| 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} | |
| } | |
| ``` |