Oriel — AI & technology worth noticing, every day.

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Paper · https://arxiv.org/abs/2610.31329

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.

First seen by Oriel on .

AI summary

WeVisOne-VL unifies object- and pixel-level visual perception in a vision-language model, reporting leading results across more than 30 benchmarks.

  • It supports object detection, referring localization, counting, OCR, segmentation, and matting, with outputs ranging from points and boxes to masks and alpha mattes.
  • A lightweight pixel decoder connects to the VLM through a special <OBJ> token to produce instance-level pixel outputs.
  • Training uses a three-stage curriculum SFT followed by mixed-task RL.
  • The model is reported to perform well on object-absent queries and is being released to the open-source community.

#vision-language models #visual perception #object detection #image segmentation

Generated by gpt-5.6-sol. Check the original for details.

Metric trends

Last 30 days · Up to 120 recorded samples per source and metric, with reposts kept separate · First and latest retained

Points

Score reported by the source.

  • Hugging Face Papers: 48, latest observation ; -172 over observed period since

Comments

Comment count reported by the source.

  • Hugging Face Papers: 4, latest observation ; +3 over observed period since

Aliases

SourceExternal IDURL
Hugging Face Papers2610.31329https://arxiv.org/abs/2610.31329 Read discussion