THU-RCSCT/vlsa-aegis

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

Official code for AffordanceVLA: Empowering Action Generation through Affordance-Aware Understanding.

✨✨Official implementation of BridgeVLA and BridgeVLA++

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

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

Official implementation for BitVLA: 1-bit Vision-Language-Action Models for Robotics Manipulation (CoRL 2026, Spotlight)

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

Evo-1: Lightweight Vision-Language-Action Model with Preserved Semantic Alignment

REKI: a 2.4B vision-language-action model pretrained on public data only, with a memory of its recent past at negligible cost.