arXiv AI September 3, 2026 By Adrien Mialland, Marc Plantevit, Julien Gallois, C\'eline Robardet

ViSAR: Training-Free Adaptive-$k$ Retrieval for Visual Document Question Answering

ViSAR is a training‑free, adaptive‑k retrieval method for Visual Document Question Answering that operates directly in the embedding space to build a query‑conditioned page‑level similarity matrix. By dynamically selecting the number of pages to retrieve based on query relevance, ViSAR reduces Retrieval‑Augmented Generation latency by up to 58.7% while maintaining or improving answer accuracy across multiple encoders and Large Vision‑Language Models. The structure of the similarity matrix also correlates with answer accuracy, indicating potential for retrieval quality‑aware document understanding.

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.

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.

rag benchmarks

arXiv Computer Vision

Sep 4

Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity

The paper introduces Invoice Haystack, a benchmark of 1,500 anonymized invoices and 200 question‑answer pairs that tests document retrieval and visual question answering under strong visual homogeneity. It shows that existing benchmarks suffer from embedding collapse, with Invoice Haystack’s mean pairwise cosine similarity at 0.73 versus 0.38 and 0.31 in DocHaystack and InfoHaystack. The authors propose VL‑RAG, a hybrid retrieval‑augmented generation framework that combines text and visual embeddings and a VLM‑based verification filter, achieving 60.0% Recall@1 on Invoice Haystack‑500 and improving performance on other benchmarks.

By Heethanjan Kanagalingam, Thenukan Pathmanathan, Mokeeshan Vathanakumar, Basim Azam, Sarah Monazam Erfani, Naveed Akhtar

llms rag nlp multimodal benchmarks

arXiv Computer Vision

Aug 25

Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering

arXiv:2608.21450v1 Announce Type: new Abstract: Knowledge-Based Visual Question Answering (KB-VQA) relies on retrieving external information to answer queries involving long-tail entities. However, e...

By Hangrui Xu, Zhengxian Wu, Yunyao Yu, Zhuohong Chen, Rui Cong, Xiangwen Deng, Zhifang Liu, Peng Jiao, Haoqian Wang

rag nlp efficiency safety

arXiv AI

Jul 29

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents

arXiv:2607. 24748v1 Announce Type: cross Abstract: Visually-rich documents such as reports, slides, and manuals often distribute the evidence needed to answer a question across multiple pages, mixing text with layout cues, tables, charts, and figures.

By Seonok Kim

rag agents nlp multimodal benchmarks

arXiv Computer Vision

Aug 24

ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval

arXiv:2608.15698v2 Announce Type: replace Abstract: Visual document retrieval is a critical component of multimodal retrieval-augmented generation, aiming to identify query-relevant pages from docume...

By Chunyi Peng, Zhipeng Xu, Yukun Yan, Zhenghao Liu, Shi Yu, Sen Mei, Yubo Sun, Yongheng Zhang, Jie Zhou, Yu Gu, Ge Yu, Maosong Sun

llms rag computer-vision multimodal benchmarks safety

arXiv Machine Learning

Aug 5

Bayesian Data Reweighting Improves Multimodal Retrieval for Knowledge-Based Visual Question Answering

arXiv:2608. 02907v1 Announce Type: new Abstract: Multimodal retrievers are essential for knowledge-based visual question answering, where they retrieve external evidence for image-question pairs.

By Jingchen Sun, Shaobo Han, Ruiyi Zhang, Naresh Kumar Devulapally, Ming Liu, Yitao Long, Vishnu Suresh Lokhande, Changyou Chen

nlp multimodal benchmarks

One email a morning, machine-written

Related stories

VaRS-Doc: Interpretation-Aware Variant Representations via Latent Self-Probing for Visual Document Retrieval

Invoice Haystack: Benchmarking Document Retrieval and Visual Question Answering Under Strong Visual Homogeneity

Beyond Visual Similarity: Entity-Aligned Retrieval for Knowledge-Based Visual Question Answering

VLD-RAG: Agentic Vision-Language Retrieval-Augmented Generation for Long, Visually-Rich Multi-Page Documents

ConceptFormer: Learning Adaptive Latent Concepts for Query-Document Alignment in Visual Document Retrieval

Bayesian Data Reweighting Improves Multimodal Retrieval for Knowledge-Based Visual Question Answering