Oral ยท Sydney
Thinking with Images as Continuous Policy: Numerical Visual Chain-of-Thought
Time not published yetRoom not published
- When
- Time not published yet
- Where
- Room not published
- Poster
- Poster of this paper
- Authors
- Kesen Zhao, Beier Zhu, Junbao Zhou, Xingyu Zhu, Zhongqi Yue, Hanwang Zhang
- Organisations
- Nanyang Technological University, University of Science and Technology of China, Microsoft
- QRS classification
- Reinforcement learning, Language models, Computer vision