Yu Bai

20

Papers

31

Total Citations

Papers (20)

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

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

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

Excluding the Impossible for Open Vocabulary Semantic Segmentation

Text2Data: Low-Resource Data Generation with Textual Control

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

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

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

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

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

Policy Optimization for Markov Games: Unified Framework and Faster Convergence

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

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

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

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

Provably Efficient Q-Learning with Low Switching Cost

Near-Optimal Reinforcement Learning with Self-Play

Towards Understanding Hierarchical Learning: Benefits of Neural Representations

Near-Optimal Offline Reinforcement Learning via Double Variance Reduction

Understanding the Under-Coverage Bias in Uncertainty Estimation