ModelFeatured
π0 (pi0)
Physical Intelligence generalist robot foundation model with flow-matching action generation.
ModelFeaturedFully open
RDT-1B
Diffusion foundation model for bimanual skill, trained with AgiBot and public data.
Why: Leading open bimanual diffusion policy
Overview
RDT-1B (Robotics Diffusion Transformer) is a diffusion-based generalist policy around the 1B scale, aiming at scalable imitation across tasks and embodiments. It sits between compact policies like Octo and larger VLM-style VLAs.
Consider RDT when you want diffusion action modeling with more capacity than classic DP, while remaining in an open research release format.
Who it is for
Researchers studying diffusion generalist policies at ~1B scale.
Key highlights
- ~1B diffusion transformer policy
- Generalist imitation focus
- Open research release
When to use
- Scaling studies for diffusion policies
- Multi-task imitation with moderate compute
When not to use
- Ultra-low-latency control without distillation
Getting started
- 1Read the paper + model card
- 2Run provided inference
- 3Finetune on a single domain first
Papers & reading
How it compares
Caveats & pitfalls
- Diffusion inference cost still applies.
Content reviewed 2026-07-23