{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T00:26:13Z","timestamp":1781223973765,"version":"3.54.1"},"reference-count":70,"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 Nature Science Foundation of China","doi-asserted-by":"publisher","award":["62402406"],"award-info":[{"award-number":["62402406"]}],"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\/iccv51701.2025.01744","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"18770-18780","source":"Crossref","is-referenced-by-count":1,"title":["GigaTok: Scaling Visual Tokenizers to 3 Billion Parameters for Autoregressive Image Generation"],"prefix":"10.1109","author":[{"given":"Tianwei","family":"Xiong","sequence":"first","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun Hao","family":"Liew","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zilong","family":"Huang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"stabilityai\/sd-vae-ft-ema","year":"2023"},{"key":"ref2","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref4","article-title":"Deepseek llm: Scaling opensource language models with longtermism","author":"Bi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02641"},{"key":"ref9","article-title":"Masked autoencoders are effective tokenizers for diffusion models","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"International conference on machine learning","author":"Chen","year":"2020"},{"key":"ref11","article-title":"Januspro: Unified multimodal understanding and generation with data and model scaling","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref15","article-title":"Data filtering networks","author":"Fang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Planting a seed of vision in large language model","author":"Ge","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Deepseek-r1: Incentivizing reasoning capability in llms via reinforcement learning","author":"Guo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Learnings from scaling visual tokenizers for reconstruction and generation","author":"Hansen-Estruch","year":"2025","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Bigr: Harnessing binary latent codes for image generation and improved visual representation capabilities","author":"Hao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref21","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"ref24","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Videopoet: A large language model for zero-shot video generation","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Kondratyuk","year":"2024"},{"issue":"10","key":"ref26","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"LeCun","year":"1995","journal-title":"The handbook of brain theory and neural networks"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref28","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref29","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Imagefolder: Autoregressive image generation with folded tokens","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Deepseek-v3 technical report","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Open-magvit2: An open-source project toward democratizing auto-regressive visual generation","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Unitok: A unified tokenizer for visual generation and understanding","author":"Ma","year":"2025","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref36","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00243"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref42","article-title":"Taming scalable visual tokenizer for autoregressive image generation","author":"Shi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","journal-title":"2024. 1,2,3,4,5"},{"key":"ref44","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref47","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref50","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref51","article-title":"Larp: Tokenizing videos with a learned autoregressive generative prior","author":"Wang","year":"2025","journal-title":"ICLR"},{"key":"ref52","article-title":"Image understanding makes for a good tokenizer for image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Maskbit: Embedding-free image generation via bit tokens","author":"Weber","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Janus: Decoupling visual encoding for unified multimodal understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","article-title":"Vila-u: a unified foundation model integrating visual understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Exploring representation-aligned latent space for better generation","author":"Xu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01464"},{"key":"ref59","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2294"},{"key":"ref62","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00741"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref68","article-title":"Image and video tokenization with binary spherical quantization","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref69","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":"ref70","article-title":"Stabilize the latent space for image autoregressive modeling: A unified perspective","author":"Zhu","year":"2024","journal-title":"arXiv preprint"}],"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\/11445446.pdf?arnumber=11445446","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:05Z","timestamp":1777611725000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445446\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01744","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}