published index · updated 2026-11-05
Filter published records by access, signals, readiness, and adoption. Missing evidence remains visible.
Source-backed datasets and models.
Google DeepMind / Open X-Embodiment collaboration · 2023-10-13
A large multi-institution collection spanning 22 robot embodiments and hundreds of skills for cross-robot policy learning.
22 robots
48% confidence · verified 2026-10-08
5 linked models
Hugging Face · ropedia-ai/xperience-10m · 2026-03-11
A large egocentric multimodal dataset with synchronized video streams, audio, depth, poses, mocap, IMU, and hierarchical language annotations.
10M experiences
48% confidence · verified 2026-10-08
2 linked models
RoboMIND collaboration · 2024-12-18
A unified multi-embodiment manipulation dataset with successful demonstrations, real-world failures, and failure causes.
107K trajectories
43% confidence · verified 2026-10-08
1 linked models
Hugging Face · builddotai/Egocentric-10K-Evaluation · 2025-11-10
An Apache-2.0 evaluation dataset for measuring hand presence and active object manipulation in first-person industrial frames.
30K samples
35% confidence · verified 2026-10-26
Robbyant · 2026-03-21
A roughly three-million-sample mixture of real indoor, robot-manipulation, and simulated RGB-D data used by LingBot-Depth.
3.0M samples
30% confidence · verified 2026-10-26
IPEC-COMMUNITY / EO-Robotics · 2025-08-28
A large multimodal corpus combining vision, text, embodied reasoning, and action supervision for EO-1 pretraining.
1.5M samples
37% confidence · verified 2026-10-26
1 linked models
RoboTwin Platform · 2024-09-18
A configurable dual-arm data generator and benchmark with strong domain randomization, pre-collected trajectories, and LeRobot integration.
100K+ trajectories
48% confidence · verified 2026-10-26
1 linked models
Hugging Face · Luel-ai/Ego-Realm · 2026
A compact Pineye-camera video set covering horticulture, kitchen, and laundry clips for quick first-person manipulation experiments.
108 clips
35% confidence
X Square Robot · 2026-05-29
An open 4B VLA pretrained across more than 20 embodiments, with physical-hardware evaluation of pretrained robotic capability.
1.5K downloads
63% confidence · verified 2026-10-08
3 linked datasets
Hugging Face LeRobot · 2025-06-03
Compact open vision-language-action policy designed for practical robot fine-tuning and deployment through the LeRobot ecosystem.
113.8K downloads
63% confidence · verified 2026-10-08
3 linked datasets
Shanghai AI Laboratory / collaborators · 2025-01-27
A spatially enhanced 4B VLA pretrained on 1.1 million real-robot episodes with explicit geometry-aware representations.
960 downloads
63% confidence · verified 2026-10-08
3 linked datasets
IPEC / EO-Robotics · 2025-08-28
A unified embodied model using interleaved vision-text-action pretraining for perception, reasoning, planning, and continuous robot control.
147 downloads
63% confidence · verified 2026-10-08
3 linked datasets
Robotics Diffusion Transformer research · 2024-10-10
Diffusion foundation model for bimanual manipulation that uses large-scale robot data to generate action trajectories.
362 downloads
63% confidence · verified 2026-10-08
3 linked datasets
Robbyant · 2026-07-07
A whole-body VLA release focused on broader cross-embodiment transfer, mobile manipulation, and predictive dynamics supervision.
Code · Weights
53% confidence · verified 2026-10-08
3 linked datasets
NVIDIA · 2025-03-18
Open foundation model for generalist humanoid robots, focused on whole-body and manipulation behavior from multimodal robot data.
438 downloads
63% confidence · verified 2026-10-08
3 linked datasets
Octo Model Team · 2024-05-20
Open-source generalist robot policy pretrained on Open X-Embodiment trajectories and designed for fine-tuning to new robots and tasks.
328 downloads
51% confidence · verified 2026-10-08
3 linked datasets
OpenGalaxea · 2025-09-09
A dual-system VLM plus VLA model for planning and fine-grained control on long-horizon mobile-manipulation tasks.
0 downloads
63% confidence · verified 2026-10-08
3 linked datasets
Physical Intelligence · 2024-10-21
Generalist robot policy family and open-source robotics model package from Physical Intelligence.
Code · Weights
63% confidence · verified 2026-10-26
3 linked datasets
Physical Intelligence · 2025
A VLA model designed for open-world generalization by combining heterogeneous robot data, semantic subtask prediction, and high-level knowledge transfer.
Artifacts not listed
23% confidence · verified 2026-10-14
3 linked datasets
Google DeepMind · 2023-07-28
Vision-language-action model that transfers web-scale vision-language knowledge into robotic control.
Artifacts not listed
23% confidence · verified 2026-10-08
3 linked datasets
ALOHA / LeRobot ecosystem · 2023-04-23
Action Chunking with Transformers predicts short action sequences for efficient imitation learning in manipulation tasks.
Weights · Checkpoint
63% confidence · verified 2026-10-26
3 linked datasets
NVIDIA · 2026-02-25
NVIDIA's current open humanoid VLA release within an end-to-end Isaac workflow for teleoperation, training, evaluation, and deployment.
Weights · Checkpoint
63% confidence · verified 2026-10-26
3 linked datasets
Columbia / Toyota Research Institute / collaborators · 2023-03-07
Visuomotor policy approach that represents robot behavior as a conditional denoising diffusion process.
Weights · Checkpoint
63% confidence · verified 2026-10-26
3 linked datasets
NVIDIA · 2025-01-07
World foundation model platform for physical AI, built around predictive world modeling and data processing workflows.
Weights · Checkpoint
52% confidence · verified 2026-10-26
3 linked datasets
