arXiv · 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·· 6 小时前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发布了指令微调与推理导向的多模态大语言模型变体，专为内容与AI安全设计。 模型采用三阶段训练流程并引入Confuse-then-Contrast Fine-Tuning，构建了Yuvion VL RiskEval基准。 Yuvion VL-32B在安全性能上超越同级开源及最佳闭源商业模型，同时保持相当的通用能力。
来源：arXiv · AI · arxiv.org