{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T09:59:10Z","timestamp":1777888750595,"version":"3.51.4"},"reference-count":45,"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":["62274142"],"award-info":[{"award-number":["62274142"]}],"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\/iccv51701.2025.02273","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"24518-24527","source":"Crossref","is-referenced-by-count":0,"title":["ViM-VQ: Efficient Post-Training Vector Quantization for Visual Mamba"],"prefix":"10.1109","author":[{"given":"Juncan","family":"Deng","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuaiting","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kedong","family":"Xu","sequence":"additional","affiliation":[{"name":"vivo Mobile Communication Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Gu","sequence":"additional","affiliation":[{"name":"vivo Mobile Communication Co., Ltd"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kejie","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Dkm: Differentiable k-means clustering layer for neural network compression","author":"Cho","year":"2021","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00122"},{"key":"ref3","article-title":"Towards the limit of network quantization","volume-title":"International Conference on Learning Representations","author":"Choi"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i15.33782"},{"key":"ref5","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Hawq-v2: Hessian aware trace-weighted quantization of neural networks","author":"Dong","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","article-title":"An image is worth $16 \\times 16$ words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Extreme compression of large language models via additive quantization","author":"Egiazarian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Learned step size quantization","author":"Steven","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Gptq: Accurate post-training quantization for generative pre-trained transformers","author":"Frantar","year":"2022","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Mamba: Linear-time sequence modeling with selective state spaces","author":"Gu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Efficiently modeling long sequences with structured state spaces","author":"Gu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2607"},{"key":"ref14","article-title":"Deep compression: Compressing deep neural network with pruning, trained quantization and huffman coding","volume-title":"International Conference on Learning Representations","author":"Han"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91979-4_2"},{"key":"ref18","article-title":"Network quantization with elementwise gradient scaling","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Ham"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1806.08342"},{"key":"ref21","first-page":"75","article-title":"Mamband: Selective state space modeling for multi-dimensional data","volume-title":"European Conference on Computer Vision","author":"Li"},{"key":"ref22","article-title":"Brecq: Pushing the limit of post-training quantization by block reconstruction","author":"Li","year":"2021","journal-title":"arXiv preprint"},{"key":"ref23","first-page":"87","article-title":"Awq: Activation-aware weight quantization for on-device $\\operatorname{llm}$ compression and acceleration","volume-title":"Proceedings of Machine Learning and Systems","volume":"6","author":"Lin"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2025.3610435"},{"key":"ref25","article-title":"Vmamba: Visual state space model","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.467"},{"key":"ref27","first-page":"28092","article-title":"Post-training quantization for vision transformer","volume":"34","author":"Liu","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01544"},{"key":"ref29","first-page":"7197","article-title":"Up or down? adaptive rounding for post-training quantization","volume-title":"International Conference on Machine Learning","author":"Nagel"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1511.08458"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00196"},{"key":"ref32","article-title":"Omniquant: Omnidirectionally calibrated quantization for large language models","author":"Shao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"And the bit goes down: Revisiting the quantization of neural networks","author":"Stock","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Quip\\#: Even better llm quantization with hadamard incoherence and lattice codebooks","author":"Tseng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Gptvq: The blessing of dimensionality for 11 m quantization","author":"van Baalen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00881"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref38","article-title":"Deep k-means: Retraining and parameter sharing with harder cluster assignments for compressing deep convolutions","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref39","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":"ref40","article-title":"Mambaquant: Quantizing the mamba family with variance aligned rotation methods","author":"Xu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Plainmamba: Improving non-hierarchical mamba in visual recognition","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Network memory footprint compression through jointly learnable codebooks and mappings","author":"Yvinec","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Incremental network quantization: Towards lossless cnns with low-precision weights","author":"Zhou","year":"2017","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","first-page":"1","article-title":"Learning lowrank representations for model compression","volume-title":"2023International Joint Conference on Neural Networks (IJCNN)","author":"Zhu"}],"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\/11445628.pdf?arnumber=11445628","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:56:43Z","timestamp":1777611403000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445628\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02273","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}