← Leaderboard

Dita

Policy
Shanghai AI Lab · Mar 25, 2025

Scalable diffusion-transformer generalist policy from Shanghai AI Lab with CUHK MMLab, PKU and SenseTime that denoises actions in-context with visual tokens. It reports LIBERO and CALVIN results.

Type
Policy
Parameters
—
Backbone
Diffusion transformer
Weights
Open
License
Apache-2.0
Commercial use
Allowed
Released
Mar 25, 2025
Robots
Franka, Franka Panda (sim)
SO-101
–
LeRobot
–
Inputs
–
VRAM
–

Benchmark results

2 of 13 benchmarks
CALVIN ABC→DNear saturationSimulation
#19 of 243.61 / 5, self-reported by the authors, not a leaderboard entry
LIBEROSaturatedSimulation
#63 of 7082.4%, self-reported by the authors, not a leaderboard entry
Not reported on 11 benchmarks
Wrong or missing number? Report an error