ConceptAI & ML
BLIP-2
A pioneering work that bridges CLIP and large language models using a trainable Q-Former to enable the language model to understand images.
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.