Join our WeChat Group
The main features of agibottech/genie-envisioner are: Embodied Foundation Models.
Open-source alternatives to agibottech/genie-envisioner include: amap-cvlab/abot-manipulation — ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning. arashakb/actquant — Official implementation of ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models. beingbeyond/being-h — Being-H is BeingBeyond's family of human-centric embodied foundation models. beingbeyond/being-h0 — Being-H0: Vision-Language-Action Pretraining from Large-Scale Human Videos (ICML 2026). buoyancy99/large-video-planner — This repo provides training and inference code for the paper "Large Video Planner Enables Generalizable Robot Control". alibaba-damo-academy/worldvla — RynnVLA-002: A Unified Vision-Language-Action and World Model.
ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learning
Official implementation of ActQuant: Sub-4-bit Action-Guided Quantization for Vision-Language-Action Models
Being-H is BeingBeyond's family of human-centric embodied foundation models.
RynnVLA-002: A Unified Vision-Language-Action and World Model