← Leaderboard

TrackVLA

VLA
Galbot & PKU · May 29, 2025

Vision-language-action model for embodied visual tracking of people and objects, not manipulation. None of the tracked benchmarks apply.

Type
VLA
Parameters
—
Backbone
–
Weights
Unknown
License
CC BY-NC-SA 4.0
Commercial use
Not allowed
Released
May 29, 2025
Robots
Quadruped (embodied visual tracking)
SO-101
–
LeRobot
–
Inputs
–
VRAM
–

Benchmark results

0 of 13 benchmarks

No benchmark results recorded yet.

Not reported on 13 benchmarks
Wrong or missing number? Report an error