[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-86436-en":3,"doc-seo-86436-105":29,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":20,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},86436,4398048950312,"Violet","https://ap-avatar.wpscdn.com/avatar/400002538284de19e3c?_k=1778320343897328908",8,"Research & Report","The Universal Language of CSI: Unifying Wireless Sensing Across Devices and Environments","WiFi sensing using Channel State Information (CSI) enables ubiquitous, device-free perception, yet existing methods suffer from a “Tower of Babel” that isolates models by hardware, fixed environments, and narrow tasks. The core obstacle is the CSI Heterogeneity Gap, where differences in signal dimensions, sampling rates, and label semantics prevent cross-system understanding. This work proposes a foundation-model framework that treats CSI as a structured language with a learnable universal grammar. By unifying heterogeneous datasets and using adapters plus a shared self-supervised Transformer, sensing semantics are decoupled from hardware syntax, improving cross-environment generalization and few-shot efficiency. ","The Universal Language of CSI:  \nUnifying Wireless Sensing Across Devices and Environments  \nJiayi Chen, Weiting Ou and Guangxu Zhu∗  \narXiv :2607 .09727v1 [ ee ss . SP] 30 Jun 2026  \nAbstract—WiFi sensing based on Channel State Information (CSI) promises ubiquitous, device-free perception, yet current research remains trapped in a “Tower of Babel”—fragmented into isolated silos where models are tailored to specific hardware“dialects”, fixed environments, and narrow tasks. The primary bottleneck is the Heterogeneity Gap: the disparity in signal dimensions, sampling rates, and semantic labels that prevents cross-system understanding. To bridge this gap, we propose a foundation-model framework that treats CSI not merely as raw signals but as a structured language with a learnable universal grammar. We first curate and standardize a large collection of heterogeneous real-world CSI datasets, establishing a unified infrastructure that allows incompatible signal formats to be treated as a single corpus. Second, we introduce a modular architecture that acts as a universal translator where lightweight dataset-specific adapters “tokenize” diverse signal inputs into a shared latent vocabulary, while a shared self-supervised Transformer backbone learns the temporal syntax of human motion and environmental dynamics. This design decouples sensing“semantics” from hardware “syntax”. Extensive evaluations show that by mastering this universal “language”, our approach consistently outperforms task-specific baselines and exhibits strong generalization capability in new environments, achieving superior efficiency in few-shot scenarios. By effectively absorbing heterogeneity, the framework offers a path toward robust, generalpurpose wireless sensing, mirroring the linguistic generalization observed in Large Language Models. The code implementation is available at: [https://github.com/cjychenjiayi/WiLLM](https://github.com/cjychenjiayi/WiLLM).  \nIndex Terms—Artificial intelligence, wireless sensing, fondation model, machine learning  \nI. INTRODUCTION  \nThe evolution toward sixth-generation (6G) wireless networks is transforming communication systems from mere data delivery pipes into platforms that read the physical world. This vision, referred to as Environmental Intelligence (EI) , requires wireless networks not only to communicate but also to perceive their surroundings, interpret contextual dynamics, and interact with the physical environment. Achieving EI requires sensing capabilities deployable at scale across heterogeneous devices and environments, demanding that networks capture shared patterns underlying physical motion, which can be interpreted as a form of latent “language” [1]–[4] .  \nThis work was supported in part by Guangdong Major Project of Basic and Applied Basic Research under Grant 2023B0303000001, in part by National Natural Science Foundation of China (Grant No. U25A20394, 62371313), in part by Guangdong Young Talent Research Project (Grant No. 2023TQ07A708), in part by the Shenzhen Science and Technology Program (Grant No. JCYJ20241202124934046), in part by by Shenzhen Loop Area Institute (Contract No. SLAI2026020007) .  \nJ. Chen and G. Zhu are with the Shenzhen Research Institute of Big Data and The Chinese University of Hong Kong, Shenzhen, Guangdong, China. G. Zhu is also with Shenzhen Loop Area Institute (SLAI), Shenzhen, Guangdong, China. W. Ou is with the Shenzhen Research Institute of Big Data, Shenzhen, Guangdong, [China. Emails:](China. Emails: {jiayichen5@link.cuhk.edu.cn)[ {](China. Emails: {jiayichen5@link.cuhk.edu.cn)[jiayichen5@link.cuhk.edu.cn](China. Emails: {jiayichen5@link.cuhk.edu.cn), [gxzhu@sribd.cn](gxzhu@sribd.cn), [ouweiting7@gmail.com](ouweiting7@gmail.com})[}](ouweiting7@gmail.com}).∗ Corresponding authors: G. Zhu.  \nWireless sensing offers a promising pathway toward this goal by leveraging existing communication infrastructure without requiring additional sensors. WiFi-based sensing has gained prom","cbCaicvUFqVt8OLM","https://ap.wps.com/l/cbCaicvUFqVt8OLM","pdf",3062301,7,1,"English","en",105,"# Introduction\n## Environmental Intelligence and Wireless Perception\n## CSI Sensing and the “Tower of Babel”\n## The CSI Heterogeneity Gap","[{\"question\":\"What problem does the document identify in current WiFi/CSI sensing research?\",\"answer\":\"Current research is trapped in a “Tower of Babel,” where models tuned to specific hardware configurations or fixed environments do not transfer coherently to other settings.\"},{\"question\":\"What is the CSI Heterogeneity Gap?\",\"answer\":\"It is the disparity across systems in signal dimensions, sampling rates, and semantic labels, which blocks shared understanding and generalization across heterogeneous datasets.\"},{\"question\":\"How does the proposed framework address heterogeneity across devices and environments?\",\"answer\":\"It curates and standardizes heterogeneous real-world CSI datasets into a unified corpus, then uses a universal translator with lightweight adapters to tokenize diverse inputs into a shared latent vocabulary, guided by a shared self-supervised Transformer backbone.\"}]",1784211735,18,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":27},"the-universal-language-of-csi-unifying-wireless-sensing-across-devices-and-environments","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/the-universal-language-of-csi-unifying-wireless-sensing-across-devices-and-environments/86436/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-28","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does the document identify in current WiFi/CSI sensing research?","Question",{"text":75,"@type":76},"Current research is trapped in a “Tower of Babel,” where models tuned to specific hardware configurations or fixed environments do not transfer coherently to other settings.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the CSI Heterogeneity Gap?",{"text":80,"@type":76},"It is the disparity across systems in signal dimensions, sampling rates, and semantic labels, which blocks shared understanding and generalization across heterogeneous datasets.",{"name":82,"@type":73,"acceptedAnswer":83},"How does the proposed framework address heterogeneity across devices and environments?",{"text":84,"@type":76},"It curates and standardizes heterogeneous real-world CSI datasets into a unified corpus, then uses a universal translator with lightweight adapters to tokenize diverse inputs into a shared latent vocabulary, guided by a shared self-supervised Transformer backbone.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,119,122,127,130,134],{"id":21,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":45,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":45,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":20,"doc_module":4,"doc_module_name":45,"category_name":116,"show_sort_weight":117,"slug":118},"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":120,"slug":121},30,"research-report",{"id":123,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},9,"Religion & Spirituality",20,"religion-spirituality",{"id":125,"doc_module":4,"doc_module_name":45,"category_name":128,"show_sort_weight":125,"slug":129},"World Cup","world-cup",{"id":131,"doc_module":4,"doc_module_name":45,"category_name":132,"show_sort_weight":131,"slug":133},10,"Lifestyle","lifestyle",{"id":135,"doc_module":4,"doc_module_name":45,"category_name":136,"show_sort_weight":106,"slug":137},19,"General","general"]