English
Related papers

Related papers: Lumos : Empowering Multimodal LLMs with Scene Text…

200 papers

Converting different modalities into general text, serving as input prompts for large language models (LLMs), is a common method to align multimodal models when there is limited pairwise data. This text-centric approach leverages the unique…

Computation and Language · Computer Science 2024-07-09 Ting-Yu Yen , Yun-Da Tsai , Keng-Te Liao , Shou-De Lin

This study aims to comprehensively review and empirically evaluate the application of multimodal large language models (MLLMs) and Large Vision Models (VLMs) in object detection for transportation systems. In the first fold, we provide a…

Computer Vision and Pattern Recognition · Computer Science 2024-09-30 Huthaifa I. Ashqar , Ahmed Jaber , Taqwa I. Alhadidi , Mohammed Elhenawy

To explore a more scalable path for adding multimodal capabilities to existing LLMs, this paper addresses a fundamental question: Can a unimodal LLM, relying solely on text, reason about its own informational needs and provide effective…

Computation and Language · Computer Science 2026-01-13 Sazia Tabasum Mim , Jack Morris , Manish Dhakal , Yanming Xiu , Maria Gorlatova , Yi Ding

Recent advancements in language multimodal models (LMMs) for video have demonstrated their potential for understanding video content, yet the task of comprehending multi-discipline lectures remains largely unexplored. We introduce…

Computer Vision and Pattern Recognition · Computer Science 2025-05-06 Enxin Song , Wenhao Chai , Weili Xu , Jianwen Xie , Yuxuan Liu , Gaoang Wang

Existing scene text spotters are designed to locate and transcribe texts from images. However, it is challenging for a spotter to achieve precise detection and recognition of scene texts simultaneously. Inspired by the glimpse-focus…

Computer Vision and Pattern Recognition · Computer Science 2024-03-18 Jiahao Lyu , Jin Wei , Gangyan Zeng , Zeng Li , Enze Xie , Wei Wang , Yu Zhou

The advent of Large Language Models (LLMs) has significantly transformed tasks across Software Engineering. In the context of Business Process Management, LLMs are now being explored as tools to derive process models directly from textual…

Software Engineering · Computer Science 2026-05-01 Pedro-Aarón Hernández-Ávalos , Luciano García-Bañuelos

Enabling agents to understand and interact with complex 3D scenes is a fundamental challenge for embodied artificial intelligence systems. While Multimodal Large Language Models (MLLMs) have achieved significant progress in 2D image…

Computer Vision and Pattern Recognition · Computer Science 2025-09-23 Haoyuan Li , Rui Liu , Hehe Fan , Yi Yang

Autoregressive large language models (LLMs) have unified a vast range of language tasks, inspiring preliminary efforts in autoregressive (AR) video generation. Existing AR video generators either diverge from standard LLM architectures,…

Computer Vision and Pattern Recognition · Computer Science 2026-03-17 Hangjie Yuan , Weihua Chen , Jun Cen , Hu Yu , Jingyun Liang , Shuning Chang , Zhihui Lin , Tao Feng , Pengwei Liu , Jiazheng Xing , Hao Luo , Jiasheng Tang , Fan Wang , Yi Yang

Multimodal Large Language Models (MLLMs) have experienced significant advancements recently. Nevertheless, challenges persist in the accurate recognition and comprehension of intricate details within high-resolution images. Despite being…

Computer Vision and Pattern Recognition · Computer Science 2024-03-05 Haogeng Liu , Quanzeng You , Xiaotian Han , Yiqi Wang , Bohan Zhai , Yongfei Liu , Yunzhe Tao , Huaibo Huang , Ran He , Hongxia Yang

This paper introduces the Learned User Significance Tracker (LUST), a framework designed to analyze video content and quantify the thematic relevance of its segments in relation to a user-provided textual description of significance. LUST…

Multimedia · Computer Science 2025-08-07 Anderson de Lima Luiz

Understanding Theory of Mind is essential for building socially intelligent multimodal agents capable of perceiving and interpreting human behavior. We introduce MoMentS (Multimodal Mental States), a comprehensive benchmark designed to…

We investigate how the ability to recognize textual content within images emerges during the training of Vision-Language Models (VLMs). Our analysis reveals a critical phenomenon: the ability to read textual information in a given image…

Computer Vision and Pattern Recognition · Computer Science 2025-06-25 Jaeyoo Park , Sanghyuk Chun , Wonjae Kim , Sangdoo Yun , Bohyung Han

Recent advancements in subject-driven image generation have made significant strides. However, current methods still fall short in diverse application scenarios, as they require test-time tuning and cannot accept interleaved multi-image and…

Computer Vision and Pattern Recognition · Computer Science 2024-04-29 Xichen Pan , Li Dong , Shaohan Huang , Zhiliang Peng , Wenhu Chen , Furu Wei

A big convergence of language, multimodal perception, action, and world modeling is a key step toward artificial general intelligence. In this work, we introduce Kosmos-1, a Multimodal Large Language Model (MLLM) that can perceive general…

Large Language Models (LLMs) have emerged as powerful tools for automating complex reasoning and decision-making tasks. In telecommunications, they hold the potential to transform network optimization, automate troubleshooting, enhance…

Scene text image super-resolution (STISR), aiming to improve image quality while boosting downstream scene text recognition accuracy, has recently achieved great success. However, most existing methods treat the foreground (character…

Computer Vision and Pattern Recognition · Computer Science 2023-08-01 Hang Guo , Tao Dai , Guanghao Meng , Shu-Tao Xia

While Large Language Models (LLMs) have demonstrated impressive natural language understanding capabilities across various text-based tasks, understanding humor has remained a persistent challenge. Humor is frequently multimodal, relying on…

Computation and Language · Computer Science 2024-12-10 Ashwin Baluja

Embodied scene understanding serves as the cornerstone for autonomous agents to perceive, interpret, and respond to open driving scenarios. Such understanding is typically founded upon Vision-Language Models (VLMs). Nevertheless, existing…

Computer Vision and Pattern Recognition · Computer Science 2024-03-08 Yunsong Zhou , Linyan Huang , Qingwen Bu , Jia Zeng , Tianyu Li , Hang Qiu , Hongzi Zhu , Minyi Guo , Yu Qiao , Hongyang Li

The perception system in personalized mobile agents requires developing indoor scene understanding models, which can understand 3D geometries, capture objectiveness, analyze human behaviors, etc. Nonetheless, this direction has not been…

Computer Vision and Pattern Recognition · Computer Science 2022-09-28 Yao-Hung Hubert Tsai , Hanlin Goh , Ali Farhadi , Jian Zhang

Deep learning based methods have achieved surprising progress in Scene Text Recognition (STR), one of classic problems in computer vision. In this paper, we propose a feasible framework for multi-lingual arbitrary-shaped STR, including…

Computer Vision and Pattern Recognition · Computer Science 2019-12-13 Jinjin Zhang , Wei Wang , Di Huang , Qingjie Liu , Yunhong Wang