tuotuoLyu/ForesightSafety-VLA

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

Open source evals for physical AI. Run any LLM/VLA on any arm/humanoid against any real/sim benchmark.

OopsieVerse provides a damage-aware, simulator-agnostic framework and benchmark for evaluating and learning safer policies

One framework to evaluate any VLA model on any robot simulation benchmark.

This is the official repository for "SAFE: Multitask Failure Detection for Vision-Language-Action Models" (NeurIPS 2025)

Code for "Evaluating Robot Policies in a World Model".

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

[ICML2026] VLAC: A Vision-Language-Action-Critic Model for Robotic Real-World Reinforcement Learning