{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T16:57:48Z","timestamp":1780505868765,"version":"3.54.1"},"reference-count":237,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2024YFF0509700"],"award-info":[{"award-number":["2024YFF0509700"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371063"],"award-info":[{"award-number":["62371063"]}],"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":["62293481"],"award-info":[{"award-number":["62293481"]}],"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":["62471290"],"award-info":[{"award-number":["62471290"]}],"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":["62471294"],"award-info":[{"award-number":["62471294"]}],"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":["62231022"],"award-info":[{"award-number":["62231022"]}],"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":["62321001"],"award-info":[{"award-number":["62321001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Natural Science Foundation","award":["L232047"],"award-info":[{"award-number":["L232047"]}]},{"name":"Post-Doctoral Fellowship Program of China Postdoctoral Science Foundation","award":["GZB20250810"],"award-info":[{"award-number":["GZB20250810"]}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Hong Kong Research Grant Council","award":["16215624"],"award-info":[{"award-number":["16215624"]}]},{"name":"Areas of Excellence Scheme","award":["AoE\/E-601\/22-R"],"award-info":[{"award-number":["AoE\/E-601\/22-R"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/comst.2026.3690542","type":"journal-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T20:05:50Z","timestamp":1778011550000},"page":"6241-6281","source":"Crossref","is-referenced-by-count":1,"title":["Generative AI Meets 6G and Beyond: Diffusion Models for Semantic Communications"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-9114-9881","authenticated-orcid":false,"given":"Hai-Long","family":"Qin","sequence":"first","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-568X","authenticated-orcid":false,"given":"Jincheng","family":"Dai","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6951-0090","authenticated-orcid":false,"given":"Guo","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2872-795X","authenticated-orcid":false,"given":"Shuo","family":"Shao","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sixian","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8712-0301","authenticated-orcid":false,"given":"Tongda","family":"Xu","sequence":"additional","affiliation":[{"name":"Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8799-1182","authenticated-orcid":false,"given":"Wenjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0269-104X","authenticated-orcid":false,"given":"Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2519-6401","authenticated-orcid":false,"given":"Khaled B.","family":"Letaief","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, SAR, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"issue":"4","key":"ref1","first-page":"261","article-title":"Recent contributions to the mathematical theory of communication","volume":"10","author":"Weaver","year":"1953","journal-title":"ETC, A Rev. Gen. Semantics"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3516819"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3616973"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3443193"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3412852"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3079836"},{"key":"ref7","article-title":"Generative AI meets semantic communication: Evolution and revolution of communication tasks","author":"Grassucci","year":"2024","journal-title":"arXiv:2401.06803"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.eng.2025.07.022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.005.2300574"},{"key":"ref10","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref11","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref12","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref13","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMLCN.2025.3628535"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3379244"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3553851"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2024.3400011"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2026.3671110"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2400428"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"issue":"24","key":"ref21","first-page":"695","article-title":"Estimation of non-normalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","year":"2005","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","article-title":"A tutorial on energy-based learning","volume-title":"Predicting Structured Data","author":"LeCun","year":"2006"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog0901_7"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3758\/s13423-016-1015-8"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008923215028"},{"key":"ref26","first-page":"2835","article-title":"Autoregressive models in vision: A survey","volume-title":"Proc. Trans. Mach. Learn. Res.","author":"Xiong"},{"key":"ref27","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref28","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Van Den Oord"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref30","first-page":"2226","article-title":"Improved techniques for training GANs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Salimans"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1525\/9780520423671-036"},{"key":"ref32","article-title":"How to train your energy-based models","author":"Song","year":"2021","journal-title":"arXiv:2101.03288"},{"issue":"153","key":"ref33","first-page":"1","article-title":"Automatic differentiation in machine learning: A survey","volume":"18","author":"Baydin","year":"2018","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","article-title":"The principles of diffusion models","author":"Lai","year":"2025","journal-title":"arXiv:2510.21890"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/NECO_a_00142"},{"key":"ref36","first-page":"681","article-title":"Bayesian learning via stochastic gradient Langevin dynamics","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Welling"},{"key":"ref37","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/0304-4149(82)90051-5"},{"key":"ref39","first-page":"26474","article-title":"Reasons for the superiority of stochastic estimators over deterministic ones: Robustness, consistency and perceptual quality","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ohayon"},{"key":"ref40","first-page":"11895","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Song"},{"key":"ref41","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref42","first-page":"6572","article-title":"Neural ordinary differential equations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref43","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref45","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. NIPS","volume":"34","author":"Dhariwal"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref47","article-title":"SDEdit: Guided image synthesis and editing with stochastic differential equations","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Meng"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1714"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1862"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref52","first-page":"16567","article-title":"Refining generative process with discriminator guidance in score-based diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Kim"},{"key":"ref53","article-title":"Diffusion posterior sampling for general noisy inverse problems","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chung"},{"key":"ref54","article-title":"Pseudoinverse-guided diffusion models for inverse problems","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2174"},{"key":"ref56","article-title":"A variational perspective on solving inverse problems with diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Mardani"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00273"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01946"},{"key":"ref59","first-page":"1128","article-title":"SitCom: Step-wise triple-consistent diffusion sampling for inverse problems","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Alkhouri"},{"key":"ref60","article-title":"Classifier-free diffusion guidance","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Ho"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref64","article-title":"Shap-E: Generating conditional 3D implicit functions","author":"Jun","year":"2023","journal-title":"arXiv:2305.02463"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02117"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref69","article-title":"AnimateDiff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Guo"},{"key":"ref70","article-title":"LLM-grounded video diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lian"},{"key":"ref71","article-title":"SEINE: Short-to-long video diffusion model for generative transition and prediction","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref73","article-title":"Direct discriminative optimization: Your likelihood-based visual generative model is secretly a GAN discriminator","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zheng"},{"key":"ref74","article-title":"T2V-Turbo-V2: Enhancing video generation model post-training through data, reward, and conditional guidance design","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1002\/mrm.21391"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1198\/jasa.2011.tm11181"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00587"},{"key":"ref78","first-page":"8489","article-title":"Reduce, reuse, recycle: Compositional generation with energy-based diffusion models and MCMC","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Du"},{"key":"ref79","article-title":"A survey on diffusion models for inverse problems","author":"Daras","year":"2024","journal-title":"arXiv:2410.00083"},{"key":"ref80","article-title":"Weak diffusion priors can still achieve strong inverse-problem performance","author":"Jia","year":"2026","journal-title":"arXiv:2601.22443"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0035"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00983"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28209"},{"key":"ref84","article-title":"Progressive distillation for fast sampling of diffusion models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Salimans"},{"key":"ref85","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Song"},{"key":"ref86","article-title":"Latent consistency models: Synthesizing high-resolution images with few-step inference","author":"Luo","year":"2023","journal-title":"arXiv:2310.04378"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1505"},{"key":"ref88","article-title":"Consistency trajectory models: Learning probability flow ODE trajectory of diffusion","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kim"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0731"},{"key":"ref90","article-title":"Truncated diffusion probabilistic models and diffusion-based adversarial auto-encoders","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zheng"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00087"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2940"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33075"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4236"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755331"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755479"},{"key":"ref99","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv:2210.02747"},{"key":"ref100","article-title":"Flow matching on general geometries","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Liu"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2497"},{"key":"ref102","article-title":"InstaFlow: One step is enough for high-quality diffusion-based text-to-image generation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Liu"},{"key":"ref103","article-title":"Mean flows for one-step generative modeling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Geng"},{"key":"ref104","first-page":"6306","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"van den Oord"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-374370-1.x0001-8"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446603"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01304"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1926"},{"key":"ref109","article-title":"Improved techniques for training consistency models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref112","first-page":"20662","article-title":"SnapFusion: Text-to-image diffusion model on mobile devices within two seconds","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Li"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref114","article-title":"S2-DMs: Skip-step diffusion models","author":"Wang","year":"2024","journal-title":"arXiv:2401.01520"},{"key":"ref115","first-page":"42947","article-title":"Align your steps: Optimizing sampling schedules in diffusion models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Sabour"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00792"},{"key":"ref117","article-title":"Improving and generalizing flow-based generative models with minibatch optimal transport","volume-title":"Proc. Trans. Mach. Learn. Res. (TMLR)","author":"Tong"},{"key":"ref118","volume-title":"NVIDIA TensorRT","year":"2024"},{"key":"ref119","article-title":"Back to basics: Let denoising generative models denoise","author":"Li","year":"2025","journal-title":"arXiv:2511.13720"},{"key":"ref120","article-title":"MonoFormer: One transformer for both diffusion and autoregression","author":"Zhao","year":"2024","journal-title":"arXiv:2409.16280"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0759"},{"key":"ref122","article-title":"Show-O: One single transformer to unify multimodal understanding and generation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Xie"},{"key":"ref123","article-title":"Transfusion: Predict the next token and diffuse images with one multi-modal model","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zhou"},{"key":"ref124","article-title":"Unified multimodal discrete diffusion","author":"Swerdlow","year":"2025","journal-title":"arXiv:2503.20853"},{"key":"ref125","first-page":"17695","article-title":"Diffusion Schr\u00f6dinger bridge with applications to score-based generative modeling","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"De Bortoli"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref128","first-page":"22134","article-title":"I2SB: Image-to-image Schr\u00f6dinger bridge","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Liu"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_11"},{"key":"ref130","first-page":"9902","article-title":"Planning with diffusion for flexible behavior synthesis","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Janner"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2023.XIX.026"},{"key":"ref132","article-title":"Training diffusion models with reinforcement learning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Black"},{"key":"ref133","article-title":"Continual diffusion: Continual customization of text-to-image diffusion with C-LoRA","volume-title":"Proc. Trans. Mach. Learn. Res. (TMLR)","author":"Smith"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02198"},{"issue":"3","key":"ref135","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"OpenAI"},{"key":"ref136","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref137","first-page":"1183","article-title":"Deep Bayesian active learning with image data","volume-title":"Proc. Int. Conf. Mach. Learning(ICML)","author":"Gal"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3485"},{"key":"ref139","article-title":"Bayesian hypernetworks","author":"Krueger","year":"2017","journal-title":"arXiv:1710.04759"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01453"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/MCOMSTD.2025.3598111"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3034501"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2022.3151935"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3175178"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2025.3596094"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2019.1900027"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2025.3559706"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.3390\/electronics10091073"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2927891"},{"key":"ref150","volume-title":"Digital Communications","author":"Haykin","year":"1988"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3180802"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.3390\/s24124005"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-96-5132-0"},{"key":"ref155","article-title":"Convergence of denoising diffusion models under the manifold hypothesis","volume-title":"Proc. Trans. Mach. Learn. Res. (TMLR)","author":"De Bortoli"},{"key":"ref156","article-title":"Sampling is as easy as learning the score: Theory for diffusion models with minimal data assumptions","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Chen"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/WCSP62071.2024.10827002"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2024.3515656"},{"key":"ref159","first-page":"64971","article-title":"Lossy image compression with conditional diffusion models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Yang"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC54389.2021.9674297"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00091"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2017.2757490"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC51071.2022.9771907"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3559158"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177703732"},{"issue":"11","key":"ref166","first-page":"3227","article-title":"Robust Gaussian process regression with a student-T likelihood","volume":"12","author":"Jyl\u00e4nki","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref167","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref169","article-title":"ImageFolder: Autoregressive image generation with folded tokens","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-024-48115-5"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448462"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3588246"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2025.3535714"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00652"},{"key":"ref176","first-page":"48062","article-title":"What makes an image realistic?","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Theis"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1948.tb01338.x"},{"key":"ref178","first-page":"675","article-title":"Rethinking lossy compression: The rate-distortion-perception tradeoff","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Blau"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref183","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Heusel"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02138"},{"key":"ref185","article-title":"Towards image compression with perfect realism at ultra-low bitrates","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Careil"},{"key":"ref186","article-title":"Idempotence and perceptual image compression","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Xu"},{"key":"ref187","first-page":"11913","article-title":"High-fidelity generative image compression","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Mentzer"},{"key":"ref188","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02648"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2019.2919300"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2023.3288243"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3424842"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2021.3078489"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.002.2200468"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2025.3627263"},{"key":"ref198","article-title":"Generative semantic communication: Diffusion models beyond bit recovery","author":"Grassucci","year":"2023","journal-title":"arXiv:2306.04321"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.004.2200050"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2025.3578724"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000373"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00490"},{"key":"ref204","article-title":"8-bit inference with TensorRT","volume-title":"Proc. NVIDIA GPU Technol. Conf. (GTC)","author":"Migacz"},{"key":"ref205","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2025.3596938"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3512934"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2025.3595688"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.2500068"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2025.3634248"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2026.3654401"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/mcomstd.2025.3632205"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3519325"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00930"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1007\/s10339-007-0168-9"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2025.3567613"},{"key":"ref217","article-title":"World models","author":"Ha","year":"2018","journal-title":"arXiv:1803.10122"},{"key":"ref218","article-title":"Dream to control: Learning behaviors by latent imagination","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hafner"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1873"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1070"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0164"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2866382"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2019.1800447"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref225","first-page":"938","article-title":"Posterior concentration for sparse deep learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NeurIPS)","author":"Polson"},{"key":"ref226","first-page":"5072","article-title":"Subspace robust Wasserstein distances","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Paty"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1561\/2200000101"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2025.3532797"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/MVT.2025.3545399"},{"key":"ref230","article-title":"Distributionally robust optimization: A review","author":"Rahimian","year":"2019","journal-title":"arXiv:1908.05659"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671997"},{"key":"ref232","article-title":"Diffusion models for smarter UAVs: Decision-making and modeling","author":"Emami","year":"2025","journal-title":"arXiv:2501.05819"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3502685"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3449645"},{"key":"ref235","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA55743.2025.11128518"},{"key":"ref236","article-title":"Generative AI for unmanned vehicle swarms: Challenges, applications and opportunities","author":"Liu","year":"2024","journal-title":"arXiv:2402.18062"},{"key":"ref237","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2025.111531"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9739\/11321210\/11506355.pdf?arnumber=11506355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T04:20:51Z","timestamp":1778905251000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11506355\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":237,"URL":"https:\/\/doi.org\/10.1109\/comst.2026.3690542","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}