{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T20:16:19Z","timestamp":1779394579448,"version":"3.53.1"},"reference-count":70,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"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":["2024YFB4505501"],"award-info":[{"award-number":["2024YFB4505501"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62341411"],"award-info":[{"award-number":["62341411"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62222214"],"award-info":[{"award-number":["62222214"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["U22A2028"],"award-info":[{"award-number":["U22A2028"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["6240073476"],"award-info":[{"award-number":["6240073476"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62302482"],"award-info":[{"award-number":["62302482"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62302478"],"award-info":[{"award-number":["62302478"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62302483"],"award-info":[{"award-number":["62302483"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0660200"],"award-info":[{"award-number":["XDB0660200"]}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0660201"],"award-info":[{"award-number":["XDB0660201"]}]},{"name":"Strategic Priority Research Program of the Chinese Academy of Sciences","award":["XDB0660202"],"award-info":[{"award-number":["XDB0660202"]}]},{"name":"Chinese Academy of Sciences (CAS) Project for Young Scientists in Basic Research","award":["YSBR-029"],"award-info":[{"award-number":["YSBR-029"]}]},{"DOI":"10.13039\/501100001809","name":"Youth Innovation Promotion Association CAS","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Comput.-Aided Des. Integr. Circuits Syst."],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1109\/tcad.2025.3627864","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:12:12Z","timestamp":1761930732000},"page":"2856-2869","source":"Crossref","is-referenced-by-count":0,"title":["DASA: Distribution-Aware Sparse Attention for Accelerating Diffusion Transformer"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4204-0686","authenticated-orcid":false,"given":"Tianyun","family":"Ma","sequence":"first","affiliation":[{"name":"University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3200-5255","authenticated-orcid":false,"given":"Jiaming","family":"Guo","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2370-0072","authenticated-orcid":false,"given":"Di","family":"Huang","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3458-1555","authenticated-orcid":false,"given":"Xinkai","family":"Song","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qian","family":"Wang","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0873-3471","authenticated-orcid":false,"given":"Husheng","family":"Han","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8267-9824","authenticated-orcid":false,"given":"Pengwei","family":"Jin","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangtao","family":"Guan","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China (USTC), Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9823-2573","authenticated-orcid":false,"given":"Yifan","family":"Hao","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7775-2724","authenticated-orcid":false,"given":"Yuanbo","family":"Wen","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6291-0531","authenticated-orcid":false,"given":"Shuyao","family":"Cheng","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7603-4210","authenticated-orcid":false,"given":"Zidong","family":"Du","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8691-8549","authenticated-orcid":false,"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9979-0561","authenticated-orcid":false,"given":"Xing","family":"Hu","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2530-5874","authenticated-orcid":false,"given":"Qi","family":"Guo","sequence":"additional","affiliation":[{"name":"Cambricon Technologies, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Diffusion-based time series imputation and forecasting with structured state space models","author":"Miguel Lopez Alcaraz","year":"2022","journal-title":"arXiv:2208.09399"},{"key":"ref2","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref3","volume-title":"Video Generation Models As World Simulators","author":"Brooks","year":"2024"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3361474"},{"key":"ref5","article-title":"PixArt-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv:2310.00426"},{"key":"ref6","article-title":"\u0394-DiT: A training-free acceleration method tailored for diffusion transformers","author":"Chen","year":"2024","journal-title":"arXiv:2406.01125"},{"key":"ref7","article-title":"Generating long sequences with sparse transformers","author":"Child","year":"2019","journal-title":"arXiv:1904.10509"},{"key":"ref8","first-page":"2257","article-title":"Faster Wasserstein distance estimation with the sinkhorn divergence","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Chizat"},{"key":"ref9","article-title":"Masked language modeling for proteins via linearly scalable long-context transformers","author":"Choromanski","year":"2020","journal-title":"arXiv:2006.03555"},{"key":"ref10","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","author":"Dao","year":"2023","journal-title":"arXiv:2307.08691"},{"key":"ref11","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3579371.3589038"},{"key":"ref13","article-title":"Diffusion models in bioinformatics: A new wave of deep learning revolution in action","author":"Guo","year":"2023","journal-title":"arXiv:2302.10907"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/hpca47549.2020.00035"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref16","article-title":"IDQL: Implicit Q-learning as an actor-critic method with diffusion policies","author":"Hansen-Estruch","year":"2023","journal-title":"arXiv:2304.10573"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0580"},{"key":"ref18","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","author":"Ho"},{"key":"ref19","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv:2205.15868"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref21","article-title":"MInference 1.0: Accelerating pre-filling for long-context LLMs via dynamic sparse attention","author":"Jiang","year":"2024","journal-title":"arXiv:2407.02490"},{"key":"ref22","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Katharopoulos"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2015.2414456"},{"key":"ref24","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"arXiv:2001.04451"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00070"},{"key":"ref26","volume-title":"Keling","year":"2024"},{"key":"ref27","first-page":"3927","article-title":"Improved precision and recall metric for assessing generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kynk\u00e4\u00e4nniemi"},{"key":"ref28","first-page":"3744","article-title":"Set Transformer: A framework for attention-based permutation-invariant neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Lee"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00080"},{"key":"ref30","article-title":"Faster diffusion: Rethinking the role of unet encoder in diffusion models","author":"Li","year":"2023","journal-title":"arXiv:2312.09608"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"ref32","volume-title":"Tinysora","author":"Lin","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref34","article-title":"RetrievalAttention: Accelerating long-context LLM inference via vector retrieval","author":"Liu","year":"2024","journal-title":"arXiv:2409.10516"},{"key":"ref35","article-title":"Generating Wikipedia by summarizing long sequences","author":"Liu","year":"2018","journal-title":"arXiv:1801.10198"},{"key":"ref36","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv:2209.03003"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref38","article-title":"DPM-Solver++: Fast solver for guided sampling of diffusion probabilistic models","author":"Lu","year":"2022","journal-title":"arXiv:2211.01095"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref40","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv:2401.03048"},{"key":"ref41","article-title":"Learning-to-cache: Accelerating diffusion transformer via layer caching","author":"Ma","year":"2024","journal-title":"arXiv:2406.01733"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01492"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-short.17"},{"key":"ref44","first-page":"50358","article-title":"Scaling data-constrained language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Muennighoff"},{"key":"ref45","volume-title":"NVIDIA A100 Tensor Core GPU Architecture","year":"2020"},{"key":"ref46","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.232"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS51556.2021.9401196"},{"key":"ref53","article-title":"FORA: Fast-forward caching in diffusion transformer acceleration","author":"Selvaraju","year":"2024","journal-title":"arXiv:2407.01425"},{"key":"ref54","first-page":"571","article-title":"SALO: An efficient spatial accelerator enabling hybrid sparse attention mechanisms for long sequences","volume-title":"Proc. 59th ACM\/IEEE Design Autom. Conf.","author":"Shen"},{"key":"ref55","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv:2010.02502"},{"key":"ref56","first-page":"11918","article-title":"Generative modeling by estimating gradients of the data distribution","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Song"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref58","article-title":"Quest: Query-aware sparsity for efficient long-context LLM inference","author":"Tang","year":"2024","journal-title":"arXiv:2406.10774"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref61","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00594"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548409"},{"key":"ref65","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv:2206.10789"},{"key":"ref66","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zaheer"},{"key":"ref67","article-title":"A survey on audio diffusion models: Text to speech synthesis and enhancement in generative AI","author":"Zhang","year":"2023","journal-title":"arXiv:2303.13336"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref69","article-title":"ViDiT-Q: Efficient and accurate quantization of diffusion transformers for image and video generation","author":"Zhao","year":"2024","journal-title":"arXiv:2406.02540"},{"key":"ref70","volume-title":"Open-Sora: Democratizing Efficient Video Production for All","author":"Zheng","year":"2024"}],"container-title":["IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/43\/11527413\/11223635.pdf?arnumber=11223635","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T19:43:14Z","timestamp":1779392594000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11223635\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":70,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcad.2025.3627864","relation":{},"ISSN":["0278-0070","1937-4151"],"issn-type":[{"value":"0278-0070","type":"print"},{"value":"1937-4151","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6]]}}}