Atlas runs on one unified multimodal autoregressive diffusion transformer, pretrained from scratch
theworldlabs · x · 2026-09-02
World Labs explains that Atlas is powered by a single unified architecture: a multimodal autoregressive diffusion transformer pretrained from scratch.
The foundation blends the best of modern LLMs and video models, inheriting architectural, algorithmic, and systems advances from both lines of work.
Related event: World Labs Launches Atlas, an Omni World Model for Spatial Intelligence(64 posts)→
More from Models
- Paying Google AI subscriber blocked: custom-domain Workspace accounts can't access AI Studio — ChrisRackauckas · 2026-10-18
- Running Ling 3.1 Flash (560B MoE, 25B Active) Across 4 DGX Sparks via llama.cpp RPC — BerryBlush_Rogers691 · 2026-10-18
- Users press OpenAI on long-delayed Adult Mode a year after it was promised — ___Patrice___ · 2026-10-18
- Polymarket opens betting market on who releases the next Gemini Argon model — Polymarket · 2026-10-18
- Grok matter-of-factly lists which groups user was racist against, exempting Africans and Latin Americans — teortaxesTex · 2026-10-18
- A quick test for benchmaxxed demos: swap in Mirror's Edge and see if it generalizes — teortaxesTex · 2026-10-18