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。

2025-10-16 至 2025-10-16 共收录 3 篇信号源：cs.CV, cs.CL, cs.AI, cs.MM, eess.AS

1. 视频多模态 3 篇

2507.05258 2025-10-16 cs.CV cs.LG 70%

Spatio-Temporal LLM: Reasoning about Environments and Actions

Haozhen Zheng, Beitong Tian, Mingyuan Wu, Zhenggang Tang, Klara Nahrstedt, Alex Schwing

机构 * University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）

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

Comments Code and data are available at https://zoezheng126.github.io/STLLM-website/

2505.16836 2025-10-16 cs.CV cs.AI 62%

Fact-R1: Towards Explainable Video Misinformation Detection with Deep Reasoning

Fanrui Zhang, Dian Li, Qiang Zhang, Jun Chen, Gang Liu, Junxiong Lin, Jiahong Yan, Jiawei Liu, Zheng-Jun Zha

机构 * MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition, USTC（脑启发智能感知与认知国家重点实验室，中国科学技术大学）； Shanghai Innovation Institute（上海创新研究院）； Tencent QQ（腾讯QQ）； Fudan University（复旦大学）

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

Comments 34 pages, 25 figures

2510.13019 2025-10-16 physics.optics 50%

Phase Matching of Orbital Angular Momentum in Rare Earth Ion Doped Solid State Systems

Owen R. Wolfe, Joshua Dugre, Grant Kirkland, R. Krishna Mohan

专题命中视频多模态：multi-modal(abstract)