{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:58Z","timestamp":1777865518870,"version":"3.51.4"},"reference-count":69,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0161000"],"award-info":[{"award-number":["2022ZD0161000"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01491","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16068-16078","source":"Crossref","is-referenced-by-count":0,"title":["LiT: Delving into a Simple Linear Diffusion Transformer for Image Generation"],"prefix":"10.1109","author":[{"given":"Jiahao","family":"Wang","sequence":"first","affiliation":[{"name":"HKU,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ning","family":"Kang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lewei","family":"Yao","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengzhao","family":"Chen","sequence":"additional","affiliation":[{"name":"HKU,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chengyue","family":"Wu","sequence":"additional","affiliation":[{"name":"HKU,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Songyang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuchen","family":"Xue","sequence":"additional","affiliation":[{"name":"UCAS,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yong","family":"Liu","sequence":"additional","affiliation":[{"name":"THUsz,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Taiqiang","family":"Wu","sequence":"additional","affiliation":[{"name":"HKU,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"HKU,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shifeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqi","family":"Shao","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenguo","family":"Li","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab,Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"HKU,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_3"},{"key":"ref2","article-title":"Large scale gan training for high fidelity natural image synthesis","volume-title":"ICLR","author":"Brock","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01587"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref5","article-title":"Pixart-\u03c3: Weak-to-strong training of diffusion transformer for 4 k text-to-image generation","author":"Chen","year":"2024","journal-title":"ECCV"},{"key":"ref6","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen","year":"2024"},{"key":"ref7","article-title":"Deep compression autoencoder for efficient high-resolution diffusion models","author":"Chen","year":"2025","journal-title":"ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref9","article-title":"Scaling instructionfinetuned language models","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","author":"Dhariwal","year":"2021"},{"key":"ref13","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref14","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref17","article-title":"Modeling Sequences with Structured State Spaces","author":"Gu","year":"2023","journal-title":"Stanford University"},{"key":"ref18","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Slab: Efficient transformers with simplified linear attention and progressive re-parameterized batch normalization","author":"Guo","year":"2024","journal-title":"ICML"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref21","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref24","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref25","article-title":"Cascaded diffusion models for high fidelity image generation","author":"Ho","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"simple diffusion: End-to-end diffusion for high resolution images","author":"Hoogeboom","year":"2023","journal-title":"ICML"},{"key":"ref28","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"CVPR"},{"key":"ref29","article-title":"Scalable adaptive computation for iterative generation","author":"Jabri","year":"2023","journal-title":"ICML"},{"key":"ref30","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Improved precision and recall metric for assessing generative models","author":"Kynk\u00e4\u00e4nniemi","year":"2019","journal-title":"NeurIPS"},{"key":"ref32","article-title":"Scaling laws for diffusion transformers","author":"Liang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"World model on million-length video and language with ringattention","author":"Liu","year":"2025","journal-title":"ICLR"},{"key":"ref34","article-title":"Clear: Conv-like linearization revs pre-trained diffusion transformers up","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Linfusion: 1 gpu, 1 minute, 16k image","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019","journal-title":"ICLR"},{"key":"ref37","article-title":"Understanding diffusion models: A unified perspective","author":"Luo","year":"2022","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref39","article-title":"Are sixteen heads really better than one","author":"Michel","year":"2019","journal-title":"NeurIPS"},{"key":"ref40","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021","journal-title":"ICML"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref42","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref44","article-title":"Efficient diffusion transformer with step-wise dynamic attention mediators","author":"Pu","year":"2024","journal-title":"ECCV"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref47","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2021","journal-title":"ICLR"},{"key":"ref48","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref49","article-title":"Styleganxl: Scaling stylegan to large diverse datasets","author":"Sauer","year":"2022","journal-title":"SIGGRAPH"},{"key":"ref50","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"Sohl-Dickstein","year":"2015","journal-title":"ICML"},{"key":"ref51","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Chameleon: Mixed-modal early-fusion foundation models","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Dim: Diffusion mamba for efficient high-resolution image synthesis","volume-title":"arXiv preprint","author":"Teng","year":"2024"},{"key":"ref54","article-title":"Training data-efficient image transformers & distillation through attention","author":"Touvron","year":"2021","journal-title":"ICML"},{"key":"ref55","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01388"},{"key":"ref57","article-title":"Wise: Rethinking the knowledge memory for lifelong model editing of large language models","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref59","article-title":"What are diffusion models","author":"Weng","year":"2021","journal-title":"lilianweng.github.io"},{"key":"ref60","article-title":"Sana: Efficient high-resolution image synthesis with linear diffusion transformers","volume-title":"ICLR","author":"Xie","year":"2025"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00787"},{"key":"ref62","article-title":"Gated linear attention transformers with hardware-efficient training","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Knowledge circuits in pretrained transformers","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Improved distribution matching distillation for fast image synthesis","volume-title":"NeurIPS","author":"Yin","year":"2024"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01183"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00718"},{"key":"ref69","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\/11444734.pdf?arnumber=11444734","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:45:26Z","timestamp":1777531526000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444734\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01491","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}