mlsanityData to 7 Oct 2026

VideoVLA: Video Generators Can Be Generalizable Robot Manipulators

arXiv 2512.06963 ↗First posted 7 Dec 2025cs.RO cs.AI cs.CVcited by 61

Not on the map. Why?

Cited by 30 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Generalization in robot manipulation is essential for deploying robots in open-world environments and advancing toward artificial general intelligence. While recent Vision-Language-Action (VLA) models leverage large pre-trained understanding models for perception and instruction following, their ability to generalize to novel tasks, objects, and settings remains limited. In this work, we present VideoVLA, a simple approach that explores the potential of transforming large video generation models into robotic VLA manipulators. Given a language instruction and an image, VideoVLA predicts an action sequence as well as the future visual outcomes. Built on a multi-modal Diffusion Transformer, VideoVLA jointly models video, language, and action modalities, using pre-trained video generative models for joint visual and action forecasting. Our experiments show that high-quality imagined futures correlate with reliable action predictions and task success, highlighting the importance of visual imagination in manipulation. VideoVLA demonstrates strong generalization, including imitating other embodiments' skills and handling novel objects. This dual-prediction strategy - forecasting both actions and their visual consequences - explores a paradigm shift in robot learning and unlocks generalization capabilities in manipulation systems.

Key facts. Cited by 61 papers in the map (data through 7 Oct 2026). Builds on 56 of its 62 references that are in the map. First posted on arXiv 7 Dec 2025.

Builds on

56 of 62 references.

References · 56

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  4. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  5. 2023Segment Anythingcited by 8,158
  6. 2023Visual Instruction Tuningcited by 7,792
  7. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  8. 2020Scaling Laws for Neural Language Modelscited by 6,411
  9. 2022Scalable Diffusion Models with Transformerscited by 5,931
  10. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  11. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,094
  12. 2023Sigmoid Loss for Language Image Pre-Trainingcited by 3,048
38 more
  1. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  2. 2022Training Compute-Optimal Large Language Modelscited by 2,927
  3. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  4. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  5. 2023InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Taskscited by 2,534
  6. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  7. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  8. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  9. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  10. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,883
  11. 2022Make-A-Video: Text-to-Video Generation without Text-Video Datacited by 1,725
  12. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  13. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  14. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  15. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 637
  16. 2023BridgeData V2: A Dataset for Robot Learning at Scalecited by 634
  17. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  18. 2022Google Scanned Objects: A High-Quality Dataset of 3D Scanned Household Itemscited by 601
  19. 2022BC-Z: Zero-Shot Task Generalization with Robotic Imitation Learningcited by 517
  20. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  21. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  22. 2022All are Worth Words: A ViT Backbone for Diffusion Modelscited by 498
  23. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  24. 2022Phenaki: Variable Length Video Generation From Open Domain Textual Descriptioncited by 475
  25. 2023Learning Interactive Real-World Simulatorscited by 440
  26. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  27. 2024One Step Diffusion via Shortcut Modelscited by 373
  28. 2023Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulationcited by 353
  29. 2023Pix2Video: Video Editing using Image Diffusioncited by 318
  30. 2024GR-2: A Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulationcited by 290
  31. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
  32. 2022Interactive Language: Talking to Robots in Real Timecited by 217
  33. 2025Unified Video Action Modelcited by 195
  34. 2024RoboDreamer: Learning Compositional World Models for Robot Imaginationcited by 187
  35. 2023Video Language Planningcited by 160
  36. 2023Learning to Act from Actionless Videos through Dense Correspondencescited by 159
  37. 2024Scaling Proprioceptive-Visual Learning with Heterogeneous Pre-trained Transformerscited by 145
  38. 2024Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulationcited by 142

50 most cited of 56 All 56 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 60.

61 papers.

Sort:

By area:

  1. 2026Causal World Modeling for Robot Controlcited by 289
  2. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 129
  3. 2026DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Controlcited by 71
  4. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  5. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 65
  6. 2026World Action Models: The Next Frontier in Embodied AIcited by 46
  7. 2026World Model for Robot Learning: A Comprehensive Surveycited by 42
  8. 2026DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generationcited by 36
  9. 2025Spatia: Video Generation with Updatable Spatial Memorycited by 33
  10. 2026Self-Supervised Flow Matching for Scalable Multi-Modal Synthesiscited by 25
  11. 2026LangForce: Bayesian Decomposition of Vision Language Action Models via Latent Action Queriescited by 24
  12. 2026DriveVA: Video Action Models are Zero-Shot Driverscited by 19
38 more
  1. 2026VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Modelscited by 17
  2. 2026S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresightcited by 16
  3. 2026TwinBrainVLA: Unleashing the Potential of Generalist VLMs for Embodied Tasks via Asymmetric Mixture-of-Transformerscited by 14
  4. 2026Next Forcing: Causal World Modeling with Multi-Chunk Predictioncited by 14
  5. 2026World Action Models: A Surveycited by 10
  6. 2026GigaWorld-1: A Roadmap to Build World Models for Robot Policy Evaluationcited by 10
  7. 2026NavDreamer: Video Models as Zero-Shot 3D Navigatorscited by 9
  8. 2026MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Modelscited by 9
  9. 2026Beyond Imitation: Reinforcement Learning-Based Sim-Real Co-Training for VLA Modelscited by 8
  10. 2026RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learningcited by 7
  11. 2026Pri4R: Learning World Dynamics for Vision-Language-Action Models with Privileged 4D Representationcited by 7
  12. 2026World2Act: Latent Action Post-Training from World Model Dynamicscited by 7
  13. 2026IntentVLA: Short-Horizon Intent Modeling for Aliased Robot Manipulationcited by 7
  14. 2026NoiseGate: Learning Per-Latent Timestep Schedules as Information Gating in World Action Modelscited by 6
  15. 2026FrameSkip: Learning from Fewer but More Informative Frames in VLA Trainingcited by 6
  16. 2026WorldFly: A World-Model-Based Vision-Language-Action Model for UAV Navigationcited by 6
  17. 2026Veo-Act: Enhancing VLA Policies with Frontier Video Modelscited by 5
  18. 2026Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modelingcited by 5
  19. 2026UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generationcited by 5
  20. 2026PACT-WAM: Predicting Actions and Visual Foresight with Compact Temporal Encoding for Robot Manipulationcited by 4
  21. 2026Data Pyramid for Embodied Manipulation: A Surveycited by 4
  22. 2026Foresight Without Seeing: Latent Futures for World Action Modelscited by 4
  23. 2026Thousand-GPU Large-Scale Training and Optimization Recipe for AI-Native Cloud Embodied Intelligence Infrastructurecited by 3
  24. 2026Generative Control as Optimization: Time Unconditional Flow Matching for Adaptive and Robust Robotic Controlcited by 3
  25. 2026EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fieldscited by 3
  26. 2026Afford-VLA: Action-Aligned Visual Planning via Internalized Affordancecited by 3
  27. 2026From Imagined Futures to Executable Actions: Mixture of Latent Actions for Robot Manipulationcited by 2
  28. 2026PhysBrain 1.0 Technical Reportcited by 2
  29. 2026PointAction: 3D Points as Universal Action Representations for Robot Controlcited by 2
  30. 2026World Pilot: Steering Vision-Language-Action Models with World-Action Priorscited by 2
  31. 2026Pondering the Way: Spatial-perceiving World Action Model for Embodied Navigationcited by 2
  32. 2026Towards Predictive, Aligned, and Scalable Robot Learningcited by 2
  33. 2026Riemann-1.0: An Embodied World Action Model for Physical AIcited by 2
  34. 2026Spatially Aware World Action Model via Geometric Latent Diffusioncited by 2
  35. 2026Beyond Dense Futures: World Models as Structured Planners for Robotic Manipulationcited by 1
  36. 2026Ink3D: Sculpting 3D Assets with Extremely Complex Textures via Video Generative Modelscited by 1
  37. 2026In-Context VLA: Endowing Vision-Language-Action Models with Language via In-Context Post-Training and Agentic Tool Usecited by 1
  38. 2026GlanceWAM: Sparse Test-Time Imagination for World-Action Modelscited by 1

50 most cited of 61 All 61 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulation
  2. 2025See Once, Then Act: Vision-Language-Action Model with Task Learning from One-Shot Video Demonstrations
  3. 2025DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge
  4. 2025Image Generation as a Visual Planner for Robotic Manipulation
  5. 2026From Human Videos to Robot Manipulation: A Survey on Scalable Vision-Language-Action Learning with Human-Centric Data
  6. 2025Large Video Planner Enables Generalizable Robot Control
  7. 2026Scaling World Model for Hierarchical Manipulation Policies
  8. 2025EMMA: Generalizing Real-World Robot Manipulation via Generative Visual Transfer