{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T05:03:23Z","timestamp":1768367003968,"version":"3.49.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,22]],"date-time":"2025-06-22T00:00:00Z","timestamp":1750550400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100014121","name":"Xilinx","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014121","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11133383","type":"proceedings-article","created":{"date-parts":[[2025,9,15]],"date-time":"2025-09-15T17:35:41Z","timestamp":1757957741000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["PARO: Hardware-Software Co-design with Pattern-aware Reorder-based Attention Quantization in Video Generation Models"],"prefix":"10.1109","author":[{"given":"Xinhao","family":"Yang","sequence":"first","affiliation":[{"name":"Tsinghua University,Dept. of EE, BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianchen","family":"Zhao","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of EE, BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of EE, BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenheng","family":"Ma","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of EE, BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shulin","family":"Zeng","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of EE, BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenhua","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of EE, BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuefei","family":"Ning","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of EE, BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huazhong","family":"Yang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of EE, BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"Tsinghua University,Dept. of EE, BNRist"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref2","article-title":"Open-Sora","year":"2024"},{"key":"ref3","article-title":"Video generation models as world simulators","year":"2024"},{"key":"ref4","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv:2408.06072"},{"key":"ref5","article-title":"Variation-aware vision transformer quantization","author":"Huang","year":"2023","journal-title":"arXiv e-prints, pp. arXiv-2307"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_12"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01565"},{"key":"ref8","first-page":"34451","article-title":"Q-vit: Accurate and fully quantized low-bit vision transformer","volume":"35","author":"Li","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01580"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/164"},{"key":"ref11","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv preprint arXiv:2010.11929"},{"key":"ref12","first-page":"9015","article-title":"Packqvit: Faster sub-8-bit vision transformers via full and packed quantization on the mobile","volume":"36","author":"Dong","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref14","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"arXiv preprint arXiv:2106.08295"},{"key":"ref15","article-title":"Vidit-q: Efficient and accurate quantization of diffusion transformers for image and video generation","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv:2406.02540"},{"key":"ref16","article-title":"Sageattention: Accurate 8-bit attention for plug-and-play inference acceleration","volume-title":"International Conference on Learning Representations (ICLR)","author":"Zhang"},{"key":"ref17","article-title":"Sageattention2: Efficient attention with thorough outlier smoothing and per-thread int4 quantization","author":"Zhang","year":"2024"},{"key":"ref18","article-title":"Spargeattn: Accurate sparse attention accelerating any model inference","author":"Zhang","year":"2025"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00035"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00018"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00060"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3503222.3507738"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00050"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071047"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480125"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071027"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640393"},{"key":"ref28","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv:2010.02502"},{"key":"ref29","article-title":"Fvd: A new metric for video generation","author":"Unterthiner","year":"2019"},{"key":"ref30","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021","journal-title":"arXiv preprint arXiv:2104.14806"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01843"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3085572"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","location":"San Francisco, CA, USA","start":{"date-parts":[[2025,6,22]]},"end":{"date-parts":[[2025,6,25]]}},"container-title":["2025 62nd ACM\/IEEE Design Automation Conference (DAC)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11132383\/11132091\/11133383.pdf?arnumber=11133383","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T20:54:35Z","timestamp":1768337675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11133383\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11133383","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}