Skip to content
NeurIPS 2026 planner

Poster · Sydney

Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT Data

When
Wed 9 Dec 2026, 17:00–20:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 4
Authors
Yunlong Hou, Fengzhuo Zhang, Yuan Cheng, Jiachun Pan, Xingyao Li, Zhuoran Yang
Organisations
National University of Singapore, Yale University, Cisco
QRS classification
Reinforcement learning, Language models

Open in scheduleOfficial page