arXiv AI
Query-Aware Token Budgeting for Efficient Late-Interaction Visual Document Retrieval
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Computer Vision
Sep 21
MAGIC: Marginal-Guided Compression with Optimal Transport for Efficient Visual Document Retrieval
arXiv:2609.21018v1 Announce Type: new Abstract: Recent visual document retrieval (VDR) systems such as ColPali use multi-vector page embeddings, in which patch-level vectors enable fine-grained evide...
Hugging Face Trending Papers
Aug 2
VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval
Visual document retrieval has recently become increasingly important in applications such as enterprise search, scientific literature discovery, and retrieval-augmented generation. These applications depend on efficiently identifying query-relevant pages across large collections of visually rich documents.
arXiv AI
Sep 2
MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval
MIDR (Multimodal Indexing for Document Retrieval) is a training‑free framework that enriches document indexes by converting rendered pages into verified textual fields with a multimodal LLM, then indexing those fields with BM25F and optionally fusing with dense retrieval. By shifting multimodal reasoning to index time, MIDR enables text‑centric serving while retaining multimodal evidence, achieving a 23.0% relative gain over BM25 on ViDoRe V3 and outperforming ColQwen2.5 on several domains with significantly smaller index memory and lower query latency.
Hugging Face Trending Papers
Aug 9
AnchorFold: A Focus-Then-Fold Framework via Recursive Attention Propagation for Efficient Multi-Vector Visual Document Retrieval
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.
arXiv AI
Jul 9
AnchorPrune: Relevance-Anchored Contextual Expansion for Visual Token Pruning
arXiv:2607. 07033v1 Announce Type: cross Abstract: Large vision-language models incur substantial inference costs because high-resolution inputs introduce thousands of visual tokens, many of which are redundant for a given query.
arXiv AI
Sep 16
StackTok: Accelerating VLMs Inference with Budget-Adaptive Visual Token Selection
arXiv:2609.16841v1 Announce Type: cross Abstract: Increasing image resolution produces ever-longer visual-token sequences in vision-language models (VLMs), substantially raising their inference cost....