资讯

On July 4th, the first train of the "Zheng He" Sea-Road-Rail International Multimodal Transport Service departed from Kunming, Yunnan.7月4日,“郑和号” 海公铁国际多式联运班列在云南昆明首发。Named after the renowned navigator Z ...
首先,谷歌发布了一系列用于健康 AI 开发的多模态模型 MedGemma ,其中包含 4B 和 27B 两个大小的几个不同模型:MedGemma 4B Multimodal、MedGemma 27B Text 和 MedGemma 27B ...
近日,阿里巴巴通义实验室联合悉尼大学、DeepGlint和帝国理工学院的研究团队发布了一项创新研究,提出了**UniME(Universal Multimodal ...
AsianFin— Sunrise, a domestic AI chipmaker spun off from SenseTime’s core semiconductor division, has raised nearly $139 ...
这项由阿里巴巴通义实验室联合悉尼大学、DeepGlint和帝国理工学院的研究团队完成的工作发表于2025年4月,论文标题为《Breaking the Modality Barrier: Universal Embedding Learning ...
微软发布Phi-4-multimodal,这是一款小型语言模型(SLM)具备处理语音、图像与文本的能力,已于Azure AI Foundry、Hugging Face及Nvidia API Catalog上线。相较于 ...
近日,明略科技与北京大学、吉林大学合作的最新研究成果《PRE-MAP: Personalized Reinforced Eye-tracking Multimodal LLM for High-Resolution Multi-Attribute Point Prediction》被ACM MM 20 ...
BEIJING, June 10 (Xinhua) -- A group of Chinese scientists confirmed that multimodal large language models (LLMs) can spontaneously develop human-like object concept representations, providing a ...