{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:21:06Z","timestamp":1777890066481,"version":"3.51.4"},"reference-count":76,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01981","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21331-21341","source":"Crossref","is-referenced-by-count":0,"title":["Multidimensional Byte Pair Encoding: Shortened Sequences for Improved Visual Data Generation"],"prefix":"10.1109","author":[{"given":"Tim","family":"Elsner","sequence":"first","affiliation":[{"name":"RWTH Aachen University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paula","family":"Usinger","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Julius","family":"Nehring-Wirxel","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gregor","family":"Kobsik","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Victor","family":"Czech","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjiang","family":"He","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isaak","family":"Lim","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Leif","family":"Kobbelt","sequence":"additional","affiliation":[{"name":"RWTH Aachen University,Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"40","article-title":"Learning representations and generative models for 3D point clouds","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Achlioptas"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/360825.360855"},{"key":"ref3","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv preprint arXiv"},{"key":"ref4","volume-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2016"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref6","volume-title":"Token merging: Your vit but faster","author":"Bolya","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73039-9_24"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00677"},{"key":"ref9","article-title":"Shapenet: An information-rich 3d model repository","author":"Chang","year":"2015","journal-title":"CoRR"},{"key":"ref10","first-page":"864","article-title":"PixelSNAIL: An improved autoregressive generative model","volume-title":"Proceedings of the 35th International Conference on Machine Learning","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00451"},{"key":"ref12","article-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref13","volume-title":"The road less scheduled","author":"Defazio","year":"2024"},{"key":"ref14","article-title":"T-free: Tokenizerfree generative 11 ms via sparse representations for memory- efficient embeddings","author":"Deiseroth","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref17","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"CoRR"},{"key":"ref18","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref19","volume-title":"Freeman. Adaptive length image tokenization via recurrent allocation","author":"Duggal","year":"2024"},{"key":"ref20","article-title":"Quantised global autoencoder: A holistic approach to representing visual data","author":"Elsner","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref21","article-title":"Taming transformers for high-resolution image synthesis","author":"Esser","year":"2020","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00641"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref25","article-title":"Gans trained by a two time-scale update rule converge to a nash equilibrium","author":"Heusel","year":"2017","journal-title":"CoRR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1126\/science.1127647"},{"key":"ref27","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Advances in Neural Information Processing Systems","author":"Ho","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02164"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00270"},{"key":"ref30","article-title":"Edibert, a generative model for image editing","author":"Issenhuth","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref31","volume-title":"One-shot learning meets depth diffusion in multi-object videos","author":"Jain","year":"2024"},{"key":"ref32","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73016-0_19"},{"key":"ref34","volume-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref36","volume-title":"Openassistant conversations - democratizing large language model alignment","author":"K\u00f6pf","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207145"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref39","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"ref41","volume-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2019"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref43","volume-title":"Gpt-4 technical report","author":"Steven","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.453"},{"key":"ref45","first-page":"11","article-title":"Tokenisation and sentence segmentation","volume-title":"Handbook of natural language processing","author":"Palmer","year":"2000"},{"key":"ref46","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref47","first-page":"652","article-title":"Pointnet: Deep learning on point sets for 3d classification and segmentation","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Qi"},{"key":"ref48","volume-title":"Improving language understanding with unsupervised learning","author":"Radford","year":"2018"},{"issue":"8","key":"ref49","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref50","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"CoRR"},{"key":"ref51","article-title":"A novel sampling scheme for text-and image-conditional image synthesis in quantized latent spaces","author":"Rampas","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref52","volume-title":"Generating diverse high-fidelity images with vq-vae-2","author":"Razavi","year":"2019"},{"key":"ref53","first-page":"26","article-title":"Pixel-level BPE for auto-regressive image generation","volume-title":"Proceedings of the First Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models","author":"Razzhigaev"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00486"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref56","first-page":"599","volume-title":"Learning internal representations by error propagation, parallel distributed processing, explorations in the microstructure of cognition","volume":"1","author":"Rumelhart","year":"1986"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1992.4.6.863"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1162"},{"key":"ref59","volume-title":"Cat: Content-adaptive image tokenization","author":"Shen","year":"2025"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00706"},{"key":"ref61","volume-title":"Byte pair encoding: A text compression scheme that accelerates pattern matching","author":"Shibata","year":"1999"},{"key":"ref62","article-title":"Linear-time wordpiece tokenization","author":"Song","year":"2020","journal-title":"CoRR"},{"key":"ref63","article-title":"Discrete acoustic space for an efficient sampling in neural text-to-speech","author":"Strong","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref65","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2014","journal-title":"CoRR"},{"key":"ref66","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2017","journal-title":"CoRR"},{"key":"ref67","volume-title":"Attention is all you need","author":"Vaswani","year":"2023"},{"key":"ref68","volume-title":"Vector quantized wasserstein auto-encoder","author":"Vuong","year":"2023"},{"key":"ref69","article-title":"Mambabyte: Token-free selective state space model","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.6108"},{"key":"ref71","article-title":"Videogpt: Video generation using vq-vae and transformers","author":"Yan","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref72","volume-title":"Elastictok: Adaptive tokenization for image and video","author":"Yan","year":"2025"},{"key":"ref73","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref74","volume-title":"From pixels to tokens: Byte-pair encoding on quantized visual modalities","author":"Zhang","year":"2025"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"},{"key":"ref76","article-title":"Designing a better asymmetric vqgan for stablediffusion","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv"}],"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\/11443306.pdf?arnumber=11443306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:28:26Z","timestamp":1777613306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":76,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01981","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}