https://jaehun.me/en/tags/video-generation/Recent content in Video Generation on Jaehun's BlogHugoen-USTue, 15 Sep 2026 08:56:51 +0900https://jaehun.me/en/posts/programmable-world-model/Tue, 15 Sep 2026 00:00:00 +0900https://jaehun.me/en/posts/programmable-world-model/<p><a href="https://arxiv.org/abs/2609.10540"target="_blank" class="inline-flex items-center gap-1" >Paper<svg class="h-3 w-3 flex-shrink-0" id="external-link" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><path fill="none" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2" d="M15 3h6v6m-11 5L21 3m-3 10v6a2 2 0 0 1-2 2H5a2 2 0 0 1-2-2V8a2 2 0 0 1 2-2h6"/></svg> </a></p> <h2 id="programmable-world-model--embedding-executable-state-into-generative-worlds">Programmable World Model — Embedding &ldquo;Executable State&rdquo; into Generative Worlds<a href="#programmable-world-model--embedding-executable-state-into-generative-worlds" class="heading-anchor" aria-label="Link to this section"><svg class="h-4 w-4" aria-hidden="true" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><g fill="none" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"/><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"/></g></svg></a></h2><h2 id="one-line-summary-tldr">One-Line Summary (TL;DR)<a href="#one-line-summary-tldr" class="heading-anchor" aria-label="Link to this section"><svg class="h-4 w-4" aria-hidden="true" xmlns="http://www.w3.org/2000/svg" viewBox="0 0 24 24"><g fill="none" stroke="currentColor" stroke-linecap="round" stroke-linejoin="round" stroke-width="2"><path d="M10 13a5 5 0 0 0 7.54.54l3-3a5 5 0 0 0-7.07-7.07l-1.72 1.71"/><path d="M14 11a5 5 0 0 0-7.54-.54l-3 3a5 5 0 0 0 7.07 7.07l1.71-1.71"/></g></svg></a></h2><p>Video world models are producing increasingly realistic interactive environments, but they only remember the pixels that flash across the screen — they have no idea &ldquo;what state the world is actually in right now.&rdquo; Alaya Lab&rsquo;s <strong>Programmable World Model (PWM)</strong> separates a <strong>lightweight engine</strong> that manages the state of the world from a <strong>generative renderer</strong> that paints that state into images. State stays programmable and verifiable, while the fine details of appearance and motion are left to a pretrained video generation model. On its own benchmark, <strong>CombatStateBench</strong>, it achieves <strong>94%</strong> count accuracy and <strong>98%</strong> state accuracy, far surpassing existing interactive video world models.</p>