MINT-SJTU

Evo-RL. We release Evo-RL, the opensource real-world offline RL on So-101 and AgileX PiPER for easier reproduction.

RoboClaw. RoboClaw is an Embodied AI Assistant.

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

LeRobot-Anything-U-Arm. U-Arm: Lerobot-Everything-Cross-Embodiment-Teleoperation

Evo-SOTA.io. This website is for the collection of VLA SOTA results.

VLA-Pruner. The official implementation of VLA-Pruner: Temporal-Aware Dual-Level Visual Token Pruning for Efficient Vision-Language-Action Inference.

Evo-Depth. Python

Evo-0. Evo-0: Vision-Language-Action Model with Implicit Spatial Understanding.

RoboFAC. RoboFAC: A Comprehensive Framework for Robotic Failure Analysis and Correction

STI-Bench. STI-Bench : Are MLLMs Ready for Precise Spatial-Temporal World Understanding?

LA4VLA. Python

EgoGrasp.

Evo-RLT. Python

RoboFAC.io. JavaScript

Evo-1.io. JavaScript

Evo-temp.io. Python