mlsanityData to 7 Oct 2026

DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge

arXiv 2507.04447 ↗First posted 6 Jul 2025cs.CV cs.ROcited by 203

On the map: Vision-language-action models → World model-based VLA

Abstract (arXiv)

Recent advances in vision-language-action (VLA) models have shown promise in integrating image generation with action prediction to improve generalization and reasoning in robot manipulation. However, existing methods are limited to challenging image-based forecasting, which suffers from redundant information and lacks comprehensive and critical world knowledge, including dynamic, spatial and semantic information. To address these limitations, we propose DreamVLA, a novel VLA framework that integrates comprehensive world knowledge forecasting to enable inverse dynamics modeling, thereby establishing a perception-prediction-action loop for manipulation tasks. Specifically, DreamVLA introduces a dynamic-region-guided world knowledge prediction, integrated with the spatial and semantic cues, which provide compact yet comprehensive representations for action planning. This design aligns with how humans interact with the world by first forming abstract multimodal reasoning chains before acting. To mitigate interference among the dynamic, spatial and semantic information during training, we adopt a block-wise structured attention mechanism that masks their mutual attention, preventing information leakage and keeping each representation clean and disentangled. Moreover, to model the conditional distribution over future actions, we employ a diffusion-based transformer that disentangles action representations from shared latent features. Extensive experiments on both real-world and simulation environments demonstrate that DreamVLA achieves 76.7% success rate on real robot tasks and 4.44 average length on the CALVIN ABC-D benchmarks.

Key facts. Cited by 203 papers in the map (data through 7 Oct 2026). Placed in World model-based VLA, one of 13 directions in Vision-language-action models. Builds on 132 of its 151 references that are in the map. First posted on arXiv 6 Jul 2025.

Builds on

132 of 151 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Pixel Motion as Universal Representation for Robot Control12 May

Other references · 131

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
  4. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  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. 2018Representation Learning with Contrastive Predictive Codingcited by 7,662
  9. 2021Masked Autoencoders Are Scalable Vision Learnerscited by 7,339
  10. 2022Scalable Diffusion Models with Transformerscited by 5,931
  11. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,223
  12. 2017PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Spacecited by 4,384
38 more
  1. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  2. 2021Zero-Shot Text-to-Image Generationcited by 4,276
  3. 2017Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layercited by 3,413
  4. 2023RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Controlcited by 2,993
  5. 2024OpenVLA: An Open-Source Vision-Language-Action Modelcited by 2,777
  6. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  7. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  8. 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,302
  9. 2024π0: A Vision-Language-Action Flow Model for General Robot Controlcited by 2,297
  10. 2023PaLM-E: An Embodied Multimodal Language Modelcited by 2,037
  11. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  12. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  13. 2023Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardwarecited by 1,490
  14. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
  15. 2024Depth Anything V2cited by 1,385
  16. 2024Depth Anything: Unleashing the Power of Large-Scale Unlabeled Datacited by 1,346
  17. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  18. 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,172
  19. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,167
  20. 2022Inner Monologue: Embodied Reasoning through Planning with Language Modelscited by 1,057
  21. 2022A Generalist Agentcited by 802
  22. 2024DROID: A Large-Scale In-The-Wild Robot Manipulation Datasetcited by 801
  23. 2018Recurrent World Models Facilitate Policy Evolutioncited by 761
  24. 2023VoxPoser: Composable 3D Value Maps for Robotic Manipulation with Language Modelscited by 733
  25. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  26. 2024RDT-1B: a Diffusion Foundation Model for Bimanual Manipulationcited by 670
  27. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  28. 2024Open-Sora: Democratizing Efficient Video Production for Allcited by 637
  29. 2021CLIPort: What and Where Pathways for Robotic Manipulationcited by 617
  30. 2021CALVIN: A Benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Taskscited by 564
  31. 2023CoTracker: It is Better to Track Togethercited by 516
  32. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  33. 2023Learning Universal Policies via Text-Guided Video Generationcited by 506
  34. 2025SpatialVLA: Exploring Spatial Representations for Visual-Language-Action Modelcited by 502
  35. 2025CoT-VLA: Visual Chain-of-Thought Reasoning for Vision-Language-Action Modelscited by 440
  36. 2024CogACT: A Foundational Vision-Language-Action Model for Synergizing Cognition and Action in Robotic Manipulationcited by 411
  37. 2025AgiBot World Colosseo: A Large-scale Manipulation Platform for Scalable and Intelligent Embodied Systemscited by 390
  38. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386

50 most cited of 131 All 131 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 37; 2026: 166.

203 papers.

Sort:

By area:

  1. 2026Fast-WAM: Do World Action Models Need Test-time Future Imagination?cited by 311
  2. 2025VLA-Adapter: An Effective Paradigm for Tiny-Scale Vision-Language-Action Modelcited by 140
  3. 2026GigaWorld-Policy: An Efficient Action-Centered World--Action Modelcited by 129
  4. 2026VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Modelcited by 104
  5. 2025F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actionscited by 85
  6. 2026Unified 4D World Action Modeling from Video Priors with Asynchronous Denoisingcited by 65
  7. 2026InternVLA-A1: Unifying Understanding, Generation and Action for Robotic Manipulationcited by 48
  8. 2025Pure Vision Language Action (VLA) Models: A Comprehensive Surveycited by 46
  9. 2025DepthVLA: Enhancing Vision-Language-Action Models with Depth-Aware Spatial Reasoningcited by 44
  10. 2026World Model for Robot Learning: A Comprehensive Surveycited by 42
  11. 2025Unified Diffusion VLA: Vision-Language-Action Model via Joint Discrete Denoising Diffusion Processcited by 37
  12. 2026Do World Action Models Generalize Better than VLAs? A Robustness Studycited by 35
38 more
  1. 2026SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Drivingcited by 34
  2. 2025Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Modelcited by 33
  3. 2026ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?cited by 33
  4. 2025HiF-VLA: Hindsight, Insight and Foresight through Motion Representation for Vision-Language-Action Modelscited by 30
  5. 2026ACoT-VLA: Action Chain-of-Thought for Vision-Language-Action Modelscited by 30
  6. 2026LaST0: Latent Spatio-Temporal Chain-of-Thought for Robotic Vision-Language-Action Modelcited by 28
  7. 2026ReMem-VLA: Empowering Vision-Language-Action Model with Memory via Dual-Level Recurrent Queriescited by 28
  8. 2026When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAscited by 27
  9. 2025Efficient Vision-Language-Action Models for Embodied Manipulation: A Systematic Surveycited by 25
  10. 2026BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generationcited by 25
  11. 2025MLA: A Multisensory Language-Action Model for Multimodal Understanding and Forecasting in Robotic Manipulationcited by 22
  12. 2025Mixture of Horizons in Action Chunkingcited by 20
  13. 2026PALM: Progress-Aware Policy Learning via Affordance Reasoning for Long-Horizon Robotic Manipulationcited by 20
  14. 2026DualCoT-VLA: Visual-Linguistic Chain of Thought via Parallel Reasoning for Vision-Language-Action Modelscited by 20
  15. 2025QDepth-VLA: Quantized Depth Prediction as Auxiliary Supervision for Vision-Language-Action Modelscited by 19
  16. 2026Latent Reasoning VLA: Latent Thinking and Prediction for Vision-Language-Action Modelscited by 19
  17. 2026Global Prior Meets Local Consistency: Dual-Memory Augmented Vision-Language-Action Model for Efficient Robotic Manipulationcited by 19
  18. 2025Reasoning in Space via Grounding in the Worldcited by 18
  19. 2025Dream-VL & Dream-VLA: Open Vision-Language and Vision-Language-Action Models with Diffusion Language Model Backbonecited by 18
  20. 2025Seeing to Act, Prompting to Specify: A Bayesian Factorization of Vision Language Action Policycited by 17
  21. 2025AstraNav-World: World Model for Foresight Control and Consistencycited by 17
  22. 2026Towards Generalizable Robotic Manipulation in Dynamic Environmentscited by 17
  23. 2026VP-VLA: Visual Prompting as an Interface for Vision-Language-Action Modelscited by 17
  24. 2026Dream-Tac: A Unified Tactile World Action Model for Contact-Rich Robot Manipulationcited by 17
  25. 2025MonoDream: Monocular Vision-Language Navigation with Panoramic Dreamingcited by 15
  26. 2025A Step Toward World Models: A Survey on Robotic Manipulationcited by 15
  27. 2025NavForesee: A Unified Vision-Language World Model for Hierarchical Planning and Dual-Horizon Navigation Predictioncited by 15
  28. 2025GeoPredict: Leveraging Predictive Kinematics and 3D Gaussian Geometry for Precise VLA Manipulationcited by 15
  29. 2026MaskWAM: Unifying Mask Prompting and Prediction for World-Action Modelscited by 15
  30. 2025Learning to Feel the Future: DreamTacVLA for Contact-Rich Manipulationcited by 14
  31. 2026FutureVLA: Joint Visuomotor Prediction for Vision-Language-Action Modelcited by 14
  32. 2026VTAM: Video-Tactile-Action Models for Complex Physical Interaction Beyond VLAscited by 14
  33. 2025Continually Evolving Skill Knowledge in Vision Language Action Modelcited by 13
  34. 2025ManualVLA: A Unified VLA Model for Chain-of-Thought Manual Generation and Robotic Manipulationcited by 13
  35. 2026World-Value-Action Model: Implicit Planning for Vision-Language-Action Systemscited by 13
  36. 2025NanoVLA: Routing Decoupled Vision-Language Understanding for Nano-sized Generalist Robotic Policiescited by 12
  37. 2025Mantis: A Versatile Vision-Language-Action Model with Disentangled Visual Foresightcited by 12
  38. 2025Unifying Perception and Action: A Hybrid-Modality Pipeline with Implicit Visual Chain-of-Thought for Robotic Action Generationcited by 12

50 most cited of 203 All 203 (JSON)

Similar, not cited

Close in wording, no citation either way

  1. 2026ThinkingVLA: Interleaved Vision and Language Reasoning for Robotic Manipulation
  2. 2025VideoVLA: Video Generators Can Be Generalizable Robot Manipulators
  3. 2026H-VLA: Hierarchical Vision-Language-Action Model with Key-Action Reasoning and Motion Planning in a Unified Action Space
  4. 2026Scaling World Model for Hierarchical Manipulation Policies
  5. 2026AWM-VLA: AlignedWorld Modeling for Efficient and Explainable Vision-Language-Action Policies
  6. 2026AC^2-VLA: Action-Context-Aware Adaptive Computation in Vision-Language-Action Models for Efficient Robotic Manipulation
  7. 2026DAM-VLA: A Dynamic Action Model-Based Vision-Language-Action Framework for Robot Manipulation
  8. 2026PHR-VLA: Planning Horizon Reasoning for Vision-Language-Action Models