Poster · Sydney
STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
- 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
- Shiqi Liu, Zeyu He, Guojian Zhan, Letian Tao, Zhilong Zheng, Jiang Wu, yinuo Wang, Yang Guan, Kehua Sheng, Bo Zhang, Keqiang Li, Jingliang Duan and 1 more
- Organisations
- Tsinghua University, University of Science and Technology Beijing, Huawei, Didi
- QRS classification
- Reinforcement learning, Language models