WeVisOne-VL: Unified Visual Perception from Objects to Pixels
Tianming Liang, Junyi Pan, Yuxi Li, Canmiao Fu, Zhipeng Huang, Chong Sun and 2 more · Tencent
Collected · snapshot shipped with the site build, not a live feed
Abstract · as written by the authors
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.
This is the original abstract from arXiv. It has not been summarised, translated or rewritten.
Terms in plain language
AutomaticMade by matching the words of the title and abstract against a fixed list of definitions. It does not read the paper and does not change the abstract above.
- vision-language models
- an AI model that takes in images and text together, and usually answers in text.
- token
- a small unit that a model reads and writes, often a part of a word.
- RL
- training by trial and error: good actions earn a reward, and the model adjusts to earn more.
- benchmarks
- a fixed set of tasks or questions used to compare models on the same test.