关闭导航

包含标签" visual question answering"的内容

Meta WebSSL无语言训练纯视觉模型 性能超CLIP助力多模态研究
AI妹 1 个月前 10 0

In the field of artificial intelligence, Meta recently introduced the WebSSL series of models. The

阿里MNN发布MnnLlmApp新版 支持Qwen-2.5-Omni3B/7B 推进移动多模态AI普及
AI妹 1 个月前 9 0

Alibaba's open-source project Mobile Neural Network (MNN) has released the latest version of its m

UC Santa Cruz推出OpenVision视觉编码器 可替代CLIP/SigLIP且高效灵活多样
AI妹 1 个月前 8 0

UC Santa Cruz recently announced the release of OpenVision, a brand-new series of visual encoders

HAI-DEF推出MedGemma与MedSigLIP 赋能健康AI研发与应用
AI妹 1 个月前 7 0

In the modern medical field, artificial intelligence (AI) is gradually becoming an important tool