Skip to content
NeurIPS 2026 planner

Poster · Sydney

Historical Relative Policy Optimization for Bootstrapping LLM Reasoning

When
Tue 8 Dec 2026, 17:00–20:00 AEDT
Where
Hall 1-4, ICC Sydney
Exhibition Centre, Level 1
Session
Sydney Poster Session 2
Authors
Sitong Wu, Haoru Tan, Bei Yu, Xiaojuan Qi, Jiaya Jia
Organisations
The Chinese University of Hong Kong, University of Hong Kong, Hong Kong University of Science and Technology
QRS classification
Reinforcement learning, Language models

Open in scheduleOfficial page