中文
相关论文

相关论文: Moving Pictures of Thought: Extracting Visual Know…

200 篇论文

Diagrams play a crucial role in visually conveying complex relationships and processes within business documentation. Despite recent advances in Vision-Language Models (VLMs) for various image understanding tasks, accurately identifying and…

软件工程 · 计算机科学 2025-02-10 Shue Shiinoki , Ryo Koshihara , Hayato Motegi , Masumi Morishige

Visual language is a system of communication that conveys information through symbols, shapes, and spatial arrangements. Diagrams are a typical example of a visual language depicting complex concepts and their relationships in the form of…

计算与语言 · 计算机科学 2025-05-27 Yifan Hou , Buse Giledereli , Yilei Tu , Mrinmaya Sachan

Vision-language models (VLMs) have demonstrated impressive performance by effectively integrating visual and textual information to solve complex tasks. However, it is not clear how these models reason over the visual and textual data…

人工智能 · 计算机科学 2025-04-15 Pouya Pezeshkpour , Moin Aminnaseri , Estevam Hruschka

Visualizations help communicate data insights, but deceptive data representations can distort their interpretation and propagate misinformation. While recent Vision Language Models (VLMs) perform well on many chart understanding tasks,…

计算机视觉与模式识别 · 计算机科学 2026-04-21 Harsh Nishant Lalai , Raj Sanjay Shah , Hanspeter Pfister , Sashank Varma , Grace Guo

This paper proposes LayoutLLM, a more flexible document analysis method for understanding imaged documents. Visually Rich Document Understanding tasks, such as document image classification and information extraction, have gained…

计算与语言 · 计算机科学 2024-03-22 Masato Fujitake

Human reasoning relies on constructing and manipulating mental models -- simplified internal representations of situations used to understand and solve problems. Conceptual diagrams (e.g., a sketch drawn to aid reasoning) externalize these…

人工智能 · 计算机科学 2025-09-30 Nasim Borazjanizadeh , Roei Herzig , Eduard Oks , Trevor Darrell , Rogerio Feris , Leonid Karlinsky

Recent advances in Vision-Language Models (VLMs) have shown promising capabilities in interpreting visualized graph data, offering a new perspective for graph-structured reasoning beyond traditional Graph Neural Networks (GNNs). However,…

人工智能 · 计算机科学 2026-04-27 Qihang Ai , Ruizhou Li , Menghui Wang , Haiyun Jiang

Recent advancements in dialogue systems have highlighted the significance of integrating multimodal responses, which enable conveying ideas through diverse modalities rather than solely relying on text-based interactions. This enrichment…

计算与语言 · 计算机科学 2024-07-08 Chang-Sheng Kao , Yun-Nung Chen

The diagram is a visual representation of a relationship illustrated with edges (lines or arrows), which is widely used in industrial and scientific communication. Although recognizing diagrams is essential for vision language models (VLMs)…

计算机视觉与模式识别 · 计算机科学 2025-05-27 Naoyuki Terashita , Yusuke Tozaki , Hideaki Omote , Congkha Nguyen , Ryosuke Nakamoto , Yuta Koreeda , Hiroaki Ozaki

A persistent challenge in AI is the effective integration of material and formal inference - the former concerning the plausibility and contextual relevance of arguments, while the latter focusing on their logical and structural validity.…

人工智能 · 计算机科学 2025-04-08 Xin Quan , Marco Valentino , Danilo S. Carvalho , Dhairya Dalal , André Freitas

Large language models (LLMs) have made significant advancements in natural language understanding. However, through that enormous semantic representation that the LLM has learnt, is it somehow possible for it to understand images as well?…

计算机视觉与模式识别 · 计算机科学 2024-07-12 Mu Cai , Zeyi Huang , Yuheng Li , Utkarsh Ojha , Haohan Wang , Yong Jae Lee

Document parsing (DP) transforms unstructured or semi-structured documents into structured, machine-readable representations, enabling downstream applications such as knowledge base construction and retrieval-augmented generation (RAG).…

Despite significant advancements, large multimodal models (LMMs) still struggle to bridge the gap between low-level visual perception -- focusing on shapes, sizes, and layouts -- and high-level language reasoning, such as semantics and…

计算与语言 · 计算机科学 2025-06-13 Zhenhailong Wang , Joy Hsu , Xingyao Wang , Kuan-Hao Huang , Manling Li , Jiajun Wu , Heng Ji

Document layout analysis is crucial for understanding document structures. On this task, vision and semantics of documents, and relations between layout components contribute to the understanding process. Though many works have been…

计算机视觉与模式识别 · 计算机科学 2021-05-14 Peng Zhang , Can Li , Liang Qiao , Zhanzhan Cheng , Shiliang Pu , Yi Niu , Fei Wu

Advances in Visually Rich Document Understanding (VrDU) have enabled information extraction and question answering over documents with complex layouts. Two tropes of architectures have emerged -- transformer-based models inspired by LLMs,…

计算与语言 · 计算机科学 2024-01-08 Dongsheng Wang , Zhiqiang Ma , Armineh Nourbakhsh , Kang Gu , Sameena Shah

Vision-Language Models (VLMs) can process visual and textual information in multiple formats: texts, images, interleaved texts and images, or even hour-long videos. In this work, we conduct fine-grained quantitative and qualitative analyses…

计算机视觉与模式识别 · 计算机科学 2025-04-15 Théo Gigant , Camille Guinaudeau , Frédéric Dufaux

Advances in large language models (LLMs) offer new possibilities for enhancing math education by automating support for both teachers and students. While prior work has focused on generating math problems and high-quality distractors, the…

人工智能 · 计算机科学 2025-03-11 Jaewook Lee , Jeongah Lee , Wanyong Feng , Andrew Lan

Vision-language pretraining models have achieved great success in supporting multimedia applications by understanding the alignments between images and text. While existing vision-language pretraining models primarily focus on understanding…

计算机视觉与模式识别 · 计算机科学 2024-04-29 Fuxiao Liu , Hao Tan , Chris Tensmeyer

Vision-Language Models (VLMs) have demonstrated remarkable performance across a variety of real-world tasks. However, existing VLMs typically process visual information by serializing images, a method that diverges significantly from the…

计算机视觉与模式识别 · 计算机科学 2026-02-10 Yueyan Li , Chenggong Zhao , Zeyuan Zang , Caixia Yuan , Xiaojie Wang

Understanding long-context visual information remains a fundamental challenge for vision-language models, particularly in agentic tasks such as GUI control and web navigation. While web pages and GUI environments are inherently structured…

计算机视觉与模式识别 · 计算机科学 2026-01-28 Gyubeum Lim , Yemo Koo , Vijay Krishna Madisetti
‹ 上一页 1 2 3 10 下一页 ›