World Labs Unveils Atlas: A Native Multimodal World Model
cihangxie · x · 2026-09-02
World Labs introduced Atlas, a next-generation world model natively operating on text, images, video, and 3D. Built as a multimodal autoregressive diffusion transformer, Atlas excels in spatial intelligence tasks, including spatial reconstruction, camera-controlled generation (outputting up to 1 minute of 1440p video), and space-time simulation. It achieves state-of-the-art performance in sparse reconstruction and scales with compute. Atlas will power future versions of Marble and other products.
Related event: World Labs Unveils Atlas, a Pixel-Perfect Multimodal World Model(22 posts)→
More from Models
- Heaviside-1: EM Foundation Model 100kx Faster Than Solvers — garrytan · 2026-09-02
- Fable 5.1: Matches High-End Rivals at Lower Cost — daniel_mac8 · 2026-09-02
- User finds regular Claude web sessions appear to run in a Linux VM — majidmanzarpour · 2026-09-02
- Perplexity uses Fable 5.1 as orchestrator with GPT 5.6 as cost-efficient subagents — AravSrinivas · 2026-09-02
- Fable 5.1 takes 1st on Artificial Analysis with a score of 66 — Anxious-Yoghurt-9207 · 2026-09-02
- Perplexity adds Claude Fable 5.1, cutting costs by 37% — perplexity_ai · 2026-09-02