Repository
Research
Diffusion Policy
A visuomotor policy approach using diffusion to generate robot actions.
Robot policies
Models / Research
genrl · mazpie
GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can…
Overview
GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can…
Publisher purpose: [NeurIPS 2024] GenRL: Multimodal-foundation world models enable grounding language and video prompts into embodied domains, by turning them into sequences of latent world model states. Latent state sequences can be decoded using the decoder of the model, allowing visualization of the expected behavior, before training the agent to execute it.
Review observation/action interfaces, checkpoints, robot embodiments and adaptation requirements. Repository code licensing does not automatically license weights or training data.
Project information
- Maintainer
- mazpie
- Primary language
- Python
- Repository code license
- MIT
- Model-weight license
- Not recorded
- Dataset license
- Not recorded
- Hardware design license
- Not recorded
- Maintenance
- Not archived in the last recorded metadata
- Last observed repository push
- 2025-04-04
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Documentation sections
- GenRL: Multimodal-foundation world models for generalization in embodied agents
- 📰 Updates
- Get started
- Creating the environment
- Downloading InternVideo2
- Data
Browse this resource’s categories
Explore related collections
Browse Models →More in Models
Repository
Research
Website
Research
openpi
Code and model resources for Physical Intelligence robot policies.
Vision-language-action
Repository
Research
NVIDIA Isaac GR00T
Robot foundation-model resources for humanoid learning workflows.
Vision-language-action
Repository
Research
Octo
A generalist robot policy framework for adapting across manipulation tasks.
Robot policies
Repository
Research
alpamayo1.5 · NVlabs
NVIDIA Alpamayo 1.5 Nano is an open 10B reasoning VLA model for autonomous vehicles with reinforcement-learning enhanced reasoning, navigation guidance, and visual question answering.
Vision-language-action
Repository
Research
iros20 6d pose tracking · wenbowen123
se(3)-TrackNet provides 6D object-pose tracking research and visual-feedback-control examples.
Perception models