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。

2025-08-21 至 2025-08-21 共收录 7 篇信号源：cs.CV, cs.CL, cs.AI, cs.MM, eess.AS

1. 多模态生成 7 篇

2504.02906 2025-08-21 cs.CL cs.AI 84%

Boosting Chart-to-Code Generation in MLLM via Dual Preference-Guided Refinement

Zhihan Zhang, Yixin Cao, Lizi Liao

机构 * Singapore Management University（新加坡国立管理学院）； Fudan University（复旦大学）

专题命中多模态生成：MLLM(title)；multimodal(abstract)；cross-modal(abstract)；分类 cs.CL、cs.AI

Comments Accepted by ACM MM 2025

2502.13034 2025-08-21 cs.CL cs.AI cs.CV cs.LG 67%

Natural Language Generation from Visual Events: State-of-the-Art and Key Open Questions

Aditya K Surikuchi, Raquel Fernández, Sandro Pezzelle

机构 * Institute for Logic, Language and Computation (ILLC), University of Amsterdam（逻辑、语言与计算研究所（ILLC），阿姆斯特丹大学）

专题命中多模态生成：multimodal(abstract)；分类 cs.CV、cs.CL、cs.AI

2508.14718 2025-08-21 cs.CL 57%

The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation

Shubham Pundhir, Ganesh Bagler

机构 * Indraprastha Institute of Information Technology（印度理工学院信息技术研究所）

专题命中多模态生成：multi-modal(abstract)；分类 cs.CL

Comments 8 pages, 4 figures. Code is available at: https://github.com/shubh-iiit/RecipeGPT2-Your-Own-AI-Chef

2508.14405 2025-08-21 cs.CV 57%

CTA-Flux: Integrating Chinese Cultural Semantics into High-Quality English Text-to-Image Communities

Yue Gong, Shanyuan Liu, Liuzhuozheng Li, Jian Zhu, Bo Cheng, Liebucha Wu, Xiaoyu Wu, Yuhang Ma, Dawei Leng, Yuhui Yin

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

2508.14393 2025-08-21 cs.CV 57%

Img2ST-Net: Efficient High-Resolution Spatial Omics Prediction from Whole Slide Histology Images via Fully Convolutional Image-to-Image Learning

Junchao Zhu, Ruining Deng, Junlin Guo, Tianyuan Yao, Juming Xiong, Chongyu Qu, Mengmeng Yin, Yu Wang, Shilin Zhao, Haichun Yang, Daguang Xu, Yucheng Tang, Yuankai Huo

机构 * Department of Computer Science, Vanderbilt University（计算机科学系，范德比尔特大学）； Weill Cornell Medicine（韦尔·科恩医学中心）； Department of Electrical and Computer Engineering, Vanderbilt University（电气与计算机工程系，范德比尔特大学）； Department of Biostatistics, Vanderbilt University Medical Center（生物统计学系，范德比尔特大学医学中心）； NVIDIA

专题命中多模态生成：multi-modal(abstract)；分类 cs.CV

2508.14359 2025-08-21 cs.CV 57%

Taming Transformer for Emotion-Controllable Talking Face Generation

Ziqi Zhang, Cheng Deng

机构 * Xidian University（西安电子科技大学）

专题命中多模态生成：multimodal(abstract)；分类 cs.CV

2408.13799 2025-08-21 math.ST math.PR stat.ML stat.TH 50%

Non-asymptotic bounds for forward processes in denoising diffusions: Ornstein-Uhlenbeck is hard to beat

Miha Brešar, Aleksandar Mijatović

专题命中多模态生成：multi-modal(abstract)

Comments new Subsection 4.1 on Kinetic Langevin diffusion as forward process included; to appear in Annals of Applied Probability; 25 pages, 4 figures; see short YouTube videos https://youtu.be/hQvfpwI0UPk?si=tfL-DrH2EzqCuGSN and https://youtu.be/xjzVPOEkl44?si=fq9l3kZFg8eELYG3 explaining the main results and ideas of proofs