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
In diesem Bericht präsentieren wir WeVisOne-VL (WeChat Vision All-in-One), ein leistungsstarkes VLM, das die Wahrnehmung auf Objektebene und Pixelebene durch strukturierte Next-Token-Vorhersage vereint. Es unterstützt mehrere visuelle Aufgaben, einschließlich Objekterkennung, Referenzlokalisierung, Zählung, OCR, Segmentierung und Matten, was die Lokalisierung bei jeder benutzerspezifischen Granularität ermöglicht, von Punkten und Boxen bis hin zu Masken und Alpha-Matten. Architektonisch integrieren wir einen leichten Pixel-Decoder in das VLM über ein spezielles Token, um Instanz-Pixel-Ausgänge auf Generationsebene zu identifizieren. Wir trainieren das Modell mit einem dreistufigen
Machine translation (Meta M2M100); the English original follows.
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)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31329, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange