# Tencent releases WeVisOne-VL-4B, a unified vision-language model for object and pixel perception

> Original title: tencent/WeVisOne-VL-4B

- Source: Tencent · new models on Hugging Face
- Published: 2026-10-22T09:48:14.000Z
- Bad Influence: https://badinfluence.news/items/tdo85iq6lpbxx8ir0gqx4uf2x
- Original: https://huggingface.co/tencent/WeVisOne-VL-4B

## Summary

Tencent's WeChat Vision team releases WeVisOne-VL-4B, a vision-language model built on Qwen3-VL that handles object-level tasks such as open-vocabulary detection, referring localization, counting, pointing, and OCR, plus pixel-level referring segmentation and alpha matting. The model adds a 9.6M-parameter pixel decoder and is intended for research use under the Apache License 2.0 for Tencent-authored code.