# Tencent releases WeVisOne-VL-2B, a unified vision-language model for object and pixel perception

> Original title: tencent/WeVisOne-VL-2B

- Source: Tencent · new models on Hugging Face
- Published: 2026-10-22T09:47:50.000Z
- Bad Influence: https://badinfluence.news/items/nvl98prli2595eut3efdein63
- Original: https://huggingface.co/tencent/WeVisOne-VL-2B

## Summary

Tencent's WeChat Vision team releases WeVisOne-VL-2B, a vision-language model built on Qwen3-VL that unifies object-level tasks such as detection, counting, and OCR with pixel-level referring segmentation and alpha matting. A lightweight 9.5M-parameter pixel decoder handles the pixel tasks, and the model is available on Hugging Face under the Apache License 2.0 for research use. The model generates structured outputs without explicit chain-of-thought reasoning, and fine alpha boundaries remain sensitive to resolution, occlusion, and prompt phrasing.