Skip to content
NeurIPS 2026 planner

Poster · Sydney

From Outcome to Representation: Tracing Reasoning Mechanisms through Integrated Policy Gradient

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
Changming Li, Kaixing Zhang, Yingdong Shi, Haoyun Xu, Zheng Zhang, Kaitao Song, Kan Ren
Organisations
ShanghaiTech University, Beijing Institute for General Artificial Intelligence, Apple
QRS classification
Reinforcement learning, Language models, Safety, fairness and privacy

Open in scheduleOfficial page