RoboAtlas
EN
← X-VLA

X-VLA Team

X-VLA 0.9B

X-VLA 0.9B

Checkpoint

Soft-prompted flow-matching VLA trained across robot embodiments.

Specifications

Architecture components
Flow-matching action expert
Source · lerobot
Architecture components
Embodiment soft prompts
Source · lerobot
Backbone
Florence-2 vision-language backbone with soft prompts and flow matching
Source · lerobot
Frameworks
LeRobot / PyTorch
Source · lerobot
Input modalities
Language instruction
Source · lerobot
Input modalities
RGB camera images
Source · lerobot
Input modalities
Robot state / proprioception
Source · lerobot
Languages
English
Source · lerobot
Model type
Vision-language-action model
Source · lerobot
Output action space
Continuous action chunks up to 20 dimensions
Source · lerobot
Parameter count
0.9B parameters
Source · lerobot
Pipeline task
Robotics
Source · lerobot
Training data scale
290K episodes
Source · X-VLA authors

Lineage

Unknown

Architecture & I/O

trajectory · continuous

Unknown

Continuous action chunks up to 20 dimensions

Source · lerobot

Default checkpoint

lerobot/xvla-base

openApache License 2.0
Checkpoint

Other releases

6

published checkpoints

lerobot/xvla-baselerobot/xvla-agibot-worldlerobot/xvla-foldinglerobot/xvla-google-robotlerobot/xvla-liberolerobot/xvla-widowx

Supported robots

No verified robot compatibility recorded.

Benchmark results

No published benchmark results.

Deployment

Training data

Resources

documentation · LeRobot X-VLA documentationpaper · X-VLA paperrepository · X-VLA repositoryweights · lerobot/xvla-base model card
Submit info