LeRobot SARM
Video reward model that predicts task stage and within-stage progress.
Research, evaluation and robot-specific training of SARM robot policies.
Access and availability
Training / fine-tuning code
- Access
- Public access
Verified on · 2026-10-27
- Code license
- Apache-2.0 (LeRobot implementation)
Release information
SourceVerified on · 2026-10-23
Getting started
- Runtime and frameworks
- LeRobot / PyTorch
- Fine-tuning requirements
- LeRobot integration: use the linked policy-specific setup and training instructions; compatibility with every upstream checkpoint is not implied.
At a glance
- Model type
- Reward model
- Backbone
- Video encoder with stage and progress prediction heads
- Input
- Language instruction / RGB camera images
Technical details
Languages
English
Functional purpose
Reward & progress
Pipeline task
Robot reward modeling
Prediction output
Task stage and normalized progress score
Before you use this version: Requires task- and embodiment-specific data, configuration and validation. Published examples and simulated results do not establish safe operation on a physical robot. Available weights or code do not establish plug-and-play robot compatibility. Check the required configuration, data and interfaces in the source documentation.
Submit a source or correction