[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83366-en":3,"doc-seo-83366-105":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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"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},83366,1099514068365,"Aurelia","https://ap-avatar.wpscdn.com/avatar/10000253d8d9f28188e?_k=1776742907772140068",8,"Research & Report","MobiDiff Semantic-Aware Multi-Channel Discrete Diffusion for Human Mobility Data Generation","Human mobility data drive transportation optimization, urban planning, and resource allocation, but real-world traces are expensive to collect and hard to share due to privacy risks. Diffusion-based synthesis can generate realistic mobility patterns, yet often depends on continuous or latent spatio-temporal traces, restricting native modeling of discrete semantic events. MobiDiff proposes an end-to-end discrete diffusion framework that denoises multichannel semantic skeletons, decomposing check-ins into spatial, activity, and temporal channels, and using structured masking. Evaluations on Atlanta, Boston, and Seattle show strong fidelity, privacy-preserving behavior, and 5.3× faster inference than GeoGen.","MobiDiff: Semantic-Aware Multi-Channel Discrete Diffusion for  \nHuman Mobility Data Generation  \nRongchao Xu  \nFlorida State University Tallahassee, Florida, USA[rx21a@fsu.edu](rx21a@fsu.edu)  \nLin Jiang  \nFlorida State University Tallahassee, Florida, USA [lj23d@fsu.edu](lj23d@fsu.edu)  \nDahai Yu  \nFlorida State University Tallahassee, Florida, USA[dahai.yu@fsu.edu](dahai.yu@fsu.edu)  \nXimiao Li  \nFlorida State University Tallahassee, Florida, USA [xl24g@fsu.edu](xl24g@fsu.edu)  \nTaichi Liu  \nRutgers University Piscataway, New Jersey, USA [taichi.liu@rutgers.edu](taichi.liu@rutgers.edu)  \nDesheng Zhang  \nRutgers University Piscataway, New Jersey, USA [desheng@cs.rutgers.edu](desheng@cs.rutgers.edu)  \narXiv :2607 .08357v 1 [ cs .AI] 9 Jul 2026  \nYuan Tian  \nUniversity of California, Los Angeles Los Angeles, California , USA [yuant@ucla.edu](yuant@ucla.edu)  \nAbstract  \nHuman mobility data are essential for transportation optimization, urban planning, and resource allocation, yet real-world mobility data are costly to collect and difficult to share due to privacy concerns. Recent diffusion-based methods have shown promise in synthesizing realistic mobility patterns, but they typically rely on continuous or latent spatio-temporal traces, limiting their ability to natively model discrete semantic events with explicit region, activity, time, and interval structures. To address this issue, we introduce MobiDiff, an end-to-end discrete diffusion framework that efficiently generates mobility data by directly denoising multichannel semantic skeletons, avoiding the costly interpolation, latent trace construction, and coarse-to-fine realization pipelines widely used in existing diffusion-based methods. Specifically, MobiDiff decomposes each human check-in event into spatial, activity, and temporal channels, and employs structured event-, group-, and channel-level masking to jointly capture trajectory-level mobility patterns and within-event dependencies. We evaluate generation fidelity, privacy-preserving, and efficiency on three large-scale realworld datasets from Atlanta, Boston, and Seattle. Results show that MobiDiff effectively preserves trajectory length and temporal interval distributions while remaining competitive across broader mobility statistics; it is also much faster than state-of-the-art methods, e.g., 5.3× faster than GeoGen on average during inference. These findings suggest that discrete diffusion offers an interpretable and efficient framework for synthetic mobility data generation.  \n∗ Prof. Guang Wang is the corresponding author.  \nPermission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than the author(s) must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission [and/or a fee. Request permissions from permissions@acm.org](and/or a fee. Request permissions from permissions@acm.org).  \nConference’17, July 2017, Washington, DC, USA  \n© 2026 Copyright held by the owner/author(s) . Publication rights licensed to ACM. ACM ISBN 978-x-xxxx-xxxx-x/YY/MM  \n[https://doi.org/10.1145/nnnnnnn.nnnnnnn](https://doi.org/10.1145/nnnnnnn.nnnnnnn)  \nGuang Wang∗ Florida State University Tallahassee, Florida, USA  \n[guang@cs.fsu.edu](guang@cs.fsu.edu)  \nCCS Concepts  \n• Information systems → Spatial-temporal systems; Data mining.  \nKeywords  \nSynthetic Data Generation, Diffusion Model, Spatiotemporal Patterns  \nACM Reference Format:  \nRongchao Xu, Lin Jiang, Dahai Yu, Ximiao Li, Taichi Liu, Desheng Zhang, Yuan Tian, and Guang Wang. 2026. MobiDiff: Semantic-Aware Multi-Channel Discrete Diffusion for Human Mobility Data Generation. In . ACM, New York, NY","cbCaiuYcYbd2vP0Z","https://ap.wps.com/l/cbCaiuYcYbd2vP0Z","pdf",814428,1,9,"English","en",105,"# Introduction\n## Related Work and Motivation\n# Method Overview\n## Discrete Diffusion for Mobility Generation\n# Experiments\n## Datasets and Evaluation Metrics\n# Results and Analysis\n## Fidelity, Privacy, and Efficiency","[{\"question\":\"Why is synthetic human mobility data generation needed?\",\"answer\":\"Real mobility data are valuable but costly to collect and difficult to share because they can reveal sensitive behavioral patterns. Synthetic generation supports large-scale access while reducing exposure of raw traces.\"},{\"question\":\"What is the key idea behind MobiDiff?\",\"answer\":\"MobiDiff uses an end-to-end discrete diffusion framework that denoises multichannel semantic skeletons directly, avoiding continuous/latent trace interpolation and coarse-to-fine realization pipelines.\"},{\"question\":\"How does MobiDiff model a human check-in event?\",\"answer\":\"It decomposes each check-in into spatial, activity, and temporal channels, and applies structured event-, group-, and channel-level masking to capture trajectory-level mobility patterns and within-event dependencies.\"}]",1784187020,23,{"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},"mobidiff-semantic-aware-multi-channel-discrete-diffusion-for-human-mobility-data-generation","",{"@graph":35,"@context":85},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"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/mobidiff-semantic-aware-multi-channel-discrete-diffusion-for-human-mobility-data-generation/83366/",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","2026-07-23","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},"Why is synthetic human mobility data generation needed?","Question",{"text":75,"@type":76},"Real mobility data are valuable but costly to collect and difficult to share because they can reveal sensitive behavioral patterns. Synthetic generation supports large-scale access while reducing exposure of raw traces.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"What is the key idea behind MobiDiff?",{"text":80,"@type":76},"MobiDiff uses an end-to-end discrete diffusion framework that denoises multichannel semantic skeletons directly, avoiding continuous/latent trace interpolation and coarse-to-fine realization pipelines.",{"name":82,"@type":73,"acceptedAnswer":83},"How does MobiDiff model a human check-in event?",{"text":84,"@type":76},"It decomposes each check-in into spatial, activity, and temporal channels, and applies structured event-, group-, and channel-level masking to capture trajectory-level mobility patterns and within-event dependencies.","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},[93,97,101,105,110,115,120,123,127,130,134],{"id":20,"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":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":124,"show_sort_weight":125,"slug":126},"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"]