DaRL Group / Hua Wei
Claude Code Unpacked
In a recent DaRL Lab group meeting, I presented a technical breakdown of the underlying architecture of Claude Code. As a terminal-based AI agent tool, Claude Code addresses engineering challenges…
Empowering Teachers with AI: Shifting from Content Dissemination to Service Provision
AI is not replacing teachers. In many ways, it is allowing teachers to return to the true essence of the profession: understanding students, supporting them, helping them build confidence, and…
Old-School Deep RL Tricks for Modern LLM Training
How to port n-step returns, TD(λ), uncertainty, safety, and friends from deep RL into RLHF/RLAIF and tool-using LLM agents — with equations.
This note collects well-known…
NSF CAREER Resources: From Confusion to Submission
When I was preparing my CAREER proposal, especially the first time, I often felt completely overwhelmed. Every day was a tug-of-war between “I cannot look at this anymore”
KDD’18: IntelliLight
How Long Until Reinforcement Learning is Applied in the Physical World?
As one of the most popular technologies in the field of machine learning in recent years, reinforcement learning (RL) has made significant progress in areas such as games, robotic control, and…
On the Future of Spatio-Temporal Data Mining for Traffic Prediction
Starting as a researcher in spatio-temporal data mining, I still vividly remember the excitement of my first paper…
DaRL Lab Handbook
https://darl-lab.gitbook.io/handbook/
Or Chat with AI Hua Bot here