SolarWM: Fully Open Framework Trains Long-Horizon Video World Models on 1.43M Clips

_akhaliq · x · 2026-09-04

SolarWM is a fully open framework for interactive long-horizon video world models, unifying 1.43M clips from 14 datasets across 4 backbones for scalable training.

Notably, training on just 5-second clips enables real-time interactive rollouts lasting minutes to hours, offering an open, reproducible recipe for long-horizon world simulation.

Related event: CUHK-SZ and Collaborators Fully Open-Source SolarWM, a Long-Horizon Interactive Video World Model(5 posts)→

Original post →

More from Multimodal

• AI film The Miracle to premiere Saturday directly on X — Kyrannio · 2026-09-04
• burnz releases AI-produced original single "Don't Make a Sound" — EddyVGG · 2026-09-04
• Meta's first image model Muse Image debuts #4 in image editing at just $0.01 per image — ArtificialAnlys · 2026-09-04
• One Prompt, One 3D Render: Astra Turns a Sentence into a Product Visual — iansilber · 2026-09-04
• The Generative Burrito Test puts 24 image models to work recreating one real burrito photo — generativist · 2026-09-04
• Immunologist one-shots a 5-minute T-cell lecture video from a single prompt with GPT-6 — DeryaTR_ · 2026-09-04

Multimodal channel →