arXiv AI October 16, 2026 By Eunchan Jo, Seounghyun Jang, Sangwoo Mo

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.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv AI

Sep 15

Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering

arXiv:2604.27724v2 Announce Type: replace Abstract: Medical retrieval-augmented generation (RAG) systems typically operate on text chunks extracted from biomedical literature, discarding the rich vis...

By Xupeng Chen, Binbin Shi, Chenqian Le, Jiaqi Zhang, Kewen Wang, Ran Gong, Jinhan Zhang, Chihang Wang

llms rag computer-vision nlp multimodal benchmarks

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.

By Debanjan Mahata, Atharva Tendle, Daniel Preotiuc-Pietro, Yong Zhuang, Ozan Irsoy

llms computer-vision multimodal

arXiv AI

2d ago

VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval

arXiv:2610.17057v1 Announce Type: new Abstract: Vision-based document retrieval has improved rapidly, but current evaluation settings still emphasize short documents and single relevant pages. This l...

By Simon Ott, Yufan Chen, Ruiping Liu, Junwei Zheng, Jiale Wei, Di Wen, Kunyu Peng, Jiaming Zhang, Rainer Stiefelhagen

rag benchmarks

arXiv Computation and Language

Aug 28

ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs

ET‑Prune is a training‑free framework that dynamically allocates visual token budgets in multimodal large language models based on question‑conditioned evidence. It protects text‑like spatial regions, converts evidence uncertainty into a token floor, and progressively prunes concentrated evidence while retaining diffuse or text‑dense tokens. In six backbone‑benchmark comparisons, ET‑Prune matches or outperforms other pruned methods while keeping roughly half the visual tokens, achieving notable gains on OCRBench‑v2 and MMBench v1.1.

By Zizhong Ding, Junxian Li, Kai Liu, Shaoqiu Zhang, Xiao Xiao, Linghe Kong, Yulun Zhang

llms computer-vision efficiency multimodal benchmarks

arXiv AI

Sep 30

FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution

arXiv:2609.36651v1 Announce Type: cross Abstract: Long-context reasoning in large language models incurs substantial computation and memory costs. Visual text compression (VTC) reduces input length b...

By FangZhi Zhong, Xuerui Qiu, Yuqi Pan, Ya Liu, Shaowei Gu, Bo Xu, Guoqi Li

llms fine-tuning multimodal

arXiv AI

Jun 16

MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA

arXiv:2606. 15906v1 Announce Type: cross Abstract: Long-document multimodal question answering requires a system to locate sparse evidence in long PDFs and integrate clues from text, tables, images, charts, and complex layouts.

By Yilong Zuo, Xunkai Li, Jing Yuan, Qiangqiang Dai, Hongchao Qin, Ronghua Li

rag agents nlp multimodal

One email a morning, machine-written

Related stories

Iterative Multimodal Retrieval-Augmented Generation for Medical Question Answering

MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrieval

VL-DocIR: A Benchmark for Vision-Based Long Document Information Retrieval

ET-Prune: Evidence-Aware Dynamic Budgeting for Visual Token Pruning in Text-Rich MLLMs

FocusVTC: Efficient and High-Performance Visual Text Compression with Adaptive Resolution

MAGE-RAG: Multigranular Adaptive Graph Evidence for Agentic Multimodal RAG in Long-Document QA