mlsanityData to 14 Oct 2026

Unified Vision-Language-Action Model

arXiv 2506.19850 ↗First posted 24 Jun 2025cs.CV cs.ROcited by 134

On the map: Vision-language-action models → Generalist VLA models and benchmarks

Abstract (arXiv)

Vision-language-action models (VLAs) have garnered significant attention for their potential in advancing robotic manipulation. However, previous approaches predominantly rely on the general comprehension capabilities of vision-language models (VLMs) to generate action signals, often overlooking the rich temporal and causal structure embedded in visual observations. In this paper, we present UniVLA, a unified and native multimodal VLA model that autoregressively models vision, language, and action signals as discrete token sequences. This formulation enables flexible multimodal tasks learning, particularly from large-scale video data. By incorporating world modeling during post-training, UniVLA captures causal dynamics from videos, facilitating effective transfer to downstream policy learning--especially for long-horizon tasks. Our approach sets new state-of-the-art results across several widely used simulation benchmarks, including CALVIN, LIBERO, and Simplenv-Bridge, significantly surpassing previous methods. For example, UniVLA achieves 95.5% average success rate on LIBERO benchmark, surpassing pi0-FAST's 85.5%. We further demonstrate its broad applicability on real-world ALOHA manipulation and autonomous driving.

Key facts. Cited by 134 papers in the map (data through 14 Oct 2026). Placed in Generalist VLA models and benchmarks, one of 13 directions in Vision-language-action models. Builds on 73 of its 79 references that are in the map. First posted on arXiv 24 Jun 2025.

Builds on

73 of 79 references.

Closest ancestors · 6

Same direction, newest first

  1. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Success27 Feb
  2. 2025UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent31 Jan
  3. 2024What Matters in Building Vision-Language-Action Models for Generalist Robots18 Dec
  4. 2024π0: A Vision-Language-Action Flow Model for General Robot Control31 Oct
  5. 2024OpenVLA: An Open-Source Vision-Language-Action Model13 Jun
  6. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control28 Jul

Other references · 67

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learningcited by 6,330
  3. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,234
  4. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,838
  5. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,071
  6. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,061
  7. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,653
  8. 2018World Modelscited by 1,513
  9. 2024Octo: An Open-Source Generalist Robot Policycited by 1,484
  10. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,410
  11. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,264
  12. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
38 more
  1. 2017The "something something" video database for learning and evaluating visual common sensecited by 1,103
  2. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,089
  3. 2022Planning-oriented Autonomous Drivingcited by 1,087
  4. 2023Open X-Embodiment: Robotic Learning Datasets and RT-X Modelscited by 862
  5. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 852
  6. 2024Emu3: Next-Token Prediction is All You Needcited by 781
  7. 2024Genie: Generative Interactive Environmentscited by 747
  8. 2018QT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulationcited by 743
  9. 2024PaliGemma: A versatile 3B VLM for transfercited by 696
  10. 2022R3M: A Universal Visual Representation for Robot Manipulationcited by 694
  11. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 665
  12. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 657
  13. 2023GAIA-1: A Generative World Model for Autonomous Drivingcited by 637
  14. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 584
  15. 2023Learning Universal Policies via Text-Guided Video Generationcited by 522
  16. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 519
  17. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 495
  18. 2022TransFuser: Imitation with Transformer-Based Sensor Fusion for Autonomous Drivingcited by 485
  19. 2023Learning Interactive Real-World Simulatorscited by 458
  20. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 451
  21. 2022DayDreamer: World Models for Physical Robot Learningcited by 400
  22. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 364
  23. 2024NAVSIM: Data-Driven Non-Reactive Autonomous Vehicle Simulation and Benchmarkingcited by 354
  24. 2023Vision-Language Foundation Models as Effective Robot Imitatorscited by 349
  25. 2024Vista: A Generalizable Driving World Model with High Fidelity and Versatile Controllabilitycited by 347
  26. 20243D-VLA: A 3D Vision-Language-Action Generative World Modelcited by 328
  27. 2023ManiSkill2: A Unified Benchmark for Generalizable Manipulation Skillscited by 327
  28. 2024Latent Action Pretraining from Videoscited by 321
  29. 2023Driving into the Future: Multiview Visual Forecasting and Planning with World Model for Autonomous Drivingcited by 319
  30. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 304
  31. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 296
  32. 2024VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planningcited by 289
  33. 2016Deep Visual Foresight for Planning Robot Motioncited by 285
  34. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Modelscited by 269
  35. 2024RT-H: Action Hierarchies Using Languagecited by 210
  36. 2020Language Conditioned Imitation Learning over Unstructured Datacited by 209
  37. 2025Unified Video Action Modelcited by 205
  38. 2024RoboDreamer: Learning Compositional World Models for Robot Imaginationcited by 195

50 most cited of 67 All 67 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 31; 2026: 103.

134 papers.

Sort:

By area:

  1. 2026Causal World Modeling for Robot Controlcited by 321
  2. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 303
  3. 2025LIBERO-PRO: Towards Robust and Fair Evaluation of Vision-Language-Action Models Beyond Memorizationcited by 179
  4. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 165
  5. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 145
  6. 2025DriveVLA-W0: World Models Amplify Data Scaling Law in Autonomous Drivingcited by 134
  7. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 118
  8. 2025F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actionscited by 86
  9. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 84
  10. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 71
  11. 2025Large VLM-based Vision-Language-Action Models for Robotic Manipulation: A Surveycited by 69
  12. 2025FlowVLA: Visual Chain of Thought-based Motion Reasoning for Vision-Language-Action Modelscited by 50
38 more
  1. 2026World Model for Robot Learning: A Comprehensive Surveycited by 46
  2. 2026Xiaomi-Robotics-0: An Open-Sourced Vision-Language-Action Model with Real-Time Executioncited by 45
  3. 2026Driving on Registerscited by 44
  4. 2025Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Processcited by 39
  5. 2026VLM4VLA: Revisiting Vision-Language-Models in Vision-Language-Action Modelscited by 39
  6. 2026ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?cited by 38
  7. 2026Do World Action Models Generalize Better than VLAs? A Robustness Studycited by 36
  8. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 36
  9. 2025ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Contextcited by 35
  10. 2025A Survey on Efficient Vision-Language-Action Modelscited by 34
  11. 2026ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Modelscited by 33
  12. 2025HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Modelscited by 32
  13. 2026LaST0: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Modelcited by 31
  14. 2026When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAscited by 30
  15. 2026RLDX-1 Technical Reportcited by 28
  16. 2026OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulationcited by 28
  17. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 26
  18. 2025SwiftVLA: Unlocking Spatiotemporal Dynamics for Lightweight VLA Models at Minimal Overheadcited by 26
  19. 2025AVA-VLA: Improving Vision-Language-Action models with Active Visual Attentioncited by 25
  20. 2025MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulationcited by 23
  21. 2025Mixture of Horizons in Action Chunkingcited by 21
  22. 2025RoVer: Robot Reward Model as Test-Time Verifier for Vision-Language-Action Modelcited by 19
  23. 2026DIAL: Decoupling Intent and Action via Latent World Modeling for End-to-End VLAcited by 19
  24. 2026S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresightcited by 17
  25. 2026HALO: A Unified Vision-Language-Action Model for Embodied Multimodal Chain-of-Thought Reasoningcited by 16
  26. 2026EponaV2: Driving World Model with Comprehensive Future Reasoningcited by 15
  27. 2026Learning 4D Geometric Priors for Inference-Efficient World Action Modelscited by 15
  28. 2025Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generationcited by 14
  29. 2026CycleVLA: Proactive Self-Correcting Vision-Language-Action Models via Subtask Backtracking and Minimum Bayes Risk Decodingcited by 14
  30. 2025Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresightcited by 13
  31. 2025Spatial-Aware VLA Pretraining through Visual-Physical Alignment from Human Videoscited by 13
  32. 2026Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directionscited by 13
  33. 2025Physical Autoregressive Model for Robotic Manipulation without Action Pretrainingcited by 12
  34. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  35. 2026CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Drivingcited by 12
  36. 2026World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesiscited by 12
  37. 2025StaMo: Unsupervised Learning of Generalizable Robot Motion from Compact State Representationcited by 11
  38. 2026Chain of World: World Model Thinking in Latent Motioncited by 11

50 most cited of 134 All 134 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2025Vision Language Action Models in Robotic Manipulation: A Systematic Review
  2. 2025Vision-Language-Action Models for Robotics: A Review Towards Real-World Applications
  3. 2025VLA-0: Building State-of-the-Art VLAs with Zero Modification
  4. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulation
  5. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actions
  6. 2024TinyVLA: Towards Fast, Data-Efficient Vision-Language-Action Models for Robotic Manipulation
  7. 2026PokeVLA: Empowering Pocket-Sized Vision-Language-Action Model with Comprehensive World Knowledge Guidance
  8. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulation