Multimodal Models and Cross-Modal Alignment
A language model reads vectors, not pixels or waveforms. See how encoders, contrastive alignment, and connectors bridge the gap, and how to test whether the input is really used.
-
-
Embeddings and Retrieval Representations
Retrieval quality is set by the representation: BM25 matches terms, dense embeddings match what training taught them. Learn the objectives, the failure modes, and how to measure them.