A municipal kite-maker loft wants the language stack to look at sail-cloth stills while it writes repair notes. Which transformer mechanism hooks another modality into the text generation path?
Select an answer to reveal the explanation.
Short Explanation
Cross-attention is the hook: the writing stream asks questions, and the image stream answers with keys and values. That is how sail-cloth patches can steer the note without dropping vision.
Full Explanation
Cross-attention conditions one modality on another by using queries from the target stream and keys/values from the conditioning stream. That is the common transformer hook for image or audio features during text generation. Dropping the image tokens, swapping attention for a static dictionary, or refusing generation entirely does not implement multimodal conditioning.