Vision-language models

Level 6: Transformers and multimodal vision

Coming soon

This page is being written. See the full roadmap for the whole syllabus.

What this chapter will cover

• Joint embedding spaces
• CLIP and contrastive pretraining
• zero-shot classification and prompt engineering
• image-text retrieval
• captioning
• multimodal LLMs (LLaVA-style architectures)
• visual question answering