Poster · Paris
The Post-Training Dilemma: Why We Should Rethink the Sequential SFT-RL Paradigm
- When
- Wed 9 Dec 2026, 17:00–19:00 CET
- Where
- Paris Poster Hall
- Session
- Paris Poster Session 2
- Authors
- Xueyan Niu, Bo Bai, Wei Han, Weixi Zhang
- Organisations
- Huawei
- QRS classification
- Reinforcement learning, Language models