Poster · Sydney
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
- 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
- Yun Qu, Qi Wang, Yixiu Mao, Heming Zou, Yuhang Jiang, Yingyue Li, Wutong Xu, Lizhou Cai, Weijie Liu, Clive Bai, Kai Yang, Yangkun Chen and 2 more
- Organisations
- Tsinghua University, University of Maryland, College Park, Tencent, LLM Department
- QRS classification
- Reinforcement learning, Language models