Poster · Sydney
DUDS: Dual-stage Data Selection for Efficient Reinforcement Learning with Verifiable Rewards
- 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
- Hongling Zheng, Li Shen, Zichuan Lin, Jiafei Lyu, Zhicong Lu, Shuhan Xu, Yong Luo, Deheng Ye, Dacheng Tao
- Organisations
- Nanyang Technological University, Sun Yat-sen University, Tencent, Tsinghua University, University of Chinese Academy of Sciences, Wuhan University
- QRS classification
- Reinforcement learning, Language models