Compare

Peking University · robot AI model

Uni-NaVid

China · 2024

Sources retrieved: 18 November 2026 (A, B, C, D)

Model type
Vision-language-action (VLA)⁠
Inputs
Camera Language⁠
Access
Open weights (download)⁠
Parameters
7B⁠
Base model
Vicuna-7B⁠

Visit website

White quadruped robot with sensors on its back walking on a wooden deck beside a low brick wall

Specifications

8 of 14 stated 6 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

Released9 December 2024

Input and output2/4 disclosed

Model typeVision-language-action (VLA)
InputsCamera Language
What it controlsNot stated
Degrees of freedom controlledNot stated

Size and speed2/2 disclosed

Parameters7B
Control rateapproximately 5Hz

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

On robot or cloudNot stated
Base modelVicuna-7B

Openness1/3 disclosed

Licence documentNot stated
Licence typeNot stated

The developer’s own claims1/2 disclosed

Learns new tasksNeeds retraining
Works across robotsNot stated

Notes

The project page lists the institutions as “1 Peking University”, “2 GalBot” and Beijing Academy of Artificial Intelligence; the page is hosted by the pku-epic group and names Peking University first.

Sources

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

  1. Agithub.com/jzhzhang/Uni-NaVidRetrieved 18 November 2026
  2. Bpku-epic.github.io/Uni-NaVid/Main source. Retrieved 18 November 2026
  3. Chuggingface.co/api/models/Jzzhang/Uni-NaVidRetrieved 18 November 2026
  4. Darxiv.org/abs/2412.06224Retrieved 18 November 2026

Wrong or missing data? Tell us

More models

Same developer

Same model type