BAAI · robot AI model
Physis-v0.1
China · 2026
Sources retrieved: 19 November 2026 (A)
- Model type
- World modelSource and note: Model typeA hub.baai.ac.cn/view/55509 · Retrieved 19 November 2026Note. BAAI Hub describes Physis-v0.1 as a general world foundation model.
- Inputs
- Camera Depth TouchSource and note: InputsA hub.baai.ac.cn/view/55509 · Retrieved 19 November 2026Note. The BAAI Hub report states that the physical state encoder takes video, depth RGB, 3D point clouds, and force-tactile feedback.

Specifications
3 of 14 stated 11 not stated
10 fields hidden 1 not-stated field with a note stays ·
How to read the figuresShow guideClose
- not statedNo source
- 0Reported as zero
- ASource
Select a source marker for source details and notes.
Release1/1 disclosed
Released14 June 2026
Source and note: ReleasedA hub.baai.ac.cn/view/55509 · Retrieved 19 November 2026
Input and output2/4 disclosed
Model typeWorld model
Source and note: Model typeA hub.baai.ac.cn/view/55509 · Retrieved 19 November 2026Note. BAAI Hub describes Physis-v0.1 as a general world foundation model.
InputsCamera Depth Touch
Source and note: InputsA hub.baai.ac.cn/view/55509 · Retrieved 19 November 2026Note. The BAAI Hub report states that the physical state encoder takes video, depth RGB, 3D point clouds, and force-tactile feedback.
What it controlsNot stated
Degrees of freedom controlledNot stated
Size and speed0/2 disclosed
ParametersNot stated
Control rateNot stated
Where it runs and what it is built on0/2 disclosed
On robot or cloudNot stated
Base modelNot stated
Openness0/3 disclosed
AccessNot stated
Licence documentNot stated
Licence typeNot stated
The developer’s own claims0/2 disclosed
Learns new tasksNot stated
Works across robotsNot stated
Source and note: Works across robotsYes only if the developer itself says the model runs on different robot models, for example robots from two manufacturers or two of one manufacturer’s models. Several units of the same robot do not count.
Notes
BAAI presented Physis-v0.1 at the 2026 BAAI Conference as a general world foundation model for physical AI.
Sources
One line per source, not per figure: a source has one retrieval date.
- Ahub.baai.ac.cn/view/55509Main source. Retrieved 19 November 2026




