ConceptAI & ML
LLaVA architecture
A popular vision-language model architecture using an image encoder, a question instruction encoder, cross-attention, and a GPT language model.
Know first
Named as a prerequisite by the lectures that define this. The number is how many say so. A grey one has no page yet.
Lecturers
1Connections
3The lectures that define it or assume it, and the concepts next to it.