Website
THE EMBODIED AI DIRECTORY
Models
Explore vision-language-action models and robotics foundation models for perception, manipulation and control.
Website
Repository
Research
Uni-NaVid · jzhzhang
Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks.
Vision-language-action
Repository
Repository
Research
VoxPoser
Language-guided 3D value-map planning for robot manipulation.
Language-guided planning
Repository
Research
Being H · BeingBeyond
Being-H is BeingBeyond's family of human-centric embodied foundation models.
Robot policies
Repository
Research
Hy-Embodied-0.5-VLA · Tencent-Hunyuan
From Vision-Language-Action Models to a Real-World Robot Learning Stack
Vision-language-action
Repository
Research
vla0 · NVlabs
VLA-0 provides research code for building vision-language-action models from vision-language models.
Vision-language-action
Repository
Research
EasyWAM · OpenMOSS
A unified framework for training, fine-tuning, and evaluating World Action Models
World models
Repository
Research
TesserAct · UMass-Embodied-AGI
ICCV 2025 | TesserAct: Learning 4D Embodied World Models
World models
Repository
Research
GreenVLA · greenvla
Green-VLA: Staged Vision-Language-Action Model for Generalist Robots
Vision-language-action
Repository
Research
RISE · OpenDriveLab
Code for RISE: Self-Improving Robot Policy with Compositional World Model
World models
Repository
Research
VLA RFT · OpenHelix-Team
VLA-RFT provides reinforcement fine-tuning resources for vision-language-action models.
Vision-language-action
Repository
Research
egosteer · egosteer
A world-model-enhanced VLA for steerable dexterous manipulation, along with optimized training infra.
World models
Repository
Research
GraspNet Baseline
A baseline implementation for grasp detection from point-cloud data.
Grasping models
Repository
Research
robotic_world_model_lite · leggedrobotics
Lightweight implementation of Robotic World Model (RWM) and Uncertainty-Aware Robotic World Model (RWM-U)
World models
Repository
Research
WholebodyVLA · OpenDriveLab
WholebodyVLA studies latent VLA representations for whole-body locomotion and manipulation.
Vision-language-action
Repository
Research
3D CovDiffusion · crystalccy1
3D-CovDiffusion implements a 3D-aware diffusion policy for coverage path planning.
Robot policies
Repository
Research
ACE-Brain-0 · DAXIAORobotics
The official repository of the first version of ACE-Brain foundation model.
Vision-language-action
Repository
Research
ACoT-VLA-WM · alexantaluo0
ACOT-VLA-WM is an advanced Vision-Language-Action robotics framework that uses a predictive world model to generate visual subgoals, improving long-horizon robotic manipulation accuracy and…
World models
Repository
Repository
Research
ALMI-Open · TeleHuman
Official Code for "Adversarial Locomotion and Motion Imitation for Humanoid Policy Learning"
Robot policies
Repository
Research
Anchor Align · dwipddalal
Anchor-Align studies VLA fine-tuning with representation anchoring and language-action alignment.
Vision-language-action
Repository
Research
AnyLoc · AnyLoc
AnyLoc provides visual place-recognition research code for localization.
Perception models
Repository
A PLACE FOR YOUR NEXT DISCOVERY
Suggest a resource ↗The ecosystem keeps growing.
Know a resource that belongs here?