Peking University · robot AI model
TrackVLA++
China · 2025
Runs on Go2 by Unitree RoboticsSource and note: Go2B arxiv.org/html/2510.07134 · Retrieved 18 November 2026
Sources retrieved: 18 November 2026 (A, B, C)
- Model type
- Vision-language-action (VLA)Source and note: Model typeA pku-epic.github.io/TrackVLA-plus-plus-Web/ · Retrieved 18 November 2026Note. Project page: “TrackVLA++ is a novel Vision-Language-Action model that incorporates spatial reasoning and target identification memory”
- Inputs
- Camera LanguageSource and note: InputsA pku-epic.github.io/TrackVLA-plus-plus-Web/ · Retrieved 18 November 2026Note. Project page: “Given a video stream and a language instruction, TrackVLA++ predicts a tracking trajectory”.
- Base model
- NavFoMSource and note: Base modelB arxiv.org/html/2510.07134 · Retrieved 18 November 2026Note. Technical report: “TrackVLA++ is built upon NavFoM”.

Specifications
5 of 14 stated 9 not stated
5 fields hidden 4 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 speed1/2 disclosed
Where it runs and what it is built on1/2 disclosed
Openness0/3 disclosed
The developer’s own claims0/2 disclosed
Notes
The project page lists the institutions as “1 Peking University 2 GalBot 3 USTC 4 BAAI 5 Beihang University 6 SUSTech 7 Beijing Normal University”.
Sources
One line per source, not per figure: a source has one retrieval date.
- Apku-epic.github.io/TrackVLA-plus-plus-Web/Main source. Retrieved 18 November 2026
- Barxiv.org/html/2510.07134Retrieved 18 November 2026
- Carxiv.org/abs/2510.07134Retrieved 18 November 2026
More models
Same developer

LAWPeking University
- No photograph
LDA-1BPeking University
- No photograph
MM-NavPeking University
- No photograph
TrackVLAPeking University

Uni-NaVidPeking University

UrbanVLAPeking University




