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。

2025-10-06 至 2025-10-06 共收录 1 篇信号源：cs.CV, cs.CL, cs.AI, cs.MM, eess.AS

1. 音频语音多模态 1 篇

2510.02322 2025-10-06 eess.AS cs.CL 81%

SpeechCT-CLIP: Distilling Text-Image Knowledge to Speech for Voice-Native Multimodal CT Analysis

Lukas Buess, Jan Geier, David Bani-Harouni, Chantal Pellegrini, Matthias Keicher, Paula Andrea Perez-Toro, Nassir Navab, Andreas Maier, Tomas Arias-Vergara

机构 * Computer Aided Medical Procedures, Technical University of Munich（慕尼黑技术大学计算机辅助医学程序）

专题命中音频语音多模态：multimodal(title,abstract)；分类 cs.CL、eess.AS

Comments Submitted to ICASSP 2026; under review

↑