# Video Generators are Robot Policies

arXiv: https://arxiv.org/abs/2508.00795 · HTML: https://mlsanity.com/paper/2508.00795/

## Key facts

- Cited by 92 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2025.

## Built on by (most cited first, 30 of 92)

- [World Action Models are Zero-shot Policies](https://mlsanity.com/paper/2602.15922/) (2026)
- [Fast-WAM: Do World Action Models Need Test-time Future Imagination?](https://mlsanity.com/paper/2603.16666/) (2026)
- [Cosmos Policy: Fine-Tuning Video Models for Visuomotor Control and Planning](https://mlsanity.com/paper/2601.16163/) (2026)
- [mimic-video: Video-Action Models for Generalizable Robot Control Beyond VLAs](https://mlsanity.com/paper/2512.15692/) (2025)
- [π0.7: a Steerable Generalist Robotic Foundation Model with Emergent Capabilities](https://mlsanity.com/paper/2604.15483/) (2026)
- [DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control](https://mlsanity.com/paper/2603.10448/) (2026)
- [Being-H0.7: A Latent World-Action Model from Egocentric Videos](https://mlsanity.com/paper/2605.00078/) (2026)
- [World Action Models: The Next Frontier in Embodied AI](https://mlsanity.com/paper/2605.12090/) (2026)
- [World Model for Robot Learning: A Comprehensive Survey](https://mlsanity.com/paper/2605.00080/) (2026)
- [DSpark: Confidence-Scheduled Speculative Decoding with Semi-Autoregressive Generation](https://mlsanity.com/paper/2607.05147/) (2026)
- [NovaFlow: Zero-Shot Manipulation via Actionable Flow from Generated Videos](https://mlsanity.com/paper/2510.08568/) (2025)
- [Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model](https://mlsanity.com/paper/2510.27607/) (2025)
- [Rethinking Video Generation Model for the Embodied World](https://mlsanity.com/paper/2601.15282/) (2026)
- [Interactive World Simulator for Robot Policy Training and Evaluation](https://mlsanity.com/paper/2603.08546/) (2026)
- [When Vision Overrides Language: Evaluating and Mitigating Counterfactual Failures in VLAs](https://mlsanity.com/paper/2602.17659/) (2026)
- [ViPRA: Video Prediction for Robot Actions](https://mlsanity.com/paper/2511.07732/) (2025)
- [Light-WAM: Efficient World Action Models with State-Fusion Action Decoding](https://mlsanity.com/paper/2606.08242/) (2026)
- [Act2Goal: From World Model To General Goal-conditioned Policy](https://mlsanity.com/paper/2512.23541/) (2025)
- [When to Trust Imagination: Adaptive Action Execution for World Action Models](https://mlsanity.com/paper/2605.06222/) (2026)
- [Flash-WAM: Modality-Aware Distillation for World Action Models](https://mlsanity.com/paper/2606.05254/) (2026)
- [PlayWorld: Learning Robot World Models from Autonomous Play](https://mlsanity.com/paper/2603.09030/) (2026)
- [Contrastive Representation Regularization for Vision-Language-Action Models](https://mlsanity.com/paper/2510.01711/) (2025)
- [WALL-WM: Carving World Action Modeling at the Event Joints](https://mlsanity.com/paper/2606.01955/) (2026)
- [MaskWAM: Unifying Mask Prompting and Prediction for World-Action Models](https://mlsanity.com/paper/2606.13515/) (2026)
- [A Step Toward World Models: A Survey on Robotic Manipulation](https://mlsanity.com/paper/2511.02097/) (2025)
- [Walk through Paintings: Egocentric World Models from Internet Priors](https://mlsanity.com/paper/2601.15284/) (2026)
- [MemoryWAM: Efficient World Action Modeling with Persistent Memory](https://mlsanity.com/paper/2606.20562/) (2026)
- [Zero-WAM: In-Context World-Action Modeling from Human Videos for Open-Ended Task Generalization](https://mlsanity.com/paper/2608.26103/) (2026)
- [Action Images: End-to-End Policy Learning via Multiview Video Generation](https://mlsanity.com/paper/2604.06168/) (2026)
- [AIM: Intent-Aware Unified world action Modeling with Spatial Value Maps](https://mlsanity.com/paper/2604.11135/) (2026)

## Abstract (arXiv)

Despite tremendous progress in dexterous manipulation, current visuomotor policies remain fundamentally limited by two challenges: they struggle to generalize under perceptual or behavioral distribution shifts, and their performance is constrained by the size of human demonstration data. In this paper, we use video generation as a proxy for robot policy learning to address both limitations simultaneously. We propose Video Policy, a modular framework that combines video and action generation that can be trained end-to-end. Our results demonstrate that learning to generate videos of robot behavior allows for the extraction of policies with minimal demonstration data, significantly improving robustness and sample efficiency. Our method shows strong generalization to unseen objects, backgrounds, and tasks, both in simulation and the real world. We further highlight that task success is closely tied to the generated video, with action-free video data providing critical benefits for generalizing to novel tasks. By leveraging large-scale video generative models, we achieve superior performance compared to traditional behavior cloning, paving the way for more scalable and data-efficient robot policy learning.