Generative Late-Interaction Embeddings For Visual Document Retrieval

Late-interaction retrieval remains the state-of-the-art for visual document search but its accuracy comes at a storage cost, since existing compression methods retain only a subset or local average of the roughly 1,000 vectors per page and degrade sharply under aggressive storage budgets. The source, an article titled "Generative Late-Interaction Embeddings For Visual Document Retrieval," does not name an author, organization, or publication date.

Late-interaction retrieval is the state-of-the-art for visual document search, but it pays for its accuracy in storage. Existing compression methods retain a subset or local average of the N~1,000 vectors per page. Under aggressive storage budgets, however, these methods degrade sharply, and alterna