# World model-based VLA

Area: [Vision-language-action models](https://mlsanity.com/vla/index.md). HTML: https://mlsanity.com/vla/world-model-based-vla/

## Key facts

- World model-based VLA: 76 papers on arXiv since 2025 (data through 7 Oct 2026).
- 22 of its 76 mapped papers (29%) cite “DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge” (2025, arXiv 2507.04447).
- 15 of its 76 mapped papers (20%) cite “World Action Models are Zero-shot Policies” (2026, arXiv 2602.15922).
- 18 new papers 17 Sep–7 Oct.

## Most cited here

- [DreamVLA: A Vision-Language-Action Model Dreamed with Comprehensive World Knowledge](https://mlsanity.com/paper/2507.04447/) (2025), cited by 22 papers here
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026), cited by 15 papers here
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026), cited by 14 papers here
- [VLA-JEPA: Enhancing Vision-Language-Action Model with Latent World Model](https://mlsanity.com/paper/2602.10098/) (2026), cited by 12 papers here
- [F1: A Vision-Language-Action Model Bridging Understanding and Generation to Actions](https://mlsanity.com/paper/2509.06951/) (2025), cited by 11 papers here
- [RynnVLA-002: A Unified Vision-Language-Action and World Model](https://mlsanity.com/paper/2511.17502/) (2025), cited by 10 papers here
- [Ctrl-World: A Controllable Generative World Model for Robot Manipulation](https://mlsanity.com/paper/2510.10125/) (2025), cited by 8 papers here
- [World Guidance: World Modeling in Condition Space for Action Generation](https://mlsanity.com/paper/2602.22010/) (2026), cited by 5 papers here
- [JEPA-VLA: Video Predictive Embedding is Needed for VLA Models](https://mlsanity.com/paper/2602.11832/) (2026), cited by 4 papers here
- [OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation](https://mlsanity.com/paper/2605.06481/) (2026), cited by 4 papers here

## New (17 Sep–7 Oct)

- [Video Prediction Policy 2: Predict Better, Act Better](https://mlsanity.com/paper/2610.10270/) (2026-10-07)
- [Juno: Taming Predictive Latents for Vision-Language-Action Models](https://mlsanity.com/paper/2610.09940/) (2026-10-07)
- [ViDAL: A Visual Dynamics-Grounded Action Latent Space for Vision-Language-Action Models](https://mlsanity.com/paper/2610.08150/) (2026-10-06)
- [ForeAct3D: Policy-Grounded Future World Modeling for VLA Policies](https://mlsanity.com/paper/2610.04607/) (2026-10-03)
- [SUAVE: Unified Video-Action Models via Masked Diffusion](https://mlsanity.com/paper/2610.04009/) (2026-10-02)
- [Imagine the Future, Internalize the Gist: Efficient VLA Reasoning via Internalized Spatiotemporal Imagination](https://mlsanity.com/paper/2610.02626/) (2026-10-02)
- [World-Calibrated Proposal-to-Action Flow for Vision-Language-Action Models](https://mlsanity.com/paper/2610.02323/) (2026-10-01)
- [UniWAM: Unified World-Action Model](https://mlsanity.com/paper/2610.02054/) (2026-10-01)
- [ATI-VLA: Action-Centric Predictive Vision-Language-Action Models via Actionable Alignment Then Adaptive Injection](https://mlsanity.com/paper/2610.01741/) (2026-10-01)
- [Devol-ONE: One Autoregressive Mixture of Transformers to Unify Vision-Language-Action and Latent World Modeling](https://mlsanity.com/paper/2609.32193/) (2026-10-01)
- [FRAM: Trajectory-Guided Visual Feature Selection for Compact Language-Conditioned Robot Manipulation](https://mlsanity.com/paper/2609.30965/) (2026-10-01)
- [Token-World: World Modeling in Vision-Language Model Token Space for Robot Manipulation](https://mlsanity.com/paper/2610.00575/) (2026-09-30)
- [EWAM: Emergent Depth-Wise Specialization in a Unified Embodied Model -- From Semantic Understanding through Visual Foresight to Action](https://mlsanity.com/paper/2609.39973/) (2026-09-30)
- [MotionWeave: Learning Motion-Centered Future Dynamics for Vision-Language-Action Policies](https://mlsanity.com/paper/2609.39324/) (2026-09-30)
- [WorldGuide: Learning Success-Failure Boundaries in Latent World Models for Vision-Language-Action Policies](https://mlsanity.com/paper/2609.34206/) (2026-09-28)
- [SLIP-VLA: Single-Step Latent Imagination for Policy Learning in Vision-Language-Action Models](https://mlsanity.com/paper/2609.33575/) (2026-09-27)
- [Towards VLA-Dreamer: Refining VLA Behavior Using World Models](https://mlsanity.com/paper/2609.31313/) (2026-09-25)
- [Think Like a World Model, Act Like a VLA: Distilling World-Model Representations into Compact Robot Policies](https://mlsanity.com/paper/2609.24682/) (2026-09-21)