mlsanityData to 14 Oct 2026

Video Generators are Robot Policies

arXiv 2508.00795 ↗First posted 1 Aug 2025cs.ROcited by 92

Not on the map. Why?

Cited by 54 in World models, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Despite tremendous progress in dexterous manipulation, current visuomotor policies remain fundamentally limited by two challenges: they struggle to generalize under perceptual or behavioral distribution shifts, and their performance is constrained by the size of human demonstration data. In this paper, we use video generation as a proxy for robot policy learning to address both limitations simultaneously. We propose Video Policy, a modular framework that combines video and action generation that can be trained end-to-end. Our results demonstrate that learning to generate videos of robot behavior allows for the extraction of policies with minimal demonstration data, significantly improving robustness and sample efficiency. Our method shows strong generalization to unseen objects, backgrounds, and tasks, both in simulation and the real world. We further highlight that task success is closely tied to the generated video, with action-free video data providing critical benefits for generalizing to novel tasks. By leveraging large-scale video generative models, we achieve superior performance compared to traditional behavior cloning, paving the way for more scalable and data-efficient robot policy learning.

Key facts. Cited by 92 papers in the map (data through 14 Oct 2026). First posted on arXiv 1 Aug 2025.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 11; 2026: 81.

92 papers.

Sort:

By area:

  1. 2026World Action Models are Zero-shot Policiescited by 465
  2. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 349
  3. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 300
  4. 2025mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAscited by 142
  5. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 138
  6. 2026DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Controlcited by 76
  7. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 75
  8. 2026World Action Models: The Next Frontier in Embodied AIcited by 50
  9. 2026World Model for Robot Learning: A Comprehensive Surveycited by 46
  10. 2026DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generationcited by 45
  11. 2025NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videoscited by 40
  12. 2025Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Modelcited by 36
38 more
  1. 2026Rethinking Video Generation Model for the Embodied Worldcited by 33
  2. 2026Interactive World Simulator for Robot Policy Training and Evaluationcited by 31
  3. 2026When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAscited by 30
  4. 2025ViPRA: Video Prediction for Robot Actionscited by 26
  5. 2026Light-WAM: Efficient World Action Models with State-Fusion Action Decodingcited by 23
  6. 2025Act2Goal: From World Model To General Goal-conditioned Policycited by 20
  7. 2026When to Trust Imagination: Adaptive Action Execution for World Action Modelscited by 20
  8. 2026Flash-WAM: Modality-Aware Distillation for World Action Modelscited by 19
  9. 2026PlayWorld: Learning Robot World Models from Autonomous Playcited by 18
  10. 2025Contrastive Representation Regularization for Vision-Language-Action Modelscited by 17
  11. 2026WALL-WM: Carving World Action Modeling at the Event Jointscited by 17
  12. 2026MaskWAM: Unifying Mask Prompting and Prediction for World-Action Modelscited by 16
  13. 2025A Step Toward World Models: A Survey on Robotic Manipulationcited by 15
  14. 2026Walk through Paintings: Egocentric World Models from Internet Priorscited by 14
  15. 2026MemoryWAM: Efficient World Action Modeling with Persistent Memorycited by 13
  16. 2026Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalizationcited by 13
  17. 2026Action Images: End-to-End Policy Learning via Multiview Video Generationcited by 12
  18. 2026AIM: Intent-Aware Unified world action Modeling with Spatial Value Mapscited by 12
  19. 2026World Action Models: A Surveycited by 12
  20. 2026Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstructioncited by 11
  21. 2026Is the Future Compatible? Diagnosing Dynamic Consistency in World Action Modelscited by 11
  22. 2026Making Foresight Actionable: Repurposing Representation Alignment in World Action Modelscited by 11
  23. 2026HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Modelscited by 10
  24. 2026PhysisForcing: Physics Reinforced World Simulator for Robotic Manipulationcited by 10
  25. 20253D Flow Diffusion Policy: Visuomotor Policy Learning via Generating Flow in 3D Spacecited by 9
  26. 2025CoVAR: Co-generation of Video and Action for Robotic Manipulation via Multi-Modal Diffusioncited by 9
  27. 2026ViVa: A Video-Generative Value Model for Robot Reinforcement Learningcited by 9
  28. 2026UNIVERSE: Unified Video Action Models for Autonomous Driving with Flexible Mask-Modulated Modality Generationcited by 9
  29. 2026NovaPlan: Zero-Shot Long-Horizon Manipulation via Closed-Loop Video Language Planningcited by 8
  30. 2026Veo-Act: Enhancing VLA Policies with Frontier Video Modelscited by 5
  31. 2026A Mechanistic Analysis of Sim-and-Real Co-Training in Generative Robot Policiescited by 5
  32. 2026Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modelingcited by 5
  33. 2026EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fieldscited by 5
  34. 2026UAM: A Dual-Stream Perspective on Forgetting in VLA Trainingcited by 5
  35. 2026Diffusion ReRoll: Revisable Denoising for Robotic Sequential Predictioncited by 5
  36. 2026Spatially Aware World Action Model via Geometric Latent Diffusioncited by 5
  37. 2026From World Models to World Action Models: A Concise Tutorial for Roboticscited by 4
  38. 2026DeVA: Decoupled Video-Action Model with physical guidance for robot policy learningcited by 4

50 most cited of 92 All 92 (JSON)