// ◉ Multimodal & Vision
Vision Transformer (ViT)
Treats 16×16 image patches as words for a standard Transformer.
视觉 Transformer ViT 2020 Foundational core
IN PLAIN WORDS
Patches are flattened, projected into tokens with positions and fed to a Transformer. With enough data it beats CNNs and is now the standard vision backbone for VLMs and DiT.
Used in: Vision encoders of CLIP, SigLIP and VLMs
TIMELINE · prerequisites → this → what builds on it
01Original paper
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, et al. · 2020
arXiv ↗ ✓ Verified · arXiv API
02Where it sits
Learn the left column first; the right column builds on this one.
Left: prerequisites · right: builds on this · dashed: related. Full map →
03Learning resources
Official docs, explainers, courses and reference code. All links checked.
Books
Courses
Explainers
04Where the course teaches it
On learning paths:Generative Models & Frontier Research
For AI / data
- Verification: verified, checked 2026-10-21.
- JSON: /api/learn/algorithms.json (id:
vit)