Markdown source

Slides: Text Diffusion — Brendan O’Donoghue, Google DeepMind

Source Video

Text Diffusion — Brendan O’Donoghue, Google DeepMind

Relationship To World's Fair 2026

These slides are extracted from a public AI Engineer YouTube video connected to World's Fair 2026. Speaker-matched clips are supporting context unless later confirmed as exact session recordings; official livestream recordings are day-level/event-level source material.

Related Scheduled Sessions

• No individual scheduled session mapping has been assigned yet; treat this as an event livestream deck.

Extracted Slides

• Recreated text/layout view: open HTML recreation
• AI slide classifier: diagram confidence 0.94
• Text source: agent_vision.

Slide text:

Image diffusion

• Recreated text/layout view: open HTML recreation
• AI slide classifier: demo_video confidence 0.88
• Text source: agent_vision.

Slide text:

Gemini Diffusion

• Recreated text/layout view: open HTML recreation
• AI slide classifier: product confidence 0.97
• Text source: agent_vision.
• OCR decision: ready — dense code/UI screenshot with small text

Slide text:

Gemini Diffusion

• Recreated text/layout view: open HTML recreation
• AI slide classifier: product confidence 0.96
• Text source: advanced OCR rapidocr-live/full.
• OCR decision: ready — dense screenshot and equation text

Slide text:

Textdiffusion candobidirectionalreasoning andself-correction

(15-3）/(22)).F1rst at1s（v（81）（2/3））2. providetheansaer andthen +Gemini Diffusion 1dns

AIE thesevare roat

GoogleDeepMind

go/try-saturn

AIEngineer

AIEn EUROPE

• Recreated text/layout view: open HTML recreation
• AI slide classifier: product confidence 0.97
• Text source: agent_vision.
• OCR decision: ready — dense comparison screenshots with small text

Slide text:

Gemini 2.5 Flash

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.96
• Text source: advanced OCR rapidocr-live/bright-screen/contrast.
• OCR decision: ready — Dense code-editor screenshot with small text is better handled by OCR than manual transcription.

Slide text:

Text diffusion can do

e211

AIE

LI

h 心··山

1s-22- to1eli-1-

eul

Mind

AI Engineer

AIE EUROPE

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.89
• Text source: agent_vision.

Slide text:

Low latency unlocks new applications

• Recreated text/layout view: open HTML recreation
• AI slide classifier: content_slide confidence 0.95
• Text source: advanced OCR rapidocr-live/bright-screen/contrast.
• OCR decision: ready — The slide contains a dense product/UI screenshot with small interface text that is suitable for OCR.

Slide text:

/ UV)6

List

(elenmme)

AIE

41tiuaep/t.11) re aita A9o0

-daalg1

lei< (4el-oeceratime) (retsrm: 1

Engineering the future of Al

AIEns

Hidden Non-Slide Evidence

• `slide-001.jpg` — title_card confidence 0.95; speaker intro/title card over stage shot

Classification audit: raw/sources/slide-ai-classification/slides/r305-aQTaU0/audit.json

Slide-Derived Subjects To Review

Subject extraction uses video title, related session titles/descriptions, transcript context, and OCR text when available. OCR is best-effort and should be reviewed against the embedded slide images.