LLaMAFactory Code Analysis
Published:
This blog post documents my learning process of the LLaMAFactory code repository.
Blog posts
2025
From RL to RLHF
Published:
In light of the widespread adoption of RLHF in large language models (LLMs), this blog is intended to document my study of RLHF, starting from reinforcement learning.
Diffusion Model for Sequential Recommendation
Published:
This blog serves as a reading note for a series of papers on applying diffusion models to recommendation systems, especially sequential recommendation.