WeChat Vision, Tencent · Vision-Language Model

WeVisOne-VL

A vision-language model from Tencent's WeChat Vision team that handles detection, referring localization, counting, pointing, OCR, segmentation and alpha matting in one model. Built on Qwen3-VL, it writes coordinates as 1,001 dedicated tokens and adds a 9.6M-parameter pixel decoder for masks and mattes, with no SAM; it answers None when a target is absent. Training used about 100M images: three SFT stages, then mixed-task GRPO RL. The team reports leading 30+ benchmarks (self-reported), for example 55.3 F1 on LVIS against 50.7 for the best baseline. 2B and 4B weights are on Hugging Face under Apache 2.0, with a live demo.