Yuke Zhu

5

Papers

482

Total Citations

Papers (5)

Eureka: Human-Level Reward Design via Coding Large Language Models

Building Minimal and Reusable Causal State Abstractions for Reinforcement Learning

Enhancing Document Understanding with Group Position Embedding: A Novel Approach to Incorporate Layout Information

LightCity: An Urban Dataset for Outdoor Inverse Rendering and Reconstruction under Multi-illumination Conditions

PIVOT: Iterative Visual Prompting Elicits Actionable Knowledge for VLMs