← Leaderboard

OneTwoVLA

VLA
Tsinghua University · May 17, 2025 · built on π0

VLA from Tsinghua with Shanghai Qi Zhi and Spirit AI that switches adaptively between explicit reasoning and acting, built on π0. Results are self-reported on the authors’ real-robot tasks (87% average over three long-horizon tasks, 30 points above π0).

Type
VLA
Parameters
—
Backbone
–
Weights
Unknown
License
MIT
Commercial use
Unclear
Released
May 17, 2025
Robots
Franka, UMI
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