Yulai Zhao

sarosavo's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 2 months ago

Every Question Has Its Own Value: Reinforcement Learning with Explicit Human Values

Paper • 2510.20187 • Published Oct 23 • 18

authored 3 papers 5 months ago

Provably Efficient CVaR RL in Low-rank MDPs

Paper • 2311.11965 • Published Nov 20, 2023

Derivative-Free Guidance in Continuous and Discrete Diffusion Models with Soft Value-Based Decoding

Paper • 2408.08252 • Published Aug 15, 2024 • 1

One Token to Fool LLM-as-a-Judge

Paper • 2507.08794 • Published Jul 11 • 31

authored a paper about 2 years ago

Local Optimization Achieves Global Optimality in Multi-Agent Reinforcement Learning

Paper • 2305.04819 • Published May 8, 2023