Poster · Sydney
ExpRFT: Exponential Reward-Weighted Fine-Tuning for Offline RL in Multi-Turn Dialogue
- 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
- Huy Dao, Lizi Liao
- Organisations
- Singapore Management University
- QRS classification
- Reinforcement learning, Language models