Week 3: Transformer review, Part 2: decoder, masking, and model families
Papers for Thursday
Animation clips
Each clip comes in two versions. The narrated version has an AI-generated voice and captions; turn them on with the CC button. The silent version is the same animation with its on-screen captions only.
Vision transformer: an image as a sequence of patches
1 min 32 s
Everything for this week
The Week 3 folder in the repository ↗, with the animation sources, the slides and the session guide.