ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models
ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models
Deep Dive
Computer Science > Robotics arXiv:2609.13231 (cs) [Submitted on 2 Sep 2026] Title: ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Action Models Authors: Manan Tayal , Akshay Nambi View a PDF of the paper titled ShieldVLA: Feasibility-Aware Safety Alignment for Vision-Language-Acti