Skip to content
View original post on X: ModelScopeOfficial
Published
Pick62/100

Tencent WeChat Vision releases open-weight WeVisOne-VL-4B perception model

AIModelScope announces WeVisOne-VL-4B, an open-weight visual perception model from Tencent's WeChat Vision team, built on Qwen3-VL. The team says one model handles seven perception tasks, including detection, counting, pointing, segmentation and alpha matting, and reports 71.3 on Dense200, 89.6 on PixMo-Count and 71.2 on ReasonSeg. It also reports a 96.4% rejection rate on WeRef-Bench and is licensed under Apache-2.0.

AIWhy it matters.

The post names the open-weight release, its Qwen3-VL base, and a Tencent WeChat Vision origin, giving context on a visual perception model covering several task types.

ModelScopeVerified on XOfficial
@ModelScope2022
View on X

One model for points, boxes, masks, and alpha mattes. WeVisOne-VL-4B is open-weight, a visual perception model from Tencent's WeChat Vision, built on Qwen3-VL.
🤖 https://modelscope.ai/models/tencent-community/WeVisOne-VL-4B
🎨 Try the demo: https://modelscope.ai/studios/AI-ModelScope/WeVisOne-VL-4B

🏆 Leading across 30+ perception benchmarks: The team reports strong results from object-level tasks to pixel-level understanding, including 71.3 on Dense200, 89.6 on PixMo-Count, and 71.2 on ReasonSeg.

🧩 One model, seven perception tasks: Detect, localize, count, point to, read, segment, and matte objects through structured next-token prediction.
✂️ From boxes to clean alpha mattes: A lightweight 9.6M pixel decoder produces masks and full-resolution continuous alpha mattes without relying on SAM.

🚫 Rejects targets that are not there: Reaches a 96.4% rejection rate on WeRef-Bench, helping avoid confident boxes for absent queried objects.

📦 Structured outputs for downstream workflows: Returns normalized boxes, points, masks, alpha mattes, and None when no matching target is found.

📜 Apache-2.0 License.

Source details

ModelScope · x.comPublished

Original title: One model for points, boxes, masks, and alpha mattes. WeVisOne-VL-4B is open-weight, a visual perception model from Tencent's WeChat Visi...

Topics

Multimodal AIOpen-source ecosystemChina AIModel releasesEvals & benchmarks