continuallearning's picture
Improve model card metadata and content (#1)
bd99809 verified
---
license: apache-2.0
library_name: lerobot
pipeline_tag: robotics
tags:
- robotics
- lerobot
---
# CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion
[**Paper**](https://huggingface.co/papers/2601.09512) | [**Project Page**](https://tum-lsy.github.io/clare/) | [**Code**](https://github.com/utiasDSL/clare)
DiT-Dec base checkpoint from "CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion", pretrained on LIBERO-90.
CLARE is a general, parameter-efficient framework for exemplar-free continual learning with Vision-Language-Action (VLA) models. It introduces lightweight modular adapters into selected feedforward layers and autonomously expands the model only where necessary when learning a new task, guided by layer-wise feature similarity. During deployment, an autoencoder-based routing mechanism dynamically activates the most relevant adapters without requiring task labels.
## BibTeX
```bibtex
@article{romer2026clare,
title={CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion},
author={Ralf R{\"o}mer and Yi Zhang and Angela P. Schoellig},
journal={arXiv preprint arXiv:2601.09512},
year={2026}
}
```