Poster · Sydney
Two is better than one: A Collapse-free Multi-Reward RLIF Training Framework
- When
- Thu 10 Dec 2026, 10:00–13:00 AEDT
- Where
- Hall 1-4, ICC Sydney
Exhibition Centre, Level 1 - Session
- Sydney Poster Session 5
- Authors
- Shourov Joarder, Diganta Sikdar, Ahsan H Akash, Binod Bhattarai, Prashnna K Gyawali
- Organisations
- University of Texas at Austin, Bangladesh University of Engineering and Technology, West Virginia University, University of Aberdeen
- QRS classification
- Reinforcement learning