Article

DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling

DiVeR estimates decision criticality from the dispersion of sampled action representations and uses it to reweight verifier learning, focusing learning on states where action selection matters most, without requiring step-level annotations or additional environment interaction. In experiments on LIBERO, RoboCasa, and a Franka Research 3 real robot, DiVeR consistently improves task success rates by guiding action selection with a more effective verifier, and verifier inference overhead is negligible.

Part of the event: DiVeR: Reweighting VLA Verifiers with Decision Criticality

This page provides a summary and source link only.