WeVisOne-VL-4B

**Paper:** WeVisOne-VL: Unified Visual Perception from Objects to Pixels | **Project Page:** WeVisOne-VL **WeVisOne-VL** (**We**Chat **Vis**ion All-in-**One**) is a unified vision-language model developed by WeChat Vision, Tencent Inc. Built upon Qwen3-VL, it unifies object-level perception (open-vocabulary object detection, referring localization, object counting, object pointing, and OCR) and pixel-level perception (referring segmentation and promptable alpha matting) through structured next-token prediction and a lightweight 9.6M-parameter pixel decoder. The model uses dedicated coordinate tokens (` ` ... ` `) to represent normalized bounding boxes and points, returns `None` when a queried target is absent, and emits a special instance token (` `, token ID `152678`) after each predicted box for dense tasks.