MarkTechPost67

Tencent WeVisOne-VL Unifies Detection, OCR, Segmentation and Matting

Name: AI HOT 精选数据集（復刻站）
License: https://aihot.yuenlau.org/llms.txt

2026/11/04 12:39· 3小时前

AI 摘要

Tencent’s WeChat Vision team released WeVisOne-VL, an Apache 2.0 vision language model in 2B and 4B sizes. It handles detection, OCR, counting, segmentation and alpha matting in one model, with a 9.6M-parameter pixel decoder. The post Tencent WeVisOne-VL Unifies Detection, OCR, Segmentation and Matting appeared first on MarkTechPost .

查看原文（MarkTechPost）