CalVLA paper proposes shaping native confidence in vision-language-action policies
A new arXiv paper introduces CalVLA, a method that shapes native action confidence in vision-language-action policies using outcome supervision, aiming to let policies signal likely task failure from their own action probabilities.
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-11-03 05:00 · arXiv cs.AI
CalVLA: Shaping Native Confidence in Vision-Language-Action Policies with Outcome Supervision