mlsanityData to 7 Oct 2026

SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Model

arXiv 2501.15830 ↗First posted 27 Jan 2025cs.RO cs.AIcited by 502

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

Abstract (arXiv)

In this paper, we claim that spatial understanding is the keypoint in robot manipulation, and propose SpatialVLA to explore effective spatial representations for the robot foundation model. Specifically, we introduce Ego3D Position Encoding to inject 3D information into the input observations of the visual-language-action model, and propose Adaptive Action Grids to represent spatial robot movement actions with adaptive discretized action grids, facilitating learning generalizable and transferrable spatial action knowledge for cross-robot control. SpatialVLA is first pre-trained on top of a vision-language model with 1.1 Million real-world robot episodes, to learn a generalist manipulation policy across multiple robot environments and tasks. After pre-training, SpatialVLA is directly applied to perform numerous tasks in a zero-shot manner. The superior results in both simulation and real-world robots demonstrate its advantage of inferring complex robot motion trajectories and its strong in-domain multi-task generalization ability. We further show the proposed Adaptive Action Grids offer a new and effective way to fine-tune the pre-trained SpatialVLA model for new simulation and real-world setups, where the pre-learned action grids are re-discretized to capture robot-specific spatial action movements of new setups. The superior results from extensive evaluations demonstrate the exceptional in-distribution generalization and out-of-distribution adaptation capability, highlighting the crucial benefit of the proposed spatial-aware representations for generalist robot policy learning. All the details and codes will be open-sourced.

Key facts. Cited by 502 papers in the map (data through 7 Oct 2026). Placed in 3D and spatial-aware VLA, one of 13 directions in Vision-language-action models. Builds on 65 of its 76 references that are in the map. First posted on arXiv 27 Jan 2025.

Builds on

65 of 76 references.

Closest ancestors · 2

Same direction, newest first

  1. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policies13 Dec
  2. 20243D-VLA: A 3D Vision-Language-Action Generative World Model14 Mar

Other references · 63

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Visual Instruction Tuningcited by 7,792
  3. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  4. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
  5. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  6. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  8. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  9. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  10. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  11. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  12. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
38 more
  1. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 849
  2. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  3. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 730
  4. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  5. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  6. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  7. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  8. 2024Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spacescited by 580
  9. 2022Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulationcited by 545
  10. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  11. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  12. 2015Policy Distillationcited by 414
  13. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  14. 2023An Embodied Generalist Agent in 3D Worldcited by 355
  15. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 344
  16. 2024Prismatic VLMs: Investigating the Design Space of Visually-Conditioned Language Modelscited by 336
  17. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 290
  18. 2023PaLI-X: On Scaling up a Multilingual Vision and Language Modelcited by 254
  19. 2021Bridge Data: Boosting Generalization of Robotic Skills with Cross-Domain Datasetscited by 248
  20. 2022Interactive Language: Talking to Robots in Real Timecited by 217
  21. 2023LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planningcited by 206
  22. 2024PaliGemma 2: A Family of Versatile VLMs for Transfercited by 204
  23. 2018RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitationcited by 202
  24. 2024LLaVA-3D: A Simple yet Effective Pathway to Empowering LMMs with 3D-awarenesscited by 178
  25. 2015Actor-Mimic: Deep Multitask and Transfer Reinforcement Learningcited by 176
  26. 2023RH20T: A Comprehensive Robotic Dataset for Learning Diverse Skills in One-Shotcited by 173
  27. 2024Scene-LLM: Extending Language Model for 3D Visual Understanding and Reasoningcited by 170
  28. 2023RoboAgent: Generalization and Efficiency in Robot Manipulation via Semantic Augmentations and Action Chunkingcited by 167
  29. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 145
  30. 2023Structured World Models from Human Videoscited by 144
  31. 2022VIOLA: Imitation Learning for Vision-Based Manipulation with Object Proposal Priorscited by 135
  32. 2023FurnitureBench: Reproducible Real-World Benchmark for Long-Horizon Complex Manipulationcited by 132
  33. 2024Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviationcited by 108
  34. 2022From Play to Policy: Conditional Behavior Generation from Uncurated Robot Datacited by 103
  35. 2022Grounding Language with Visual Affordances over Unstructured Datacited by 101
  36. 2022Robot Learning on the Job: Human-in-the-Loop Autonomy and Learning During Deploymentcited by 101
  37. 2023On Bringing Robots Homecited by 101
  38. 2024What Matters in Building Vision-Language-Action Models for Generalist Robotscited by 88

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 175; 2026: 327.

502 papers.

Sort:

By area:

  1. 2026Causal World Modeling for Robot Controlcited by 289
  2. 2025MoGe-2: Accurate Monocular Geometry with Metric Scale and Sharp Detailscited by 250
  3. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledgecited by 203
  4. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 183
  5. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 166
  6. 2025FutureSightDrive: Thinking Visually with Spatio-Temporal CoT for Autonomous Drivingcited by 165
  7. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  8. 2025Unified Vision-Language-Action Modelcited by 128
  9. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  10. 2025Spatial Forcing: Implicit Spatial Representation Alignment for Vision-language-action Modelcited by 125
  11. 2025NORA: A Small Open-Sourced Generalist Vision Language Action Model for Embodied Taskscited by 119
  12. 2025Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priorscited by 111
38 more
  1. 2025GR-3 Technical Reportcited by 110
  2. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 104
  3. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 103
  4. 2025PointVLA: Injecting the 3D World into Vision-Language-Action Modelscited by 101
  5. 2026A Pragmatic VLA Foundation Modelcited by 97
  6. 2026ABot-M0: VLA Foundation Model for Robotic Manipulation with Action Manifold Learningcited by 94
  7. 2025Discrete Diffusion VLA: Bringing Discrete Diffusion to Action Decoding in Vision-Language-Action Policiescited by 90
  8. 2025PD-VLA: Accelerating Vision-Language-Action Model Integrated with Action Chunking via Parallel Decodingcited by 88
  9. 2025F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actionscited by 85
  10. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 83
  11. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applicationscited by 82
  12. 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Modelscited by 77
  13. 2025Dita: Scaling Diffusion Transformer for Generalist Vision-Language-Action Policycited by 73
  14. 2025Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challengescited by 72
  15. 2025A Survey on Vision-Language-Action Models for Autonomous Drivingcited by 72
  16. 2025InstructVLA: Vision-Language-Action Instruction Tuning from Understanding to Manipulationcited by 71
  17. 2025CogVLA: Cognition-Aligned Vision-Language-Action Model via Instruction-Driven Routing & Sparsificationcited by 70
  18. 2025GeoVLA: Empowering 3D Representations in Vision-Language-Action Modelscited by 68
  19. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  20. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 66
  21. 2025VLA-RFT: Vision-Language-Action Reinforcement Fine-tuning with Verified Rewards in World Simulatorscited by 65
  22. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 65
  23. 2025Scalable Vision-Language-Action Model Pretraining for Robotic Manipulation with Real-Life Human Activity Videoscited by 63
  24. 2025VideoVLA: Video Generators Can Be Generalizable Robot Manipulatorscited by 61
  25. 2026Being-H0.5: Scaling Human-Centric Robot Learning for Cross-Embodiment Generalizationcited by 61
  26. 2025villa-X: Enhancing Latent Action Modeling in Vision-Language-Action Modelscited by 58
  27. 2025Hume: Introducing System-2 Thinking in Visual-Language-Action Modelcited by 56
  28. 2025RoboMonkey: Scaling Test-Time Sampling and Verification for Vision-Language-Action Modelscited by 56
  29. 20254D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibrationcited by 55
  30. 2025Evo-0: Vision-Language-Action Model with Implicit Spatial Understandingcited by 55
  31. 2025Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgettingcited by 52
  32. 2025FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Modelscited by 50
  33. 2025Long-VLA: Unleashing Long-Horizon Capability of Vision Language Action Model for Robot Manipulationcited by 48
  34. 2025TGRPO :Fine-tuning Vision-Language-Action Model via Trajectory-wise Group Relative Policy Optimizationcited by 47
  35. 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulationcited by 46
  36. 2025TrackVLA: Embodied Visual Tracking in the Wildcited by 46
  37. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  38. 2026MolmoAct2: Action Reasoning Models for Real-world Deploymentcited by 45

50 most cited of 502 All 502 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026ST-π: Structured SpatioTemporal VLA for Robotic Manipulation
  2. 2026The Moving Eye: Enhancing VLA Spatial Generalization via Hybrid Dynamic Data Collection
  3. 2026ST-VLA: Enabling 4D-Aware Spatiotemporal Understanding for General Robot Manipulation
  4. 2026StemVLA:An Open-Source Vision-Language-Action Model with Future 3D Spatial Geometry Knowledge and 4D Historical Representation
  5. 2026Towards Generalizable Robotic Manipulation in Dynamic Environments
  6. 2026GeneralVLA: Generalizable Vision-Language-Action Models with Knowledge-Guided Trajectory Planning
  7. 2026VeriSpace: Spatially Grounded Action Verification for Vision-Language-Action Models
  8. 2026SpaceVLA: Spatially Grounded VLA for Robotic Manipulation with User-Authored Grasp and Place Anchors