{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T04:18:51Z","timestamp":1777954731592,"version":"3.51.4"},"reference-count":36,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3686867","type":"journal-article","created":{"date-parts":[[2026,4,23]],"date-time":"2026-04-23T19:59:49Z","timestamp":1776974389000},"page":"64655-64665","source":"Crossref","is-referenced-by-count":0,"title":["NABLA: Neighborhood Adaptive Block-Level Attention for Efficient Video Generation"],"prefix":"10.1109","volume":"14","author":[{"given":"Dmitrii","family":"Mikhailov","sequence":"first","affiliation":[{"name":"Kandinsky Laboratory, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Aleksey","family":"Letunovskiy","sequence":"additional","affiliation":[{"name":"Kandinsky Laboratory, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Maria","family":"Kovaleva","sequence":"additional","affiliation":[{"name":"Kandinsky Laboratory, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Vladimir","family":"Arkhipkin","sequence":"additional","affiliation":[{"name":"Kandinsky Laboratory, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5019-5633","authenticated-orcid":false,"given":"Vladimir","family":"Korviakov","sequence":"additional","affiliation":[{"name":"Kandinsky Laboratory, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9784-9067","authenticated-orcid":false,"given":"Vladimir","family":"Polovnikov","sequence":"additional","affiliation":[{"name":"Kandinsky Laboratory, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Viacheslav","family":"Vasilev","sequence":"additional","affiliation":[{"name":"Kandinsky Laboratory, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Evelina","family":"Sidorova","sequence":"additional","affiliation":[{"name":"Kandinsky Laboratory, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Denis","family":"Dimitrov","sequence":"additional","affiliation":[{"name":"Kandinsky Laboratory, Moscow, Russia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref2","article-title":"Scalable diffusion models with transformers","author":"Peebles","year":"2022","journal-title":"arXiv:2212.09748"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","article-title":"Auto-encoding variational Bayes","volume-title":"Proc. 2nd Int. Conf. Learn. Represent.","author":"Kingma"},{"key":"ref5","first-page":"12606","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Esser"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","volume-title":"Video Generation Models As World Simulators","year":"2024"},{"key":"ref8","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2025","journal-title":"arXiv:2410.13720"},{"key":"ref9","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2025","journal-title":"arXiv:2412.03603"},{"key":"ref10","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2025","journal-title":"arXiv:2408.06072"},{"key":"ref11","volume-title":"Kling AI: Next-Gen AI Video & Ai Image Generator","year":"2024"},{"key":"ref12","article-title":"Wan: Open and advanced large-scale video generative models","author":"Wan","year":"2025","journal-title":"arXiv:2503.20314"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3522510"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-demo.48"},{"key":"ref15","article-title":"How sparse attention approximates exact attention? Your attention is naturally nc-sparse","author":"Deng","year":"2025","journal-title":"arXiv:2404.02690"},{"key":"ref16","article-title":"DSV: Exploiting dynamic sparsity to accelerate large-scale video DiT training","author":"Tan","year":"2025","journal-title":"arXiv:2502.07590"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01483"},{"key":"ref18","article-title":"Spargeattn: Accurate sparse attention accelerating any model inference","author":"Zhang","year":"2025","journal-title":"arXiv:2502.18137"},{"key":"ref19","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":"ref20","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref23","article-title":"Dilated neighborhood attention transformer","author":"Hassani","year":"2022","journal-title":"arXiv:2209.15001"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2065"},{"key":"ref25","article-title":"Fast video generation with sliding tile attention","author":"Zhang","year":"2025","journal-title":"arXiv:2502.04507"},{"key":"ref26","article-title":"Sparse VideoGen: Accelerating video diffusion transformers with spatial\u2013temporal sparsity","author":"Xi","year":"2025","journal-title":"arXiv:2502.01776"},{"key":"ref27","article-title":"Analysis of attention in video diffusion transformers","author":"Wen","year":"2025","journal-title":"arXiv:2504.10317"},{"key":"ref28","first-page":"59808","article-title":"Fast attention over long sequences with dynamic sparse flash attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Pagliardini"},{"key":"ref29","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"arXiv:2001.04451"},{"key":"ref30","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref31","article-title":"AdaSplash: Adaptive sparse flash attention","author":"Goncalves","year":"2025","journal-title":"arXiv:2502.12082"},{"key":"ref32","article-title":"Delta attention: Fast and accurate sparse attention inference by delta correction","author":"Willette","year":"2025","journal-title":"arXiv:2505.11254"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1126"},{"key":"ref34","article-title":"Comem: Compositional concept-graph memory for vision-language adaptation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhou"},{"key":"ref35","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"arXiv:2010.11929"},{"key":"ref36","article-title":"Flex attention: A programming model for generating optimized attention kernels","author":"Dong","year":"2024","journal-title":"arXiv:2412.05496"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11493909.pdf?arnumber=11493909","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T19:37:11Z","timestamp":1777923431000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11493909\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3686867","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}