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。

2026-02-09 至 2026-02-09 共收录 2 篇信号源：cs.CV, cs.CL, cs.AI, cs.MM, eess.AS

1. 图文多模态 2 篇

2602.06184 2026-02-09 cs.CV cs.CL 79%

PhenoLIP: Integrating Phenotype Ontology Knowledge into Medical Vision-Language Pretraining

PhenoLIP：将表型本体知识整合到医学视觉-语言预训练中

Cheng Liang, Chaoyi Wu, Weike Zhao, Ya Zhang, Yanfeng Wang, Weidi Xie

机构 * School of Artificial Intelligence, Shanghai Jiao Tong University（上海交通大学人工智能学院）； Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）

专题命中图文多模态：multimodal(abstract)；cross-modal(abstract)；image-text(abstract)；分类 cs.CV、cs.CL

AI总结 PhenoLIP通过整合表型本体知识提升医学视觉-语言模型的表型识别与跨模态检索性能。

2602.06799 2026-02-09 cs.CL 57%

Visual Word Sense Disambiguation with CLIP through Dual-Channel Text Prompting and Image Augmentations

通过双通道文本提示和图像增强的CLIP实现视觉词义消歧

Shamik Bhattacharya, Daniel Perkins, Yaren Dogan, Vineeth Konjeti, Sudarshan Srinivasan, Edmon Begoli

机构 * 2 The Bredesen Center for Interdisciplinary Research ； 3 Department of Electrical Engineering \& Computer Science, University of Tennessee, Knoxville, TN 37916 ； 4 Oak Ridge National Laboratory (ORNL), Oak Ridge, TN 37830

专题命中图文多模态：multimodal(abstract)；分类 cs.CL

AI总结本文提出通过CLIP和双通道提示与图像增强实现视觉词义消歧，提升MRR和命中率，验证了精确提示的有效性。

Comments 9 pages, 6 figures, pending journal/workshop submission