WeVisOne-VL: Unified Visual Perception from Objects to Pixels

WeVisOne-VL is a vision-language model that unifies object-level and pixel-level perception through structured next-token prediction. It supports tasks such as object detection, segmentation, OCR, and matting, and uses a lightweight pixel decoder with a special <OBJ> token to generate instance-level pixel outputs. The model is trained with a three-stage curriculum SFT followed by mixed-task RL and reportedly achieves leading performance across over 30 benchmarks.