← Leaderboard

UP-VLA

VLA
Tsinghua University · Jan 31, 2025

Unified understanding-and-prediction VLA that is trained to predict future images as well as actions. A CALVIN checkpoint is released; the repo has no license file.

Type
VLA
Parameters
—
Backbone
Show-o (Phi-1.5)
Weights
Open
License
–
Commercial use
Unclear
Released
Jan 31, 2025
Robots
Franka Panda, Franka Panda (sim)
SO-101
–
LeRobot
–
Inputs
–
VRAM
–

Benchmark results

1 of 13 benchmarks
CALVIN ABC→DNear saturationSimulation
#14 of 244.08 / 5, self-reported by the authors, not a leaderboard entry
Not reported on 12 benchmarks
Wrong or missing number? Report an error