{"ID":2857162,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.10274","arxiv_id":"2510.10274","title":"X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Model","abstract":"Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich, diverse robotic data sources, we propose a novel Soft Prompt approach with minimally added parameters, by infusing prompt learning concepts into cross-embodiment robot learning and introducing separate sets of learnable embeddings for each distinct data source. These embeddings serve as embodiment-specific prompts, which in unity empower VLA models with effective exploitation of varying cross-embodiment features. Our new X-VLA, a neat flow-matching-based VLA architecture, relies exclusively on soft-prompted standard Transformer encoders, enjoying both scalability and simplicity. Evaluated across 6 simulations as well as 3 real-world robots, our 0.9B instantiation-X-VLA-0.9B simultaneously achieves SOTA performance over a sweep of benchmarks, demonstrating superior results on a wide axes of capabilities, from flexible dexterity to quick adaptation across embodiments, environments, and tasks. Website: https://thu-air-dream.github.io/X-VLA/","short_abstract":"Successful generalist Vision-Language-Action (VLA) models rely on effective training across diverse robotic platforms with large-scale, cross-embodiment, heterogeneous datasets. To facilitate and leverage the heterogeneity in rich, diverse robotic data sources, we propose a novel Soft Prompt approach with minimally add...","url_abs":"https://arxiv.org/abs/2510.10274","url_pdf":"https://arxiv.org/pdf/2510.10274v1","authors":"[\"Jinliang Zheng\",\"Jianxiong Li\",\"Zhihao Wang\",\"Dongxiu Liu\",\"Xirui Kang\",\"Yuchun Feng\",\"Yinan Zheng\",\"Jiayin Zou\",\"Yilun Chen\",\"Jia Zeng\",\"Ya-Qin Zhang\",\"Jiangmiao Pang\",\"Jingjing Liu\",\"Tai Wang\",\"Xianyuan Zhan\"]","published":"2025-10-11T16:20:17Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.CV\"]","methods":"[\"Transformer\"]","has_code":false}