Han Zhong

A new approach to enhance learning in infinite-horizon average-reward MDPs.

2025-08-09T05:03:40+00:00 ― 10 min read

A new method enhances language models by actively seeking diverse responses.

2025-08-05T06:41:00+00:00 ― 6 min read

Learn about 2D magnets and their potential in technology.

2025-07-20T18:32:42+00:00 ― 6 min read