Skip to content
NeurIPS 2026 planner

Poster · Sydney

Learning Where to Look: Observation Policy Optimization for Thinking with Images

When
Wed 9 Dec 2026, 10:00–13:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 3
Authors
Junfeng Wang, Jiawei Liu, Yongchao Xu, Tao Jiang, jiangbo Ai, Jin Zhang, Chong Wang, Qixing Zhang
Organisations
University of Science and Technology of China, Alibaba, University of Bristol
QRS classification
Reinforcement learning, Language models, Computer vision

Open in scheduleOfficial page