Poster · Sydney
Manifold Drift in Flow Preference Optimization: A Root Cause of Reward Hacking
- When
- Tue 8 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 2
- Authors
- Yansen Han, Shengyi Liao, Yuanxing Zhang, Pengfei Wan, Tao Lin
- Organisations
- Zhejiang University, Westlake University, Alibaba, Kuaishou
- QRS classification
- Generative models