Poster · Sydney
Gradient Routing Localizes and Removes Unintended Behaviors in 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
- Jake Ward, Shawn Hu, Aria Wong, Nathan Hu, Bryce Woodworth, Alexander Turner, Alex Cloud
- Organisations
- D_Model, ML, Alignment Theory Scholars, Stanford University, MATS Research, Google DeepMind, Anthropic
- QRS classification
- Reinforcement learning, Language models