Tabular data is frequently captured in image form across a wide range of real-world scenarios such as financial reports, handwritten records, and document scans. These visual representations pose unique challenges for machine understanding, as they combine both structural and visual complexities. While recent advances in Multimodal Large Language Models (MLLMs) show promising results in table understanding, they typically assume the relevant table is readily available. However, a more practical scenario involves identifying and reasoning over relevant tables from large-scale collections to answer user queries. To address this gap, we propose TabRAG, a framework that enables MLLMs to answer queries over large collections of table images. Our approach first retrieves candidate tables using jointly trained visual-text foundation models, then leverages MLLMs to perform fine-grained reranking of these candidates, and finally employs MLLMs to reason over the selected tables for answer generation. Through extensive experiments on a newly constructed dataset comprising 88,161 training and 9,819 testing samples across 8 benchmarks with 48,504 unique tables, we demonstrate that our framework significantly outperforms existing methods by 7.0% in retrieval recall and 6.1% in answer accuracy, offering a practical solution for real-world table understanding tasks.
TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering
University of California, Los Angeles（加州大学洛杉矶分校）；McGill University（麦吉尔大学）；Université de Montréal（蒙特利尔大学）；The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；SimpleWay
MultiModalQA: Complex Question Answering over Text, Tables and Images
The Allen Institute for AI（艾伦人工智能研究所）；Tel-Aviv University（特拉维夫大学）；University of Washington（华盛顿大学）
在回答复杂的问题时，人们可以无缝地结合来自视觉，文本和表格来源的信息。虽然近年来对多个证据推理的模型的兴趣激增，但对跨多个模态推理的问答模型的研究相对较少。在本文中，我们提出了MultiModalQA（MMQA）：一个具有挑战性的问答数据集，需要联合推理的文本，表格和图像。我们使用一个新的框架来创建MMQA，该框架用于大规模生成复杂的多模态问题，从维基百科获取表格，并使用每个表格中出现的实体附加图像和文本段落。然后，我们定义了一个形式语言，使我们能够采取的问题，可以回答从一个单一的模态，并将它们结合起来，以产生跨模态的问题。最后，众包工作人员将这些自动生成的问题转化为更流畅的语言。我们通过这个过程创建了29，918个问题，并以经验证明了多模态多跳方法解决我们任务的必要性：我们的多跳模型ImplicitDecomp在跨模态问题上的平均F1为51.7，大大超过了达到38.2 F1的强大基线，但仍然明显落后于人类表现，这是90.1 F1
Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models
School of Computer Science and Engineering, University of Electronic Science and Technology of China（电子科技大学计算机科学与工程学院）；Research Center for Scientific Data Hub, Zhejiang Lab, Hangzhou, China（浙江实验室科学数据中心研究中心）；School of Computer Science and Technology, Tongji University（同济大学计算机科学与技术学院）
Institute of Information Engineering, Chinese Academy of Sciences（中国科学院信息工程研究所）；Baidu Inc（百度公司）；School of Artificial Intelligence, Beijing Normal University（北京师范大学人工智能学院）；School of Cyber Security, University of Chinese Academy of Sciences（中国科学院大学网络空间安全学院）
Towards Platonic Representation for Table Reasoning: A Foundation for Permutation-Invariant Retrieval
Department of Mathematics and Data Science, Vrije Universiteit Brussel (VUB)（瓦隆公国布鲁塞尔自由大学数学与数据科学系）；Data Science Lab, Royal Library of Belgium (KBR)（比利时皇家图书馆数据科学实验室）
Benchmarking Multimodal LLMs on Recognition and Understanding over Chemical Tables
State Key Laboratory of Cognitive Intelligence（认知智能国家重点实验室）；University of Science and Technology of China（中国科学技术大学）；Artificial Intelligence Research Institute（人工智能研究院）；iFLYTEK Co., Ltd（iFLYTEK公司）
PIPER: Content-Based Table Search via profiling and LLM-Generated Pseudoqueries
Centre for Industrial Software, University of Southern Denmark（丹麦南部大学工业软件中心）；Department of Electronics, Information and Bioengineering, Politecnico di Milano（米兰理工学院电子、信息与生物工程系）
Hidden in the Metadata: Stealth Poisoning Attacks on Multimodal Retrieval-Augmented Generation
The City University of New York, CSI, Staten Island, NY 10314, USA（纽约城市大学，CSI，史泰登岛分校）；The City University of New York, Graduate Center, New York, NY 10016, USA（纽约城市大学研究生中心）
CORE-T: COherent REtrieval of Tables for Text-to-SQL
Ubiquitous Knowledge Processing Lab (UKP Lab), Department of Computer Science TU Darmstadt and National Research Center for Applied Cybersecurity ATHENE, Germany（普适知识处理实验室（UKP实验室），计算机科学系 TU Darmstadt 和应用网络安全国家研究中心 ATHENE，德国）；Arizona State University（亚利桑那州立大学）；University of Pennsylvania（宾夕法尼亚大学）
School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳）计算机科学与技术学院）；School of Computer Science, University of Sydney（悉尼大学计算机学院）；Alibaba Group（阿里巴巴集团）
MARA: A Multimodal Adaptive Retrieval-Augmented Framework for Document Question Answering
Key Laboratory of Target Cognition and Application Technology (TCAT), AIRI, CAS（目标认知与应用技术重点实验室（TCAT），空气动力研究所，中国科学院）；School of Electronic, Electrical and Communication Engineering, UCAS（电子、电气与通信工程学院，中国科学院大学）；Aerospace Information Research Institute, Chinese Academy of Sciences（航天信息研究所，中国科学院）；Baidu Inc.（百度公司）
