---
title: "Slides: Text Diffusion — Brendan O’Donoghue, Google DeepMind"
category: "slides"
video_id: "r305-aQTaU0"
sourceLabels: ["Public YouTube video frames", "Public YouTube metadata"]
---

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

## Source Video
[Text Diffusion — Brendan O’Donoghue, Google DeepMind](https://www.youtube.com/watch?v=r305-aQTaU0)

## 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
![[assets/slides/r305-aQTaU0/slide-002.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/r305-aQTaU0/slide-002.html)
- AI slide classifier: `diagram` confidence `0.94`
- Text source: agent_vision.

Slide text:

> Image diffusion

![[assets/slides/r305-aQTaU0/slide-003.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/r305-aQTaU0/slide-003.html)
- AI slide classifier: `demo_video` confidence `0.88`
- Text source: agent_vision.

Slide text:

> Gemini Diffusion

![[assets/slides/r305-aQTaU0/slide-004.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/r305-aQTaU0/slide-004.html)
- 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

![[assets/slides/r305-aQTaU0/slide-005.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/r305-aQTaU0/slide-005.html)
- 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）/(2*2)).F1rst at1s（v（81）（2/3））*2. providetheansaer andthen +Gemini Diffusion 1dns
> AIE thesevare roat
> GoogleDeepMind
> go/try-saturn
> AIEngineer
> AIEn EUROPE

![[assets/slides/r305-aQTaU0/slide-006.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/r305-aQTaU0/slide-006.html)
- 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

![[assets/slides/r305-aQTaU0/slide-007.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/r305-aQTaU0/slide-007.html)
- 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

![[assets/slides/r305-aQTaU0/slide-008.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/r305-aQTaU0/slide-008.html)
- AI slide classifier: `content_slide` confidence `0.89`
- Text source: agent_vision.

Slide text:

> Low latency unlocks new applications

![[assets/slides/r305-aQTaU0/slide-009.jpg]]

- Recreated text/layout view: [open HTML recreation](/assets/slide-recreations/slides/r305-aQTaU0/slide-009.html)
- 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`](/assets/slides/r305-aQTaU0/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.