Skip to content
English

Switch theme

Discover▾

Not sure where to start? This week’s hottest software, models and stacks in three minutes.

AI Apps▾

AI software people use: from assistants like ChatGPT to tools for coding, video and workflows, picked by purpose.

For Agents▾

Software for AI: tools that let your agent (Claude Code, Codex, Cursor…) browse, read docs, run code and remember.

Models▾

Choose models, estimate cost, self-host: prices, rankings, benchmarks, free tiers and compute.

Solutions▾

A goal or an error message? Ready-made stacks, steps and fixes by scenario.

Learn▾

A systematic course from zero to the frontier, with an algorithm library, must-read papers and tutorials.

Frontier▾

Daily AI news, weekly highlights, the latest papers and how AI is changing every discipline.

Multimodal AI

How Vision-Language Models See

Image encoders, patches, projection layers and multimodal training.

Advanced 20 min For: Developers / Researchers ✎ In progress

✎ This lesson is still being written. Below is the planned outline; it is not indexed by search engines yet.

What this lesson will cover

  1. ViT and image patches
  2. CLIP-style contrastive learning
  3. Connecting vision to an LLM
  4. OCR, charts and screens

Related AI news

Links go to the original publishers.

Part of these paths

③ Researcher Path: How Models Really Work

Data updated: Learn AI curriculum · Lesson news(UTC+8)