{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:21:37Z","timestamp":1792786897766,"version":"4.5.0"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62476264"],"award-info":[{"award-number":["62476264"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Youth Key Project of the Chinese Academy of Sciences","award":["GFQN-2026-34"],"award-info":[{"award-number":["GFQN-2026-34"]}],"id":[{"id":"https:\/\/ror.org\/034t30j35","id-type":"ROR","asserted-by":"crossref"}]},{"name":"Beijing Natural Science Foundation","award":["QG26011"],"award-info":[{"award-number":["QG26011"]}]},{"name":"Schweizerischer Nationalfonds zur F\u00f6rderung der Wissenschaftlichen Forschung"},{"name":"Neuromorphic Attention Models for Event Data"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/tpami.2026.3700583","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T19:38:54Z","timestamp":1780688334000},"page":"12644-12660","source":"Crossref","is-referenced-by-count":4,"title":["MPQ-DMv2: Flexible Residual Mixed Precision Quantization for Low-Bit Diffusion Models With Temporal Distillation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-8171-9555","authenticated-orcid":false,"given":"Weilun","family":"Feng","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5890-289X","authenticated-orcid":false,"given":"Chuanguang","family":"Yang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haotong","family":"Qin","sequence":"additional","affiliation":[{"name":"ETH Zurich","place":["Z\u00fcrich, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7314-6863","authenticated-orcid":false,"given":"Yuqi","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangqi","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7593-8293","authenticated-orcid":false,"given":"Zhulin","family":"An","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4479-5840","authenticated-orcid":false,"given":"Libo","family":"Huang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8360-7718","authenticated-orcid":false,"given":"Boyu","family":"Diao","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9170-7009","authenticated-orcid":false,"given":"Fuzhen","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Beihang University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0368-8923","authenticated-orcid":false,"given":"Michele","family":"Magno","sequence":"additional","affiliation":[{"name":"ETH Zurich","place":["Z\u00fcrich, Switzerland"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6647-0986","authenticated-orcid":false,"given":"Yongjun","family":"Xu","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4458-360X","authenticated-orcid":false,"given":"Yingli","family":"Tian","sequence":"additional","affiliation":[{"name":"The City College","place":["New York, NY, USA"],"department":["Department of Electrical Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9610-846X","authenticated-orcid":false,"given":"Tingwen","family":"Huang","sequence":"additional","affiliation":[{"name":"Shenzhen University of Advanced Technology","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref2","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dhariwal"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00473"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26094"},{"key":"ref6","article-title":"CogVideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022"},{"key":"ref7","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0843"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01178"},{"key":"ref10","article-title":"A survey on audio diffusion models: Text to speech synthesis and enhancement in generative AI","author":"Zhang","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/bxae110"},{"key":"ref13","article-title":"Sketch-fusion: A gradient compression method with multi-layer fusion for communication-efficient distributed training","volume-title":"J. Parallel Distrib. Comput.","volume":"185","author":"Dai","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.xinn.2025.100948"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/INFOTEH.2018.8345545"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01531"},{"key":"ref18","first-page":"238","article-title":"SCP: A structure combination pruning method via structured sparse for deep convolutional neural networks","volume-title":"Proc. Int. Conf. Pattern Recognit.","author":"Chen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2023.102990"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.551"},{"key":"ref21","article-title":"Q-Mamba: On first exploration of vision Mamba for image quality assessment","author":"Guan","year":"2024"},{"key":"ref22","article-title":"Learned step size quantization","author":"Esser","year":"2019"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref24","article-title":"Quantizing deep convolutional networks for efficient inference: A whitepaper","author":"Krishnamoorthi","year":"1806"},{"key":"ref25","article-title":"BinaryDM: Towards accurate binarization of diffusion model","author":"Zheng","year":"2024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3350"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1231"},{"key":"ref28","article-title":"Improving post training neural quantization: Layer-wise calibration and integer programming","author":"Hubara","year":"2020"},{"key":"ref29","first-page":"9847","article-title":"Towards accurate post-training network quantization via bit-split and stitching","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref30","article-title":"QDrop: Randomly dropping quantization for extremely low-bit post-training quantization","author":"Wei","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02340"},{"key":"ref32","article-title":"EfficientDM: Efficient quantization-aware fine-tuning of low-bit diffusion models","author":"He","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i16.33823"},{"key":"ref34","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"ref35","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00744"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2938"},{"key":"ref39","article-title":"Pseudo numerical methods for diffusion models on manifolds","author":"Liu","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref42","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022"},{"key":"ref43","first-page":"32211","article-title":"Consistency models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680768"},{"key":"ref45","article-title":"Q-VDiT: Towards accurate quantization and distillation of video-generation diffusion transformers","author":"Feng","year":"2025"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3272925"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3554523"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref49","first-page":"38087","article-title":"SmoothQuant: Accurate and efficient post-training quantization for large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiao"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0580"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00703"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01517"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2006"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01442"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26084"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350534"},{"key":"ref59","first-page":"680","article-title":"Larq compute engine: Design, benchmark and deploy state-of-the-art binarized neural networks","volume-title":"Proc. Mach. Learn. Syst.","author":"Bannink"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3257878"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0323"},{"key":"ref63","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/0024-3795(87)90114-5"},{"key":"ref65","first-page":"11875","article-title":"HAWQ-V3: Dyadic neural network quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yao"},{"key":"ref66","article-title":"LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop","author":"Yu","year":"2015"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref69","first-page":"2234","article-title":"Improved techniques for training GANs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Salimans"},{"key":"ref70","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local Nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref71","article-title":"Generating images with sparse representations","author":"Nash","year":"2021"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01200"},{"key":"ref74","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Paszke"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11674301\/11552026.pdf?arnumber=11552026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T17:17:25Z","timestamp":1790270245000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11552026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":74,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3700583","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}