mlsanityData to 14 Oct 2026

InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy

arXiv 2510.13778 ↗First posted 15 Oct 2025cs.RO cs.AI cs.CVcited by 84

On the map: Vision-language-action models → 3D and spatial-aware VLA

Abstract (arXiv)

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.

Key facts. Cited by 84 papers in the map (data through 14 Oct 2026). Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models. Builds on 79 of its 83 references that are in the map. First posted on arXiv 15 Oct 2025.

Builds on

79 of 83 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025GraphCoT-VLA: A 3D Spatial-Aware Reasoning Vision-Language-Action Model for Robotic Manipulation with Ambiguous Instructions11 Aug
  2. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model27 Jan

Other references · 77

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  4. 2025Qwen2.5-VL Technical Reportcited by 5,587
  5. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,109
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 3,080
  7. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,887
  8. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  9. 2024LLaVA-OneVision: Easy Visual Task Transfercited by 2,719
  10. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,565
  11. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,407
  12. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
38 more
  1. 2025InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Modelscited by 1,834
  2. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,761
  3. 2023Evaluating Object Hallucination in Large Vision-Language Modelscited by 1,729
  4. 2019Towards VQA Models That Can Readcited by 1,718
  5. 2023MME: A Comprehensive Evaluation Benchmark for Multimodal Large Language Modelscited by 1,652
  6. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  7. 2023MM-Vet: Evaluating Large Multimodal Models for Integrated Capabilitiescited by 1,239
  8. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  9. 2016Modeling Context in Referring Expressionscited by 1,063
  10. 2021Isaac Gym: High Performance GPU-Based Physics Simulation For Robot Learningcited by 998
  11. 2015Generation and Comprehension of Unambiguous Object Descriptionscited by 904
  12. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 883
  13. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  14. 2020CURL: Contrastive Unsupervised Representations for Reinforcement Learningcited by 760
  15. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 750
  16. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  17. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  18. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 530
  19. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 451
  20. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 422
  21. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 410
  22. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 405
  23. 2025WorldVLA: Towards Autoregressive Action World Modelcited by 367
  24. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 346
  25. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 327
  26. 2024Latent Action Pretraining from Videoscited by 321
  27. 2024ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulationcited by 315
  28. 2023SayPlan: Grounding Large Language Models using 3D Scene Graphs for Scalable Robot Task Planningcited by 294
  29. 2024RoboPoint: A Vision-Language Model for Spatial Affordance Prediction for Roboticscited by 251
  30. 2025Hi Robot: Open-Ended Instruction Following with Hierarchical Vision-Language-Action Modelscited by 221
  31. 2024RT-H: Action Hierarchies Using Languagecited by 210
  32. 2022AnyGrasp: Robust and Efficient Grasp Perception in Spatial and Temporal Domainscited by 208
  33. 2025Unified Video Action Modelcited by 205
  34. 2025MolmoAct: Action Reasoning Models that can Reason in Spacecited by 197
  35. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 175
  36. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulationcited by 161
  37. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 146
  38. 2025Magma: A Foundation Model for Multimodal AI Agentscited by 139

50 most cited of 77 All 77 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 8; 2026: 76.

84 papers.

Sort:

By area:

  1. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 112
  2. 2026A Pragmatic VLA Foundation Modelcited by 103
  3. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 66
  4. 2025InternData-A1: Pioneering High-Fidelity Synthetic Data for Pre-training Generalist Policycited by 50
  5. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 50
  6. 2026World Action Models: The Next Frontier in Embodied AIcited by 50
  7. 2026Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodimentscited by 44
  8. 2026World Guidance: World Modeling in Condition Space for Action Generationcited by 36
  9. 2025VLA-Arena: An Open-Source Framework for Benchmarking Vision-Language-Action Modelscited by 31
  10. 2026StarVLA-α: Reducing Complexity in Vision-Language-Action Systemscited by 31
  11. 2026ABot-M0.5: Unified Mobility-and-Manipulation World Action Modelcited by 30
  12. 2026ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queriescited by 29
38 more
  1. 2026OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulationcited by 28
  2. 2025Counterfactual VLA: Self-Reflective Vision-Language-Action Model with Adaptive Reasoningcited by 22
  3. 2026Towards Generalizable Robotic Manipulation in Dynamic Environmentscited by 20
  4. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Actioncited by 18
  5. 2025AsyncVLA: Asynchronous Flow Matching for Vision-Language-Action Modelscited by 17
  6. 2026FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Modelcited by 16
  7. 2026RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulationcited by 14
  8. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 14
  9. 2025MM-ACT: Learn from Multimodal Parallel Generation to Actcited by 12
  10. 2026Dynamic Skill Lifecycle Management for Agentic Reinforcement Learningcited by 12
  11. 2026ROCKET: Residual-Oriented Multi-Layer Alignment for Spatially-Aware Vision-Language-Action Modelscited by 11
  12. 2026PRTS: A Primitive Reasoning and Tasking System via Contrastive Representationscited by 9
  13. 2026SafeVLA-Bench: A Benchmark for the Success-Safety Gap in Vision-Language-Action Modelscited by 9
  14. 2026HiVLA: A Visual-Grounded-Centric Hierarchical Embodied Manipulation Systemcited by 8
  15. 2026OFlow: Injecting Object-Aware Temporal Flow Matching for Robust Robotic Manipulationcited by 8
  16. 2026PointACT: Vision-Language-Action Models with Multi-Scale Point-Action Interactioncited by 8
  17. 2025Unified Embodied VLM Reasoning with Robotic Action via Autoregressive Discretized Pre-trainingcited by 7
  18. 2026Rethinking Visual-Language-Action Model Scaling: Alignment, Mixture, and Regularizationcited by 7
  19. 2025How Do VLAs Effectively Inherit from VLMs?cited by 6
  20. 2026FocusVLA: Focused Visual Utilization for Vision-Language-Action Modelscited by 6
  21. 2026FrameSkip: Learning from Fewer but More Informative Frames in VLA Trainingcited by 6
  22. 2026From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Modelcited by 6
  23. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 6
  24. 2026ω-0: A Latent Predictive World Action Model for Concurrent Humanoid Loco-Manipulationcited by 6
  25. 2026SkillVLA: Tackling Combinatorial Diversity in Dual-Arm Manipulation via Skill Reusecited by 5
  26. 2026TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patchescited by 5
  27. 2026APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policiescited by 5
  28. 2026Human-Centric Transferable Tactile Pre-Training for Dexterous Robotic Manipulationcited by 5
  29. 2026Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulationcited by 5
  30. 2026Spatial Memory for Out-of-Vision Manipulation in Vision-Language-Actioncited by 4
  31. 2026VisualThink-VLA: Visual Intermediate Reasoning for Effective and Low-Latency Vision-Language-Action Policiescited by 4
  32. 2026DynamicWAM: Dual-Path Motion Conditioning for World-Action Models in Dynamic Manipulationcited by 4
  33. 2026Riemann-1.0: An Embodied World Action Model for Physical AIcited by 4
  34. 2026Closed-Loop Action Chunks with Dynamic Corrections for Training-Free Diffusion Policycited by 3
  35. 2026Learning Action Manifold with Multi-view Latent Priors for Robotic Manipulationcited by 3
  36. 2026Guide, Think, Act: Interactive Embodied Reasoning in Vision-Language-Action Modelscited by 3
  37. 2026RoVLA: Multi-Consistency Constraints for Robust Vision-Language-Action Modelscited by 3
  38. 2026World Pilot: Steering Vision-Language-Action Models with World-Action Priorscited by 3

50 most cited of 84 All 84 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Spa-Bench: A Real-Robot Benchmark for Spatial Grounding in Vision-Language-Action Models
  2. 2026ST4VLA: Spatially Guided Training for Vision-Language-Action Models
  3. 2026Spatially Grounded Long-Horizon Task Planning in the Wild
  4. 2025From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation
  5. 2024Emma-X: An Embodied Multimodal Action Model with Grounded Chain of Thought and Look-ahead Spatial Reasoning
  6. 2026Decoupling Semantics and Geometric Grounding: Spatial Visual Prompts for Language-Conditioned Imitation Learning
  7. 2025Toward Embodiment Equivariant Vision-Language-Action Policy
  8. 2026Direct Action-Head Injection of A Grounded 3D Point Unlocks Spatial and Task Generalization