WeVisOne-VL
WeVisOne-VL is a powerful VLM by the WeChat Vision Team at Tencent, unifying object-level and pixel-level perception from points and boxes to masks and alpha mattes.
WeVisOne-VL launched on 22 October 2026. It ranked #94 on Daily Launch on 4 November 2026 with a Launch Score of 26, from 797 stars in 13 days on GitHub. It was new in the ranking that day.
What is We Vis One VL?
Headline numbers for WeVisOne-VL-4B against the strongest open baseline in each benchmark (Qwen3-VL / Qwen3.5 up to 9B, Rex-Omni, LocateAnything, and task-specific segmentation / matting models). F1 for detection, referring and OCR is averaged over IoU thresholds 0.5:0.95 ("Mean"). Greedy decoding, ≤ 1,960 visual tokens per image.
From its README on GitHub
We Vis One VL (WeVisOne-VL) is a repo by Tencent on GitHub. It is written in Jupyter Notebook.
How to get We Vis One VL
Get it from its repository on GitHub.
Launch timeline
Launch Score, last 7 days
Ranked on one day so far: 26 of 100 on 4 November.