Yu Bai

papers

963

total citations

papers (19)

Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

NEURIPS 2023arXiv

271

citations

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning

NEURIPS 2021arXiv

184

citations

What can a Single Attention Layer Learn? A Study Through the Random Features Lens

NEURIPS 2023arXiv

citations

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

NEURIPS 2022arXiv

citations

TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model

CVPR 2025arXiv

citations

Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent

NEURIPS 2022arXiv

citations

Understanding the Under-Coverage Bias in Uncertainty Estimation

NEURIPS 2021arXiv

citations

Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials

NEURIPS 2022arXiv

citations

DeIL: Direct-and-Inverse CLIP for Open-World Few-Shot Learning

CVPR 2024

citations

Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games

NEURIPS 2022arXiv

citations

Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective

ICML 2024arXiv

citations

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

NEURIPS 2023

citations

Text2Data: Low-Resource Data Generation with Textual Control

AAAI 2025arXiv

citations

Collaborative Consortium of Foundation Models for Open-World Few-Shot Learning

AAAI 2024

citations

Excluding the Impossible for Open Vocabulary Semantic Segmentation

AAAI 2025

citations

Yu Bai

papers (19)

Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning

Near-Optimal Reinforcement Learning with Self-Play

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games

Near-Optimal Offline Reinforcement Learning via Double Variance Reduction

Towards Understanding Hierarchical Learning: Benefits of Neural Representations

What can a Single Attention Layer Learn? A Study Through the Random Features Lens

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model

Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent

Understanding the Under-Coverage Bias in Uncertainty Estimation

Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials

DeIL: Direct-and-Inverse CLIP for Open-World Few-Shot Learning

Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games

Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

Text2Data: Low-Resource Data Generation with Textual Control

Collaborative Consortium of Foundation Models for Open-World Few-Shot Learning

Excluding the Impossible for Open Vocabulary Semantic Segmentation

papers (19)

Transformers as Statisticians: Provable In-Context Learning with In-Context Algorithm Selection

Policy Finetuning: Bridging Sample-Efficient Offline and Online Reinforcement Learning

Near-Optimal Reinforcement Learning with Self-Play

Sample-Efficient Learning of Stackelberg Equilibria in General-Sum Games

Near-Optimal Offline Reinforcement Learning via Double Variance Reduction

Towards Understanding Hierarchical Learning: Benefits of Neural Representations

What can a Single Attention Layer Learn? A Study Through the Random Features Lens

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

TopV: Compatible Token Pruning with Inference Time Optimization for Fast and Low-Memory Multimodal Vision Language Model

Efficient Phi-Regret Minimization in Extensive-Form Games via Online Mirror Descent

Understanding the Under-Coverage Bias in Uncertainty Estimation

Identifying good directions to escape the NTK regime and efficiently learn low-degree plus sparse polynomials

DeIL: Direct-and-Inverse CLIP for Open-World Few-Shot Learning

Sample-Efficient Learning of Correlated Equilibria in Extensive-Form Games

Is Inverse Reinforcement Learning Harder than Standard Reinforcement Learning? A Theoretical Perspective

Efficient RL with Impaired Observability: Learning to Act with Delayed and Missing State Observations

Text2Data: Low-Resource Data Generation with Textual Control

Collaborative Consortium of Foundation Models for Open-World Few-Shot Learning

Excluding the Impossible for Open Vocabulary Semantic Segmentation