Poster · Sydney
Extrapolative Weight Averaging Reveals Correctness–Efficiency Frontiers in Code RL
- 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
- Kunhao Zheng, Juliette Decugis, Pierre Chambon, Jonas Gehring, Taco Cohen, Benjamin Negrevergne, Gabriel Synnaeve
- Organisations
- Meta, École Normale Supérieure, Paris-Dauphine University - PSL
- QRS classification
- Reinforcement learning, Agentic AI