# Action Images: End-to-End Policy Learning via Multiview Video Generation

arXiv: https://arxiv.org/abs/2604.06168 · HTML: https://mlsanity.com/paper/2604.06168/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in Embodied and robot world models, one of 11 directions in World models.
- Builds on 63 of its 71 references that are in the map.
- First posted on arXiv 7 Apr 2026.

## Placed in

- World models / [Embodied and robot world models](https://mlsanity.com/wm/embodied-and-robot-world-models/)

## Builds on (most cited first, 30 of 63)

- [Classifier-Free Diffusion Guidance](https://mlsanity.com/paper/2207.12598/) (2022)
- [Flow Matching for Generative Modeling](https://mlsanity.com/paper/2210.02747/) (2022)
- [RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control](https://mlsanity.com/paper/2307.15818/) (2023)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Diffusion Policy: Visuomotor Policy Learning via Action Diffusion](https://mlsanity.com/paper/2303.04137/) (2023)
- [Wan: Open and Advanced Large-Scale Video Generative Models](https://mlsanity.com/paper/2503.20314/) (2025)
- [π0: A Vision-Language-Action Flow Model for General Robot Control](https://mlsanity.com/paper/2410.24164/) (2024)
- [RT-1: Robotics Transformer for Real-World Control at Scale](https://mlsanity.com/paper/2212.06817/) (2022)
- [π0.5: a Vision-Language-Action Model with Open-World Generalization](https://mlsanity.com/paper/2504.16054/) (2025)
- [VGGT: Visual Geometry Grounded Transformer](https://mlsanity.com/paper/2503.11651/) (2025)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [ZeRO: Memory Optimizations Toward Training Trillion Parameter Models](https://mlsanity.com/paper/1910.02054/) (2019)
- [WorldSimBench: Towards Video Generation Models as World Simulators](https://mlsanity.com/paper/2410.18072/) (2024)
- [DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset](https://mlsanity.com/paper/2403.12945/) (2024)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023)
- [RLBench: The Robot Learning Benchmark & Learning Environment](https://mlsanity.com/paper/1909.12271/) (2019)
- [BridgeData V2: A Dataset for Robot Learning at Scale](https://mlsanity.com/paper/2308.12952/) (2023)
- [Learning Universal Policies via Text-Guided Video Generation](https://mlsanity.com/paper/2302.00111/) (2023)
- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [DayDreamer: World Models for Physical Robot Learning](https://mlsanity.com/paper/2206.14176/) (2022)
- [3D-VLA: A 3D Vision-Language-Action Generative World Model](https://mlsanity.com/paper/2403.09631/) (2024)
- [π*0.6: a VLA That Learns From Experience](https://mlsanity.com/paper/2511.14759/) (2025)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations](https://mlsanity.com/paper/2412.14803/) (2024)
- [TAPIR: Tracking Any Point with per-frame Initialization and temporal Refinement](https://mlsanity.com/paper/2306.08637/) (2023)
- [ReCamMaster: Camera-Controlled Generative Rendering from A Single Video](https://mlsanity.com/paper/2503.11647/) (2025)
- [Navigation World Models](https://mlsanity.com/paper/2412.03572/) (2024)
- [Imitating Human Behaviour with Diffusion Models](https://mlsanity.com/paper/2301.10677/) (2023)
- [Text-To-4D Dynamic Scene Generation](https://mlsanity.com/paper/2301.11280/) (2023)

## Built on by (most cited first, 12 of 12)

- [4D-WAM: Infusing Spatiotemporal Awareness into World Action Models through Trajectory Fields](https://mlsanity.com/paper/2608.08023/) (2026)
- [World Action Models: A Survey](https://mlsanity.com/paper/2606.20781/) (2026)
- [World-Action Models for Robot Learning and Control: A Survey](https://mlsanity.com/paper/2609.16074/) (2026)
- [EA-WM: Event-Aware Generative World Model with Structured Kinematic-to-Visual Action Fields](https://mlsanity.com/paper/2605.06192/) (2026)
- [iMaC: Translating Actions into Motion and Contact Images for Embodied World Models](https://mlsanity.com/paper/2606.09813/) (2026)
- [SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution](https://mlsanity.com/paper/2605.19319/) (2026)
- [XPACE: Joint World and Action Modeling from Heterogeneous Experience](https://mlsanity.com/paper/2609.17372/) (2026)
- [An Action Is Worth One Patch: Unified World-Action Modeling with PatchWAM](https://mlsanity.com/paper/2609.25961/) (2026)
- [Revision, Not Restart: Revisable Visual Plans for Closed-Loop World-Action Models](https://mlsanity.com/paper/2609.35439/) (2026)
- [WorldLine: Action-Driven Visual Simulation for Robotic Manipulation](https://mlsanity.com/paper/2609.38059/) (2026)
- [XGenAct: Geometry-Enhanced World Action Models through Cross-Task Generation](https://mlsanity.com/paper/2610.03516/) (2026)
- [KineWorld: Action-Induced Transport Fields for Embodied World Modeling](https://mlsanity.com/paper/2610.06349/) (2026)

## Abstract (arXiv)

World action models (WAMs) have emerged as a promising direction for robot policy learning, as they can leverage powerful video backbones to model the future states. However, existing approaches often rely on separate action modules, or use action representations that are not pixel-grounded, making it difficult to fully exploit the pretrained knowledge of video models and limiting transfer across viewpoints and environments. In this work, we present Action Images, a unified world action model that formulates policy learning as multiview video generation. Instead of encoding control as low-dimensional tokens, we translate 7-DoF robot actions into interpretable action images: multi-view action videos that are grounded in 2D pixels and explicitly track robot-arm motion. This pixel-grounded action representation allows the video backbone itself to act as a zero-shot policy, without a separate policy head or action module. Beyond control, the same unified model supports video-action joint generation, action-conditioned video generation, and action labeling under a shared representation. On RLBench and real-world evaluations, our model achieves the strongest zero-shot success rates and improves video-action joint generation quality over prior video-space world models, suggesting that interpretable action images are a promising route to policy learning.