{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:08:46Z","timestamp":1777889326701,"version":"3.51.4"},"reference-count":67,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276123"],"award-info":[{"award-number":["62276123"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.01567","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16871-16881","source":"Crossref","is-referenced-by-count":0,"title":["Memory-Efficient Generative Models via Product Quantization"],"prefix":"10.1109","author":[{"given":"Jie","family":"Shao","sequence":"first","affiliation":[{"name":"Nanjing University, School of Artificial Intelligence, Nanjing University,National Key Laboratory for Novel Software Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hanxiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanjing University, School of Artificial Intelligence, Nanjing University,National Key Laboratory for Novel Software Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Yu","sequence":"additional","affiliation":[{"name":"Nanjing University, School of Artificial Intelligence, Nanjing University,National Key Laboratory for Novel Software Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianxin","family":"Wu","sequence":"additional","affiliation":[{"name":"Nanjing University, School of Artificial Intelligence, Nanjing University,National Key Laboratory for Novel Software Technology,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"A note on the inception score","author":"Barratt","year":"2018","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Pixart-alpha: Fast training of diffusion transformer for photorealistic text-to-image synthesis","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02636"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3581312"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33782"},{"key":"ref9","article-title":"Extreme compression of large language models via additive quantization","author":"Egiazarian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref11","article-title":"Learned step size quantization","author":"Esser","year":"2019","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"GPTQ: Accurate post-training quantization for generative pre-trained transformers","volume-title":"The Eleventh International Conference on Learning Representations","author":"Frantar"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00421"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.379"},{"key":"ref15","article-title":"Vector quantization and signal compression","author":"Gersho","year":"1991","journal-title":"Kluwer Academic Publishers"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref17","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref19","article-title":"Efficientdm: Efficient quantization-aware fine-tuning of low-bit diffusion models","author":"He","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00520"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0580"},{"key":"ref22","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"47","key":"ref23","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3443"},{"issue":"4","key":"ref25","article-title":"Estimation of nonnormalized statistical models by score matching","volume":"6","author":"Hyv\u00e4rinen","year":"2005","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref27","article-title":"Lord: Low rank decomposition of monolingual code 11 ms for one-shot compression","author":"Kaushal","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref30","article-title":"Large memory layers with product keys","volume":"32","author":"Lample","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207145"},{"key":"ref32","article-title":"Svdqunat: Absorbing outliers by lowrank components for 4-bit diffusion models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01608"},{"key":"ref34","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device 11 m compression and acceleration","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Lin"},{"key":"ref35","article-title":"The era of 1-bit 11 ms: All large language models are in 1.58 bits","volume":"1","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0950"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01544"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2973"},{"key":"ref39","first-page":"16318","article-title":"Overcoming oscillations in quantization-aware training","volume-title":"International Conference on Machine Learning","author":"Nagel"},{"key":"ref40","article-title":"Compact3d: Compressing gaussian splat radiance field models with vector quantization","volume":"4","author":"K","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"GLIDE: towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.388"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref44","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2022","journal-title":"arXiv preprint"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"2","key":"ref47","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00353"},{"key":"ref50","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"ref52","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref53","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref55","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"And the bit goes down: Revisiting the quantization of neural networks","volume-title":"International Conference on Learning Representations","author":"Stock"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2161"},{"key":"ref58","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Quip#: Even better llm quantization with hadamard incoherence and lattice codebooks","author":"Tseng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Gptvq: The blessing of dimensionality for 11 m quantization","author":"van Baalen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Bitnet: Scaling 1-bit transformers for large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73636-0_5"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3158"},{"key":"ref64","first-page":"38087","article-title":"Smoothquant: Accurate and efficient post-training quantization for large language models","volume-title":"International Conference on Machine Learning","author":"Xiao"},{"key":"ref65","article-title":"1.58-bit flux","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26304"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01498"},{"key":"ref68","volume-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"}],"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\/11445514.pdf?arnumber=11445514","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:19Z","timestamp":1777612159000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445514\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":67,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01567","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}