{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T15:10:10Z","timestamp":1778166610507,"version":"3.51.4"},"reference-count":24,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01823","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19608-19616","source":"Crossref","is-referenced-by-count":1,"title":["Edit: Efficient Diffusion Transformers with Linear Compressed Attention"],"prefix":"10.1109","author":[{"given":"Philipp","family":"Becker","sequence":"first","affiliation":[{"name":"Samsung, AI Center Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Abhinav","family":"Mehrotra","sequence":"additional","affiliation":[{"name":"Samsung, AI Center Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruchika","family":"Chavhan","sequence":"additional","affiliation":[{"name":"Samsung, AI Center Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Malcolm","family":"Chadwick","sequence":"additional","affiliation":[{"name":"Samsung, AI Center Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Luca","family":"Morreale","sequence":"additional","affiliation":[{"name":"Samsung, AI Center Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mehdi","family":"Noroozi","sequence":"additional","affiliation":[{"name":"Samsung, AI Center Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alberto Gil C. P.","family":"Ramos","sequence":"additional","affiliation":[{"name":"Samsung, AI Center Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sourav","family":"Bhattacharya","sequence":"additional","affiliation":[{"name":"Samsung, AI Center Cambridge"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73411-3_5"},{"key":"ref3","article-title":"Pixart-$\\alpha$: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen","year":"2024"},{"key":"ref4","first-page":"10041","article-title":"Transformers are ssms: generalized models and efficient algorithms through structured state space duality","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Dao","year":"2024"},{"key":"ref5","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser","year":"2024"},{"key":"ref6","article-title":"Dimba: Transformermamba diffusion models","author":"Fei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72664-4_9"},{"key":"ref10","first-page":"5156","article-title":"Transformers are rnns: Fast autoregressive transformers with linear attention","volume-title":"International conference on machine learning","author":"Katharopoulos","year":"2020"},{"key":"ref11","volume-title":"Black Forest Labs. Flux.","year":"2024"},{"key":"ref12","first-page":"51597","article-title":"Koala: Empirical lessons toward memory-efficient and fast diffusion models for text-toimage synthesis","volume-title":"Advances in Neural Information Processing Systems","volume":"37","author":"Lee","year":"2025"},{"key":"ref13","author":"Liu","year":"2024","journal-title":"Clear: Conv-like linearization revs pre-trained diffusion transformers up"},{"key":"ref14","article-title":"Linfusion: $1 \\text{gpu}, 1$ minute, 16k image","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","volume-title":"The Eleventh International Conference on Learning Representations","author":"Liu","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref17","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02663"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref22","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","volume-title":"arXiv preprint","author":"Xie","year":"2024"},{"key":"ref23","article-title":"Sana 1.5: Efficient scaling of training-time and inferencetime compute in linear diffusion transformer","author":"Xie","year":"2025","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Lumina-next: Making lumina-t2x stronger and faster with next-dit","author":"Zhuo","year":"2024","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445871.pdf?arnumber=11445871","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:17Z","timestamp":1777611797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445871\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01823","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}