AI Foundationspredict · compress · act

concepts → Architecture

Architecture

Omni-model

frontieras of 2026-093 connections

one model for text, audio, images and video, instead of a relay of specialists

Where it sits

The prism has six jobs across and eight layers down. Its primary cell isrepresent × L1. Hatched cells cannot exist — a GPU does not learn, an institution does not infer.

What must come first — and what it unlocks

Left to right is reading order, derived from the prerequisite_of edges. Nothing here is hand-ordered: the diagram is the graph.

nothing comes first — this is a starting pointOmni-modelAny-to-any

Unlocks: Any-to-any

What kind of thing it is — and what it is made of

It is made of: Any-to-any, Modality encoder.

Where to read it

The chapter that introduces it, and any chapter that uses it again.

54Omni-Modelsact 11 · Beyond Text

Where it comes from

paperQwen3-Omni Technical ReportQwen Team · 2025

Every connection

All 3 edges touching this node, grouped by relation family — the sections above are highlights from this list. Colours match the relation families inthe atlas.

Structure · 2
has as a partAny-to-anyProperty
has as a partModality encoderArchitecture
Order · 1
must come beforeAny-to-anyProperty

This page is a projection of one node in src/data/concepts.ts. It has no prose file of its own — 230 declared edges produce all 236 of these pages. Edit an edge and both endpoints change.