Yuexiang Zhai

6

Papers

658

Total Citations

Papers (6)

Eyes Wide Shut? Exploring the Visual Shortcomings of Multimodal LLMs

LMRL Gym: Benchmarks for Multi-Turn Reinforcement Learning with Language Models

RLIF: Interactive Imitation Learning as Reinforcement Learning

Learning to Reconstruct 3D Manhattan Wireframes From a Single Image

Convolutional Normalization: Improving Deep Convolutional Network Robustness and Training

Unpacking Reward Shaping: Understanding the Benefits of Reward Engineering on Sample Complexity