{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T06:12:07Z","timestamp":1758089527122,"version":"3.44.0"},"reference-count":39,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,22]]},"DOI":"10.1109\/dac63849.2025.11132632","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":["SQ-DM: Accelerating Diffusion Models with Aggressive Quantization and Temporal Sparsity"],"prefix":"10.1109","author":[{"given":"Zichen","family":"Fan","sequence":"first","affiliation":[{"name":"University of Michigan,Ann Arbor,MI"}]},{"given":"Steve","family":"Dai","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA"}]},{"given":"Rangharajan","family":"Venkatesan","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA"}]},{"given":"Dennis","family":"Sylvester","sequence":"additional","affiliation":[{"name":"University of Michigan,Ann Arbor,MI"}]},{"given":"Brucek","family":"Khailany","sequence":"additional","affiliation":[{"name":"NVIDIA,Santa Clara,CA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"eDiff-I: Text-to-Image Diffusion Models with an Ensemble of Expert Denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint arXiv:2211.01324"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","article-title":"Generative Residual Diffusion Modeling for Km-scale Atmospheric Downscaling","author":"Mardani","year":"2023","journal-title":"arXiv preprint arXiv:2309.15214"},{"key":"ref4","article-title":"Elucidating the Design Space of Diffusion-based Generative Models","author":"Karras","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02282"},{"article-title":"VS-Quant: Per-vector Scaled Quantization for Accurate Low-Precision Neural Network Inference","volume-title":"Conf. on Machine Learning and Systems (MLSys)","author":"Dai","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"ref9","article-title":"PTQD: Accurate Post-Training Quantization for Diffusion Models","author":"He","year":"2023","journal-title":"arXiv preprint arXiv:2305.10657"},{"key":"ref10","article-title":"Efficient Quantization Strategies for Latent Diffusion Models","author":"Yang","year":"2023","journal-title":"arXiv preprint arXiv:2312.05431"},{"key":"ref11","article-title":"TMPQDM: Joint Timestep Reduction and Quantization Precision Selection for Efficient Diffusion Models","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv:2404.09532"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00703"},{"key":"ref13","article-title":"SVDQunat: Absorbing Outliers by Low-Rank Components for 4-Bit Diffusion Models","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2411.05007"},{"key":"ref14","article-title":"Accelerating Sparse Deep neural Networks","author":"Mishra","year":"2021","journal-title":"arXiv preprint arXiv:2104.08378"},{"key":"ref15","article-title":"Structural Pruning for Diffusion Models","author":"Fang","year":"2023","journal-title":"arXiv preprint arXiv:2305.10924"},{"key":"ref16","article-title":"SparseDM: Toward Sparse Efficient Diffusion Models","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2404.10445"},{"article-title":"Learning Multiple Layers of Features from Tiny Images","year":"2009","author":"Krizhevsky","key":"ref17"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00821"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref21","article-title":"GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref22","article-title":"Microscaling Data Formats for Deep Learning","author":"Rouhani","year":"2023","journal-title":"arXiv preprint arXiv:2310.10537"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10665247"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref26","article-title":"The Sparsity Roofline: Understanding the Hardware Limits of Sparse Neural Networks","author":"Shinn","year":"2023","journal-title":"arXiv preprint arXiv:2310.00496"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942127"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173176"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA.2016.30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783723"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358291"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358275"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA47549.2020.00015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/hpca47549.2020.00062"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00068"},{"key":"ref37","article-title":"Enabling Flexibility for Sparse Tensor Acceleration via Heterogeneity","author":"Qin","year":"2022","journal-title":"arXiv preprint arXiv:2201.08916"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IISWC53511.2021.00028"},{"key":"ref39","article-title":"Video Diffusion Models","author":"Ho","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"}],"event":{"name":"2025 62nd ACM\/IEEE Design Automation Conference (DAC)","start":{"date-parts":[[2025,6,22]]},"location":"San Francisco, CA, USA","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\/11132632.pdf?arnumber=11132632","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T05:24:07Z","timestamp":1758000247000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11132632\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,22]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/dac63849.2025.11132632","relation":{},"subject":[],"published":{"date-parts":[[2025,6,22]]}}}