Qiushi Han
@qiushi-han · 1 works
Researcher studying how multimodal models reason and applying them to interactive task-solving environments.
Recent posts by Qiushi Han
- VISTA: A Visual Harness for Reasoning in an Interactive World - We show that multimodal models possess strong reasoning abilities and that an appropriate harness can unlock their potential to solve tasks across diverse interactive environments. We introduce… · Paper · arxiv.org