Robotics & physical AI Model or AI service
Unitree’s UnifoLM-WMA-0 links scene prediction with robot actions
Unitree’s UnifoLM-WMA-0 is a research system for predicting interactions between a robot and its surroundings and selecting movements for manipulation. [1]
- Model access
- Unitree publishes code on GitHub and links to separately hosted model checkpoints. [1]
What the model does
Unitree documents a world model that predicts interactions, and a decision mode for choosing actions. Its repository announced release of code and model weights in September 2025. [1]
Why it matters
Learning to predict what may happen after an action gives researchers another way to study robot control alongside direct action prediction. [1]
Key dates
- Unitree announced code and model weight release [1]
Ways to use it
Unitree documents separate checkpoints and configurations for research. Match the checkpoint to the robot and task before evaluating performance. [1]
Model limitations
Unitree’s examples use selected research platforms and tasks. Performance on other robots and in new environments requires validation. [1]
Sources and verification
Catalog evidence checked How we verify records
- Primary source Unitree’s UnifoLM world-model-action repository
Related profiles
Robotics & physical AI
Gemini Robotics 2.5
Google DeepMind
The models are intended to interpret a robot's surroundings and support compatible robot tasks.
Robotics & physical AI
NEURA 4NE1
NEURA Robotics
A humanoid platform NEURA presents for development and industrial training, with multiple distinct hardware generations.
Robotics & physical AI
LUMO all-terrain humanoid
Shenzhen Dobot (DOBOT)
LUMO is a humanoid robotics platform whose proposed applications include interaction and service tasks.