ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?

• URL: http://arxiv.org/abs/2606.19531v1
• Date: Wed, 17 Jun 2026 19:25:28 GMT
• Title: ImageWAM: Do World Action Models Really Need Video Generation, or Just Image Editing?
• Abstract summary: We propose ImageWAM, a framework that repurposes pretrained image editing models for robot action prediction.<n>ImageWAM does not decode the target frame at inference time; instead, it conditions a flow-matching action expert on the KV caches.<n>It also reduces FLOPs to 1/6 and latency to 1/4 of video-based WAMs.
• Score: 70.07849531480132
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: World Action Models (WAMs) commonly rely on video generation to bridge visual world modeling and robot control. However, video-based WAMs face three coupled limitations: dense multi-frame future tokens make inference costly, full video prediction spends capacity on action-irrelevant temporal and appearance details, and long-horizon future imagination may introduce errors that mislead action prediction. These issues raise a simple question: Does world action model really need video generation? We propose ImageWAM, a simple WAM framework that repurposes pretrained image editing models for robot action prediction. In contrast to video generation, image editing provides a better-matched prior: it only needs to model a target-frame transformation, focuses on action-relevant current-to-target visual differences, and grounds task instructions to localized visual changes through edit pretraining. In practice, ImageWAM does not decode the target frame at inference time; instead, it conditions a flow-matching action expert on the KV caches produced by image-editing denoising, using them as a compact world-action context. ImageWAM outperforms standard VLA baselines and matching competitive WAMs without additional policy pretraining across different simulator and real-world experiments. It also reduces FLOPs to 1/6 and latency to 1/4 of video-based WAMs. Attention analysis further shows that editing caches focus on task-relevant change regions, supporting image editing as an effective alternative to video-based world-action modeling.

Related papers

• World Tokens: Enhancing Embodied Policies with Training-Time World Modeling [29.442423651761107]
  We introduce World Tokens, an embodied policy architecture built around a World Adapter.<n>World Tokens bridges visual-language understanding, world-dynamics modeling, and action generation.<n>We attains the best reported averages on SIMPLE, substantially improves real-world R1 Pro success over a matched action-only baseline, and generates each action chunk at VLA-level latency.
  arXiv  Detail & Related papers  (2026-08-10T15:30:38Z)
• SWEET: Sparse World Modeling with Image Editing for Embodied Task Execution [61.612676324369595]
  We study whether image editing models can serve as sparse visual world models for robot manipulation.<n>We propose SWEET, a one-shot prediction visual planning framework.<n>Experiments on DROID and RoboMimic show that SWEET improves prediction across seen and unseen scenes.
  arXiv  Detail & Related papers  (2026-05-19T03:54:46Z)
• Action Images: End-to-End Policy Learning via Multiview Video Generation [70.67042168383638]
  We present Action Images, a unified world action model that formulates policy learning as multiview video generation.<n>Our model achieves the strongest zero-shot success rates and improves video-action joint generation quality over prior video-space world models.
  arXiv  Detail & Related papers  (2026-04-07T17:59:30Z)
• IMAGEdit: Let Any Subject Transform [61.666509860041124]
  IMAGEdit is a training-free framework for any number of video subject editing.<n>It manipulates the appearances of multiple designated subjects while preserving non-target regions.<n>It is compatible with any mask-driven video generation model.
  arXiv  Detail & Related papers  (2025-10-01T17:59:56Z)
• RealGeneral: Unifying Visual Generation via Temporal In-Context Learning with Video Models [22.042487298092883]
  RealGeneral is a novel framework that reformulates image generation as a conditional frame prediction task.<n>It mitigates a 14.5% improvement in subject similarity for customized generation and a 10% enhancement in image quality for canny-to-image task.
  arXiv  Detail & Related papers  (2025-03-13T14:31:52Z)
• FramePainter: Endowing Interactive Image Editing with Video Diffusion Priors [64.54220123913154]
  We introduce FramePainter as an efficient instantiation of image-to-video generation problem.<n>It only uses a lightweight sparse control encoder to inject editing signals.<n>It domainantly outperforms previous state-of-the-art methods with far less training data.
  arXiv  Detail & Related papers  (2025-01-14T16:09:16Z)
• VASE: Object-Centric Appearance and Shape Manipulation of Real Videos [108.60416277357712]
  In this work, we introduce a framework that is object-centric and is designed to control both the object's appearance and, notably, to execute precise and explicit structural modifications on the object. We build our framework on a pre-trained image-conditioned diffusion model, integrate layers to handle the temporal dimension, and propose training strategies and architectural modifications to enable shape control. We evaluate our method on the image-driven video editing task showing similar performance to the state-of-the-art, and showcasing novel shape-editing capabilities.
  arXiv  Detail & Related papers  (2024-01-04T18:59:24Z)
• Pix2Video: Video Editing using Image Diffusion [43.07444438561277]
  We investigate how to use pre-trained image models for text-guided video editing. Our method works in two simple steps: first, we use a pre-trained structure-guided (e.g., depth) image diffusion model to perform text-guided edits on an anchor frame. We demonstrate that realistic text-guided video edits are possible, without any compute-intensive preprocessing or video-specific finetuning.
  arXiv  Detail & Related papers  (2023-03-22T16:36:10Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.