Tianming Liang, Junyi Pan, Yuxi Li, Canmiao Fu, Zhipeng Huang, Chong Sun, Chen Li, Jing Lyu · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31329 · open-access PDF
이 보고서에서는 WeVisOne-VL (WeChat Vision All-in-One), 구조화된 다음 토큰 예측을 통해 객체 수준과 픽셀 수준의 인식을 통합하는 강력한 VLM을 소개합니다. 그것은 객체 탐지, 참조 위치, 계산, OCR, 분할 및 매팅을 포함한 여러 가지 시각적 작업을 지원하며, 포인트와 상자에서 알파 매트와 마스크에 이르기까지 모든 사용자 특정 균형에 위치를 허용합니다. 건축적으로, 우리는 특별한 <OBJ>를 통해 VLM에 가벼운 픽셀 디코더를 통합합니다.
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 <OBJ>
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
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