Skip to content
NeurIPS 2026 planner

Poster · Sydney

SIRAS: Sibling-Relative Advantage Shaping for Reinforcement Learning from Verifiable Rewards

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
Zairun Yang, Jun Xu, Lei Liang, Huajun Chen, Qiang Zhang
Organisations
Zhejiang University, Ant Group, College of Computer Science
QRS classification
Reinforcement learning

Open in scheduleOfficial page