SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915318365945856 |
|---|---|
| author | Shukor, Mustafa Aubakirova, Dana Capuano, Francesco Kooijmans, Pepijn Palma, Steven Zouitine, Adil Aractingi, Michel Pascal, Caroline Russi, Martino Marafioti, Andres Alibert, Simon Cord, Matthieu Wolf, Thomas Cadene, Remi |
| author_facet | Shukor, Mustafa Aubakirova, Dana Capuano, Francesco Kooijmans, Pepijn Palma, Steven Zouitine, Adil Aractingi, Michel Pascal, Caroline Russi, Martino Marafioti, Andres Alibert, Simon Cord, Matthieu Wolf, Thomas Cadene, Remi |
| contents | Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches adapt VLMs into vision-language-action (VLA) models that enable natural language-driven perception and control. However, existing VLAs are typically massive--often with billions of parameters--leading to high training costs and limited real-world deployability. Moreover, they rely on academic and industrial datasets, overlooking the growing availability of community-collected data from affordable robotic platforms. In this work, we present SmolVLA, a small, efficient, and community-driven VLA that drastically reduces both training and inference costs, while retaining competitive performance. SmolVLA is designed to be trained on a single GPU and deployed on consumer-grade GPUs or even CPUs. To further improve responsiveness, we introduce an asynchronous inference stack decoupling perception and action prediction from action execution, allowing higher control rates with chunked action generation. Despite its compact size, SmolVLA achieves performance comparable to VLAs that are 10x larger. We evaluate SmolVLA on a range of both simulated as well as real-world robotic benchmarks and release all code, pretrained models, and training data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01844 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics Shukor, Mustafa Aubakirova, Dana Capuano, Francesco Kooijmans, Pepijn Palma, Steven Zouitine, Adil Aractingi, Michel Pascal, Caroline Russi, Martino Marafioti, Andres Alibert, Simon Cord, Matthieu Wolf, Thomas Cadene, Remi Machine Learning Robotics Vision-language models (VLMs) pretrained on large-scale multimodal datasets encode rich visual and linguistic knowledge, making them a strong foundation for robotics. Rather than training robotic policies from scratch, recent approaches adapt VLMs into vision-language-action (VLA) models that enable natural language-driven perception and control. However, existing VLAs are typically massive--often with billions of parameters--leading to high training costs and limited real-world deployability. Moreover, they rely on academic and industrial datasets, overlooking the growing availability of community-collected data from affordable robotic platforms. In this work, we present SmolVLA, a small, efficient, and community-driven VLA that drastically reduces both training and inference costs, while retaining competitive performance. SmolVLA is designed to be trained on a single GPU and deployed on consumer-grade GPUs or even CPUs. To further improve responsiveness, we introduce an asynchronous inference stack decoupling perception and action prediction from action execution, allowing higher control rates with chunked action generation. Despite its compact size, SmolVLA achieves performance comparable to VLAs that are 10x larger. We evaluate SmolVLA on a range of both simulated as well as real-world robotic benchmarks and release all code, pretrained models, and training data. |
| title | SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Robotics |
| topic | Machine Learning Robotics |
| url | https://arxiv.org/abs/2506.01844 |