Poster · Sydney
Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
- When
- Tue 8 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 1
- Authors
- Jiakang Wang, Runze Liu, Fuzheng Zhang, Xiu Li, Guorui Zhou, Kun Gai, Ling Pan
- Organisations
- Kuaishou, Hong Kong University of Science and Technology, Alibaba
- QRS classification
- Language models