English
Related papers

Related papers: DMAP: Human-Aligned Structural Document Map for Mu…

200 papers

While many NLP pipelines assume raw, clean texts, many texts we encounter in the wild, including a vast majority of legal documents, are not so clean, with many of them being visually structured documents (VSDs) such as PDFs. Conventional…

Computation and Language · Computer Science 2021-11-09 Yuta Koreeda , Christopher D. Manning

Visual Question Answering (VQA) has become an important benchmark for assessing how large multimodal models (LMMs) interpret images. However, most VQA datasets focus on real-world images or simple diagrammatic analysis, with few focused on…

Computer Vision and Pattern Recognition · Computer Science 2026-02-02 Jill P. Naiman , Daniel J. Evans , JooYoung Seo

Recent advances in Large Language Models (LLMs) have significantly improved table understanding tasks such as Table Question Answering (TableQA), yet challenges remain in ensuring reliability, scalability, and efficiency, especially in…

Computation and Language · Computer Science 2026-04-22 Sieun Hyeon , Jusang Oh , Sunghwan Steve Cho , Jaeyoung Do

Tables condense key transactional and administrative information into compact layouts, but practical extraction requires more than text recognition: systems must also recover structure (rows, columns, merged cells, headers) and interpret…

Computer Vision and Pattern Recognition · Computer Science 2026-04-20 Laziz Hamdi , Amine Tamasna , Thierry Paquet

We introduce WordScape, a novel pipeline for the creation of cross-disciplinary, multilingual corpora comprising millions of pages with annotations for document layout detection. Relating visual and textual items on document pages has…

We propose a new CogQA framework for multi-hop question answering in web-scale documents. Inspired by the dual process theory in cognitive science, the framework gradually builds a \textit{cognitive graph} in an iterative process by…

Computation and Language · Computer Science 2019-06-05 Ming Ding , Chang Zhou , Qibin Chen , Hongxia Yang , Jie Tang

Retrieval-Augmented Generation (RAG) mitigates hallucinations in Multimodal Large Language Models (MLLMs), yet existing systems struggle with complex cross-modal reasoning. Flat vector retrieval often ignores structural dependencies, while…

Information Retrieval · Computer Science 2026-04-08 Sijun Dai , Qiang Huang , Xiaoxing You , Jun Yu

Visual Dialog is a vision-language task that requires an AI agent to engage in a conversation with humans grounded in an image. It remains a challenging task since it requires the agent to fully understand a given question before making an…

Computation and Language · Computer Science 2019-12-19 Feilong Chen , Fandong Meng , Jiaming Xu , Peng Li , Bo Xu , Jie Zhou

The CMAP (cultural mapping and pattern analysis) visualization toolkit introduced in this paper is an open-source suite for analyzing and visualizing text data - from qualitative fieldnotes and in-depth interview transcripts to historical…

Applications · Statistics 2025-10-21 Corey M. Abramson , Yuhan , Nian

With their high information density and intuitive readability, charts have become the de facto medium for data analysis and communication across disciplines. Recent multimodal large language models (MLLMs) have made notable progress in…

Computer Vision and Pattern Recognition · Computer Science 2025-12-17 Boran Wang , Xinming Wang , Yi Chen , Xiang Li , Jian Xu , Jing Yuan , Chenglin Liu

The traditional RAG paradigm, which typically engages in the comprehension of relevant text chunks in response to received queries, inherently restricts both the depth of knowledge internalization and reasoning capabilities. To address this…

Computation and Language · Computer Science 2025-10-17 Jihao Zhao , Zhiyuan Ji , Simin Niu , Hanyu Wang , Feiyu Xiong , Zhiyu Li

This paper introduces layout-aware graph modeling for multimodal RAG. Different from traditional RAG methods that mostly deal with flat text chunks, the proposed method takes into account the relationship of multimodalities by using a graph…

Computation and Language · Computer Science 2025-03-10 Jeff Yang , Duy-Khanh Vu , Minh-Tien Nguyen , Xuan-Quang Nguyen , Linh Nguyen , Hung Le

This paper proposes the problem of Deep Question Generation (DQG), which aims to generate complex questions that require reasoning over multiple pieces of information of the input passage. In order to capture the global structure of the…

Computation and Language · Computer Science 2020-04-28 Liangming Pan , Yuxi Xie , Yansong Feng , Tat-Seng Chua , Min-Yen Kan

Document Visual Question Answering (DocVQA) refers to the task of answering questions from document images. Existing work on DocVQA only considers single-page documents. However, in real scenarios documents are mostly composed of multiple…

Computer Vision and Pattern Recognition · Computer Science 2023-04-05 Rubèn Tito , Dimosthenis Karatzas , Ernest Valveny

Topological materials occupy a frontier in condensed-matter physics thanks to their remarkable electronic and quantum properties, yet their cross-scale design remains bottlenecked by inefficient discovery workflows. Here, we introduce…

Materials Science · Physics 2025-07-08 Baohua Zhang , Xin Li , Huangchao Xu , Zhong Jin , Quansheng Wu , Ce Li

Deep Research systems have revolutionized how LLMs solve complex questions through iterative reasoning and evidence gathering. However, current systems remain fundamentally constrained to textual web data, overlooking the vast knowledge…

Information Retrieval · Computer Science 2025-10-27 Kuicai Dong , Shurui Huang , Fangda Ye , Wei Han , Zhi Zhang , Dexun Li , Wenjun Li , Qu Yang , Gang Wang , Yichao Wang , Chen Zhang , Yong Liu

Reasoning, the ability to logically draw conclusions from existing knowledge, is a hallmark of human. Together with perception, they constitute the two major themes of artificial intelligence. While deep learning has pushed the limit of…

Artificial Intelligence · Computer Science 2024-10-18 Zhaocheng Zhu

Current language understanding approaches focus on small documents, such as newswire articles, blog posts, product reviews and discussion forum entries. Understanding and extracting information from large documents like legal briefs,…

Computation and Language · Computer Science 2017-09-05 Muhammad Mahbubur Rahman , Tim Finin

Multimodal information-gathering settings, where users collaborate with AI in dynamic environments, are increasingly common. These involve complex processes with textual and multimodal interactions, often requiring additional structural…

In this paper, we informally introduce dynamic mind-maps that represent a new approach on the basis of a dynamic construction of connectionist structures during the processing of a data stream. This allows the representation and processing…

Neural and Evolutionary Computing · Computer Science 2008-12-18 Christoph Schommer