| title | WeVisOne-VL: Unified Visual Perception from Objects to Pixels |
|---|---|
| authors | Tianming Liang, Junyi Pan, Yuxi Li, Canmiao Fu, Zhipeng Huang, Chong Sun, Chen Li, Jing Lyu |
| date | 2026-10-22 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2610.31329 |
| affiliation | Tencent |
| upvotes | 48 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | Existing vision-language models (VLMs) remain unreliable for fine-grained visual perception. In this report, we present WeVisOne-VL (WeChat Vision All-in-One), a powerful VLM that unifies object-level and pixel-level perception through structured next-token prediction. It supports multiple visual tasks including object detection, referring localization, counting, OCR, segmentation, and matting, enabling localization at any user-specific granularity, from points and boxes to masks and alpha mattes. Architecturally, we integrate a lightweight pixel decoder into the VLM via a special <OBJ> token to generate instance-level pixel outputs. We train the model with a three-stage curriculum SFT followed by mixed-task RL. Across over 30 benchmarks, WeVisOne-VL demonstrates leading performance on both object-level and pixel-level tasks, while maintaining robust rejection for object-absent queries. By releasing WeVisOne-VL to the open-source community, we hope to advance VLMs from broad visual understanding toward truly reliable perception systems for real-world deployment. |
cite
@misc{liang2026wevisone,
title={WeVisOne-VL: Unified Visual Perception from Objects to Pixels},
author={Tianming Liang and Junyi Pan and Yuxi Li and Canmiao Fu and Zhipeng Huang and Chong Sun and Chen Li and Jing Lyu},
year={2026},
eprint={2610.31329},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2610.31329}
}