{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T14:18:13Z","timestamp":1783174693949,"version":"3.54.6"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62073295"],"award-info":[{"award-number":["62073295"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072409"],"award-info":[{"award-number":["62072409"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62476247"],"award-info":[{"award-number":["62476247"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Zhejiang Province Natural Science Foundation","doi-asserted-by":"publisher","award":["LR21F020003"],"award-info":[{"award-number":["LR21F020003"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Fusion"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.inffus.2026.104499","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T23:50:55Z","timestamp":1779925855000},"page":"104499","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Conditional diffusion transformer enabled few-shot spatiotemporal modeling"],"prefix":"10.1016","volume":"136","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7007-6623","authenticated-orcid":false,"given":"Zhenzhen","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xueming","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guojiang","family":"Shen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9677-3213","authenticated-orcid":false,"given":"Wenchao","family":"Weng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenfeng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2698-3319","authenticated-orcid":false,"given":"Xiangjie","family":"Kong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8324-1859","authenticated-orcid":false,"given":"Feng","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.inffus.2026.104499_bib0001","series-title":"Proceedings of the ACM International Conference on Information and Knowledge Management","first-page":"224","article-title":"Region profile enhanced urban spatio-temporal prediction via adaptive meta-learning","author":"Chen","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0002","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2455","article-title":"Effective diffusion transformer architecture for image super-resolution","author":"Cheng","year":"2025"},{"key":"10.1016\/j.inffus.2026.104499_bib0003","doi-asserted-by":"crossref","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","article-title":"Diffusion models in vision: a survey","volume":"45","author":"Croitoru","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104499_bib0004","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","author":"Dhariwal","year":"2021"},{"key":"10.1016\/j.inffus.2026.104499_bib0005","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"2969","article-title":"Dit4edit: diffusion transformer for image editing","author":"Feng","year":"2025"},{"key":"10.1016\/j.inffus.2026.104499_bib0006","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102228","article-title":"STGAFormer: spatial\u2013temporal gated attention transformer based graph neural network for traffic flow forecasting","volume":"105","author":"Geng","year":"2024","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104499_bib0007","series-title":"Proceedings of the International Conference on Learning Representations","first-page":"1","article-title":"Prompt-to-prompt image editing with cross-attention control","author":"Hertz","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0008","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"6840","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020"},{"key":"10.1016\/j.inffus.2026.104499_bib0009","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.121533","article-title":"Controlled graph neural networks with denoising diffusion for anomaly detection","volume":"237","author":"Li","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.inffus.2026.104499_bib0010","series-title":"Proceedings of the International Conference on Learning Representations","first-page":"1","article-title":"Transformer-modulated diffusion models for probabilistic multivariate time series forecasting","author":"Li","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0011","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"30211","article-title":"SparseTSF: modeling long-term time series forecasting with 1k parameters","author":"Lin","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0012","doi-asserted-by":"crossref","first-page":"4846","DOI":"10.1109\/TKDE.2025.3570705","article-title":"ST-LLM+: graph enhanced spatio-temporal large language models for traffic prediction","volume":"37","author":"Liu","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.inffus.2026.104499_bib0013","series-title":"Proceedings of the ACM International Conference on Information and Knowledge Management","first-page":"4125","article-title":"Spatio-temporal adaptive embedding makes vanilla transformer sota for traffic forecasting","author":"Liu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0014","doi-asserted-by":"crossref","first-page":"157","DOI":"10.1162\/tacl_a_00638","article-title":"Lost in the middle: how language models use long contexts","volume":"12","author":"Liu","year":"2024","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"10.1016\/j.inffus.2026.104499_bib0015","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"PyraFormer: low-complexity pyramidal attention for long-range time series modeling and forecasting","author":"Liu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104499_bib0016","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"itransformer: inverted transformers are effective for time series forecasting","author":"Liu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0017","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"12271","article-title":"Koopa: learning non-stationary time series dynamics with Koopman predictors","author":"Liu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0018","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"9881","article-title":"Non-stationary transformers: exploring the stationarity in time series forecasting","author":"Liu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104499_bib0019","series-title":"Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"1162","article-title":"Spatio-temporal graph few-shot learning with cross-city knowledge transfer","author":"Lu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104499_bib0020","series-title":"Proceedings of the Annual Meeting of the Association for Computational Linguistics","first-page":"8086","article-title":"Fantastically ordered prompts and where to find them: overcoming few-shot prompt order sensitivity","author":"Lu","year":"2022"},{"key":"10.1016\/j.inffus.2026.104499_bib0021","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"56784","article-title":"Add and thin: diffusion for temporal point processes","author":"L\u00fcdke","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0022","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"14255","article-title":"U-mixer: an unet-mixer architecture with stationarity correction for time series forecasting","author":"Ma","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0023","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"A time series is worth 64 words: long-term forecasting with transformers","author":"Nie","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0024","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4195","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0025","series-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"2400","article-title":"FredFormer: frequency debiased transformer for time series forecasting","author":"Piao","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0026","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"10684","article-title":"High-resolution image synthesis with latent diffusion models","author":"Rombach","year":"2022"},{"key":"10.1016\/j.inffus.2026.104499_bib0027","doi-asserted-by":"crossref","DOI":"10.1016\/j.inffus.2024.102872","article-title":"ST-MambaSync: complement the power of mamba and transformer fusion for less computational cost in spatial\u2013temporal traffic forecasting","volume":"117","author":"Shao","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.inffus.2026.104499_bib0028","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9370","article-title":"Rethinking the spatial inconsistency in classifier-free diffusion guidance","author":"Shen","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0029","series-title":"Proceedings of the International Conference on Learning Representations","first-page":"1","article-title":"Denoising diffusion implicit models","author":"Song","year":"2021"},{"key":"10.1016\/j.inffus.2026.104499_bib0030","series-title":"Proceedings of the ACM International Conference on Multimedia","first-page":"5419","article-title":"Underwater image enhancement by transformer-based diffusion model with non-uniform sampling for skip strategy","author":"Tang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0031","series-title":"Proceedings of the International Conference on Advances in Neural Information Processing Systems","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017"},{"key":"10.1016\/j.inffus.2026.104499_bib0032","series-title":"Proceedings of the International Conference on Learning Representations","first-page":"1","article-title":"Structural inference with dynamics encoding and partial correlation coefficients","author":"Wang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0033","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"22206","article-title":"Rethinking the power of timestamps for robust time series forecasting: a global-local fusion perspective","author":"Wang","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0034","series-title":"Proceedings of the International Joint Conference on Artificial Intelligence","first-page":"6778","article-title":"Transformers in time series: a survey","author":"Wen","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0035","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"22419","article-title":"AutoFormer: decomposition transformers with auto-correlation for long-term series forecasting","author":"Wu","year":"2021"},{"key":"10.1016\/j.inffus.2026.104499_bib0036","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"5338","article-title":"Can graph learning improve planning in LLM-based agents?","author":"Wu","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0037","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"6225","article-title":"Dynamic semantic-based spatial graph convolution network for skeleton-based human action recognition","author":"Xie","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0038","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"Differential transformer","author":"Ye","year":"2025"},{"key":"10.1016\/j.inffus.2026.104499_bib0039","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"10238","article-title":"Graph denoising diffusion for inverse protein folding","author":"Yi","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0040","series-title":"Proceedings of the ACM International Conference on Information and Knowledge Management","first-page":"3062","article-title":"DSFormer: a double sampling transformer for multivariate time series long-term prediction","author":"Yu","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0041","series-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"4095","article-title":"Unist: a prompt-empowered universal model for urban spatio-temporal prediction","author":"Yuan","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0042","series-title":"Proceedings of the ACM SIGKDD Conference on Knowledge Discovery and Data Mining","first-page":"3173","article-title":"Spatio-temporal diffusion point processes","author":"Yuan","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0043","series-title":"Proceedings of the International Conference on Neural Information Processing Systems","first-page":"1196","article-title":"DiTFastAttn: attention compression for diffusion transformer models","author":"Yuan","year":"2024"},{"key":"10.1016\/j.inffus.2026.104499_bib0044","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11121","article-title":"Are transformers effective for time series forecasting?","author":"Zeng","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0045","doi-asserted-by":"crossref","first-page":"4115","DOI":"10.1109\/TPAMI.2024.3355414","article-title":"MotionDiffuse: text-driven human motion generation with diffusion model","volume":"46","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.inffus.2026.104499_bib0046","series-title":"Proceedings of the International Conference on Learning Representations","article-title":"CrossFormer: transformer utilizing cross-dimension dependency for multivariate time series forecasting","author":"Zhang","year":"2023"},{"key":"10.1016\/j.inffus.2026.104499_bib0047","first-page":"1","article-title":"Advancing realistic precipitation nowcasting with a spatiotemporal transformer-based denoising diffusion model","volume":"62","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.inffus.2026.104499_bib0048","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"11106","article-title":"Informer: beyondefficient transformer for long sequence time-series forecasting","author":"Zhou","year":"2021"},{"key":"10.1016\/j.inffus.2026.104499_bib0049","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"27268","article-title":"FedFormer: frequency enhanced decomposed transformer for long-term series forecasting","author":"Zhou","year":"2022"},{"key":"10.1016\/j.inffus.2026.104499_bib0050","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.114466","article-title":"A transformer-based approach for traffic prediction with fusion spatiotemporal attention","volume":"329","author":"Zhou","year":"2025","journal-title":"Knowl. Based Syst."}],"container-title":["Information Fusion"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003787?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1566253526003787?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T13:39:40Z","timestamp":1783172380000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1566253526003787"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":50,"alternative-id":["S1566253526003787"],"URL":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104499","relation":{},"ISSN":["1566-2535"],"issn-type":[{"value":"1566-2535","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Conditional diffusion transformer enabled few-shot spatiotemporal modeling","name":"articletitle","label":"Article Title"},{"value":"Information Fusion","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.inffus.2026.104499","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104499"}}