Poster · Sydney
Hearing the Unspoken: Simulator-Induced Asymmetric-View Policy Optimization for Proactive Task-Oriented Dialogue
- 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
- Hongbin Zhang, Ning Gao, Yuqin Dai, Ruiyuan Wu, Jinpeng Wang, Rena Gao, Bingdong Tan, Shuzheng Gao, Chaozheng Wang
- Organisations
- Harbin Institute of Technology, Beihang University, Tsinghua University, Meituan, ByteDance, Hong Kong Baptist University, The Chinese University of Hong Kong
- QRS classification
- Reinforcement learning, Language models