Newest papers

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Tianming Liang, Junyi Pan, Yuxi Li, Canmiao Fu, Zhipeng Huang, Chong Sun, Chen Li, Jing Lyu · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31329 · cited by 0 works (OpenAlex) · open-access PDF

Hindi

मौजूदा दृष्टि-भाषा मॉडल (VLMs) सूक्ष्म-जीने वाली दृश्य धारणा के लिए अविश्वसनीय रहते हैं। इस रिपोर्ट में, हम WeVisOne-VL (WeChat Vision All-in-One) प्रस्तुत करते हैं, एक शक्तिशाली VLM जो संरचित अगले टोकन पूर्वानुमान के माध्यम से वस्तु स्तर और पिक्सेल स्तर की धारणा को एकीकृत करता है। यह वस्तु डिटेक्शन, संदर्भ स्थान, गिनती, ओसीआर, विभाजन, और मैटिंग सहित कई दृश्य कार्यों का समर्थन करता है, जो किसी भी उपयोगकर्ता-विशिष्ट granularity पर स्थान को सक्षम करता है, बिंदुओं और बॉक्सों से मास्क और अल्फा मैट तक। आर्किटेक्चरिक रूप से, हम एक विशेष ट

Machine translation (Meta M2M100); the English original follows.

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 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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Artificial intelligence, Computer vision, Pixel, Computer science, Perception, Object (grammar)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange