Compare

Peking University · robot AI model

ViGAR

China · 2026

Sources retrieved: 19 November 2026 (A, B, C)

Model type
World action model⁠
What it controls
Arms and hands⁠
Inputs
Camera Language⁠
Access
Open weights (download)⁠
Base model
Cosmos3-Nano⁠
Licence document
OpenMDW-1.1⁠

Visit website

Silver AgiBot robot with two robot hands above a table with a stamp, a wooden block and a sheet of paper, seen from the front from the shoulders down

Specifications

7 of 14 stated 7 not stated

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

Released1 October 2026

Input and output3/4 disclosed

Model typeWorld action model
InputsCamera Language
What it controlsArms and hands
Degrees of freedom controlledNot stated

Size and speed0/2 disclosed

ParametersNot stated
Control rateNot stated

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

On robot or cloudNot stated
Base modelCosmos3-Nano

Openness2/3 disclosed

Licence documentOpenMDW-1.1
Licence typeNot stated

The developer’s own claims0/2 disclosed

Learns new tasksNot stated
Works across robotsNot stated

Notes

Developed by researchers from Peking University, AgiBot, and CocoMatrix.

Described by the authors as “We propose Visual Goal-conditioned Action Reasoning (ViGAR), a hierarchical framework that factorizes manipulation into a visual subgoal planner and a subgoal executor.”

Sources

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

  1. Aarxiv.org/abs/2610.02368Retrieved 19 November 2026
  2. Bdagroup-pku.github.io/ViGAR/Main source. Retrieved 19 November 2026
  3. Chuggingface.co/DAGroup-PKU/ViGARRetrieved 19 November 2026

Wrong or missing data? Tell us

More models

Same developer

Same model type