HuggingPapers· @HuggingPapers · X·· 3 天前AI 评分
腾讯在 Hugging Face 发布 WeVisOne-VL 统一视觉感知模型
腾讯在 Hugging Face 发布 WeVisOne-VL,以一个 VLM 统一处理视觉感知任务。模型支持从点和框到掩码与 alpha matte 的输出,覆盖检测、计数、OCR、分割和抠图,并能可靠拒绝不存在的目标。
Tencent released WeVisOne-VL on Hugging Face
One VLM for unified visual perception, from points and boxes to masks and alpha mattes. It handles detection, counting, OCR, segmentation and matting, and reliably rejects absent targets.
来源:HuggingPapers · x.com