arXiv cs.AI· Shikai Qiu, Xiaowen Xu, Benlei Cui, Ting Ma, Xiufeng Huang, Wenjing Jiang, Shaoxuan He, Haolei Xu, Chunyang Chai, Yujian Li, Yiliang Zhang, Guanghui Wang, Ziheng Wang, Ziwen Xu, Zhaoyu Fan, Jinhao Chen, Ruijie Jian, Hongxing Li, Chuxi Xiao, Xinyue Chen, Wenxuan Liu, Libin Dong, Yupeng Cao, Xiaoqian Xia, Jing Wang, Zhe Jiang, Zhenan Ye, Guang Yang, Bin Liu, Wei Peng, Ziqiang Zhu, Meihui Lian, Kaiwen Lv Kacuila, Haidong Ding, Dongjie Zhang, Yangfan Zhou, Bingyu Zhu, Yan Wang, Hai Zhao, Xuan Jin, Wei Zhao, Pengfei Sun, Huiming Zhang, Wei Wang, Xipeng Cao, Jialun Chen, Xiao Chen, Shaola Ren, Yunqing Hu, Bin Li, Chengwen Yao, Meng Huang, Xianfeng Li, Bin Tang, Chao Liu, Hui Xue, Longtao Huang, Haiwen Hong·· 1 天前AI 评分41
Yuvion VL：面向对抗性内容与 AI 安全的多模态基础模型
Yuvion VL: A Multimodal Foundation Model for Adversarial Content and AI Safety
AI 导读
Yuvion VL 是一系列专为内容与 AI 安全构建的多模态大语言模型，提供指令微调与推理导向两种变体。其训练采用三阶段流程（风险概念跨模态对齐的继续预训练、生产级安全任务的指令后训练、推理后训练），并提出 Confuse-then-Contrast 微调框架和 Yuvion VL RiskEval（YVRE）评测基准。
来源：arXiv cs.AI · arxiv.org