Yihua Zhang's picture

1 1 3

Yihua Zhang

NormalUhr

·

https://www.yihua-zhang.com

AI & ML interests

None yet

Recent Activity

published an article 14 days ago

DualPipe Explained: A Comprehensive Guide to DualPipe That Anyone Can Understand—Even Without a Distributed Training Background

published an article about 1 month ago

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

published an article about 1 month ago

DeepSeek-R1 Dissection: Understanding PPO & GRPO Without Any Prior Reinforcement Learning Knowledge

View all activity

Organizations

Articles 6

Article

2

DualPipe Explained: A Comprehensive Guide to DualPipe That Anyone Can Understand—Even Without a Distributed Training Background

Article

12

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

View all Articles

Papers 1

arxiv:2402.11846

models

None public yet

datasets

None public yet