Poster · Sydney
Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction
- When
- Thu 10 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 5
- Authors
- Xiao Cui, Mo Zhu, Yulei Qin, Yuze Wu, Wengang Zhou, Houqiang Li
- Organisations
- University of Science and Technology of China, Zhejiang University, Tencent
- QRS classification
- Reinforcement learning, Safety, fairness and privacy