Research

Sparse Feature Policy Unlearning Mitigates State Hallucination in Vision-Language-Action Models

Single source1 source8 Oct 2026

arXiv:2610.09496v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by leveraging rich representations from pretrained vision-language models.

Reported by 1 source

arxiv.orghttps://arxiv.org/abs/2610.09496

← Back to all developments · Signals are a development reported by more than one source. See the methodology.