{"work":{"id":"8a11d29e-4bf8-4a9c-a97e-d87e7350dd9c","openalex_id":null,"doi":null,"arxiv_id":"2510.13778","raw_key":null,"title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","authors":null,"authors_text":"Xinyi Chen, Yilun Chen, Yanwei Fu, Ning Gao, Jiaya Jia, Weiyang Jin","year":2025,"venue":"cs.RO","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.","external_url":"https://arxiv.org/abs/2510.13778","cited_by_count":null,"metadata_source":"pith","metadata_fetched_at":"2026-05-21T04:19:33.410231+00:00","pith_arxiv_id":"2510.13778","created_at":"2026-05-10T06:51:45.878670+00:00","updated_at":"2026-05-21T04:19:33.410231+00:00","title_quality_ok":true,"display_title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy","render_title":"InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy"},"hub":{"state":{"work_id":"8a11d29e-4bf8-4a9c-a97e-d87e7350dd9c","tier":"hub","tier_reason":"10+ Pith inbound or 1,000+ external citations","pith_inbound_count":28,"external_cited_by_count":null,"distinct_field_count":4,"first_pith_cited_at":"2025-11-18T05:21:11+00:00","last_pith_cited_at":"2026-05-20T17:10:31+00:00","author_build_status":"not_needed","summary_status":"needed","contexts_status":"needed","graph_status":"needed","ask_index_status":"not_needed","reader_status":"not_needed","recognition_status":"not_needed","updated_at":"2026-06-04T15:57:46.132937+00:00","tier_text":"hub"},"tier":"hub","role_counts":[{"context_role":"background","n":10},{"context_role":"baseline","n":2},{"context_role":"dataset","n":1},{"context_role":"method","n":1}],"polarity_counts":[{"context_polarity":"background","n":11},{"context_polarity":"baseline","n":2},{"context_polarity":"use_method","n":1}],"runs":{},"summary":{},"graph":{},"authors":[]}}