Skip to yearly menu bar Skip to main content


Show Detail
Schedule Mon Tue Wed Thu Fri
Timezone: Africa/Kigali
 
Filter Rooms:  

MON 1 MAY
7 a.m.
Registration / Check-in
(ends 7:30 PM)
8:15 a.m.
Remarks:
Opening Remarks
(ends 8:30 AM)
8:30 a.m.
Invited Talk:
Entanglements, Exploring Artificial Biodiversity
Sofia Crespo
(ends 9:30 AM)
9:30 a.m.
Break:
Coffee Break
(ends 10:00 AM)
10 a.m.
Oral 1 Track 1: Deep Learning and representational learning I [10:00-11:30]
Orals 10:10-11:00
[10:10] Token Merging: Your ViT But Faster
[10:20] TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
[10:30] Learning Group Importance using the Differentiable Hypergeometric Distribution
[10:40] Neural Networks and the Chomsky Hierarchy
[10:50] Learning on Large-scale Text-attributed Graphs via Variational Inference
(ends 11:30 AM)
Oral 1 Track 2: Machine Learning for Sciences [10:00-11:30]
Orals 10:00-11:10
[10:00] Phase2vec: dynamical systems embedding with a physics-informed convolutional network
[10:10] Evolve Smoothly, Fit Consistently: Learning Smooth Latent Dynamics For Advection-Dominated Systems
[10:20] Compressing multidimensional weather and climate data into neural networks
[10:30] D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory
[10:40] Conditional Antibody Design as 3D Equivariant Graph Translation
[10:50] Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
[11:00] CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations
(ends 11:30 AM)
Oral 1 Track 3: Neuroscience and Cognitive Science & General Machine Learning [10:00-11:30]
Orals 10:00-10:50
[10:00] A probabilistic framework for task-aligned intra- and inter-area neural manifold estimation
[10:10] Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
[10:20] Disentanglement with Biological Constraints: A Theory of Functional Cell Types
[10:30] Hebbian Deep Learning Without Feedback
[10:40] Domain Generalization via Heckman-type Selection Models
(ends 11:30 AM)
Oral 1 Track 4: Social Aspects of Machine Learning [10:00-11:30]
Orals 10:00-11:20
[10:00] Quantifying Memorization Across Neural Language Models
[10:10] Human-Guided Fair Classification for Natural Language Processing
[10:20] Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
[10:30] Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
[10:40] UNICORN: A Unified Backdoor Trigger Inversion Framework
[10:50] Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
[11:00] Learning to Estimate Shapley Values with Vision Transformers
[11:10] Provable Defense Against Geometric Transformations
(ends 11:30 AM)
Oral 1 Track 5: Reinforcement Learning [10:00-11:30]
Orals 10:00-11:10
[10:00] DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
[10:10] The In-Sample Softmax for Offline Reinforcement Learning
[10:20] Emergence of Maps in the Memories of Blind Navigation Agents
[10:30] Does Zero-Shot Reinforcement Learning Exist?
[10:40] Learning Soft Constraints From Constrained Expert Demonstrations
[10:50] Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes
[11:00] VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
(ends 11:30 AM)
Oral 1 Track 6: Deep Learning and representational learning II [10:00-11:30]
Orals 10:00-11:10
[10:00] Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
[10:10] Fisher-Legendre (FishLeg) optimization of deep neural networks
[10:20] Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
[10:30] Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets
[10:40] NeRN: Learning Neural Representations for Neural Networks
[10:50] Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
[11:00] Continual Unsupervised Disentangling of Self-Organizing Representations
(ends 11:30 AM)
11:30 a.m.
Poster Session 1 [11:30-1:30]
Posters 11:30-1:30
GOGGLE: Generative Modelling for Tabular Data by Learning Relational Structure
MaskViT: Masked Visual Pre-Training for Video Prediction
DiffuSeq: Sequence to Sequence Text Generation with Diffusion Models
Understanding Edge-of-Stability Training Dynamics with a Minimalist Example
Pushing the Accuracy-Group Robustness Frontier with Introspective Self-play
A Neural Mean Embedding Approach for Back-door and Front-door Adjustment
Understanding DDPM Latent Codes Through Optimal Transport
How to prepare your task head for finetuning
GLM-130B: An Open Bilingual Pre-trained Model
An efficient encoder-decoder architecture with top-down attention for speech separation
Characterizing intrinsic compositionality in transformers with Tree Projections
Pushing the Limits of Fewshot Anomaly Detection in Industry Vision: Graphcore
CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers
3D Segmenter: 3D Transformer based Semantic Segmentation via 2D Panoramic Distillation
Light Sampling Field and BRDF Representation for Physically-based Neural Rendering
Generating Sequences by Learning to Self-Correct
Rethinking skip connection model as a learnable Markov chain
Modeling Multimodal Aleatoric Uncertainty in Segmentation with Mixture of Stochastic Experts
Masked Vision and Language Modeling for Multi-modal Representation Learning
Explaining Temporal Graph Models through an Explorer-Navigator Framework
Trainability Preserving Neural Pruning
Sparsity May Cry: Let Us Fail (Current) Sparse Neural Networks Together!
Neural Networks and the Chomsky Hierarchy
Mega: Moving Average Equipped Gated Attention
Fisher-Legendre (FishLeg) optimization of deep neural networks
Meta-prediction Model for Distillation-Aware NAS on Unseen Datasets
Can discrete information extraction prompts generalize across language models?
Token Merging: Your ViT But Faster
How Informative is the Approximation Error from Tensor Decomposition for Neural Network Compression?
Broken Neural Scaling Laws
Softened Symbol Grounding for Neuro-symbolic Systems
Continuous-time identification of dynamic state-space models by deep subspace encoding
TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
A VAE for Transformers with Nonparametric Variational Information Bottleneck
Cross-Layer Retrospective Retrieving via Layer Attention
Avoiding spurious correlations via logit correction
Mitigating Dataset Bias by Using Per-Sample Gradient
Test-Time Adaptation via Self-Training with Nearest Neighbor Information
LPT: Long-tailed Prompt Tuning for Image Classification
Modeling the Data-Generating Process is Necessary for Out-of-Distribution Generalization
Divide to Adapt: Mitigating Confirmation Bias for Domain Adaptation of Black-Box Predictors
Continual Unsupervised Disentangling of Self-Organizing Representations
Editing models with task arithmetic
Learning Group Importance using the Differentiable Hypergeometric Distribution
TaskPrompter: Spatial-Channel Multi-Task Prompting for Dense Scene Understanding
Towards Better Selective Classification
Structure by Architecture: Structured Representations without Regularization
Learning on Large-scale Text-attributed Graphs via Variational Inference
Deep Declarative Dynamic Time Warping for End-to-End Learning of Alignment Paths
Interpretable Debiasing of Vectorized Language Representations with Iterative Orthogonalization
NeRN: Learning Neural Representations for Neural Networks
Learning to Induce Causal Structure
On the Soft-Subnetwork for Few-Shot Class Incremental Learning
Learning to reason over visual objects
QAID: Question Answering Inspired Few-shot Intent Detection
Contrastive Meta-Learning for Partially Observable Few-Shot Learning
Learning topology-preserving data representations
DAG Matters! GFlowNets Enhanced Explainer for Graph Neural Networks
Distributed Extra-gradient with Optimal Complexity and Communication Guarantees
Unsupervised Manifold Alignment with Joint Multidimensional Scaling
Deconstructing Distributions: A Pointwise Framework of Learning
Neural Agents Struggle to Take Turns in Bidirectional Emergent Communication
PandA: Unsupervised Learning of Parts and Appearances in the Feature Maps of GANs
Diffusion-based Image Translation using disentangled style and content representation
Finding the Global Semantic Representation in GAN through Fréchet Mean
Domain Generalization via Heckman-type Selection Models
Interaction-Based Disentanglement of Entities for Object-Centric World Models
Matching receptor to odorant with protein language and graph neural networks
Equiformer: Equivariant Graph Attention Transformer for 3D Atomistic Graphs
Compressing multidimensional weather and climate data into neural networks
Conditional Antibody Design as 3D Equivariant Graph Translation
Phase2vec: dynamical systems embedding with a physics-informed convolutional network
Protein Sequence and Structure Co-Design with Equivariant Translation
CROM: Continuous Reduced-Order Modeling of PDEs Using Implicit Neural Representations
Interpretable Geometric Deep Learning via Learnable Randomness Injection
Learning Cut Selection for Mixed-Integer Linear Programming via Hierarchical Sequence Model
D4FT: A Deep Learning Approach to Kohn-Sham Density Functional Theory
Understanding Neural Coding on Latent Manifolds by Sharing Features and Dividing Ensembles
A probabilistic framework for task-aligned intra- and inter-area neural manifold estimation
How gradient estimator variance and bias impact learning in neural networks
Hebbian Deep Learning Without Feedback
Disentanglement with Biological Constraints: A Theory of Functional Cell Types
Multi-objective optimization via equivariant deep hypervolume approximation
Momentum Stiefel Optimizer, with Applications to Suitably-Orthogonal Attention, and Optimal Transport
Why (and When) does Local SGD Generalize Better than SGD?
EPISODE: Episodic Gradient Clipping with Periodic Resampled Corrections for Federated Learning with Heterogeneous Data
Denoising Diffusion Samplers
Weighted Clock Logic Point Process
Causal Balancing for Domain Generalization
Dynamic Update-to-Data Ratio: Minimizing World Model Overfitting
Q-Pensieve: Boosting Sample Efficiency of Multi-Objective RL Through Memory Sharing of Q-Snapshots
A Control-Centric Benchmark for Video Prediction
Preference Transformer: Modeling Human Preferences using Transformers for RL
Emergence of Maps in the Memories of Blind Navigation Agents
Learning Zero-Shot Cooperation with Humans, Assuming Humans Are Biased
Offline Q-learning on Diverse Multi-Task Data Both Scales And Generalizes
Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward
Learning Soft Constraints From Constrained Expert Demonstrations
LS-IQ: Implicit Reward Regularization for Inverse Reinforcement Learning
MoDem: Accelerating Visual Model-Based Reinforcement Learning with Demonstrations
RPM: Generalizable Multi-Agent Policies for Multi-Agent Reinforcement Learning
The In-Sample Softmax for Offline Reinforcement Learning
Does Zero-Shot Reinforcement Learning Exist?
Scaling Pareto-Efficient Decision Making via Offline Multi-Objective RL
DEP-RL: Embodied Exploration for Reinforcement Learning in Overactuated and Musculoskeletal Systems
Safe Reinforcement Learning From Pixels Using a Stochastic Latent Representation
Performance Bounds for Model and Policy Transfer in Hidden-parameter MDPs
VIP: Towards Universal Visual Reward and Representation via Value-Implicit Pre-Training
Neuroevolution is a Competitive Alternative to Reinforcement Learning for Skill Discovery
Wasserstein Auto-encoded MDPs: Formal Verification of Efficiently Distilled RL Policies with Many-sided Guarantees
Quantifying Memorization Across Neural Language Models
Fooling SHAP with Stealthily Biased Sampling
Valid P-Value for Deep Learning-driven Salient Region
UNICORN: A Unified Backdoor Trigger Inversion Framework
Human-Guided Fair Classification for Natural Language Processing
Canary in a Coalmine: Better Membership Inference with Ensembled Adversarial Queries
Sound Randomized Smoothing in Floating-Point Arithmetic
Provable Defense Against Geometric Transformations
Is the Performance of My Deep Network Too Good to Be True? A Direct Approach to Estimating the Bayes Error in Binary Classification
Is Adversarial Training Really a Silver Bullet for Mitigating Data Poisoning?
Equal Improvability: A New Fairness Notion Considering the Long-term Impact
On the Perils of Cascading Robust Classifiers
Learning to Estimate Shapley Values with Vision Transformers
Neural-based classification rule learning for sequential data
Machine Unlearning of Federated Clusters
Multimodal Federated Learning via Contrastive Representation Ensemble
A new characterization of the edge of stability based on a sharpness measure aware of batch gradient distribution
On The Relative Error of Random Fourier Features for Preserving Kernel Distance
A General Framework For Proving The Equivariant Strong Lottery Ticket Hypothesis
Contextual bandits with concave rewards, and an application to fair ranking
Why adversarial training can hurt robust accuracy
Continuous pseudo-labeling from the start
Neural Groundplans: Persistent Neural Scene Representations from a Single Image
A Multi-Grained Self-Interpretable Symbolic-Neural Model For Single/Multi-Labeled Text Classification
Hyperbolic Self-paced Learning for Self-supervised Skeleton-based Action Representations
Identifiability Results for Multimodal Contrastive Learning
Diffusion Adversarial Representation Learning for Self-supervised Vessel Segmentation
Guiding Safe Exploration with Weakest Preconditions
(ends 1:30 PM)
Break:
Lunch
(ends 1:30 PM)
12:30 p.m.
1:30 p.m.
Invited Talk:
Understanding Systematic Deviations in Data for Trustworthy AI
Girmaw Abebe Tadesse
(ends 2:30 PM)
2:30 p.m.
Break:
Coffee Break
(ends 3:00 PM)
3 p.m.
Oral 2 Track 1: Applications [3:00-4:30]
Orals 3:00-4:20
[3:00] GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
[3:20] Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
[3:30] Human Motion Diffusion Model
[3:40] NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning
[3:50] UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks
[4:00] Mass-Editing Memory in a Transformer
[4:10] On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation
(ends 4:30 PM)
Oral 2 Track 2: General Machine Learning [3:00-4:30]
Orals 3:00-4:20
[3:00] The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium
[3:10] Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
[3:20] Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives
[3:40] LAVA: Data Valuation without Pre-Specified Learning Algorithms
[4:00] Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering
[4:10] Learning where and when to reason in neuro-symbolic inference
(ends 4:30 PM)
Oral 2 Track 3: Generative models [3:00-4:30]
Orals 3:00-4:00
[3:00] Diffusion Posterior Sampling for General Noisy Inverse Problems
[3:10] Prompt-to-Prompt Image Editing with Cross-Attention Control
[3:20] Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting
[3:30] Diffusion Models Already Have A Semantic Latent Space
[3:40] DreamFusion: Text-to-3D using 2D Diffusion
[3:50] Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
(ends 4:30 PM)
Oral 2 Track 4: Reinforcement Learning [3:00-4:30]
Orals 3:00-4:20
[3:00] Multi-skill Mobile Manipulation for Object Rearrangement
[3:10] The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
[3:20] A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
[3:30] Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
[3:40] Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
[3:50] Near-optimal Policy Identification in Active Reinforcement Learning
[4:00] BC-IRL: Learning Generalizable Reward Functions from Demonstrations
[4:10] Learning About Progress From Experts
(ends 4:30 PM)
Oral 2 Track 5: Generative models & Theory [3:00-4:30]
Orals 3:00-4:00
[3:00] Neural Optimal Transport
[3:10] Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
[3:20] Effects of Graph Convolutions in Multi-layer Networks
[3:40] Modeling content creator incentives on algorithm-curated platforms
[3:50] Optimal Transport for Offline Imitation Learning
(ends 4:30 PM)
Oral 2 Track 6: Applications & Social Aspects of Machine Learning [3:00-4:30]
Orals 3:00-4:20
[3:00] A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
[3:10] Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception
[3:20] MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
[3:30] ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
[3:40] Ask Me Anything: A simple strategy for prompting language models
[3:50] Code Translation with Compiler Representations
[4:00] Hidden Markov Transformer for Simultaneous Machine Translation
[4:10] Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
(ends 4:30 PM)
4:30 p.m.
Poster Session 2 [4:30-6:30]
Posters 4:30-6:30
Domain Generalisation via Domain Adaptation: An Adversarial Fourier Amplitude Approach
Dynamic Prompt Learning via Policy Gradient for Semi-structured Mathematical Reasoning
Selective Frequency Network for Image Restoration
Pareto Invariant Risk Minimization: Towards Mitigating the Optimization Dilemma in Out-of-Distribution Generalization
Error Sensitivity Modulation based Experience Replay: Mitigating Abrupt Representation Drift in Continual Learning
Complexity-Based Prompting for Multi-step Reasoning
Language Models Are Greedy Reasoners: A Systematic Formal Analysis of Chain-of-Thought
Ask Me Anything: A simple strategy for prompting language models
Human Motion Diffusion Model
NTFields: Neural Time Fields for Physics-Informed Robot Motion Planning
On the Usefulness of Embeddings, Clusters and Strings for Text Generation Evaluation
Temporal Coherent Test Time Optimization for Robust Video Classification
UNIFIED-IO: A Unified Model for Vision, Language, and Multi-modal Tasks
Mass-Editing Memory in a Transformer
Robust Scheduling with GFlowNets
TranSpeech: Speech-to-Speech Translation With Bilateral Perturbation
In-Situ Text-Only Adaptation of Speech Models with Low-Overhead Speech Imputations
A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification
Open-Vocabulary Object Detection upon Frozen Vision and Language Models
H2RBox: Horizontal Box Annotation is All You Need for Oriented Object Detection
ROSCOE: A Suite of Metrics for Scoring Step-by-Step Reasoning
GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
Weakly Supervised Knowledge Transfer with Probabilistic Logical Reasoning for Object Detection
Iterative Circuit Repair Against Formal Specifications
Hidden Markov Transformer for Simultaneous Machine Translation
An Equal-Size Hard EM Algorithm for Diverse Dialogue Generation
DFlow: Learning to Synthesize Better Optical Flow Datasets via a Differentiable Pipeline
Discrete Contrastive Diffusion for Cross-Modal Music and Image Generation
Code Translation with Compiler Representations
Iterative Patch Selection for High-Resolution Image Recognition
MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
Learning Iterative Neural Optimizers for Image Steganography
Associative Memory Augmented Asynchronous Spatiotemporal Representation Learning for Event-based Perception
Is Reinforcement Learning (Not) for Natural Language Processing: Benchmarks, Baselines, and Building Blocks for Natural Language Policy Optimization
FIGARO: Controllable Music Generation using Learned and Expert Features
General Neural Gauge Fields
Preserving Pre-trained Features Helps Calibrate Fine-tuned Language Models
Grounding Graph Network Simulators using Physical Sensor Observations
$\mathscr{N}$-WL: A New Hierarchy of Expressivity for Graph Neural Networks
Spatial Attention Kinetic Networks with E(n)-Equivariance
ChordMixer: A Scalable Neural Attention Model for Sequences with Different Length
Decomposed Prompting: A Modular Approach for Solving Complex Tasks
Bit-Pruning: A Sparse Multiplication-Less Dot-Product
Over-Training with Mixup May Hurt Generalization
Exploring and Exploiting Decision Boundary Dynamics for Adversarial Robustness
Can CNNs Be More Robust Than Transformers?
Scaffolding a Student to Instill Knowledge
Constraining Representations Yields Models That Know What They Don't Know
TVSPrune - Pruning Non-discriminative filters via Total Variation separability of intermediate representations without fine tuning
MLPInit: Embarrassingly Simple GNN Training Acceleration with MLP Initialization
Towards One-shot Neural Combinatorial Solvers: Theoretical and Empirical Notes on the Cardinality-Constrained Case
Decoupled Training for Long-Tailed Classification With Stochastic Representations
REPAIR: REnormalizing Permuted Activations for Interpolation Repair
Feature Reconstruction From Outputs Can Mitigate Simplicity Bias in Neural Networks
Gradient Gating for Deep Multi-Rate Learning on Graphs
The Symmetric Generalized Eigenvalue Problem as a Nash Equilibrium
Targeted Hyperparameter Optimization with Lexicographic Preferences Over Multiple Objectives
PASHA: Efficient HPO and NAS with Progressive Resource Allocation
Direct Embedding of Temporal Network Edges via Time-Decayed Line Graphs
Metadata Archaeology: Unearthing Data Subsets by Leveraging Training Dynamics
Learning where and when to reason in neuro-symbolic inference
LAVA: Data Valuation without Pre-Specified Learning Algorithms
Learning a Data-Driven Policy Network for Pre-Training Automated Feature Engineering
Neural Optimal Transport
DreamFusion: Text-to-3D using 2D Diffusion
Diffusion Models Already Have A Semantic Latent Space
Diffusion Posterior Sampling for General Noisy Inverse Problems
Generative Modelling with Inverse Heat Dissipation
Discrete Predictor-Corrector Diffusion Models for Image Synthesis
Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization
Explicitly Minimizing the Blur Error of Variational Autoencoders
Sequential Latent Variable Models for Few-Shot High-Dimensional Time-Series Forecasting
Prompt-to-Prompt Image Editing with Cross-Attention Control
Sampling is as easy as learning the score: theory for diffusion models with minimal data assumptions
Factorized Fourier Neural Operators
Competitive Physics Informed Networks
Learning Symbolic Models for Graph-structured Physical Mechanism
Improved Training of Physics-Informed Neural Networks Using Energy-Based Priors: a Study on Electrical Impedance Tomography
Diffusion Probabilistic Modeling of Protein Backbones in 3D for the motif-scaffolding problem
Protein Representation Learning by Geometric Structure Pretraining
Uni-Mol: A Universal 3D Molecular Representation Learning Framework
Computational Language Acquisition with Theory of Mind
Exploring perceptual straightness in learned visual representations
Learning Sparse and Low-Rank Priors for Image Recovery via Iterative Reweighted Least Squares Minimization
CUTS: Neural Causal Discovery from Irregular Time-Series Data
Diffusion Models for Causal Discovery via Topological Ordering
Accurate Bayesian Meta-Learning by Accurate Task Posterior Inference
Trading Information between Latents in Hierarchical Variational Autoencoders
Neural Causal Models for Counterfactual Identification and Estimation
Causal Reasoning in the Presence of Latent Confounders via Neural ADMG Learning
Scaling up and Stabilizing Differentiable Planning with Implicit Differentiation
SpeedyZero: Mastering Atari with Limited Data and Time
Diminishing Return of Value Expansion Methods in Model-Based Reinforcement Learning
Optimal Transport for Offline Imitation Learning
On the Feasibility of Cross-Task Transfer with Model-Based Reinforcement Learning
Policy Expansion for Bridging Offline-to-Online Reinforcement Learning
The Surprising Effectiveness of Equivariant Models in Domains with Latent Symmetry
Multi-skill Mobile Manipulation for Object Rearrangement
Near-optimal Policy Identification in Active Reinforcement Learning
Powderworld: A Platform for Understanding Generalization via Rich Task Distributions
Minimum Description Length Control
BC-IRL: Learning Generalizable Reward Functions from Demonstrations
Become a Proficient Player with Limited Data through Watching Pure Videos
Learning About Progress From Experts
Certifiably Robust Policy Learning against Adversarial Multi-Agent Communication
Sample-Efficient Reinforcement Learning by Breaking the Replay Ratio Barrier
A System for Morphology-Task Generalization via Unified Representation and Behavior Distillation
POPGym: Benchmarking Partially Observable Reinforcement Learning
Cheap Talk Discovery and Utilization in Multi-Agent Reinforcement Learning
Global Explainability of GNNs via Logic Combination of Learned Concepts
Revisiting Graph Adversarial Attack and Defense From a Data Distribution Perspective
Selection-Inference: Exploiting Large Language Models for Interpretable Logical Reasoning
An Exact Poly-Time Membership-Queries Algorithm for Extracting a Three-Layer ReLU Network
Fairness and Accuracy under Domain Generalization
Variational Information Pursuit for Interpretable Predictions
Quantile Risk Control: A Flexible Framework for Bounding the Probability of High-Loss Predictions
Quantifying and Mitigating the Impact of Label Errors on Model Disparity Metrics
Measure the Predictive Heterogeneity
MultiViz: Towards Visualizing and Understanding Multimodal Models
Effects of Graph Convolutions in Multi-layer Networks
Memorization Capacity of Neural Networks with Conditional Computation
Implicit Bias of Large Depth Networks: a Notion of Rank for Nonlinear Functions
Constructive TT-representation of the tensors given as index interaction functions with applications
Benign Overfitting in Classification: Provably Counter Label Noise with Larger Models
Uniform-in-time propagation of chaos for the mean-field gradient Langevin dynamics
Information-Theoretic Analysis of Unsupervised Domain Adaptation
Modeling content creator incentives on algorithm-curated platforms
Optimizing Spca-based Continual Learning: A Theoretical Approach
Amortised Invariance Learning for Contrastive Self-Supervision
Unsupervised visualization of image datasets using contrastive learning
Self-Supervised Set Representation Learning for Unsupervised Meta-Learning
Temperature Schedules for self-supervised contrastive methods on long-tail data
The hidden uniform cluster prior in self-supervised learning
(ends 6:30 PM)
5 p.m.
6:30 p.m.
Remarks:
Opening Ceremony
(ends 6:50 PM)
6:50 p.m.
Reception:
Reception
(ends 8:00 PM)

TUE 2 MAY
8 a.m.
Registration / Check-in
(ends 6:00 PM)
8:30 a.m.
Invited Talk:
Importance-Weighting Approach to Distribution Shift Adaptation
Masashi Sugiyama
(ends 9:30 AM)
9:30 a.m.
Break:
Coffee Break
(ends 10:00 AM)
10 a.m.
Oral 3 Track 1: Reinforcement Learning [10:00-11:30]
Orals 10:00-11:20
[10:00] Adversarial Diversity in Hanabi
[10:10] Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
[10:20] Programmatically Grounded, Compositionally Generalizable Robotic Manipulation
[10:30] On the Sensitivity of Reward Inference to Misspecified Human Models
[10:40] Understanding and Adopting Rational Behavior by Bellman Score Estimation
[10:50] SMART: Self-supervised Multi-task pretrAining with contRol Transformers
[11:00] Dichotomy of Control: Separating What You Can Control from What You Cannot
[11:10] Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
(ends 11:30 AM)
Oral 3 Track 2: Deep Learning and representational learning [10:00-11:30]
Orals 10:00-11:20
[10:00] Efficient Conditionally Invariant Representation Learning
[10:10] Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
[10:20] Omnigrok: Grokking Beyond Algorithmic Data
[10:30] Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
[10:40] Multi-Rate VAE: Train Once, Get the Full Rate-Distortion Curve
[10:50] Multi-lingual Evaluation of Code Generation Models
[11:00] Rethinking the Expressive Power of GNNs via Graph Biconnectivity
[11:10] Hyperbolic Deep Reinforcement Learning
(ends 11:30 AM)
Oral 3 Track 3: Generative models [10:00-11:30]
Orals 10:00-11:20
[10:00] The Role of ImageNet Classes in Fréchet Inception Distance
[10:10] Learning Diffusion Bridges on Constrained Domains
[10:20] Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
[10:30] Learning multi-scale local conditional probability models of images
[10:40] An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
[10:50] Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
[11:00] Deterministic training of generative autoencoders using invertible layers
[11:10] 3D generation on ImageNet
(ends 11:30 AM)
Oral 3 Track 4: General Machine Learning & Unsupervised and Self-supervised learning [10:00-11:30]
Orals 10:00-11:20
[10:00] On the duality between contrastive and non-contrastive self-supervised learning
[10:10] Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning
[10:20] The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
[10:30] Self-supervised learning with rotation-invariant kernels
[10:40] DINO as a von Mises-Fisher mixture model
[10:50] Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent
[11:00] Efficient Discrete Multi Marginal Optimal Transport Regularization
[11:10] Sparsity-Constrained Optimal Transport
(ends 11:30 AM)
Oral 3 Track 5: Deep Learning and representational learning & Neuroscience and Cognitive Science [10:00-11:30]
Orals 10:00-11:20
[10:00] Sign and Basis Invariant Networks for Spectral Graph Representation Learning
[10:10] ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks
[10:20] Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
[10:30] QuAnt: Quantum Annealing with Learnt Couplings
[10:40] Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
[10:50] The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
[11:00] The Lie Derivative for Measuring Learned Equivariance
[11:10] Training language models to summarize narratives improves brain alignment
(ends 11:30 AM)
11:30 a.m.
Poster Session 3 [11:30-1:30]
Posters 11:30-1:30
Few-shot Backdoor Attacks via Neural Tangent Kernels
Mid-Vision Feedback
Markup-to-Image Diffusion Models with Scheduled Sampling
Language models are multilingual chain-of-thought reasoners
Language Models Can Teach Themselves to Program Better
A Non-monotonic Self-terminating Language Model
DiffusER: Diffusion via Edit-based Reconstruction
Understanding Embodied Reference with Touch-Line Transformer
Rethinking Self-Supervised Visual Representation Learning in Pre-training for 3D Human Pose and Shape Estimation
Active Image Indexing
Voint Cloud: Multi-View Point Cloud Representation for 3D Understanding
Edge Guided GANs with Contrastive Learning for Semantic Image Synthesis
Agent-based Graph Neural Networks
Limitless Stability for Graph Convolutional Networks
The Asymmetric Maximum Margin Bias of Quasi-Homogeneous Neural Networks
Rethinking the Expressive Power of GNNs via Graph Biconnectivity
Anti-Symmetric DGN: a stable architecture for Deep Graph Networks
ACMP: Allen-Cahn Message Passing with Attractive and Repulsive Forces for Graph Neural Networks
LilNetX: Lightweight Networks with EXtreme Model Compression and Structured Sparsification
Unmasking the Lottery Ticket Hypothesis: What's Encoded in a Winning Ticket's Mask?
QuAnt: Quantum Annealing with Learnt Couplings
TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specialization
Treeformer: Dense Gradient Trees for Efficient Attention Computation
Latent Bottlenecked Attentive Neural Processes
The Onset of Variance-Limited Behavior for Networks in the Lazy and Rich Regimes
Multi-lingual Evaluation of Code Generation Models
DFPC: Data flow driven pruning of coupled channels without data.
The Lie Derivative for Measuring Learned Equivariance
DINO: DETR with Improved DeNoising Anchor Boxes for End-to-End Object Detection
Sparse MoE as the New Dropout: Scaling Dense and Self-Slimmable Transformers
Scaling Forward Gradient With Local Losses
Self-Ensemble Protection: Training Checkpoints Are Good Data Protectors
The Curious Case of Benign Memorization
Topology-aware Robust Optimization for Out-of-Distribution Generalization
Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Task
This Looks Like It Rather Than That: ProtoKNN For Similarity-Based Classifiers
ODAM: Gradient-based Instance-Specific Visual Explanations for Object Detection
Cross-Level Distillation and Feature Denoising for Cross-Domain Few-Shot Classification
DBQ-SSD: Dynamic Ball Query for Efficient 3D Object Detection
Leveraging Unlabeled Data to Track Memorization
Data Valuation Without Training of a Model
Multivariate Time-series Imputation with Disentangled Temporal Representations
Learning to Compose Soft Prompts for Compositional Zero-Shot Learning
TimesNet: Temporal 2D-Variation Modeling for General Time Series Analysis
Image to Sphere: Learning Equivariant Features for Efficient Pose Prediction
Sign and Basis Invariant Networks for Spectral Graph Representation Learning
SoftMatch: Addressing the Quantity-Quality Tradeoff in Semi-supervised Learning
Unicom: Universal and Compact Representation Learning for Image Retrieval
Online Boundary-Free Continual Learning by Scheduled Data Prior
Efficient Conditionally Invariant Representation Learning
Learning to Extrapolate: A Transductive Approach
FedFA: Federated Feature Augmentation
Decepticons: Corrupted Transformers Breach Privacy in Federated Learning for Language Models
Omnigrok: Grokking Beyond Algorithmic Data
Backpropagation through Combinatorial Algorithms: Identity with Projection Works
Neural Radiance Field Codebooks
Autoregressive Conditional Neural Processes
Loss Landscapes are All You Need: Neural Network Generalization Can Be Explained Without the Implicit Bias of Gradient Descent
FIT: A Metric for Model Sensitivity
Classically Approximating Variational Quantum Machine Learning with Random Fourier Features
Label Propagation with Weak Supervision
Learning to CROSS exchange to solve min-max vehicle routing problems
Continual Pre-training of Language Models
Diffusion Probabilistic Fields
FunkNN: Neural Interpolation for Functional Generation
Rarity Score : A New Metric to Evaluate the Uncommonness of Synthesized Images
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
The Role of ImageNet Classes in Fréchet Inception Distance
3D generation on ImageNet
LDMIC: Learning-based Distributed Multi-view Image Coding
Learning multi-scale local conditional probability models of images
Learning Diffusion Bridges on Constrained Domains
StyleMorph: Disentangled 3D-Aware Image Synthesis with a 3D Morphable StyleGAN
Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flow
A critical look at the evaluation of GNNs under heterophily: Are we really making progress?
E3Bind: An End-to-End Equivariant Network for Protein-Ligand Docking
Sampling-free Inference for Ab-Initio Potential Energy Surface Networks
Actionable Neural Representations: Grid Cells from Minimal Constraints
Training language models to summarize narratives improves brain alignment
Sparsity-Constrained Optimal Transport
Noise Is Not the Main Factor Behind the Gap Between Sgd and Adam on Transformers, But Sign Descent Might Be
Variance Reduction is an Antidote to Byzantines: Better Rates, Weaker Assumptions and Communication Compression as a Cherry on the Top
Efficient Discrete Multi Marginal Optimal Transport Regularization
ROCO: A General Framework for Evaluating Robustness of Combinatorial Optimization Solvers on Graphs
Sampling-based inference for large linear models, with application to linearised Laplace
Bridge the Inference Gaps of Neural Processes via Expectation Maximization
Estimating individual treatment effects under unobserved confounding using binary instruments
Imitating Human Behaviour with Diffusion Models
Programmatically Grounded, Compositionally Generalizable Robotic Manipulation
Integrating Symmetry into Differentiable Planning with Steerable Convolutions
Transformer-based World Models Are Happy With 100k Interactions
Adversarial Diversity in Hanabi
On the Sensitivity of Reward Inference to Misspecified Human Models
Fast and Precise: Adjusting Planning Horizon with Adaptive Subgoal Search
Moving Forward by Moving Backward: Embedding Action Impact over Action Semantics
Provable Sim-to-real Transfer in Continuous Domain with Partial Observations
Understanding and Adopting Rational Behavior by Bellman Score Estimation
Using Both Demonstrations and Language Instructions to Efficiently Learn Robotic Tasks
Dichotomy of Control: Separating What You Can Control from What You Cannot
Adversarial Imitation Learning with Preferences
SMART: Self-supervised Multi-task pretrAining with contRol Transformers
Hyperbolic Deep Reinforcement Learning
Efficient Planning in a Compact Latent Action Space
Stateful Active Facilitator: Coordination and Environmental Heterogeneity in Cooperative Multi-Agent Reinforcement Learning
A Mixture-of-Expert Approach to RL-based Dialogue Management
Efficient Deep Reinforcement Learning Requires Regulating Overfitting
Large Language Models are Human-Level Prompt Engineers
Holistic Adversarially Robust Pruning
FaiREE: fair classification with finite-sample and distribution-free guarantee
Efficient Certified Training and Robustness Verification of Neural ODEs
ESD: Expected Squared Difference as a Tuning-Free Trainable Calibration Measure
How to Exploit Hyperspherical Embeddings for Out-of-Distribution Detection?
GeneFace: Generalized and High-Fidelity Audio-Driven 3D Talking Face Synthesis
Easy Differentially Private Linear Regression
Revisiting Robustness in Graph Machine Learning
CANIFE: Crafting Canaries for Empirical Privacy Measurement in Federated Learning
Tuning Frequency Bias in Neural Network Training with Nonuniform Data
Adaptive Optimization in the $\infty$-Width Limit
How Sharpness-Aware Minimization Minimizes Sharpness?
Mini-batch $k$-means terminates within $O(d/\epsilon)$ iterations
Fundamental limits on the robustness of image classifiers
Offline Congestion Games: How Feedback Type Affects Data Coverage Requirement
Interpretations of Domain Adaptations via Layer Variational Analysis
Long-Tailed Learning Requires Feature Learning
Generalization Bounds for Federated Learning: Fast Rates, Unparticipating Clients and Unbounded Losses
KwikBucks: Correlation Clustering with Cheap-Weak and Expensive-Strong Signals
Robust Fair Clustering: A Novel Fairness Attack and Defense Framework
Link Prediction with Non-Contrastive Learning
Learning Rates as a Function of Batch Size: A Random Matrix Theory Approach to Neural Network Training
Towards a Unified Theoretical Understanding of Non-contrastive Learning via Rank Differential Mechanism
DINO as a von Mises-Fisher mixture model
Unsupervised Meta-learning via Few-shot Pseudo-supervised Contrastive Learning
On the duality between contrastive and non-contrastive self-supervised learning
The Trade-off between Universality and Label Efficiency of Representations from Contrastive Learning
Self-supervised learning with rotation-invariant kernels
(ends 1:30 PM)
Affinity Poster Session:
Blog Track Poster Session
(ends 1:30 PM)
Break:
Lunch
(ends 1:30 PM)
12:30 p.m.
1:30 p.m.
Invited Talk:
AI, History and Equity
Elaine Nsoesie
(ends 2:30 PM)
2:30 p.m.
Break:
Coffee Break
(ends 3:00 PM)
3 p.m.
Oral 4 Track 1: Unsupervised and Self-supervised learning [3:00-4:30]
Orals 3:00-4:20
[3:00] Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform
[3:10] AANG : Automating Auxiliary Learning
[3:20] STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
[3:30] Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts
[3:40] When Source-Free Domain Adaptation Meets Learning with Noisy Labels
[3:50] Towards Stable Test-time Adaptation in Dynamic Wild World
[4:00] Proposal-Contrastive Pretraining for Object Detection from Fewer Data
[4:10] Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations
(ends 4:30 PM)
Oral 4 Track 2: Probabilistic Methods [3:00-4:30]
Orals 3:00-4:10
[3:00] Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle
[3:10] SAM as an Optimal Relaxation of Bayes
[3:20] Generative Augmented Flow Networks
[3:30] A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation
[3:40] Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation
[3:50] GRACE-C: Generalized Rate Agnostic Causal Estimation via Constraints
[4:00] Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise
(ends 4:30 PM)
Oral 4 Track 3: Reinforcement Learning I [3:00-4:30]
Orals 3:00-4:20
[3:00] Planning Goals for Exploration
[3:10] Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation
[3:20] Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning
[3:30] Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
[3:40] Choreographer: Learning and Adapting Skills in Imagination
[3:50] A CMDP-within-online framework for Meta-Safe Reinforcement Learning
[4:00] Confidence-Conditioned Value Functions for Offline Reinforcement Learning
[4:10] Extreme Q-Learning: MaxEnt RL without Entropy
(ends 4:30 PM)
Oral 4 Track 4: Reinforcement Learning II [3:00-4:30]
Orals 3:00-4:20
[3:00] Transformers are Sample-Efficient World Models
[3:10] Building a Subspace of Policies for Scalable Continual Learning
[3:20] Neural Episodic Control with State Abstraction
[3:30] Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
[3:40] Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization
[3:50] Is Conditional Generative Modeling all you need for Decision Making?
[4:00] RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
[4:10] Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
(ends 4:30 PM)
Oral 4 Track 5: Machine Learning for Sciences & Probabilistic Methods [3:00-4:30]
Orals 3:00-4:10
[3:00] Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
[3:10] Flow Annealed Importance Sampling Bootstrap
[3:20] Learning Controllable Adaptive Simulation for Multi-resolution Physics
[3:30] Minimax Optimal Kernel Operator Learning via Multilevel Training
[3:40] Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics
[3:50] Pre-training via Denoising for Molecular Property Prediction
[4:00] MARS: Meta-learning as Score Matching in the Function Space
(ends 4:30 PM)
Oral 4 Track 6: Deep Learning and representational learning- Reinforcement Learning [3:00-4:30]
Orals 3:00-4:20
[3:00] CUDA: Curriculum of Data Augmentation for Long-tailed Recognition
[3:10] One-Pixel Shortcut: On the Learning Preference of Deep Neural Networks
[3:20] Learning Label Encodings for Deep Regression
[3:30] Multifactor Sequential Disentanglement via Structured Koopman Autoencoders
[3:40] A Unified Algebraic Perspective on Lipschitz Neural Networks
[3:50] From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data
[4:00] Git Re-Basin: Merging Models modulo Permutation Symmetries
[4:10] In-context Reinforcement Learning with Algorithm Distillation
(ends 4:30 PM)
3:30 p.m.
4:30 p.m.
Poster Session 4 [4:30-6:30]
Posters 4:30-6:30
Mind the Pool: Convolutional Neural Networks Can Overfit Input Size
Generalizing and Decoupling Neural Collapse via Hyperspherical Uniformity Gap
f-DM: A Multi-stage Diffusion Model via Progressive Signal Transformation
Compositional Semantic Parsing with Large Language Models
NANSY++: Unified Voice Synthesis with Neural Analysis and Synthesis
Principal Components Bias in Over-parameterized Linear Models, and its Manifestation in Deep Neural Networks
Revisiting Populations in multi-agent Communication
Topologically penalized regression on manifolds
Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
D4AM: A General Denoising Framework for Downstream Acoustic Models
Sparse Token Transformer with Attention Back Tracking
Meta Learning to Bridge Vision and Language Models for Multimodal Few-Shot Learning
Video Scene Graph Generation from Single-Frame Weak Supervision
Personalized Reward Learning with Interaction-Grounded Learning (IGL)
Learning Locality and Isotropy in Dialogue Modeling
Latent Graph Inference using Product Manifolds
Spikformer: When Spiking Neural Network Meets Transformer
Specformer: Spectral Graph Neural Networks Meet Transformers
A Unified Algebraic Perspective on Lipschitz Neural Networks
Git Re-Basin: Merging Models modulo Permutation Symmetries
The Lazy Neuron Phenomenon: On Emergence of Activation Sparsity in Transformers
Don’t forget the nullspace! Nullspace occupancy as a mechanism for out of distribution failure
DELTA: DEGRADATION-FREE FULLY TEST-TIME ADAPTATION
Extremely Simple Activation Shaping for Out-of-Distribution Detection
A Unified Framework for Soft Threshold Pruning
Modelling Long Range Dependencies in $N$D: From Task-Specific to a General Purpose CNN
Massively Scaling Heteroscedastic Classifiers
That Label's got Style: Handling Label Style Bias for Uncertain Image Segmentation
What Can we Learn From The Selective Prediction And Uncertainty Estimation Performance Of 523 Imagenet Classifiers?
Towards Robust Object Detection Invariant to Real-World Domain Shifts
Self-Distillation for Further Pre-training of Transformers
CUDA: Curriculum of Data Augmentation for Long-tailed Recognition
From Play to Policy: Conditional Behavior Generation from Uncurated Robot Data
Multifactor Sequential Disentanglement via Structured Koopman Autoencoders
One-Pixel Shortcut: On the Learning Preference of Deep Neural Networks
Enhancing Meta Learning via Multi-Objective Soft Improvement Functions
Learning Label Encodings for Deep Regression
Hard-Meta-Dataset++: Towards Understanding Few-Shot Performance on Difficult Tasks
PerFedMask: Personalized Federated Learning with Optimized Masking Vectors
Data augmentation alone can improve adversarial training
(Certified!!) Adversarial Robustness for Free!
Scaling Laws For Deep Learning Based Image Reconstruction
Learning with Auxiliary Activation for Memory-Efficient Training
Weakly-supervised HOI Detection via Prior-guided Bi-level Representation Learning
FiT: Parameter Efficient Few-shot Transfer Learning for Personalized and Federated Image Classification
Contrastive Learning for Unsupervised Domain Adaptation of Time Series
Disentangling Learning Representations with Density Estimation
Linearly Mapping from Image to Text Space
Towards Understanding and Mitigating Dimensional Collapse in Heterogeneous Federated Learning
Reliability of CKA as a Similarity Measure in Deep Learning
Beyond calibration: estimating the grouping loss of modern neural networks
Approximate Vanishing Ideal Computations at Scale
Artificial Neuronal Ensembles with Learned Context Dependent Gating
Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks
Online Bias Correction for Task-Free Continual Learning
On the Importance and Applicability of Pre-Training for Federated Learning
Towards Smooth Video Composition
Long Range Language Modeling via Gated State Spaces
A Graph Neural Network Approach to Automated Model Building in Cryo-EM Maps
DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking
Neural Lagrangian Schr\"{o}dinger Bridge: Diffusion Modeling for Population Dynamics
Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofs
On the Word Boundaries of Emergent Languages Based on Harris's Articulation Scheme
Deep Generative Symbolic Regression
De Novo Molecular Generation via Connection-aware Motif Mining
Enhancing the Inductive Biases of Graph Neural ODE for Modeling Physical Systems
Pre-training via Denoising for Molecular Property Prediction
Flow Annealed Importance Sampling Bootstrap
Minimax Optimal Kernel Operator Learning via Multilevel Training
Learning Controllable Adaptive Simulation for Multi-resolution Physics
HyperDeepONet: learning operator with complex target function space using the limited resources via hypernetwork
One Transformer Can Understand Both 2D & 3D Molecular Data
Simplicial Hopfield networks
Bayesian Oracle for bounding information gain in neural encoding models
TiAda: A Time-scale Adaptive Algorithm for Nonconvex Minimax Optimization
Symmetries, Flat Minima, and the Conserved Quantities of Gradient Flow
Faster federated optimization under second-order similarity
Generative Augmented Flow Networks
Domain-Indexing Variational Bayes: Interpretable Domain Index for Domain Adaptation
SAM as an Optimal Relaxation of Bayes
A Laplace-inspired Distribution on SO(3) for Probabilistic Rotation Estimation
GFlowNets and variational inference
GRACE-C: Generalized Rate Agnostic Causal Estimation via Constraints
Energy-Based Test Sample Adaptation for Domain Generalization
MARS: Meta-learning as Score Matching in the Function Space
Active Learning in Bayesian Neural Networks with Balanced Entropy Learning Principle
Active Learning for Object Detection with Evidential Deep Learning and Hierarchical Uncertainty Aggregation
Versatile Neural Processes for Learning Implicit Neural Representations
Rhino: Deep Causal Temporal Relationship Learning with History-dependent Noise
Causal Imitation Learning via Inverse Reinforcement Learning
Neural Episodic Control with State Abstraction
Greedy Actor-Critic: A New Conditional Cross-Entropy Method for Policy Improvement
Towards Effective and Interpretable Human-Agent Collaboration in MOBA Games: A Communication Perspective
Learnable Behavior Control: Breaking Atari Human World Records via Sample-Efficient Behavior Selection
Population-size-Aware Policy Optimization for Mean-Field Games
Is Conditional Generative Modeling all you need for Decision Making?
Conservative Bayesian Model-Based Value Expansion for Offline Policy Optimization
Building a Subspace of Policies for Scalable Continual Learning
Choreographer: Learning and Adapting Skills in Imagination
Outcome-directed Reinforcement Learning by Uncertainty \& Temporal Distance-Aware Curriculum Goal Generation
Investigating Multi-task Pretraining and Generalization in Reinforcement Learning
RLx2: Training a Sparse Deep Reinforcement Learning Model from Scratch
Offline Reinforcement Learning via High-Fidelity Generative Behavior Modeling
Information-Theoretic Characterization of the Generalization Error for Iterative Semi-Supervised Learning
Offline RL with No OOD Actions: In-Sample Learning via Implicit Value Regularization
Benchmarking Offline Reinforcement Learning on Real-Robot Hardware
Planning Goals for Exploration
A CMDP-within-online framework for Meta-Safe Reinforcement Learning
The Provable Benefit of Unsupervised Data Sharing for Offline Reinforcement Learning
Imitating Graph-Based Planning with Goal-Conditioned Policies
Decision Transformer under Random Frame Dropping
Transformers are Sample-Efficient World Models
Extreme Q-Learning: MaxEnt RL without Entropy
In-context Reinforcement Learning with Algorithm Distillation
Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning
Confidence-Conditioned Value Functions for Offline Reinforcement Learning
Priors, Hierarchy, and Information Asymmetry for Skill Transfer in Reinforcement Learning
MAESTRO: Open-Ended Environment Design for Multi-Agent Reinforcement Learning
Prompting GPT-3 To Be Reliable
Temporal Disentanglement of Representations for Improved Generalisation in Reinforcement Learning
Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 Small
Incompatibility Clustering as a Defense Against Backdoor Poisoning Attacks
simpleKT: A Simple But Tough-to-Beat Baseline for Knowledge Tracing
Efficient Model Updates for Approximate Unlearning of Graph-Structured Data
Re-weighting Based Group Fairness Regularization via Classwise Robust Optimization
Private Federated Learning Without a Trusted Server: Optimal Algorithms for Convex Losses
The Implicit Bias of Minima Stability in Multivariate Shallow ReLU Networks
Learning to Linearize Deep Neural Networks for Secure and Efficient Private Inference
On Achieving Optimal Adversarial Test Error
Ollivier-Ricci Curvature for Hypergraphs: A Unified Framework
Learning Low Dimensional State Spaces with Overparameterized Recurrent Neural Nets
Meta-Learning in Games
Towards Stable Test-time Adaptation in Dynamic Wild World
Task-customized Masked Autoencoder via Mixture of Cluster-conditional Experts
AANG : Automating Auxiliary Learning
When Source-Free Domain Adaptation Meets Learning with Noisy Labels
Minimalistic Unsupervised Representation Learning with the Sparse Manifold Transform
STUNT: Few-shot Tabular Learning with Self-generated Tasks from Unlabeled Tables
A Unified Approach to Reinforcement Learning, Quantal Response Equilibria, and Two-Player Zero-Sum Games
Don’t fear the unlabelled: safe semi-supervised learning via debiasing
Unsupervised Semantic Segmentation with Self-supervised Object-centric Representations
wav2tok: Deep Sequence Tokenizer for Audio Retrieval
Proposal-Contrastive Pretraining for Object Detection from Fewer Data
Jointly Learning Visual and Auditory Speech Representations from Raw Data
Weighted Ensemble Self-Supervised Learning
(ends 6:30 PM)
5 p.m.

WED 3 MAY
8 a.m.
Registration / Check-in
(ends 6:00 PM)
8:30 a.m.
Invited Talk:
Dialogue Research in the Era of LLMs
Dilek Hakkani-Tur
(ends 9:30 AM)
9:30 a.m.
Break:
Coffee Break
(ends 10:00 AM)
10 a.m.
Oral 5 Track 1: Unsupervised and Self-supervised learning & Social Aspects of Machine Learning- [10:00-11:30]
Orals 10:00-11:20
[10:00] Progress measures for grokking via mechanistic interpretability
[10:10] Localized Randomized Smoothing for Collective Robustness Certification
[10:20] Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes
[10:30] CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
[10:40] Model-based Causal Bayesian Optimization
[10:50] Corrupted Image Modeling for Self-Supervised Visual Pre-Training
[11:00] SimPer: Simple Self-Supervised Learning of Periodic Targets
[11:10] Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
(ends 11:30 AM)
Oral 5 Track 2: Optimization [10:00-11:30]
Orals 10:00-11:10
[10:00] DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity
[10:10] Single-shot General Hyper-parameter Optimization for Federated Learning
[10:20] Solving Constrained Variational Inequalities via a First-order Interior Point-based Method
[10:30] FedExP: Speeding Up Federated Averaging via Extrapolation
[10:40] LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence
[10:50] Multi-Objective Online Learning
[11:00] Continuous PDE Dynamics Forecasting with Implicit Neural Representations
(ends 11:30 AM)
Oral 5 Track 3: Deep Learning and representational learning [10:00-11:30]
Orals 10:00-11:20
[10:00] Hungry Hungry Hippos: Towards Language Modeling with State Space Models
[10:10] Relative representations enable zero-shot latent space communication
[10:20] ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion
[10:30] Distilling Model Failures as Directions in Latent Space
[10:40] Graph Neural Networks for Link Prediction with Subgraph Sketching
[10:50] The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks
[11:00] REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH
[11:10] A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
(ends 11:30 AM)
Oral 5 Track 4: Applications & Optimization [10:00-11:30]
Orals 10:00-11:10
[10:00] Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
[10:10] Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
[10:20] DocPrompting: Generating Code by Retrieving the Docs
[10:30] View Synthesis with Sculpted Neural Points
[10:40] VA-DepthNet: A Variational Approach to Single Image Depth Prediction
[10:50] Visual Classification via Description from Large Language Models
[11:00] Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach
(ends 11:30 AM)
Oral 5 Track 5: Deep Learning and representational learning & Reinforcement Learning [10:00-11:30]
Orals 10:00-11:20
[10:00] Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
[10:10] PLOT: Prompt Learning with Optimal Transport for Vision-Language Models
[10:20] Aligning Model and Macaque Inferior Temporal Cortex Representations Improves Model-to-Human Behavioral Alignment and Adversarial Robustness
[10:30] Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
[10:40] A Primal-Dual Framework for Transformers and Neural Networks
[10:50] Learning with Logical Constraints but without Shortcut Satisfaction
[11:00] No Reason for No Supervision: Improved Generalization in Supervised Models
[11:10] Generating Diverse Cooperative Agents by Learning Incompatible Policies
(ends 11:30 AM)
11:30 a.m.
Poster Session 5 [11:30-1:30]
Posters 11:30-1:30
A Simple Approach for Visual Room Rearrangement: 3D Mapping and Semantic Search
Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners
Globally Injective ReLU Networks
View Synthesis with Sculpted Neural Points
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Calibrating Sequence likelihood Improves Conditional Language Generation
DocPrompting: Generating Code by Retrieving the Docs
DamoFD: Digging into Backbone Design on Face Detection
Clean-image Backdoor: Attacking Multi-label Models with Poisoned Labels Only
Weakly Supervised Explainable Phrasal Reasoning with Neural Fuzzy Logic
Selective Annotation Makes Language Models Better Few-Shot Learners
The KFIoU Loss for Rotated Object Detection
$\mathrm{SE}(3)$-Equivariant Attention Networks for Shape Reconstruction in Function Space
Perfectly Secure Steganography Using Minimum Entropy Coupling
SLTUNET: A Simple Unified Model for Sign Language Translation
VA-DepthNet: A Variational Approach to Single Image Depth Prediction
Visual Classification via Description from Large Language Models
E-CRF: Embedded Conditional Random Field for Boundary-caused Class Weights Confusion in Semantic Segmentation
Proactive Multi-Camera Collaboration for 3D Human Pose Estimation
AnyDA: Anytime Domain Adaptation
SMART: Sentences as Basic Units for Text Evaluation
GAIN: On the Generalization of Instructional Action Understanding
Scaleformer: Iterative Multi-scale Refining Transformers for Time Series Forecasting
Red PANDA: Disambiguating Image Anomaly Detection by Removing Nuisance Factors
Equivariant Descriptor Fields: SE(3)-Equivariant Energy-Based Models for End-to-End Visual Robotic Manipulation Learning
Learning Math Reasoning from Self-Sampled Correct and Partially-Correct Solutions
Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling
Revocable Deep Reinforcement Learning with Affinity Regularization for Outlier-Robust Graph Matching
Graph Neural Networks are Inherently Good Generalizers: Insights by Bridging GNNs and MLPs
Graph Neural Networks for Link Prediction with Subgraph Sketching
Confidence-Based Feature Imputation for Graphs with Partially Known Features
Sparse tree-based Initialization for Neural Networks
REVISITING PRUNING AT INITIALIZATION THROUGH THE LENS OF RAMANUJAN GRAPH
Self-Stabilization: The Implicit Bias of Gradient Descent at the Edge of Stability
Liquid Structural State-Space Models
Predictive Inference with Feature Conformal Prediction
ExpressivE: A Spatio-Functional Embedding For Knowledge Graph Completion
Out-of-distribution Detection with Implicit Outlier Transformation
Improving Deep Regression with Ordinal Entropy
How I Learned to Stop Worrying and Love Retraining
Distilling Model Failures as Directions in Latent Space
Efficient Edge Inference by Selective Query
Understanding Zero-shot Adversarial Robustness for Large-Scale Models
A Primal-Dual Framework for Transformers and Neural Networks
Hungry Hungry Hippos: Towards Language Modeling with State Space Models
Implicit regularization in Heavy-ball momentum accelerated stochastic gradient descent
Efficient recurrent architectures through activity sparsity and sparse back-propagation through time
Diversify and Disambiguate: Out-of-Distribution Robustness via Disagreement
The Augmented Image Prior: Distilling 1000 Classes by Extrapolating from a Single Image
How Much Data Are Augmentations Worth? An Investigation into Scaling Laws, Invariance, and Implicit Regularization
A Closer Look at Model Adaptation using Feature Distortion and Simplicity Bias
Surgical Fine-Tuning Improves Adaptation to Distribution Shifts
Linear Connectivity Reveals Generalization Strategies
PLOT: Prompt Learning with Optimal Transport for Vision-Language Models
Learning with Logical Constraints but without Shortcut Satisfaction
Confidence Estimation Using Unlabeled Data
NORM: Knowledge Distillation via N-to-One Representation Matching
Does Deep Learning Learn to Abstract? A Systematic Probing Framework
The Influence of Learning Rule on Representation Dynamics in Wide Neural Networks
A Generalized Projected Bellman Error for Off-policy Value Estimation in Reinforcement Learning
Is Forgetting Less a Good Inductive Bias for Forward Transfer?
Deep Learning on Implicit Neural Representations of Shapes
FreeMatch: Self-adaptive Thresholding for Semi-supervised Learning
Bispectral Neural Networks
Bias Propagation in Federated Learning
On The Inadequacy of Optimizing Alignment and Uniformity in Contrastive Learning of Sentence Representations
Relative representations enable zero-shot latent space communication
No Reason for No Supervision: Improved Generalization in Supervised Models
DCI-ES: An Extended Disentanglement Framework with Connections to Identifiability
Recursive Time Series Data Augmentation
Autoencoders as Cross-Modal Teachers: Can Pretrained 2D Image Transformers Help 3D Representation Learning?
Leveraging Importance Weights in Subset Selection
Generative Modeling Helps Weak Supervision (and Vice Versa)
Discovering Evolution Strategies via Meta-Black-Box Optimization
DAG Learning on the Permutahedron
Kernel Neural Optimal Transport
DiGress: Discrete Denoising diffusion for graph generation
Neural Architecture Design and Robustness: A Dataset
An Extensible Multi-modal Multi-task Object Dataset with Materials
ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skills
FINDE: Neural Differential Equations for Finding and Preserving Invariant Quantities
Clifford Neural Layers for PDE Modeling
A Self-Attention Ansatz for Ab-initio Quantum Chemistry
Learning differentiable solvers for systems with hard constraints
Learning Domain-Agnostic Representation for Disease Diagnosis
GAMR: A Guided Attention Model for (visual) Reasoning
RandProx: Primal-Dual Optimization Algorithms with Randomized Proximal Updates
Finding Actual Descent Directions for Adversarial Training
DASHA: Distributed Nonconvex Optimization with Communication Compression and Optimal Oracle Complexity
Solving Constrained Variational Inequalities via a First-order Interior Point-based Method
LMC: Fast Training of GNNs via Subgraph Sampling with Provable Convergence
An Adaptive Policy to Employ Sharpness-Aware Minimization
Mitigating Gradient Bias in Multi-objective Learning: A Provably Convergent Approach
FedExP: Speeding Up Federated Averaging via Extrapolation
Multi-Objective Online Learning
Single-shot General Hyper-parameter Optimization for Federated Learning
SWIFT: Rapid Decentralized Federated Learning via Wait-Free Model Communication
Robustness to corruption in pre-trained Bayesian neural networks
Particle-based Variational Inference with Preconditioned Functional Gradient Flow
Calibrating Transformers via Sparse Gaussian Processes
Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories
Measuring axiomatic soundness of counterfactual image models
Latent State Marginalization as a Low-cost Approach for Improving Exploration
Model-based Causal Bayesian Optimization
Hybrid RL: Using both offline and online data can make RL efficient
Value Memory Graph: A Graph-Structured World Model for Offline Reinforcement Learning
Generating Diverse Cooperative Agents by Learning Incompatible Policies
User-Interactive Offline Reinforcement Learning
Simple Emergent Action Representations from Multi-Task Policy Training
Timing is Everything: Learning to Act Selectively with Costly Actions and Budgetary Constraints
Proto-Value Networks: Scaling Representation Learning with Auxiliary Tasks
Energy-based Out-of-Distribution Detection for Graph Neural Networks
Localized Randomized Smoothing for Collective Robustness Certification
Planning with Sequence Models through Iterative Energy Minimization
Robust Explanation Constraints for Neural Networks
Strategic Classification with Graph Neural Networks
Discovering Latent Knowledge in Language Models Without Supervision
Concept Gradient: Concept-based Interpretation Without Linear Assumption
A law of adversarial risk, interpolation, and label noise
Measuring Forgetting of Memorized Training Examples
Progress measures for grokking via mechanistic interpretability
Everybody Needs Good Neighbours: An Unsupervised Locality-based Method for Bias Mitigation
CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networks
Individual Privacy Accounting with Gaussian Differential Privacy
Temporal Dependencies in Feature Importance for Time Series Prediction
Explaining RL Decisions with Trajectories
Stochastic Differentially Private and Fair Learning
Towards Interpretable Deep Reinforcement Learning with Human-Friendly Prototypes
How robust is unsupervised representation learning to distribution shift?
A Non-Asymptotic Analysis of Oversmoothing in Graph Neural Networks
On the Saturation Effect of Kernel Ridge Regression
Characterizing the spectrum of the NTK via a power series expansion
Collaborative Pure Exploration in Kernel Bandit
Learning ReLU networks to high uniform accuracy is intractable
Understanding The Robustness of Self-supervised Learning Through Topic Modeling
Bidirectional Language Models Are Also Few-shot Learners
Self-Supervised Category-Level Articulated Object Pose Estimation with Part-Level SE(3) Equivariance
From $t$-SNE to UMAP with contrastive learning
Simplicial Embeddings in Self-Supervised Learning and Downstream Classification
Corrupted Image Modeling for Self-Supervised Visual Pre-Training
SimPer: Simple Self-Supervised Learning of Periodic Targets
What Do Self-Supervised Vision Transformers Learn?
Human-level Atari 200x faster
(ends 1:30 PM)
Break:
Lunch
(ends 1:30 PM)
12:30 p.m.
Town Hall:
Town Hall: LLMs in the ICLR Writing Process?
(ends 1:00 PM)
1:30 p.m.
Invited Talk:
Learned optimizers: why they're the future, why they’re hard, and what they can do now
Jascha Sohl-Dickstein
(ends 2:30 PM)
2:30 p.m.
Remarks:
Closing Ceremony
(ends 2:35 PM)
Break:
Coffee Break
(ends 3:00 PM)
3 p.m.
Oral 6 Track 4: Applications & Social Aspects of Machine Learning & General Machine Learning [3:00-4:30]
Orals 3:00-4:20
[3:00] Binding Language Models in Symbolic Languages
[3:10] MeshDiffusion: Score-based Generative 3D Mesh Modeling
[3:20] The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation
[3:30] AutoGT: Automated Graph Transformer Architecture Search
[3:40] Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
[3:50] LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation
[4:00] Certified Training: Small Boxes are All You Need
[4:10] Inequality phenomenon in $l_{\infty}$-adversarial training, and its unrealized threats
(ends 4:30 PM)
Oral 6 Track 2: Infrastructure & Social Aspects of Machine Learning [3:00-4:30]
Orals 3:00-4:10
[3:00] DaxBench: Benchmarking Deformable Object Manipulation with Differentiable Physics
[3:10] Betty: An Automatic Differentiation Library for Multilevel Optimization
[3:20] WikiWhy: Answering and Explaining Cause-and-Effect Questions
[3:30] MEDFAIR: Benchmarking Fairness for Medical Imaging
[3:40] Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
[3:50] Confidential-PROFITT: Confidential PROof of FaIr Training of Trees
[4:00] Disparate Impact in Differential Privacy from Gradient Misalignment
(ends 4:30 PM)
Oral 6 Track 3: Deep Learning and representational learning [3:00-4:30]
Orals 3:00-4:20
[3:00] Agree to Disagree: Diversity through Disagreement for Better Transferability
[3:10] What learning algorithm is in-context learning? Investigations with linear models
[3:20] Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
[3:30] Encoding Recurrence into Transformers
[3:40] Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
[3:50] Simplified State Space Layers for Sequence Modeling
[4:00] Relational Attention: Generalizing Transformers for Graph-Structured Tasks
[4:10] Sparse Mixture-of-Experts are Domain Generalizable Learners
(ends 4:30 PM)
Oral 6 Track 1: Theory [3:00-4:30]
Orals 3:00-4:20
[3:00] Near-optimal Coresets for Robust Clustering
[3:10] Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
[3:20] Towards Understanding Ensemble, Knowledge Distillation and Self-Distillation in Deep Learning
[3:30] Statistical Efficiency of Score Matching: The View from Isoperimetry
[3:40] Subquadratic Algorithms for Kernel Matrices via Kernel Density Estimation
[3:50] Depth Separation with Multilayer Mean-Field Networks
[4:00] Learning with Stochastic Orders
[4:10] Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities
(ends 4:30 PM)
Oral 6 Track 5: Applications- & Deep Learning and representational learning [3:00-4:30]
Orals 3:00-4:20
[3:00] Language Modelling with Pixels
[3:10] Parametrizing Product Shape Manifolds by Composite Networks
[3:20] ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
[3:30] Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer
[3:40] Dual Algorithmic Reasoning
[3:50] DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
[4:00] Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning
[4:10] Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
(ends 4:30 PM)
Oral 6 Track 6: Deep Learning [3:00-4:30]
Orals 3:00-3:50
[3:00] Unsupervised Model Selection for Time Series Anomaly Detection
[3:10] A Kernel Perspective of Skip Connections in Convolutional Networks
[3:20] ReAct: Synergizing Reasoning and Acting in Language Models
[3:30] A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet
[3:40] Packed Ensembles for efficient uncertainty estimation
(ends 4:30 PM)
Affinity Event:
Women in Machine Learning Social
(ends 5:00 PM)
4:30 p.m.
Poster Session 6 [4:30-6:30]
Posters 4:30-6:30
Summarization Programs: Interpretable Abstractive Summarization with Neural Modular Trees
Binding Language Models in Symbolic Languages
WiNeRT: Towards Neural Ray Tracing for Wireless Channel Modelling and Differentiable Simulations
Static Prediction of Runtime Errors by Learning to Execute Programs with External Resource Descriptions
ReAct: Synergizing Reasoning and Acting in Language Models
Greedification Operators for Policy Optimization: Investigating Forward and Reverse KL Divergences
Automating Nearest Neighbor Search Configuration with Constrained Optimization
On the Robustness to Misspecification of α-posteriors and Their Variational Approximations
Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction
CodeBPE: Investigating Subtokenization Options for Large Language Model Pretraining on Source Code
GOOD: Exploring geometric cues for detecting objects in an open world
Short-Term Memory Convolutions
Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Model
Diagnosing and Rectifying Vision Models using Language
Real-Time Image Demoir$\acute{e}$ing on Mobile Devices
Switch-NeRF: Learning Scene Decomposition with Mixture of Experts for Large-scale Neural Radiance Fields
Is Attention All That NeRF Needs?
Consolidator: Mergable Adapter with Group Connections for Visual Adaptation
DropIT: Dropping Intermediate Tensors for Memory-Efficient DNN Training
Learning Uncertainty for Unknown Domains with Zero-Target-Assumption
Offline RL for Natural Language Generation with Implicit Language Q Learning
LightGCL: Simple Yet Effective Graph Contrastive Learning for Recommendation
Language Modelling with Pixels
CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos
A framework for benchmarking Class-out-of-distribution detection and its application to ImageNet
Reversible Column Networks
AutoGT: Automated Graph Transformer Architecture Search
Compositionality with Variation Reliably Emerges in Neural Networks
Equivariance-aware Architectural Optimization of Neural Networks
Semi-Parametric Inducing Point Networks and Neural Processes
Relational Attention: Generalizing Transformers for Graph-Structured Tasks
Parametrizing Product Shape Manifolds by Composite Networks
DIFFormer: Scalable (Graph) Transformers Induced by Energy Constrained Diffusion
PowerQuant: Automorphism Search for Non-Uniform Quantization
Over-parameterized Model Optimization with Polyak-{\L}ojasiewicz Condition
Last Layer Re-Training is Sufficient for Robustness to Spurious Correlations
Ordered GNN: Ordering Message Passing to Deal with Heterophily and Over-smoothing
What Is Missing in IRM Training and Evaluation? Challenges and Solutions
Dual Algorithmic Reasoning
ImageNet-X: Understanding Model Mistakes with Factor of Variation Annotations
MA-BERT: Towards Matrix Arithmetic-only BERT Inference by Eliminating Complex Non-Linear Functions
Composing Ensembles of Pre-trained Models via Iterative Consensus
Hierarchical Abstraction for Combinatorial Generalization in Object Rearrangement
$\Lambda$-DARTS: Mitigating Performance Collapse by Harmonizing Operation Selection among Cells
Encoding Recurrence into Transformers
Agree to Disagree: Diversity through Disagreement for Better Transferability
Deep Transformers without Shortcuts: Modifying Self-attention for Faithful Signal Propagation
More ConvNets in the 2020s: Scaling up Kernels Beyond 51x51 using Sparsity
Addressing Parameter Choice Issues in Unsupervised Domain Adaptation by Aggregation
TTN: A Domain-Shift Aware Batch Normalization in Test-Time Adaptation
Lossless Adaptation of Pretrained Vision Models For Robotic Manipulation
Verifying the Union of Manifolds Hypothesis for Image Data
Unveiling the sampling density in non-uniform geometric graphs
Geometrically regularized autoencoders for non-Euclidean data
Simplified State Space Layers for Sequence Modeling
Data Continuity Matters: Improving Sequence Modeling with Lipschitz Regularizer
Write and Paint: Generative Vision-Language Models are Unified Modal Learners
$k$NN Prompting: Beyond-Context Learning with Calibration-Free Nearest Neighbor Inference
A Simple Yet Powerful Deep Active Learning With Snapshots Ensembles
Packed Ensembles for efficient uncertainty estimation
What learning algorithm is in-context learning? Investigations with linear models
Part-Based Models Improve Adversarial Robustness
Effectively Modeling Time Series with Simple Discrete State Spaces
Warping the Space: Weight Space Rotation for Class-Incremental Few-Shot Learning
The Modality Focusing Hypothesis: Towards Understanding Crossmodal Knowledge Distillation
Understanding the Covariance Structure of Convolutional Filters
Universal Few-shot Learning of Dense Prediction Tasks with Visual Token Matching
Hyperparameter Optimization through Neural Network Partitioning
Unsupervised Model Selection for Time Series Anomaly Detection
ContraNorm: A Contrastive Learning Perspective on Oversmoothing and Beyond
Bridging the Gap to Real-World Object-Centric Learning
Disentanglement of Correlated Factors via Hausdorff Factorized Support
EquiMod: An Equivariance Module to Improve Visual Instance Discrimination
When to Make and Break Commitments?
Block and Subword-Scaling Floating-Point (BSFP) : An Efficient Non-Uniform Quantization For Low Precision Inference
A Statistical Framework for Personalized Federated Learning and Estimation: Theory, Algorithms, and Privacy
Blurring Diffusion Models
Neural Implicit Shape Editing using Boundary Sensitivity
MeshDiffusion: Score-based Generative 3D Mesh Modeling
Efficient Federated Domain Translation
Betty: An Automatic Differentiation Library for Multilevel Optimization
Winning Both the Accuracy of Floating Point Activation and the Simplicity of Integer Arithmetic
SoftZoo: A Soft Robot Co-design Benchmark For Locomotion In Diverse Environments
WikiWhy: Answering and Explaining Cause-and-Effect Questions
DaxBench: Benchmarking Deformable Object Manipulation with Differentiable Physics
Equivariant Shape-Conditioned Generation of 3D Molecules for Ligand-Based Drug Design
Multiple sequence alignment as a sequence-to-sequence learning problem
Context-enriched molecule representations improve few-shot drug discovery
Interneurons accelerate learning dynamics in recurrent neural networks for statistical adaptation
SGDA with shuffling: faster convergence for nonconvex-PŁ minimax optimization
Trainable Weight Averaging: Efficient Training by Optimizing Historical Solutions
Solving stochastic weak Minty variational inequalities without increasing batch size
Min-Max Multi-objective Bilevel Optimization with Applications in Robust Machine Learning
Fast Nonlinear Vector Quantile Regression
Meta Temporal Point Processes
Riemannian Metric Learning via Optimal Transport
Evolving Populations of Diverse RL Agents with MAP-Elites
Provably Efficient Risk-Sensitive Reinforcement Learning: Iterated CVaR and Worst Path
Diffusion Policies as an Expressive Policy Class for Offline Reinforcement Learning
Scaling Laws for a Multi-Agent Reinforcement Learning Model
Simplifying Model-based RL: Learning Representations, Latent-space Models, and Policies with One Objective
Impossibly Good Experts and How to Follow Them
Reward Design with Language Models
Harnessing Mixed Offline Reinforcement Learning Datasets via Trajectory Weighting
Visual Imitation Learning with Patch Rewards
Backstepping Temporal Difference Learning
Expressive Monotonic Neural Networks
Semantic Uncertainty: Linguistic Invariances for Uncertainty Estimation in Natural Language Generation
Certified Training: Small Boxes are All You Need
Confidential-PROFITT: Confidential PROof of FaIr Training of Trees
MEDFAIR: Benchmarking Fairness for Medical Imaging
Inequality phenomenon in $l_{\infty}$-adversarial training, and its unrealized threats
Disparate Impact in Differential Privacy from Gradient Misalignment
Causal Confusion and Reward Misidentification in Preference-Based Reward Learning
Panning for Gold in Federated Learning: Targeted Text Extraction under Arbitrarily Large-Scale Aggregation
Excess Risk of Two-Layer ReLU Neural Networks in Teacher-Student Settings and its Superiority to Kernel Methods
On The Specialization of Neural Modules
Label-free Concept Bottleneck Models
Depth Separation with Multilayer Mean-Field Networks
Pitfalls of Gaussians as a noise distribution in NCE
Near-optimal Coresets for Robust Clustering
Towards convergence to Nash equilibria in two-team zero-sum games
Efficiently Computing Nash Equilibria in Adversarial Team Markov Games
Robust Algorithms on Adaptive Inputs from Bounded Adversaries
A view of mini-batch SGD via generating functions: conditions of convergence, phase transitions, benefit from negative momenta.
Variance-Aware Sparse Linear Bandits
Strong inductive biases provably prevent harmless interpolation
Subquadratic Algorithms for Kernel Matrices via Kernel Density Estimation
Forward Super-Resolution: How Can GANs Learn Hierarchical Generative Models for Real-World Distributions
Plateau in Monotonic Linear Interpolation --- A "Biased" View of Loss Landscape for Deep Networks
Statistical Efficiency of Score Matching: The View from Isoperimetry
Nonlinear Reconstruction for Operator Learning of PDEs with Discontinuities
Learning in temporally structured environments
A Kernel Perspective of Skip Connections in Convolutional Networks
Learning with Stochastic Orders
DAVA: Disentangling Adversarial Variational Autoencoder
Fake It Until You Make It : Towards Accurate Near-Distribution Novelty Detection
Unsupervised 3D Object Learning through Neuron Activity aware Plasticity
Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles
SlotFormer: Unsupervised Visual Dynamics Simulation with Object-Centric Models
A Message Passing Perspective on Learning Dynamics of Contrastive Learning
Universal Approximation Theorems for Differentiable Geometric Deep Learning
Rethinking the Effect of Data Augmentation in Adversarial Contrastive Learning
Self-Supervised Geometric Correspondence for Category-Level 6D Object Pose Estimation in the Wild
Exploring The Role of Mean Teachers in Self-supervised Masked Auto-Encoders
(ends 6:30 PM)

THU 4 MAY
7 a.m.
Registration / Check-in
(ends 6:00 PM)
8:20 a.m.
Affinity Workshop:
Joint IndabaXRwanda / BlackInAI
(ends 6:00 PM)
8:30 a.m.
Affinity Workshop:
Kaggle@ICLR 2023: ML Solutions in Africa
(ends 5:00 PM)
8:45 a.m.
Workshop:
Trustworthy and Reliable Large-Scale Machine Learning Models
(ends 5:30 PM)
9 a.m.
Workshop:
Trustworthy Machine Learning for Healthcare
(ends 5:00 PM)
Workshop:
Tackling Climate Change with Machine Learning: Global Perspectives and Local Challenges
(ends 6:45 PM)
Workshop:
Reincarnating Reinforcement Learning
(ends 5:00 PM)
Workshop:
Physics for Machine Learning
(ends 6:00 PM)
Workshop:
AI for Agent-Based Modelling (AI4ABM)
(ends 6:00 PM)
9:15 a.m.
Workshop:
Mathematical and Empirical Understanding of Foundation Models (ME-FoMo)
(ends 4:45 PM)
9:30 a.m.
Break:
Coffee Break
(ends 10:00 AM)
9:40 a.m.
Workshop:
Neural Fields across Fields: Methods and Applications of Implicit Neural Representations
(ends 6:05 PM)
10 a.m.
Workshop:
What do we need for successful domain generalization?
(ends 6:40 PM)
Workshop:
Neurosymbolic Generative Models (NeSy-GeMs)
(ends 7:00 PM)
noon
Break:
Lunch
(ends 1:30 PM)
2:30 p.m.
Break:
Coffee Break
(ends 3:00 PM)
3 p.m.
Workshop:
From Molecules to Materials: ICLR 2023 Workshop on Machine learning for materials (ML4Materials)
(ends 12:00 AM)
6 p.m.

FRI 5 MAY
7 a.m.
Registration / Check-in
(ends 12:00 PM)
8 a.m.
8:50 a.m.
Workshop:
Scene Representations for Autonomous Driving
(ends 5:30 PM)
9 a.m.
Workshop:
ICLR 2023 Workshop on Machine Learning for Remote Sensing
(ends 5:30 PM)
Workshop:
Multimodal Representation Learning (MRL): Perks and Pitfalls
(ends 6:00 PM)
Workshop:
First workshop on "Machine Learning & Global Health".
(ends 5:00 PM)
Workshop:
The 4th Workshop on practical ML for Developing Countries: learning under limited/low resource settings
(ends 5:00 PM)
Workshop:
Pitfalls of limited data and computation for Trustworthy ML
(ends 6:00 PM)
Workshop:
ICLR 2023 Workshop on Sparsity in Neural Networks: On practical limitations and tradeoffs between sustainability and efficiency
(ends 7:00 PM)
Affinity Workshop:
Tiny Papers Showcase Day (a DEI initiative)
(ends 5:00 PM)
9:30 a.m.
Break:
Coffee Break
(ends 10:00 AM)
10 a.m.
Workshop:
4th Workshop on African Natural Language Processing (AfricaNLP 2023)
(ends 7:00 PM)
10:10 a.m.
Workshop:
Time Series Representation Learning for Health
(ends 7:00 PM)
11 a.m.
Workshop:
Machine Learning for Drug Discovery (MLDD)
(ends 8:00 PM)
noon
Break:
Lunch
(ends 1:30 PM)
2:30 p.m.
Workshop:
Deep Learning for Code (DL4C)
(ends 11:00 PM)
Workshop:
Machine Learning for IoT: Datasets, Perception, and Understanding
(ends 11:30 PM)
Break:
Coffee Break
(ends 3:00 PM)
3 p.m.
Workshop:
Backdoor Attacks and Defenses in Machine Learning
(ends 12:05 AM)