Peking University · robot AI model
MM-Nav
China · 2025
Sources retrieved: 18 November 2026 (A, B)
- Model type
- Vision-language-action (VLA)Source and note: Model typeB pku-epic.github.io/MM-Nav-Web/ · Retrieved 18 November 2026Note. Developer wording: “a 7B multi-view VLA model for robust visual navigation with 360° observation and 7 Hz inference”.
- Inputs
- CameraSource and note: InputsA arxiv.org/abs/2510.03142 · Retrieved 18 November 2026Note. Paper abstract: “we implement the VLA model, MM-Nav, as a multi-view VLA (with 360 observations) based on pretrained large language models and visual foundation models”.
- Parameters
- 7BSource and note: ParametersB pku-epic.github.io/MM-Nav-Web/ · Retrieved 18 November 2026Note. Project page: “a 7B multi-view VLA model for robust visual navigation with 360° observation and 7 Hz inference”.

Specifications
5 of 14 stated 9 not stated
7 fields hidden 2 not-stated fields with a note stay ·
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
Input and output2/4 disclosed
Size and speed2/2 disclosed
Where it runs and what it is built on0/2 disclosed
Openness0/3 disclosed
The developer’s own claims0/2 disclosed
Notes
The project page (pku-epic.github.io) lists the affiliations “1 Peking University” and “2 Galbot”, and the venue “European Conference on Computer Vision (ECCV 2026)”. The page links the paper but no code or model weights.
Sources
One line per source, not per figure: a source has one retrieval date.
- Aarxiv.org/abs/2510.03142Retrieved 18 November 2026
- Bpku-epic.github.io/MM-Nav-Web/Main source. Retrieved 18 November 2026
More models
Same developer

LAWPeking University
- No photograph
LDA-1BPeking University
- No photograph
TrackVLAPeking University
- No photograph
TrackVLA++Peking University

Uni-NaVidPeking University

UrbanVLAPeking University




