mlsanityData to 7 Oct 2026

mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs

arXiv 2512.15692 ↗First posted 17 Dec 2025cs.RO cs.AI cs.CVcited by 133

On the map: Vision-language-action models → Human-video and latent-action pretraining

Abstract (arXiv)

Prevailing Vision-Language-Action Models (VLAs) for robotic manipulation are built upon vision-language backbones pretrained on large-scale, but disconnected static web data. As a result, despite improved semantic generalization, the policy must implicitly infer complex physical dynamics and temporal dependencies solely from robot trajectories. This reliance creates an unsustainable data burden, necessitating continuous, large-scale expert data collection to compensate for the lack of innate physical understanding. We contend that while vision-language pretraining effectively captures semantic priors, it remains blind to physical causality. A more effective paradigm leverages video to jointly capture semantics and visual dynamics during pretraining, thereby isolating the remaining task of low-level control. To this end, we introduce mimic-video, a novel Video-Action Model (VAM) that pairs a pretrained Internet-scale video model with a flow matching-based action decoder conditioned on its latent representations. The decoder serves as an Inverse Dynamics Model (IDM), generating low-level robot actions from the latent representation of video-space action plans. Our extensive evaluation shows that our approach achieves state-of-the-art performance on simulated and real-world robotic manipulation tasks, improving sample efficiency by 10x and convergence speed by 2x compared to traditional VLA architectures.

Key facts. Cited by 133 papers in the map (data through 7 Oct 2026). Placed in Human-video and latent-action pretraining, one of 13 directions in Vision-language-action models. Builds on 55 of its 63 references that are in the map. First posted on arXiv 17 Dec 2025.

Builds on

55 of 63 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024Latent Action Pretraining from Videos15 Oct

Other references · 54

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  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. 2021LoRA: Low-Rank Adaptation of Large Language Modelscited by 14,084
  5. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  6. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  7. 2022Scalable Diffusion Models with Transformerscited by 5,931
  8. 2022Flow Matching for Generative Modelingcited by 5,426
  9. 2018Neural Ordinary Differential Equationscited by 3,733
  10. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  11. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  12. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
38 more
  1. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  2. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  3. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  4. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  5. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  6. 2022A Generalist Agentcited by 802
  7. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planningcited by 738
  8. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  9. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  10. 2024Evaluating Real-World Robot Manipulation Policies in Simulationcited by 484
  11. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  12. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 373
  13. 2024Robotic Control via Embodied Chain-of-Thought Reasoningcited by 340
  14. 2019Learning Latent Plans from Playcited by 310
  15. 2016Deep Visual Foresight for Planning Robot Motioncited by 276
  16. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 266
  17. 2016Unsupervised Learning for Physical Interaction through Video Predictioncited by 256
  18. 2025Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasetscited by 218
  19. 2023MimicPlay: Long-Horizon Imitation Learning by Watching Human Playcited by 214
  20. 2025Video models are zero-shot learners and reasonerscited by 208
  21. 2025World Simulation with Video Foundation Models for Physical AIcited by 183
  22. 2015Action-Conditional Video Prediction using Deep Networks in Atari Gamescited by 171
  23. 2023Video Language Planningcited by 160
  24. 2024EgoMimic: Scaling Imitation Learning via Egocentric Videocited by 160
  25. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planningcited by 152
  26. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulationcited by 149
  27. 2025Knowledge Insulating Vision-Language-Action Models: Train Fast, Run Fast, Generalize Bettercited by 142
  28. 2022What Matters in Language Conditioned Robotic Imitation Learning over Unstructured Datacited by 137
  29. 2023RoboCat: A Self-Improving Generalist Agent for Robotic Manipulationcited by 108
  30. 2024Scaling Cross-Embodied Learning: One Policy for Manipulation, Navigation, Locomotion and Aviationcited by 108
  31. 2022VideoDex: Learning Dexterity from Internet Videoscited by 101
  32. 2025Video Generators are Robot Policiescited by 86
  33. 2024Dreamitate: Real-World Visuomotor Policy Learning via Video Generationcited by 84
  34. 2025RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learningcited by 76
  35. 2024The Ingredients for Robotic Diffusion Transformerscited by 72
  36. 2015Learning Visual Predictive Models of Physics for Playing Billiardscited by 58
  37. 2025FLOWER: Democratizing Generalist Robot Policies with Efficient Vision-Language-Action Flow Policiescited by 56
  38. 2025Training Strategies for Efficient Embodied Reasoningcited by 53

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 1; 2026: 132.

133 papers.

Sort:

By area:

  1. 2026World Action Models are Zero-shot Policiescited by 411
  2. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 311
  3. 2026Causal World Modeling for Robot Controlcited by 289
  4. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 129
  5. 2026π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilitiescited by 127
  6. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 103
  7. 2026DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Controlcited by 71
  8. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  9. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 65
  10. 2026Motubrain: An Advanced World Action Model for Robot Controlcited by 54
  11. 2026World Action Models: The Next Frontier in Embodied AIcited by 46
  12. 2026LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policiescited by 46
38 more
  1. 2026World Model for Robot Learning: A Comprehensive Surveycited by 42
  2. 2025Emergence of Human to Robot Transfer in Vision-Language-Action Modelscited by 36
  3. 2026DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generationcited by 36
  4. 2026Do World Action Models Generalize Better than VLAs? A Robustness Studycited by 35
  5. 2026ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queriescited by 28
  6. 2026ABot-M0.5: Unified Mobility-and-Manipulation World Action Modelcited by 28
  7. 2026Interactive World Simulator for Robot Policy Training and Evaluationcited by 27
  8. 2026BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generationcited by 25
  9. 2026Self-Supervised Flow Matching for Scalable Multi-Modal Synthesiscited by 25
  10. 2026Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectoriescited by 24
  11. 2026GigaBrain-0.5M*: a VLA That Learns From World Model-Based Reinforcement Learningcited by 23
  12. 2026DriveVA: Video Action Models are Zero-Shot Driverscited by 19
  13. 2026When to Trust Imagination: Adaptive Action Execution for World Action Modelscited by 18
  14. 2026EgoWAM: World Action Models Beyond Pixels with In-the-Wild Egocentric Human Datacited by 17
  15. 2026S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresightcited by 16
  16. 2026Mask World Model: Predicting What Matters for Robust Robot Policy Learningcited by 15
  17. 2026MaskWAM: Unifying Mask Prompting and Prediction for World-Action Modelscited by 15
  18. 2026EVA: Aligning Video World Models with Executable Robot Actions via Inverse Dynamics Rewardscited by 14
  19. 2026WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigationcited by 14
  20. 2026WALL-WM: Carving World Action Modeling at the Event Jointscited by 14
  21. 2026Next Forcing: Causal World Modeling with Multi-Chunk Predictioncited by 14
  22. 2026Learning 4D Geometric Priors for Inference-Efficient World Action Modelscited by 14
  23. 2026Latent Geometry Beyond Search: Amortizing Planning in World Modelscited by 13
  24. 2026Robotic Video World Models: A Survey of Applications, Research Challenges, Future Directionscited by 12
  25. 2026MemoryWAM: Efficient World Action Modeling with Persistent Memorycited by 12
  26. 2026LaMP: Learning Vision-Language-Action Policy with 3D Scene Flow as Latent Motion Priorcited by 11
  27. 2026Wall-OSS-0.5 Technical Reportcited by 11
  28. 2026HarmoWAM: Harmonizing Generalizable and Precise Manipulation via Adaptive World Action Modelscited by 10
  29. 2026Turning Video Models into Generalist Robot Policiescited by 10
  30. 2026World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesiscited by 10
  31. 2026Metis: A Generalizable and Efficient World-Action Model for Autonomous Driving and Urban Navigationcited by 10
  32. 2026Geometric Action Model for Robot Policy Learningcited by 10
  33. 2026World Action Models: A Surveycited by 10
  34. 2026FlowWAM: Optical Flow as a Unified Action Representation for World Action Modelscited by 10
  35. 2026GigaWorld-Policy-0.5: A Faster and Stronger WAM Empowered by AutoResearchcited by 10
  36. 2026NavDreamer: Video Models as Zero-Shot 3D Navigatorscited by 9
  37. 2026Fast-dVLA: Accelerating Discrete Diffusion VLA to Real-Time Performancecited by 9
  38. 2026MemoryVLA++: Temporal Modeling via Memory and Imagination in Vision-Language-Action Modelscited by 9

50 most cited of 133 All 133 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026Native Video-Action Pretraining for Generalizable Robot Control
  2. 2026InternW0-Δ: A World Action Model Bridging Predictive Dynamics and Actions with 20K+ Hours of Open Data
  3. 2026Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining
  4. 2026Native Action-Prior Learning from Videos for World Action Models
  5. 2025AMPLIFY: Actionless Motion Priors for Robot Learning from Videos
  6. 2025VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
  7. 2025Latent Action Pretraining Through World Modeling
  8. 2025Large Video Planner Enables Generalizable Robot Control