mlsanityData to 7 Oct 2026

Causal World Modeling for Robot Control

arXiv 2601.21998 ↗First posted 29 Jan 2026cs.CV cs.ROcited by 289

On the map: World models → Embodied and robot world models

also in 1 more
Abstract (arXiv)

This work highlights that video world modeling, alongside vision-language pre-training, establishes a fresh and independent foundation for robot learning. Intuitively, video world models provide the ability to imagine the near future by understanding the causality between actions and visual dynamics. Inspired by this, we introduce LingBot-VA, an autoregressive diffusion framework that learns frame prediction and policy execution simultaneously. Our model features three carefully crafted designs: (1) a shared latent space, integrating vision and action tokens, driven by a Mixture-of-Transformers (MoT) architecture, (2) a closed-loop rollout mechanism, allowing for ongoing acquisition of environmental feedback with ground-truth observations, (3) an asynchronous inference pipeline, parallelizing action prediction and motor execution to support efficient control. We evaluate our model on both simulation benchmarks and real-world scenarios, where it shows significant promise in long-horizon manipulation, data efficiency in post-training, and strong generalizability to novel configurations. The code and model are made publicly available to facilitate the community.

Key facts. Cited by 289 papers in the map (data through 7 Oct 2026). Placed in Embodied and robot world models, one of 11 directions in World models. Builds on 86 of its 99 references that are in the map. First posted on arXiv 29 Jan 2026.

Builds on

86 of 99 references.

Closest ancestors · 11

Same direction, newest first

  1. 2025Act2Goal: From World Model To General Goal-conditioned Policy29 Dec
  2. 2025Motus: A Unified Latent Action World Model15 Dec
  3. 2025Evaluating Gemini Robotics Policies in a Veo World Simulator11 Dec
  4. 2025Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets3 Apr
  5. 2024Predictive Inverse Dynamics Models are Scalable Learners for Robotic Manipulation19 Dec
  6. 2024Dream to Manipulate: Compositional World Models Empowering Robot Imitation Learning with Imagination19 Dec
  7. 2024RoboDreamer: Learning Compositional World Models for Robot Imagination18 Apr
  8. 20243D-VLA: A 3D Vision-Language-Action Generative World Model14 Mar
  9. 2023Zero-Shot Robotic Manipulation with Pretrained Image-Editing Diffusion Models16 Oct
  10. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar
  11. 2022RoboCraft: Learning to See, Simulate, and Shape Elasto-Plastic Objects with Graph Networks5 May

Other references · 75

  1. 2017Attention Is All You Needcited by 59,932
  2. 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
  3. 2022Flow Matching for Generative Modelingcited by 5,426
  4. 2022Flow Straight and Fast: Learning to Generate and Transfer Data with Rectified Flowcited by 3,550
  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. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  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. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  11. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  12. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
38 more
  1. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  2. 2024WorldSimBench: Towards Video Generation Models as World Simulatorscited by 867
  3. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  4. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  5. 2023Improving and generalizing flow-based generative models with minibatch optimal transportcited by 835
  6. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  7. 2024Genie: Generative Interactive Environmentscited by 706
  8. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  9. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  10. 2024Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusioncited by 634
  11. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  12. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  13. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  14. 2017Deep learning for universal linear embeddings of nonlinear dynamicscited by 491
  15. 2023TD-MPC2: Scalable, Robust World Models for Continuous Controlcited by 482
  16. 2025RoboTwin 2.0: A Scalable Data Generator and Benchmark with Strong Domain Randomization for Robust Bimanual Robotic Manipulationcited by 477
  17. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  18. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  19. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  20. 2024Universal Manipulation Interface: In-The-Wild Robot Teaching Without In-The-Wild Robotscited by 373
  21. 2022DayDreamer: World Models for Physical Robot Learningcited by 372
  22. 2024TraceVLA: Visual Trace Prompting Enhances Spatial-Temporal Awareness for Generalist Robotic Policiescited by 298
  23. 2025X-VLA: Soft-Prompted Transformer as Scalable Cross-Embodiment Vision-Language-Action Modelcited by 285
  24. 2024Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representationscited by 279
  25. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 274
  26. 2015Embed to Control: A Locally Linear Latent Dynamics Model for Control from Raw Imagescited by 266
  27. 2025Real-Time Execution of Action Chunking Flow Policiescited by 199
  28. 2025Unified Video Action Modelcited by 195
  29. 2025MemoryVLA: Perceptual-Cognitive Memory in Vision-Language-Action Models for Robotic Manipulationcited by 183
  30. 2024RoboMIND: Benchmark on Multi-embodiment Intelligence Normative Data for Robot Manipulationcited by 166
  31. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planningcited by 152
  32. 2024Mixture-of-Transformers: A Sparse and Scalable Architecture for Multi-Modal Foundation Modelscited by 151
  33. 2024Data Scaling Laws in Imitation Learning for Robotic Manipulationcited by 144
  34. 2024Gen2Act: Human Video Generation in Novel Scenarios enables Generalizable Robot Manipulationcited by 142
  35. 2025SimpleVLA-RL: Scaling VLA Training via Reinforcement Learningcited by 141
  36. 2025mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAscited by 133
  37. 2025Unified Vision-Language-Action Modelcited by 128
  38. 2025A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulationcited by 125

50 most cited of 75 All 75 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 289.

289 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. 2026Cosmos 3: Omnimodal World Models for Physical AIcited by 137
  4. 2026StarVLA: A Lego-like Codebase for Vision-Language-Action Model Developingcited by 103
  5. 2026DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Controlcited by 71
  6. 2026Being-H0.7: A Latent World-Action Model from Egocentric Videoscited by 68
  7. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 65
  8. 2026Motubrain: An Advanced World Action Model for Robot Controlcited by 54
  9. 2026World Action Models: The Next Frontier in Embodied AIcited by 46
  10. 2026LaWAM: Latent World Action Models for Efficient Dynamics-Aware Robot Policiescited by 46
  11. 2026World Model for Robot Learning: A Comprehensive Surveycited by 42
  12. 2026Qwen-VLA: Unifying Vision-Language-Action Modeling across Tasks, Environments, and Robot Embodimentscited by 42
38 more
  1. 2026AHA-WAM:Asynchronous Horizon-Adaptive World-Action Modeling with Observation-Guided Context Routingcited by 41
  2. 2026Solaris: Building a Multiplayer Video World Model in Minecraftcited by 38
  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. 2026ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?cited by 33
  6. 2026Native Video-Action Pretraining for Generalizable Robot Controlcited by 30
  7. 2026ABot-M0.5: Unified Mobility-and-Manipulation World Action Modelcited by 28
  8. 2026Interactive World Simulator for Robot Policy Training and Evaluationcited by 27
  9. 2026OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulationcited by 25
  10. 2026Xiaomi-Robotics-1: Scaling Vision-Language-Action Models with over 100K Hours of Real-World Trajectoriescited by 24
  11. 2026ABot-PhysWorld: Interactive World Foundation Model for Robotic Manipulation with Physics Alignmentcited by 23
  12. 2026Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Modelscited by 23
  13. 2026τ0-WM: A Unified Video-Action World Model for Robotic Manipulationcited by 21
  14. 2026HoloBrain-0 Technical Reportcited by 20
  15. 2026VGGT-Omegacited by 20
  16. 2026DriveVA: Video Action Models are Zero-Shot Driverscited by 19
  17. 2026Light-WAM: Efficient World Action Models with State-Fusion Action Decodingcited by 19
  18. 2026When to Trust Imagination: Adaptive Action Execution for World Action Modelscited by 18
  19. 2026UniDriveVLA: Unifying Understanding, Perception, and Action Planning for Autonomous Drivingcited by 17
  20. 2026Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulationcited by 17
  21. 2026Efficient-WAM: A 1B-Parameter World-Action Model with Low-Cost Future Imaginationcited by 17
  22. 2026G0.5: One Autoregressive Stream for Robot Reasoning and Actioncited by 17
  23. 2026S-VAM: Shortcut Video-Action Model by Self-Distilling Geometric and Semantic Foresightcited by 16
  24. 2026Flash-WAM: Modality-Aware Distillation for World Action Modelscited by 16
  25. 2026Action-to-Action Flow Matchingcited by 15
  26. 2026MaskWAM: Unifying Mask Prompting and Prediction for World-Action Modelscited by 15
  27. 2026WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigationcited by 14
  28. 2026WALL-WM: Carving World Action Modeling at the Event Jointscited by 14
  29. 2026Next Forcing: Causal World Modeling with Multi-Chunk Predictioncited by 14
  30. 2026Learning 4D Geometric Priors for Inference-Efficient World Action Modelscited by 14
  31. 2026Faster-WAM: Efficient Inference-Time Future Conditioning for Robust World Action Modelscited by 14
  32. 2026World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetrycited by 13
  33. 2026World-Value-Action Model: Implicit Planning for Vision-Language-Action Systemscited by 13
  34. 2026Scaling Mixture-of-Experts Video Pretraining for Embodied Intelligencecited by 13
  35. 2026RoboTTT: Context Scaling for Robot Policiescited by 13
  36. 2026VLANeXt: Recipes for Building Strong VLA Modelscited by 12
  37. 2026AIM: Intent-Aware Unified world action Modeling with Spatial Value Mapscited by 12
  38. 2026DriveWAM: Video Generative Priors Enable Scalable World-Action Modeling for Autonomous Drivingcited by 12

50 most cited of 289 All 289 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026OpenWAM: An Open Framework for Composable World-Action Models
  2. 2026Vid2WAM: Distilling Video Diffusion Priors into World Action Models
  3. 2026Persistent Robot World Models: Stabilizing Multi-Step Rollouts via Reinforcement Learning
  4. 2026Qwen-RobotWorld Technical Report: Unifying Embodied World Modeling through Language-Conditioned Video Generation
  5. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Model
  6. 2026DriftWorld: Fast World Modeling through Drifting
  7. 2026EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields
  8. 2026BWM: A Low-Cost High-Fidelity World Simulator for Robot Learning