Compare

DeepCybo, Zhongguancun Academy & Zhongguancun Institute of AI · robot AI model

PhysBrain 1.5

China · 2026

Sources retrieved: 19 November 2026 (A, B)

What it controls
Arms and hands⁠
Inputs
Camera Language⁠
Access
Open weights (download)⁠
Parameters
8B⁠
Base model
Qwen3-VL-8B-Instruct⁠

Illustrative image — not this model

Specifications

7 of 14 stated 7 not stated

How to read the figuresShow guideClose
  • not statedNo source
  • yesStated by a source
  • 0Reported as zero
  • ASource

Select a source marker for source details and notes.

Release1/1 disclosed

Released14 September 2026

Input and output2/4 disclosed

Model typeNot stated
InputsCamera Language
What it controlsArms and hands
Degrees of freedom controlledNot stated

Size and speed1/2 disclosed

Parameters8B
Control rateNot stated

Where it runs and what it is built on1/2 disclosed

On robot or cloudNot stated
Base modelQwen3-VL-8B-Instruct

Openness1/3 disclosed

Licence documentNot stated
Licence typeNot stated

The developer’s own claims1/2 disclosed

Learns new tasksNot stated
Works across robotsYes

Notes

Developers describe PhysBrain 1.5: “PhysBrain 1.5 is an embodied vision-language model that unifies three core capabilities essential for physical interaction: **understanding** the observed world, **generating** goal-directed actions, and **predicting** how the environment will evolve.” (arXiv “[Submitted on 14 Sep 2026]”).

Sources

One line per source, not per figure: a source has one retrieval date.

  1. Ahuggingface.co/DeepCybo/PhysBrain1.5-8BMain source. Retrieved 19 November 2026
  2. Barxiv.org/abs/2609.14973Retrieved 19 November 2026

Wrong or missing data? Tell us