arXivDaily arXiv每日学术速递 周一至周五更新

AI 大模型

多模态大模型

跨文本、图像、视频、音频等模态的大模型与学习方法。

2025-08-22 至 2025-08-22 共收录 5 信号源:cs.CV, cs.CL, cs.AI, cs.MM, eess.AS

1. 视频多模态 5 篇

2508.15717 2025-08-22 cs.CV cs.AI 62%

StreamMem: Query-Agnostic KV Cache Memory for Streaming Video Understanding

Yanlai Yang, Zhuokai Zhao, Satya Narayan Shukla, Aashu Singh, Shlok Kumar Mishra, Lizhu Zhang, Mengye Ren

机构 * Meta AI New York University(纽约大学)

专题命中 视频多模态 :multimodal(abstract);分类 cs.CV、cs.AI

Comments 15 pages, 3 figures

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14941 2025-08-22 cs.MM cs.CL 62%

Robust Symbolic Reasoning for Visual Narratives via Hierarchical and Semantically Normalized Knowledge Graphs

Yi-Chun Chen

机构 * Yale University(耶鲁大学)

专题命中 视频多模态 :multimodal(abstract);分类 cs.CL、cs.MM

Comments 12 pages, 4 figures, 2 tables. Extends our earlier framework on hierarchical narrative graphs with a semantic normalization module

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.11988 2025-08-22 cs.CV 57%

Exploring Spatial-Temporal Dynamics in Event-based Facial Micro-Expression Analysis

Nicolas Mastropasqua, Ignacio Bugueno-Cordova, Rodrigo Verschae, Daniel Acevedo, Pablo Negri, Maria E. Buemi

机构 * Universidad de Buenos Aires, Facultad de Ciencias Exactas y Naturales(布宜诺斯艾利斯大学,精确科学与自然学院) Institute of Engineering Sciences, Universidad de O’Higgins(工程科学研究所,奥希金斯大学) CONICET-UBA, Instituto de Ciencias de la Computacion (ICC)(CONICET-UBA,计算科学研究所) L3S Research Center, Leibniz Universität Hannover(L3S研究中心,汉诺威莱布尼茨大学)

专题命中 视频多模态 :multi-modal(abstract);分类 cs.CV

Journal ref 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW); 2nd Workshop on Neuromorphic Vision (NeVi)

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.15036 2025-08-22 cs.CR cs.AI 57%

MoEcho: Exploiting Side-Channel Attacks to Compromise User Privacy in Mixture-of-Experts LLMs

Ruyi Ding, Tianhong Xu, Xinyi Shen, Aidong Adam Ding, Yunsi Fei

机构 * Louisiana State University(路易斯安那州立大学) Northeastern University(东北大学) Yale University(耶鲁大学)

专题命中 视频多模态 :multimodal(abstract);分类 cs.AI

Comments This paper will appear in CCS 2025

详情

展开后加载摘要…

URL PDF HTML 收藏
2508.14942 2025-08-22 cs.LG 50%

Structure-Aware Temporal Modeling for Chronic Disease Progression Prediction

Jiacheng Hu, Bo Zhang, Ting Xu, Haifeng Yang, Min Gao

专题命中 视频多模态 :multimodal(abstract)

详情

展开后加载摘要…

URL PDF HTML 收藏