Yihua Zhang PRO

NormalUhr

·

https://www.yihua-zhang.com

AI & ML interests

None yet

Recent Activity

published an article 3 days ago

Score Function Centering: Your Stale Rollout Does Not Have to Be Importance Sampled and Stabilize Your Async RL Training with Trainer-Generator KL

published an article 4 days ago

The Most Intuitive Way to Understand Score Function Centering: Understand Trainer-Generator Mismatch in Async RL from the Score Function

commentedon their article 11 days ago

Navigating the RLHF Landscape: From Policy Gradients to PPO, GAE, and DPO for LLM Alignment

View all activity

Organizations

upvoted a paper about 1 year ago

Understanding R1-Zero-Like Training: A Critical Perspective

Paper • 2503.20783 • Published Mar 26, 2025 • 61

upvoted a paper over 1 year ago

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Credit Assignment

Paper • 2505.11821 • Published May 17, 2025 • 14

upvoted an article about 2 years ago

Article

Optimizing your LLM in production

patrickvonplaten

•

Sep 15, 2023

• 23