Reka Labs lays out Omni-World Models: one architecture for language and physical AI
RekaAILabs · x · 2026-09-17
Reka Labs argues LLMs are merely an intermediate step toward physical-world intelligence and proposes "omni world models" — a single unified architecture handling language, image, video and actions as both inputs and outputs. Key challenge: jointly modeling discrete signals (text, autoregressive) and continuous signals (audio, pixels, diffusion). Unifying VLA and world-model approaches under one backbone, they contend, is necessary to capture motion and geometry in the real world.
More from Multimodal
- Runway's Model Router auto-picks the best model per generation by cost, quality or latency — tlakomy · 2026-09-18
- 45M Gaussians, 520MB: Croatia's medieval town of Trogir walkable in a browser tab — willeastcott · 2026-09-18
- AI photo-edit prompt template for celebration shots that keeps your real face and body — aitrendz_xyz · 2026-09-18
- Day-in-the-life AI photo prompt keeps identity intact with blurred realistic backgrounds — aitrendz_xyz · 2026-09-18
- Pro headshot AI prompt template keeps your face and reserves space for text overlays — aitrendz_xyz · 2026-09-18
- Private-jet photo AI prompt locks identity and uses sunset light for realism — aitrendz_xyz · 2026-09-18