Poster · Sydney
Boosting Off-Policy RLVR with Data-Centric Replay
- When
- Thu 10 Dec 2026, 17:00–20:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 6
- Authors
- Yuxiao He, Junge Zhang, Ziqi Wang
- Organisations
- Chinese Academy of Sciences
- QRS classification
- Reinforcement learning, Language models