Xiaoxiao Ma

Xiaoxiao Ma

I am a Senior Applied Scientist at Oracle OAC and a third year Ph.D. candidate at Macquarie University. My principal supervisor is Prof. Jian Yang and my associate supervisor is A. Prof. Jia Wu. I am focusing on research in all areas in AI, including LLMs, deep learning, graph mining, and deep generative models.

Reinforcement Learning and LLM Post-Training: How Does DeepSeek R1 Gain Reasoning Capabilities?

less than 1 minute read

Published:

This is a very detailed doc for RL and LLM Reasoning. I folked this page from Wei-Min Lu.

Link to the blog

Reinforcement Learning and LLM Post-Training: How Does DeepSeek R1 Gain Reasoning Capabilities?

You May Also Enjoy