intuitive-robots/MoDE_Diffusion_Policy

[ICLR 25] Code for "Efficient Diffusion Transformer Policies with Mixture of Expert Denoisers for Multitask Learning"

43
/ 100
Emerging

This project offers a method for training robotic agents to perform a variety of tasks more efficiently and accurately. By taking in diverse robotic demonstration datasets, it outputs policies that enable robots to execute complex sequences of actions with high success rates. This is primarily useful for robotics researchers and engineers who develop and deploy advanced robotic systems for automation and manipulation.

117 stars. No commits in the last 6 months.

Use this if you need to train a robotic agent to learn multiple complex manipulation skills from various demonstration datasets and achieve high performance across these tasks.

Not ideal if you are looking for a simple, out-of-the-box solution for basic robot control or if you do not have access to diverse robot demonstration data.

robotics-research robot-learning robotic-manipulation multitask-learning automation-engineering
Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 15 / 25

How are scores calculated?

Stars

117

Forks

16

Language

C++

License

MIT

Last pushed

May 16, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/intuitive-robots/MoDE_Diffusion_Policy"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.