformers
On the Robustness to Misspecification of α-posteriors and Their Variational Approximations
Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning
Online Bias Correction for Task-Free Continual Learning
Provable Unsupervised Data Sharing for Offline Reinforcement Learning
One Transformer Can Understand Both 2D & 3D Molecular Data
Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement
Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization
Confidence-Conditioned Value Functions for Offline Reinforcement Learning
Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
Learning Locality and Isotropy in Dialogue Modeling
Multifactor Sequential Disentanglement via Structured Koopman Autoencoders
Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
Approximate Vanishing Ideal Computations at Scale
Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation
When Source-Free Domain Adaptation Meets Learning with Noisy Labels
Towards Stable Test-time Adaptation in Dynamic Wild World
HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetwork
In-context Reinforcement Learning with Algorithm Distillation
Beyond calibration: estimating the grouping loss of modern neural networks
RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise
Sparse Q-Learning: Offline Reinforcement Learning with Implicit Value Regularization
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
Causal Imitation Learning via Inverse Reinforcement Learning
Artificial Neuronal Ensembles with Learned Context Dependent Gating
Transformers are Sample-Efficient World Models
Topologically penalized regression on manifolds
A Unified Framework of Soft Threshold Pruning
Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small
Population-size-Aware Policy Optimization for Mean-Field Games
Average Sensitivity of Decision Tree Learning
Extremely Simple Activation Shaping for Out-of-Distribution Detection
GFlowNets and variational inference
Building a Subspace of Policies for Scalable Continual Learning
Minimalistic Unsupervised Learning with the Sparse Manifold Transform
Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning
Simplicial Hopfield networks
Proposal-Contrastive Pretraining for Object Detection from Fewer Data
Latent Graph Inference using Product Manifolds
SAM as an Optimal Relaxation of Bayes
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Data augmentation alone can improve adversarial training
One-Pixel Shortcut: On the Learning Preference of Deep Neural Networks
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
MMVAE+: Enhancing the Generative Quality of Multimodal VAEs without Compromises
Towards Smooth Video Composition
Bayesian Oracle for bounding information gain in neural encoding models
Linearly Mapping from Image to Text Space
That Label's got Style: Handling Label Style Bias for Uncertain Image Segmentation
PerFedMask: Personalized Federated Learning with Optimized Masking Vectors
Efficient Model Updates for Approximate Unlearning of Graph-Structured Data
Deep Generative Symbolic Regression
TiAda: A Time-scale Adaptive Algorithm For Nonconvex Minimax Optimization
Learning Label Encodings for Deep Regression
Video Scene Graph Generation from Single-Frame Weak Supervision
Enhancing the Inductive Biases of Graph Neural ODE for Modeling Dynamical Systems
Choreographer: Learning and Adapting Skills in Imagination
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
Disentangling Learning Representations with Density Estimation
Parameter-Efficient Fine-Tuning Design Spaces
Spikformer: When Spiking Neural Network Meets Transformer
A CMDP-within-online framework for Meta-Safe Reinforcement Learning
(ends 9:30 AM)
WED 3 MAY
1 a.m.
Oral Session 5 Track 1 [1:00-2:30]
Progress measures for grokking via mechanistic interpretability
Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes
CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
(ends 2:30 AM)
Oral Session 5 Track 2 [1:00-2:30]
Corrupted Image Modeling for Self-Supervised Visual Pre-Training
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
SimPer: Simple Self-Supervised Learning of Periodic Targets
(ends 2:30 AM)
Oral Session 5 Track 3 [1:00-2:30]
Oral s 1:00-2:00
[1:00] DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity
[1:10] Single-shot General Hyper-parameter Optimization for Federated Learning
[1:20] Solving Constrained Variational Inequalities via a First-order Interior Point-based Method
[1:30] FedExP: Speeding up Federated Averaging via Extrapolation
[1:40] LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence
[1:50] Multi-Objective Online Learning
(ends 2:30 AM)
Oral Session 5 Track 4 [1:00-2:30]
Oral s 1:00-2:20
[1:00] Hungry Hungry Hippos: Towards Language Modeling with State Space Models
[1:10] Relative representations enable zero-shot latent space communication
[1:20] ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion
[1:30] Distilling Model Failures as Directions in Latent Space
[1:40] Graph Neural Networks for Link Prediction with Subgraph Sketching
[1:50] The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks
[2:00] REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH
[2:10] A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
(ends 2:30 AM)
Oral Session 5 Track 5 [1:00-2:30]
Oral s 1:00-2:10
[1:00] Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
[1:10] Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
[1:20] DocPrompting: Generating Code by Retrieving the Docs
[1:30] View Synthesis with Sculpted Neural Points
[1:40] VA-DepthNet: A Variational Approach to Single Image Depth Prediction
[1:50] Visual Classification via Description from Large Language Models
[2:00] Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach
(ends 2:30 AM)
Oral Session 5 Track 6 [1:00-2:30]
Oral s 1:00-2:20
[1:00] Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
[1:10] PLOT: Prompt Learning with Optimal Transport for Vision-Language Models
[1:20] Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
[1:30] Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
[1:40] A Primal-Dual Framework for Transformers and Neural Networks
[1:50] Learning with Logical Constraints but without Shortcut Satisfaction
[2:00] No Reason for No Supervision: Improved Generalization in Supervised Models
[2:10] Generating Diverse Cooperative Agents by Learning Incompatible Policies
(ends 2:30 AM)
2:30 a.m.
Poster Session 5 [2:30-4:30]
Out-of-distribution Detection with Implicit Outlier Transformation
View Synthesis with Sculpted Neural Points
Latent State Marginalization as a Low-cost Approach to Improving Exploration
Digging into Backbone Design on Face Detection
Learning ReLU networks to high uniform accuracy is intractable
No Reason for No Supervision: Improved Generalization in Supervised Models
Is Forgetting Less a Good Inductive Bias for Forward Transfer?
DAG Learning on the Permutahedron
Stochastic Differentially Private and Fair Learning
KNN-Diffusion: Image Generation via Large-Scale Retrieval
Learning with Logical Constraints but without Shortcut Satisfaction
Selective Annotation Makes Language Models Better Few-Shot Learners
Relative representations enable zero-shot latent space communication
Learning differentiable solvers for systems with hard constraints
Individual Privacy Accounting with Gaussian Differential Privacy
Kernel Neural Optimal Transport
Recursive Time Series Data Augmentation
Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning
NORM: Knowledge Distillation via N-to-One Representation Matching
Generative Modeling Helps Weak Supervision (and Vice Versa)
Confidence-Based Feature Imputation for Graphs with Partially Known Features
Progress measures for grokking via mechanistic interpretability
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling
Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic
Robustness to corruption in pre-trained Bayesian neural networks
A law of adversarial risk, interpolation, and label noise
Corrupted Image Modeling for Self-Supervised Visual Pre-Training
Particle-based Variational Inference with Preconditioned Functional Gradient Flow
Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
On The Inadequacy of Optimizing Alignment and Uniformity in Contrastive Learning of Sentence Representations
Hybrid RL: Using both offline and online data can make RL efficient
DiGress: Discrete Denoising diffusion for graph generation
Liquid Structural State-Space Models
GAMR: A Guided Attention Model for (visual) Reasoning
Human-level Atari 200x faster
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions
Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning
Deep Learning on Implicit Neural Representations of Shapes
Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching
AnyDA: Anytime Domain Adaptation
Solving Constrained Variational Inequalities via a First-order Interior Point-based Method
A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
Understanding The Robustness of Self-supervised Learning Through Topic Modeling
SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs
Globally Injective ReLU Networks
Leveraging Importance Weights in Subset Selection
A non-asymptotic analysis of oversmoothing in Graph Neural Networks
ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity
How I Learned to Stop Worrying and Love Retraining
Confidence Estimation Using Unlabeled Data
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach
A Primal-Dual Framework for Transformers and Neural Networks
CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
The KFIoU Loss for Rotated Object Detection
An Adaptive Policy to Employ Sharpness-Aware Minimization
Characterizing the spectrum of the NTK via a power series expansion
VA-DepthNet: A Variational Approach to Single Image Depth Prediction
SLTUNET: A Simple Unified Model for Sign Language Translation
Interpretable Debiasing of Vectorized Language Representations with Iterative Orthogonalization
Distilling Model Failures as Directions in Latent Space
Simple Emergent Action Representations from Multi-Task Policy Training
Multi-Objective Online Learning
$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space
Predictive Inference with Feature Conformal Prediction
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
Bias Propagation in Federated Learning
Energy-based Out-of-Distribution Detection for Graph Neural Networks
Guess the Instruction! Making Language Models Stronger Zero-Shot Learners
DocPrompting: Generating Code by Retrieving the Docs
Calibrating Transformers via Sparse Gaussian Processes
An Extensible Multi-modal Multi-task Object Dataset with Materials
Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement
Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting
SMART: Sentences as Basic Units for Text Evaluation
Collaborative Pure Exploration in Kernel Bandit
Meta-Learning Black-Box Optimization via Black-Box Optimization
RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates
SimPer: Simple Self-Supervised Learning of Periodic Targets
Calibrating Sequence likelihood Improves Conditional Language Generation
E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation
Red PANDA: Disambiguating Anomaly Detection by Removing Nuisance Factors
From $t$-SNE to UMAP with contrastive learning
FINDE: Neural Differential Equations for Finding and Preserving Invariant Quantities
A Self-Attention Ansatz for Ab-initio Quantum Chemistry
Understanding Zero-shot Adversarial Robustness for Large-Scale Models
PLOT: Prompt Learning with Optimal Transport for Vision-Language Models
The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
Perfectly Secure Steganography Using Minimum Entropy Coupling
Discovering Latent Knowledge in Language Models Without Supervision
GAIN: On the Generalization of Instructional Action Understanding
Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning
Everybody Needs Good Neighbours: An Unsupervised Locality-based Method for Bias Mitigation
How robust is unsupervised representation learning to distribution shift?
Label-free Concept Bottleneck Models
Learning Domain-Agnostic Representation for Disease Diagnosis
Robust Explanation Constraints for Neural Networks
Visual Classification via Description from Large Language Models
FedExP: Speeding up Federated Averaging via Extrapolation
How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization
What Do Self-Supervised Vision Transformers Learn?
ISAAC Newton: Input-based Approximate Curvature for Newton's Method
Hungry Hungry Hippos: Towards Language Modeling with State Space Models
REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH
Bispectral Neural Networks
Temporal Dependencies in Feature Importance for Time Series Prediction
Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
Adversarial Training descends without descent: Finding actual descent directions based on Danskin's theorem
Measuring axiomatic soundness of counterfactual image models
Proactive Multi-Camera Collaboration for 3D Human Pose Estimation
User-Interactive Offline Reinforcement Learning
Measuring Forgetting of Memorized Training Examples
Generating Diverse Cooperative Agents by Learning Incompatible Policies
Linear Connectivity Reveals Generalization Strategies
Improving Deep Regression with Ordinal Entropy
ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion
Does Deep Learning Learn to Abstract? A Systematic Probing Framework
Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
Graph Neural Networks for Link Prediction with Subgraph Sketching
Explaining RL Decisions with Trajectories
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Neural Architecture Design and Robustness: A Dataset
Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes
On the Saturation Effect of Kernel Ridge Regression
Single-shot General Hyper-parameter Optimization for Federated Learning
The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks
Clifford Neural Layers for PDE Modeling
Sparse tree-based Initialization for Neural Networks
Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks
Efficient Edge Inference by Selective Query
Concept Gradient: Concept-based Interpretation Without Linear Assumption
Bidirectional Language Models Are Also Few-shot Learners
LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
(ends 4:30 AM)
6 a.m.
Oral Session 6 Track 1 [6:00-7:30]
Oral s 6:00-7:30
[6:00] Near-optimal Coresets for Robust Clustering
[6:10] Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
[6:20] Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
[6:30] Statistical Efficiency of Score Matching: The View from Isoperimetry
[6:40] Sublinear Algorithms for Kernel Matrices via Kernel Density Estimation
[6:50] Depth Separation with Multilayer Mean-Field Networks
[7:00] Learning with Stochastic Orders
[7:10] Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities
[7:20] A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning
(ends 7:30 AM)
Oral Session 6 Track 2 [6:00-7:30]
Benchmarking Deformable Object Manipulation with Differentiable Physics
Betty: An Automatic Differentiation Library for Multilevel Optimization
WikiWhy: Answering and Explaining Cause-and-Effect Questions
(ends 7:30 AM)
Oral Session 6 Track 3 [6:00-7:30]
Oral s 6:00-7:20
[6:00] Agree to Disagree: Diversity through Disagreement for Better Transferability
[6:10] What learning algorithm is in-context learning? Investigations with linear models
[6:20] Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
[6:30] Encoding Recurrence into Transformers
[6:40] Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
[6:50] Simplified State Space Layers for Sequence Modeling
[7:00] Relational Attention: Generalizing Transformers for Graph-Structured Tasks
[7:10] Sparse Mixture-of-Experts are Domain Generalizable Learners
(ends 7:30 AM)
Oral Session 6 Track 4 [6:00-7:30]
Oral s 6:00-6:40
[6:00] MEDFAIR: BENCHMARKING FAIRNESS FOR MEDICAL IMAGEING
[6:10] Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
[6:20] Confidential-PROFITT: Confidential PROof of FaIr Training of Trees
[6:30] Disparate Impact in Differential Privacy from Gradient Misalignment
(ends 7:30 AM)
Oral Session 6 Track 5 [6:00-7:30]
Oral s 6:00-6:50
[6:00] Binding Language Models in Symbolic Languages
[6:10] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
[6:20] Simple Yet Effective Graph Contrastive Learning for Recommendation
[6:30] Certified Training: Small Boxes are All You Need
[6:40] Inequality phenomenon in $l_{\infty}$-adversarial training, and its unrealized threats
(ends 7:30 AM)
Oral Session 6 Track 6 [6:00-7:30]
Oral s 6:00-7:20
[6:00] Language Modelling with Pixels
[6:10] Parametrizing Product Shape Manifolds by Composite Networks
[6:20] ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
[6:30] Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer
[6:40] Dual Algorithmic Reasoning
[6:50] DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
[7:00] Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning
[7:10] Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
(ends 7:30 AM)
7:30 a.m.
Poster Session 6 [7:30-9:30]
Encoding Recurrence into Transformers
Bayes-MIL: A New Probabilistic Perspective on Attention-based Multiple Instance Learning for Whole Slide Images
ResAct: Reinforcing Long-term Engagement in Sequential Recommendation with Residual Actor
Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement
Universal Approximation Theorems for Differentiable Geometric Deep Learning
Equivariance-aware Architectural Optimization of Neural Networks
DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
$k$NN Prompting: Learning Beyond the Context with Nearest Neighbor Inference
Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design
Hyperparameter Optimization through Neural Network Partitioning
When to Make and Break Commitments?
PowerQuant: Automorphism Search for Non-Uniform Quantization
Inequality phenomenon in $l_{\infty}$-adversarial training, and its unrealized threats
EquiMod: An Equivariance Module to Improve Self-Supervised Learning
WikiWhy: Answering and Explaining Cause-and-Effect Questions
Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics
Bridging the Gap to Real-World Object-Centric Learning
Near-optimal Coresets for Robust Clustering
Riemannian Metric Learning via Optimal Transport
Betty: An Automatic Differentiation Library for Multilevel Optimization
Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning
A Study of Causal Confusion in Preference-Based Reward Learning
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Sparse Mixture-of-Experts are Domain Generalizable Learners
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
GOOD: Exploring geometric cues for detecting objects in an open world
Expressive Monotonic Neural Networks
Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning
MEDFAIR: BENCHMARKING FAIRNESS FOR MEDICAL IMAGEING
Meta Temporal Point Processes
Relational Attention: Generalizing Transformers for Graph-Structured Tasks
Impossibly Good Experts and How to Follow Them
Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation
Semi Parametric Inducing Point Networks
Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code
Simplified State Space Layers for Sequence Modeling
A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy
Scaling Laws for a Multi-Agent Reinforcement Learning Model
Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path
What learning algorithm is in-context learning? Investigations with linear models
Solving stochastic weak Minty variational inequalities without increasing batch size
Blurring Diffusion Models
Context-enriched molecule representations improve few-shot drug discovery
Unsupervised 3d object learning through neuron activity aware plasticity
Unveiling the sampling density in non-uniform geometric graphs
Neural Implicit Shape Editing using Boundary Sensitivity
ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond
Over-parameterized Model Optimization with Polyak-{\L}ojasiewicz Condition
Disentanglement of Correlated Factors via Hausdorff Factorized Support
Binding Language Models in Symbolic Languages
Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing
How Can GANs Learn Hierarchical Generative Models for Real-World Distributions
More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
WiNeRT: Towards Neural Ray Tracing for Wireless Channel Modelling and Differentiable Simulations
Composing Ensembles of Pre-trained Models via Iterative Consensus
Strong inductive biases provably prevent harmless interpolation
Certified Training: Small Boxes are All You Need
Parametrizing Product Shape Manifolds by Composite Networks
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
Learning with Stochastic Orders
Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders
Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions
Towards convergence to Nash equilibria in two-team zero-sum games
Depth Separation with Multilayer Mean-Field Networks
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Reversible Column Networks
SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models
TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation
Variable Compositionality Reliably Emerges in Neural Networks
Disparate Impact in Differential Privacy from Gradient Misalignment
SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization
Learning Uncertainty for Unknown Domains with Zero-Target-Assumption
Learning in temporally structured environments
Language Modelling with Pixels
DAVA: Disentangling Adversarial Variational Autoencoder
Agree to Disagree: Diversity through Disagreement for Better Transferability
Statistical Efficiency of Score Matching: The View from Isoperimetry
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training
Understanding the Covariance Structure of Convolutional Filters
Confidential-PROFITT: Confidential PROof of FaIr Training of Trees
Fake It Until You Make It : Towards Accurate Near-Distribution Novelty Detection
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
Winning Both the Accuracy of Floating Point Activation and the Simplicity of Integer Arithmetic
Consolidator: Mergable Adapter with Group Connections for Vision Transformer
MA-BERT: Towards Matrix Arithmetic-only BERT Inference by Eliminating Complex Non-linear Functions
Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance Fields
Self-supervised Geometric Correspondence for Category-level 6D Object Pose Estimation in the Wild
$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells
Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation
Benchmarking Deformable Object Manipulation with Differentiable Physics
Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta.
Plateau in Monotonic Linear Interpolation --- A "Biased" View of Loss Landscape for Deep Networks
Is Attention All That NeRF Needs?
Automating Nearest Neighbor Search Configuration with Constrained Optimization
What Is Missing in IRM Training and Evaluation? Challenges and Solutions
Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting
Diagnosing and Rectifying Vision Models using Language
Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences
Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles
Real-Time Image Demoir$\acute{e}$ing on Mobile Devices
Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees
Evolving Populations of Diverse RL Agents with MAP-Elites
Multiple sequence alignment as a sequence-to-sequence learning problem
Robust Algorithms on Adaptive Inputs from Bounded Adversaries
Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer
Part-Based Models Improve Adversarial Robustness
Simple Yet Effective Graph Contrastive Learning for Recommendation
A General Framework for Sample-Efficient Function Approximation in Reinforcement Learning
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
Sublinear Algorithms for Kernel Matrices via Kernel Density Estimation
Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
Min-Max Multi-objective Bilevel Optimization with Applications in Robust Machine Learning
Geometrically regularized autoencoders for non-Euclidean data
Short-Term Memory Convolutions
Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective
Efficient Federated Domain Translation
Fast Nonlinear Vector Quantile Regression
Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories
Backstepping Temporal Difference Learning
Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods
Offline RL for Natural Language Generation with Implicit Language Q Learning
Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities
Verifying the Union of Manifolds Hypothesis for Image Data
Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation
Effectively Modeling Time Series with Simple Discrete State Spaces
Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions
Visual Imitation Learning with Patch Rewards
On The Specialization of Neural Modules
Variance-Aware Sparse Linear Bandits
A Message Passing Perspective on Learning Dynamics of Contrastive Learning
Block and Subword-Scaling Floating-Point (BSFP) : An Efficient Non-Uniform Quantization For Low Precision Inference
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation
Pitfalls of Gaussians as a noise distribution in NCE
SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments
Dual Algorithmic Reasoning
A Simple Yet Powerful Deep Active Learning With Snapshots Ensembles
Reward Design with Language Models
(ends 9:30 AM)
11:30 p.m.
Workshop:
Trustworthy and Reliable Large-Scale Machine Learning Models
(ends 8:00 AM)
Workshop:
Tackling Climate Change with Machine Learning: Global Perspectives and Local Challenges
(ends 8:00 AM)
Workshop:
Neurosymbolic Generative Models (NeSy-GeMs)
(ends 8:00 AM)
Workshop:
Reincarnating Reinforcement Learning
(ends 8:00 AM)
Workshop:
Physics for Machine Learning
(ends 8:00 AM)
Workshop:
Neural Fields across Fields: Methods and Applications of Implicit Neural Representations
(ends 8:00 AM)
Workshop:
Accelerating Model Driven Discovery with ML
(ends 3:00 AM)
Workshop:
AI for Agent-Based Modelling (AI4ABM)
(ends 8:00 AM)
Workshop:
Mathematical and Empirical Understanding of Foundation Models (ME-FoMo)
(ends 8:00 AM)
Workshop:
Kaggle@ICLR
(ends 8:00 AM)
Workshop:
IndabaX Rwanda 2023
(ends 8:00 AM)
THU 4 MAY
11:30 p.m.
Workshop:
ICLR 2023 Workshop on Machine Learning for Remote Sensing
(ends 8:00 AM)
Workshop:
Scene Representations for Autonomous Driving
(ends 8:00 AM)
Workshop:
Machine Learning for IoT: Datasets, Perception, and Understanding
(ends 8:00 AM)
Workshop:
4th Workshop on African Natural Language Processing (AfricaNLP 2023)
(ends 8:00 AM)
Workshop:
First workshop on "Machine Learning & Global Health".
(ends 8:00 AM)
Workshop:
The 4th Workshop on practical ML for Developing Countries: learning under limited/low resource settings
(ends 8:00 AM)
Workshop:
Pitfalls of limited data and computation for Trustworthy ML
(ends 8:00 AM)
Workshop:
ICLR 2023 Workshop on Sparsity in Neural Networks: On practical limitations and tradeoffs between sustainability and efficiency
(ends 8:00 AM)
Affinity Workshop:
DEI Workshop
(ends 8:00 AM)