ConceptAI & ML
CogAgent
A high-resolution vision-language model that uses cross-attention to handle high-resolution image inputs without inflating the hidden size of the 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
2The lectures that define it or assume it, and the concepts next to it.