Jiuhai Chen

A new method quantifies confidence in language model answers for better reliability.

2025-10-02T14:33:48+00:00 ― 5 min read

Exploring the challenges and solutions of reward hacking in AI model training.

2025-09-09T06:58:48+00:00 ― 7 min read

Florence-2 and DBFusion redefine how machines interpret images and text.

2025-04-11T23:06:54+00:00 ― 7 min read