SARM2 + SPIRAL: Multi-Task Reward Models and RL Refinement for Long-Horizon Dexterous Manipulation
Combines scalable autonomous reward modeling with RL-based refinement to improve vision-language-action policies on long-horizon dexterous manipulation tasks via autonomous rollouts. Demonstrates significant gains over imitation learning baselines.
The skinny
The skinny isn't ready yet — notes appear once the transcript is processed.