mlsanityData to 7 Oct 2026

WorldBagel: Uncovering the Power of Unified Multimodal Models for Vision-Language-Action-World Modeling

arXiv 2607.03461 ↗First posted 3 Jul 2026cs.CV cs.LGcited by 0

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

also in 1 more
Abstract (arXiv)

World models aim to capture environment dynamics in ways that support perception, reasoning, and action, and have recently become a central direction in Vision-Language-Action-World (VLAW) modeling. Meanwhile, unified vision-language models have demonstrated strong multimodal generation capabilities, yet their potential as world models remains underexplored. In this work, we introduce textttWorldBagel, a unified VLAW framework built on BAGEL, a modern multimodal unified model, and use it to systematically investigate the role of unification in world modeling. Across multi-task robotic manipulation and cross-domain experiments, textttWorldBagel consistently outperforms task-specific alternatives and learns action representations that are more structured and semantically aligned with visual and linguistic context. Experiments on LIBERO, Language Table, and Franka show that unification is not only an architectural convenience, but also a key factor in learning effective VLAW models, leading to consistent empirical gains and deeper insights into multimodal world modeling. Code and model checkpoints will be released upon acceptance.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Embodied and robot world models, one of 11 directions in World models. Builds on 63 of its 68 references that are in the map. First posted on arXiv 3 Jul 2026.

Builds on

63 of 68 references.

Closest ancestors · 7

Same direction, newest first

  1. 2026DreamDojo: A Generalist Robot World Model from Large-Scale Human Videos6 Feb
  2. 2025RynnVLA-002: A Unified Vision-Language-Action and World Model21 Nov
  3. 2025Semantic World Models22 Oct
  4. 2025Ctrl-World: A Controllable Generative World Model for Robot Manipulation11 Oct
  5. 2025V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning11 Jun
  6. 2025WorldGym: World Model as An Environment for Policy Evaluation31 May
  7. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusion7 Mar

Other references · 56

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,069
  3. 2022Flamingo: a Visual Language Model for Few-Shot Learningcited by 4,337
  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. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  7. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,170
  8. 2022RT-1: Robotics Transformer for Real-World Control at Scalecited by 2,007
  9. 2025π0.5: a Vision-Language-Action Model with Open-World Generalizationcited by 1,653
  10. 2019Dream to Control: Learning Behaviors by Latent Imaginationcited by 1,598
  11. 2018World Modelscited by 1,444
  12. 2024Octo: An Open-Source Generalist Robot Policycited by 1,427
38 more
  1. 2023LIBERO: Benchmarking Knowledge Transfer for Lifelong Robot Learningcited by 1,338
  2. 2018Learning Latent Dynamics for Planning from Pixelscited by 1,221
  3. 2021Perceiver: General Perception with Iterative Attentioncited by 1,089
  4. 2015Prioritized Experience Replaycited by 1,070
  5. 2024Chameleon: Mixed-Modal Early-Fusion Foundation Modelscited by 904
  6. 2025Emerging Properties in Unified Multimodal Pretrainingcited by 855
  7. 2025Fine-Tuning Vision-Language-Action Models: Optimizing Speed and Successcited by 844
  8. 2022A Generalist Agentcited by 802
  9. 2024Show-o: One Single Transformer to Unify Multimodal Understanding and Generationcited by 734
  10. 2025FAST: Efficient Action Tokenization for Vision-Language-Action Modelscited by 643
  11. 2025SmolVLA: A Vision-Language-Action Model for Affordable and Efficient Roboticscited by 507
  12. 2024Transfusion: Predict the Next Token and Diffuse Images with One Multi-Modal Modelcited by 468
  13. 2024Janus: Decoupling Visual Encoding for Unified Multimodal Understanding and Generationcited by 447
  14. 2025UniVLA: Learning to Act Anywhere with Task-centric Latent Actionscited by 386
  15. 2024DINO-WM: World Models on Pre-trained Visual Features enable Zero-shot Planningcited by 357
  16. 2019Learning Latent Plans from Playcited by 310
  17. 2024VILA-U: a Unified Foundation Model Integrating Visual Understanding and Generationcited by 290
  18. 2026Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planningcited by 274
  19. 2025History-Guided Video Diffusioncited by 165
  20. 2024Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learningcited by 158
  21. 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planningcited by 152
  22. 2024Multimodal Diffusion Transformer: Learning Versatile Behavior from Multimodal Goalscited by 131
  23. 2025Training Agents Inside of Scalable World Modelscited by 122
  24. 2025Emu3.5: Native Multimodal Models are World Learnerscited by 119
  25. 2025HunyuanWorld 1.0: Generating Immersive, Explorable, and Interactive 3D Worlds from Words or Pixelscited by 91
  26. 2025InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policycited by 83
  27. 2025Zebra-CoT: A Dataset for Interleaved Vision Language Reasoningcited by 78
  28. 2018PointSIFT: A SIFT-like Network Module for 3D Point Cloud Semantic Segmentationcited by 58
  29. 2015On Learning to Think: Algorithmic Information Theory for Novel Combinations of Reinforcement Learning Controllers and Recurrent Neural World Modelscited by 52
  30. 2024MUSE-VL: Modeling Unified VLM through Semantic Discrete Encodingcited by 44
  31. 2024Diffusion Transformer Policycited by 41
  32. 2022Tracking Objects as Pixel-wise Distributionscited by 36
  33. 2026BagelVLA: Enhancing Long-Horizon Manipulation via Interleaved Vision-Language-Action Generationcited by 25
  34. 2021ProTo: Program-Guided Transformer for Program-Guided Taskscited by 19
  35. 2025Unified Multimodal Models as Auto-Encoderscited by 13
  36. 2026MV-S2V: Multi-View Subject-Consistent Video Generationcited by 9
  37. 2026ACWM-Phys: Investigating Generalized Physical Interaction in Action-Conditioned Video World Modelscited by 9
  38. 2024Grounding and Enhancing Grid-based Models for Neural Fieldscited by 8

50 most cited of 56 All 56 (JSON)

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026World-Language-Action Model for Unified World Modeling, Language Reasoning, and Action Synthesis
  2. 2026UniWAM: Unified World-Action Model
  3. 2025Adapting Vision-Language Models for Evaluating World Models
  4. 2026Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
  5. 2026AWM-VLA: AlignedWorld Modeling for Efficient and Explainable Vision-Language-Action Policies
  6. 2026DeltaVLA: Prior-Guided Vision-Language-Action Models via World Knowledge Variation
  7. 2025Unified Vision-Language-Action Model
  8. 2026Do World Action Models Generalize Better than VLAs? A Robustness Study