vla-safe/SAFE

RL²-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models

Official code for ForesightSafety-VLA (IROS 2026): a unified diagnostic safety benchmark for vision-language-action models on RoboTwin

[Arxiv] Vision-Language-Action Safety: Threats, Challenges, Evaluations, and Mechanisms

A Vision-Language-Model for Detecting and Reasoning Over Failures in Robotic Manipulation

A vision-language-safety action architecture, named AEGIS, which contains a plug-and-play safety constraint layer formulated via control barrier functions.

DeepThinkVLA: Enhancing Reasoning Capability of Vision-Language-Action Models

A Controlled Laboratory for Vision-Language-Action Policy Research

Official code for FoveaVLA: Foveation Actions Replace the Wrist Camera in VLAs