{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:15:13Z","timestamp":1777889713644,"version":"3.51.4"},"reference-count":61,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFB4708200"],"award-info":[{"award-number":["2024YFB4708200"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B20173,62321005"],"award-info":[{"award-number":["U24B20173,62321005"]}],"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\/iccv51701.2025.01757","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18906-18916","source":"Crossref","is-referenced-by-count":1,"title":["CODA: Repurposing Continuous VAEs for Discrete Tokenization"],"prefix":"10.1109","author":[{"given":"Zeyu","family":"Liu","sequence":"first","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zanlin","family":"Ni","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeguo","family":"Hua","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xin","family":"Deng","sequence":"additional","affiliation":[{"name":"Renmin University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Ma","sequence":"additional","affiliation":[{"name":"Lenovo Research, AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"Zhong","sequence":"additional","affiliation":[{"name":"Lenovo Research, AI Lab"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gao","family":"Huang","sequence":"additional","affiliation":[{"name":"Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110792"},{"key":"ref4","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"BlackForest","year":"2024","journal-title":"Black forest labs; frontier ai lab"},{"key":"ref6","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref8","first-page":"4055","article-title":"Muse: Text-to-image generation via masked generative transformers","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Chang","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","author":"Fifty","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Planting a seed of vision in large language model","author":"Ge","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"Lora: Lowrank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02164"},{"key":"ref16","first-page":"14096","article-title":"Straightening out the straight-through estimator: Overcoming optimization challenges in vector quantized networks","volume-title":"International Conference on Machine Learning","author":"Huh","year":"2023"},{"key":"ref17","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of naacL-HLT Minneapolis, Minnesota","author":"Devlin","year":"2019"},{"key":"ref18","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref21","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems, 36"},{"key":"ref23","article-title":"ngpt: Normalized transformer with representation learning on the hypersphere","author":"Loshchilov","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0418"},{"key":"ref25","article-title":"Open-magvit2: An open-source project toward democratizing auto-regressive visual generation","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Finite scalar quantization: Vq-vae made simple","volume-title":"The Twelfth International Conference on Learning Representations. 2, 3","author":"Mentzer"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01363"},{"key":"ref28","article-title":"Enat: Rethinking spatial-temporal interactions in token-based image synthesis","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems. 1","author":"Ni"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00669"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_17"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref32","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"The Twelfth International Conference on Learning Representations. 1","author":"Podell"},{"key":"ref33","author":"Radford","journal-title":"Improving language understanding by generative pre-training"},{"key":"ref34","author":"Radford","journal-title":"Language models are unsupervised multitask learners"},{"issue":"140","key":"ref35","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref36","article-title":"Generating diverse high-fidelity images with vq-vae-2","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems, 32"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref38","first-page":"30105","article-title":"Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis","volume-title":"International conference on machine learning","author":"Sauer","year":"2023"},{"key":"ref39","article-title":"Taming scalable visual tokenizer for autoregressive image generation","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Divae: Photorealistic images synthesis with denoising diffusion decoder","volume-title":"arXiv preprint","author":"Shi","year":"2022"},{"key":"ref41","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Neural discrete representation learning","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref45","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref46","article-title":"Omnitokenizer: A joint image-video tokenizer for visual generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Emu 3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02162"},{"key":"ref49","article-title":"Maskbit: Embedding-free image generation via bit tokens","author":"Weber","journal-title":"Transactions on Machine Learning Research. 2, 3"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01210"},{"key":"ref51","article-title":"ivideogpt: Interactive videogpts are scalable world models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Vila-u: a unified foundation model integrating visual understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Language model beats diffusion-tokenizer is key to visual generation","volume-title":"The Twelfth International Conference on Learning Representations. 2","author":"Yu"},{"key":"ref56","article-title":"Randomized autoregressive visual generation","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Root mean square layer normalization","author":"Zhang","year":"2019","journal-title":"Advances in Neural Information Processing Systems, 32"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref60","article-title":"Scaling the codebook size of vqgan to 100,000 with a utilization rate of 99%","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0899"}],"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\/11445714.pdf?arnumber=11445714","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:17:21Z","timestamp":1777612641000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445714\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01757","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}