MuseVLA: An Adaptive Multimodal Sensing Vision-Language-Action Model for Robotic Manipulation
Humans naturally leverage diverse sensing modalities to interact with the physical world, while most Vision-Language-Action (VLA) models for robotics rely solely on RGB observations. This limits their ability to perceive physical properties that are difficult or impossible to infer from RGB cameras, such as temperature, sound, or radar response. We present MuseVLA, an adaptive multimodal sensing VLA model that integrates novel sensors as on-demand tools for robotic manipulation. Given a task instruction and visual context, MuseVLA first generates a sensor token and target description that select the sensing modality to invoke and what to attend to, analogous to a tool call with arguments....
| Authors | Xingyuming Liu, Ruichun Ma, Heyu Guo et al. |
|---|---|
| Primary category | cs.RO |
| Published | 16 June 2026 |
| Last updated at source | 12 August 2026 |
Connected in the knowledge graph
- microsoft/MuseVLA-datasetDataset · cited by
Models and datasets referencing this paper
- microsoft/MuseVLA-datasetDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.