Website
Research
Segment Anything
Image segmentation models that can support robotic perception pipelines.
Perception models
Models / Research
theia · rai-opensource
Theia: Distilling Diverse Vision Foundation Models for Robot Learning
Overview
Theia: Distilling Diverse Vision Foundation Models for Robot Learning
Inspect installation instructions, supported versions, examples and interfaces in the source. This directory does not claim the software has been installed or tested on your robot.
Project information
- Maintainer
- rai-opensource
- Primary language
- Python
- Repository code license
- Not specified
- 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
- 2025-11-06
Code licenses do not automatically cover model weights, datasets or hardware designs. Unrecorded license details require confirmation with the publisher.
Documentation sections
- Quick Start: Use Pre-trained Theia Models
- Theia / intermediate feature, mainly used for robot learning.
- To change different feature reduction methods, pass `feature_reduction_method` argument in AutoModel.from_pretrained() method
- predicted_features is dict[str, torch.Tensor] where each kv pair is target model name and predicted feature
- they are predicted features that tries to match teacher model features.
- Installation
Browse this resource’s categories
Explore related collections
Browse Models →More in Models
Website
Research