Reproduce “WorldGuide: Goal-Directed Video World Model for Procedural Task Execution” on OpenResearch

Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.

Universal app for Apple silicon and Intel. Requires macOS 11 or later.

About this paper

Ankan Deria, Komal Kumar, Hisham Cholakkal, Fahad Shahbaz Khan, Salman Khan

WorldGuide generates procedural videos through a stepwise loop: it proposes an action, generates a clip, then uses the resulting visual state to choose the next action or stop. Its planner and video executor are trained on the same step-level demonstrations. Visual feedback raises Task Success from 14.72% to 33.33%, but this generated-video result does not establish reliable completion in general.

Summary by alphaXiv.

Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.