Hugging Face Trending Papers

AnchorFold: A Focus-Then-Fold Framework via Recursive Attention Propagation for Efficient Multi-Vector Visual Document Retrieval

Read the original on Hugging Face Trending Papers →

Multi-vector vision-language retrievers enable fine-grained Visual Document Retrieval (VDR) through late interaction, but storing and scoring hundreds of visual patch embeddings per page incurs substantial overhead. Existing training-free methods rely on pruning or merging: pruning degrades sharply under aggressive compression, whereas merging does not explicitly prioritize important regions when forming representatives.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

Hugging Face Trending Papers
Jul 6

Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval

Multi-vector vision-language retrieval preserves fine-grained visual evidence through maximum-similarity late interaction, but dense image-side tokens make storage and scoring expensive. Existing token compression methods reduce this cost, yet they can remove or collapse object- and region-level evidence that future query tokens may need to select.