Skip to content
NeurIPS 2026 planner

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

Open in scheduleOfficial page