Skip to content
NeurIPS 2026 planner

Poster · Sydney

Learn from the Gap: Differential-Aware Advantage Pruning with Adaptive Rollout Sampling for GRPO

When
Tue 8 Dec 2026, 10:00–13:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 1
Authors
Jiahua Yang, Chuangchuang Wang, Zhiwei Yang, Xianpeng Zhang, Dongyu Chen, Xing Chen, Tianhuang Su, Haonan Lu, Quanlong Guan, Kai Tang
Organisations
Jinan University, OPPO, AgiBot Innovation Technology Co, Ragentile Intelligence
QRS classification
Reinforcement learning, Efficient and distributed ML systems

Open in scheduleOfficial page