arXiv Computation and Language
Inverting Multi-Vector Visual Document Indices
Read the original on arXiv Computation and Language →The Flow has not summarised this story yet — read it at arXiv Computation and Language.
Related stories
arXiv AI
Oct 2
Walking the Embedding Space: Datastore Extraction from Multimodal RAG
arXiv:2610. 01871v1 Announce Type: cross Abstract: Multimodal Retrieval-Augmented Generation (MRAG) has emerged as a reliable and cost-effective technique of grounding the generative capabilities of Multimodal Large Language Models (MLLMs) into relevant, up-to-date, external knowledge.
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...
arXiv Machine Learning
3d ago
Signed but Steerable: Measuring and Closing the Text-Vector Integrity Gap in Offline Retrieval-Augmented Generation
arXiv:2611.06498v1 Announce Type: cross Abstract: Offline retrieval-augmented generation (RAG) on edge devices is updated through signed knowledge packs that carry text and precomputed embedding vect...
arXiv AI
3d ago
Discarded or Unreachable? Diagnosing and Repairing Spatial Relation Failure in Vision--Language Similarity
The paper investigates why contrastive vision‑language models often fail to capture left/right spatial relations, identifying two distinct failure modes: an access failure where the relation exists in the pooled embedding but is unreachable by native similarity, and a pooling failure where the relation is lost during pooling but retained in dense features. The authors propose a zero‑parameter, query‑conditioned spatial moment that recomputes geometry from the patch grid and augments the native embedding, dramatically improving left/right pairwise accuracy and recall on large image indexes while preserving native rankings for non‑relational queries.
arXiv AI
Oct 16
Loud and Clear: Making Visual Evidence Count in Multimodal Document RAG
The paper introduces Loud and Clear (LoC), a method that enhances multimodal document retrieval-augmented generation by fully utilizing visual token capacity and refining retrieved pages to highlight evidence. LoC combines higher-resolution pages with OCR of query-relevant regions, achieving significant accuracy gains over eight prior methods on multiple benchmarks. The study demonstrates that the way retrieved pages are presented to the generator is a critical bottleneck beyond retrieval itself.
arXiv Computation and Language
Aug 31
CamoDocs: A Poisoning Attack Against Retrieval-Augmented Language Models Using Camouflaged Documents
arXiv:2608. 28389v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) augments LLMs with external documents, but public or user-editable sources expose RAG systems to data poisoning: attackers can inject malicious documents to steer outputs toward targeted answers.