---
format: "aidr-story-markdown/v1"
id: "f2a6f50dd497059b9964c7b11a68ab3c1bcadff20218f531241ccf0e233d6f3d"
canonical_url: "https://aidr.today/f2a6f50d?lang=en"
title: "Tencent WeVisOne-VL Unifies Detection, OCR, Segmentation and Matting"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-11-04T04:39:27.000Z"
category: "Open Source"
topics: ["open-source"]
source_urls: ["https://www.marktechpost.com/2026/11/03/tencent-wevisone-vl-vision-language-model/"]
summary: "Tencent's WeChat Vision team released WeVisOne-VL, an Apache 2.0 vision language model in 2B and 4B sizes that handles detection, OCR, counting, segmentation and alpha matting in one model, with a 9.6M-parameter pixel decoder."
---

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

> [Open the canonical story](<https://aidr.today/f2a6f50d?lang=en>)

**Published:** 2026-11-04T04:39:27.000Z
**Category:** Open Source
**Topics:** open\-source

## Summary

Tencent's WeChat Vision team released WeVisOne\-VL, an Apache 2\.0 vision language model in 2B and 4B sizes that handles detection, OCR, counting, segmentation and alpha matting in one model, with a 9\.6M\-parameter pixel decoder\.

## Sources

- [Story source](<https://www.marktechpost.com/2026/11/03/tencent-wevisone-vl-vision-language-model/>)