Paper Detail
Tianming Liang, Junyi Pan, Yuxi Li, Canmiao Fu, Zhipeng Huang, Chong Sun, Chen Li, Jing Lyu
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@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},
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 matte},
url = {https://huggingface.co/papers/2610.31329},
keywords = {vision-language models, structured next-token prediction, object-level perception, pixel-level perception, pixel decoder, <OBJ> token, curriculum SFT, mixed-task RL, object-absent queries, code available, huggingface daily},
eprint = {2610.31329},
archiveprefix = {arXiv},
}
{}