ConceptAI & ML
Fusion-in-decoder
An architecture where multiple passages are first encoded independently, concatenated, and then fed to a decoder to support a large number of retrieved documents.
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.