--- title: Beyond VLAs: How World Action Models Reshape Robot... description: World Action Models (WAMs) are proposed as a successor to Vision-Language-Action (VLA) models for robot manipulation. While VLAs use vision-language model... canonical: https://daily.dev/posts/beyond-vlas-how-world-action-models-reshape-robot-manipulation-t943bn1zw twitter:card: summary_large_image twitter:site: @dailydotdev og:type: website og:site_name: daily.dev og:title: Beyond VLAs: How World Action Models Reshape Robot Manipulation | daily.dev og:description: World Action Models (WAMs) are proposed as a successor to Vision-Language-Action (VLA) models for robot manipulation. While VLAs use vision-language model... og:url: https://daily.dev/posts/beyond-vlas-how-world-action-models-reshape-robot-manipulation-t943bn1zw og:image: https://api.daily.dev/og/posts/t943Bn1Zw.png og:image:alt: Beyond VLAs: How World Action Models Reshape Robot Manipulation og:image:width: 1200 og:image:height: 630 og:locale: en --- > ## Documentation Index > Fetch the complete documentation index at: https://daily.dev/llms.txt > Use this file to discover all available pages before exploring further. # Beyond VLAs: How World Action Models Reshape Robot Manipulation **[NVIDIA Developer](https://daily.dev/sources/nvidiadev)** · 7 min read · 0 upvotes · 0 comments ## Summary World Action Models (WAMs) are proposed as a successor to Vision-Language-Action (VLA) models for robot manipulation. While VLAs use vision-language model backbones that describe the world, WAMs use video world models that predict how the world evolves, giving them a physics prior. NVIDIA's Cosmos 3 is presented as an open foundation model for building WAMs, featuring a Mixture-of-Transformers architecture trained on 767M images, 348M videos, and 8M action samples. Two post-trained policy models are available: Cosmos3-Nano-Policy-DROID (16B) for workstation serving and Cosmos3-Edge-Policy-DROID (4B) for on-device deployment on Jetson hardware. Benchmarks show the omni-pretrained checkpoint improved RoboLab success rates from 28.1% to 36.8% over a base checkpoint, demonstrating the value of the physical prior. WAMs require less task-specific data, generalize better to unseen environments, and adapt faster to new robot embodiments. ## Full article daily.dev links to this article rather than hosting it. Read it at the original source: ## Similar posts on daily.dev - [A Comprehensive Overview of Vision-Language-Action Models](https://daily.dev/posts/a-comprehensive-overview-of-vision-language-action-models-3qx6p4llr) · DigitalOcean Community · 1 upvotes · 0 comments - [How Visual-Language-Action \(VLA\) Models Work](https://daily.dev/posts/how-visual-language-action-vla-models-work-jln0xmknn) · Towards Data Science · 2 upvotes · 0 comments - [Vision-Language-Action \(VLA\) Models: From Seeing to Acting with AI Training Data](https://daily.dev/posts/vision-language-action-vla-models-from-seeing-to-acting-with-ai-training-data-cw2kbituu) · Medium · 1 upvotes · 0 comments --- Tags: [#robotics](https://daily.dev/tags/robotics) [View this post on daily.dev](https://daily.dev/posts/beyond-vlas-how-world-action-models-reshape-robot-manipulation-t943bn1zw) ```json {"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]} {"@context":"https://schema.org","@type":"TechArticle","headline":"Beyond VLAs: How World Action Models Reshape Robot Manipulation","url":"https://daily.dev/posts/beyond-vlas-how-world-action-models-reshape-robot-manipulation-t943bn1zw","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/beyond-vlas-how-world-action-models-reshape-robot-manipulation-t943bn1zw"},"datePublished":"2026-08-04T16:03:53.317Z","dateModified":"2026-08-06T13:33:42.283Z","description":"World Action Models (WAMs) are proposed as a successor to Vision-Language-Action (VLA) models for robot manipulation. While VLAs use vision-language model...","image":"https://developer-blogs.nvidia.com/wp-content/uploads/2026/07/Cosmos-World-Models.gif","thumbnailUrl":"https://developer-blogs.nvidia.com/wp-content/uploads/2026/07/Cosmos-World-Models.gif","isAccessibleForFree":true,"articleSection":"NVIDIA Developer","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"NVIDIA Developer","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/86e45aab42ba48ce83103d01b1119910","url":"https://daily.dev/sources/nvidiadev"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/beyond-vlas-how-world-action-models-reshape-robot-manipulation-t943bn1zw","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"robotics","timeRequired":"PT7M"} {"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"NVIDIA Developer","item":"https://daily.dev/sources/nvidiadev"},{"@type":"ListItem","position":3,"name":"Beyond VLAs: How World Action Models Reshape Robot Manipulation"}]} ```