{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T06:11:36Z","timestamp":1784182296612,"version":"3.55.0"},"reference-count":16,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:00:00Z","timestamp":1779580800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,5,24]]},"DOI":"10.1109\/iccworkshops63917.2026.11586562","type":"proceedings-article","created":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T20:00:48Z","timestamp":1784145648000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["Seeing Radio: From Zero RF Priors to Explainable Modulation Recognition with Vision Language Models"],"prefix":"10.1109","author":[{"given":"Hang","family":"Zou","sequence":"first","affiliation":[{"name":"Khalifa University,Research Institute for Digital Future,Abu Dhabi,UAE,127788"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bohao","family":"Wang","sequence":"additional","affiliation":[{"name":"Khalifa University,Research Institute for Digital Future,Abu Dhabi,UAE,127788"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Tian","sequence":"additional","affiliation":[{"name":"Khalifa University,Research Institute for Digital Future,Abu Dhabi,UAE,127788"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lina","family":"Bariah","sequence":"additional","affiliation":[{"name":"Khalifa University,Research Institute for Digital Future,Abu Dhabi,UAE,127788"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chongwen","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Information Science and Electronic Engineering,Hangzhou,China,310027"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Samson","family":"Lasaulce","sequence":"additional","affiliation":[{"name":"Université de Lorraine, CNRS, CRAN,Nancy,France,F-54000"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"M\u00e9rouane","family":"Debbah","sequence":"additional","affiliation":[{"name":"Khalifa University,Research Institute for Digital Future,Abu Dhabi,UAE,127788"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Language Models are Few-Shot Learners","author":"Brown","year":"2020","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref3","article-title":"Qwen2.5-VL Technical Report","author":"Bai","year":"2025"},{"key":"ref4","article-title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","author":"Zhu","year":"2025"},{"key":"ref5","volume-title":"Introducing GPT-5","year":"2025"},{"key":"ref6","article-title":"A Comprehensive Survey of 6G Wireless Communications","author":"Zhao","year":"2020"},{"key":"ref7","article-title":"6G: The Intelligent Network of Everything \u2013 A Comprehensive Vision and Tutorial","author":"Giordani","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2024.10582827"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2300364"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3465447"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2025.3593184"},{"key":"ref12","article-title":"Vision language models are few-shot audio spectrogram classifiers","volume-title":"Audio Imagination: NeurIPS 2024 Workshop AI-Driven Speech, Music, and Sound Generation","author":"Dixit"},{"key":"ref13","article-title":"Large scale radio frequency signal classification","author":"Boegner","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0441"},{"key":"ref15","article-title":"Xcit: Cross-covariance image transformers","author":"El-Nouby","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"}],"event":{"name":"2026 IEEE International Conference on Communications Workshops (ICC Workshops)","location":"Glasgow, United Kingdom","start":{"date-parts":[[2026,5,24]]},"end":{"date-parts":[[2026,5,28]]}},"container-title":["2026 IEEE International Conference on Communications Workshops (ICC Workshops)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11586035\/11586192\/11586562.pdf?arnumber=11586562","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T05:43:32Z","timestamp":1784180612000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11586562\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,24]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/iccworkshops63917.2026.11586562","relation":{},"subject":[],"published":{"date-parts":[[2026,5,24]]}}}