Poster · Sydney
CPA: Efficient and Stable FP4 RL Training via Cross-Precision Alignment
- 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
- Gu Gong, Yining Wei, Yuechen Tao, Tianyuan Wu, Peijie Dong, Ruibo FAN, Wenhu Hu, Yinghao Yu, Jiamang Wang, Wenbo Su, Guodong Yang, Liping Zhang and 2 more
- Organisations
- Hong Kong University of Science and Technology (Guangzhou), Hong Kong University of Science and Technology, Alibaba, Zhejiang University
- QRS classification
- Reinforcement learning, Language models, Efficient and distributed ML systems