{"ID":2855333,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2510.13778","arxiv_id":"2510.13778","title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","abstract":"We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its core idea is spatially guided vision-language-action training, where spatial grounding serves as the critical link between instructions and robot actions. InternVLA-M1 employs a two-stage pipeline: (i) spatial grounding pre-training on over 2.3M spatial reasoning data to determine ``where to act'' by aligning instructions with visual, embodiment-agnostic positions, and (ii) spatially guided action post-training to decide ``how to act'' by generating embodiment-aware actions through plug-and-play spatial prompting. This spatially guided training recipe yields consistent gains: InternVLA-M1 outperforms its variant without spatial guidance by +14.6% on SimplerEnv Google Robot, +17% on WidowX, and +4.3% on LIBERO Franka, while demonstrating stronger spatial reasoning capability in box, point, and trace prediction. To further scale instruction following, we built a simulation engine to collect 244K generalizable pick-and-place episodes, enabling a 6.2% average improvement across 200 tasks and 3K+ objects. In real-world clustered pick-and-place, InternVLA-M1 improved by 7.3%, and with synthetic co-training, achieved +20.6% on unseen objects and novel configurations. Moreover, in long-horizon reasoning-intensive scenarios, it surpassed existing works by over 10%. These results highlight spatially guided training as a unifying principle for scalable and resilient generalist robots. Code and models are available at https://github.com/InternRobotics/InternVLA-M1.","short_abstract":"We introduce InternVLA-M1, a unified framework for spatial grounding and robot control that advances instruction-following robots toward scalable, general-purpose intelligence. Its core idea is spatially guided vision-language-action training, where spatial grounding serves as the critical link between instructions and...","url_abs":"https://arxiv.org/abs/2510.13778","url_pdf":"https://arxiv.org/pdf/2510.13778v1","authors":"[\"Xinyi Chen\",\"Yilun Chen\",\"Yanwei Fu\",\"Ning Gao\",\"Jiaya Jia\",\"Weiyang Jin\",\"Hao Li\",\"Yao Mu\",\"Jiangmiao Pang\",\"Yu Qiao\",\"Yang Tian\",\"Bin Wang\",\"Bolun Wang\",\"Fangjing Wang\",\"Hanqing Wang\",\"Tai Wang\",\"Ziqin Wang\",\"Xueyuan Wei\",\"Chao Wu\",\"Shuai Yang\",\"Jinhui Ye\",\"Junqiu Yu\",\"Jia Zeng\",\"Jingjing Zhang\",\"Jinyu Zhang\",\"Shi Zhang\",\"Feng Zheng\",\"Bowen Zhou\",\"Yangkun Zhu\"]","published":"2025-10-15T17:30:05Z","proceeding":"cs.RO","tasks":"[\"cs.RO\",\"cs.AI\",\"cs.CV\"]","methods":"[]","has_code":false,"code_links":[{"ID":608246,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_id":2855333,"paper_url":"https://arxiv.org/abs/2510.13778","paper_title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","repo_url":"https://github.com/InternRobotics/InternVLA-M1","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}