{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T17:29:26Z","timestamp":1791566966711,"version":"4.3.4"},"reference-count":71,"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\/iccv51701.2025.01464","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15781-15791","source":"Crossref","is-referenced-by-count":15,"title":["Beyond Next-Token: Next-X Prediction for Autoregressive Visual Generation"],"prefix":"10.1109","author":[{"given":"Sucheng","family":"Ren","sequence":"first","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qihang","family":"Yu","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ju","family":"He","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohui","family":"Shen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alan","family":"Yuille","sequence":"additional","affiliation":[{"name":"Johns Hopkins University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang-Chieh","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"Alpha-vllm. large-dit-imagenet"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.58"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02171"},{"key":"ref4","article-title":"Large scale gan training for high fidelity natural image synthesis","volume-title":"arXiv preprint arXiv","author":"Brock","year":"2018"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"NeurIPS"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref7","article-title":"Generative pretraining from pixels","author":"Chen","year":"2020","journal-title":"ICML"},{"key":"ref8","article-title":"Causal diffusion transformers for generative modeling","author":"Deng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref10","article-title":"Diffusion models beat gans on image synthesis","volume-title":"NeurIPS","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref12","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"ICML","author":"Esser","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02117"},{"key":"ref14","article-title":"Generative adversarial nets","author":"Goodfellow","year":"2014","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Dart: Denoising autoregressive transformer for scalable text-to-image generation","author":"Gu","year":"2025","journal-title":"ICLR"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01544"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.415"},{"key":"ref18","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"NeurIPS"},{"key":"ref19","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref20","article-title":"simple diffusion: End-to-end diffusion for high resolution images","author":"Hoogeboom","year":"2023","journal-title":"ICML"},{"key":"ref21","article-title":"Simpler diffusion (sid2): 1.5 fid on imagenet512 with pixel-space diffusion","author":"Hoogeboom","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref23","article-title":"Democratizing text-to-image masked generative models with compact textaware one-dimensional tokens","author":"Kim","year":"2025","journal-title":"ICCV"},{"key":"ref24","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"In ICLR"},{"key":"ref25","article-title":"Applying guidance in a limited interval improves sample and distribution quality in diffusion models","author":"Kynk\u00e4\u00e4nniemi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref27","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref28","article-title":"Flow matching for generative modeling","author":"Lipman","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref29","article-title":"Alleviating distortion in image generation via multi-resolution diffusion models","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref30","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref31","article-title":"Open-magvit2: An open-source project toward democratizing auto-regressive visual generation","author":"Luo","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72980-5_2"},{"key":"ref33","volume-title":"OpenAI. Introducing chatgpt","year":"2022"},{"key":"ref34","article-title":"OpenAI. Gpt-4 technical report","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref35","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref37","volume-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"key":"ref38","article-title":"Sequence level training with recurrent neural networks","author":"Ranzato","year":"2016","journal-title":"In ICLR"},{"key":"ref39","article-title":"Generating diverse high-fidelity images with vq-vae-2","author":"Razavi","year":"2019","journal-title":"NeurIPS"},{"key":"ref40","article-title":"Ultrapixel: Advancing ultra high-resolution image synthesis to new peaks","volume-title":"NeurIPS","author":"Ren","year":"2024"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01687"},{"key":"ref42","article-title":"M-var: Decoupled scale-wise autoregressive modeling for high-quality image generation","author":"Ren","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Autoregressive pretraining with mamba in vision","author":"Ren","year":"2025","journal-title":"ICLR"},{"key":"ref44","article-title":"Flowar: Scale-wise autoregressive image generation meets flow matching","author":"Ren","year":"2025","journal-title":"ICML"},{"key":"ref45","article-title":"Grouping first, attending smartly: Trainingfree acceleration for diffusion transformers","author":"Ren","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref46","article-title":"Arvideo: Autoregressive pretraining for self-supervised video representation learning","author":"Ren","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref49","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"NeurIPS"},{"key":"ref50","article-title":"Styleganxl: Scaling stylegan to large diverse datasets","author":"Sauer","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01535"},{"key":"ref52","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref53","article-title":"Generative modeling by estimating gradients of the data distribution","author":"Song","year":"2019","journal-title":"NeurIPS"},{"key":"ref54","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref55","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"NeurIPS"},{"key":"ref56","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref57","article-title":"Conditional image generation with pixelcnn decoders","author":"Van","year":"2016","journal-title":"NeurIPS"},{"key":"ref58","article-title":"Pixel recurrent neural networks","author":"Van","year":"2016","journal-title":"In ICML"},{"key":"ref59","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"NeurIPS"},{"key":"ref60","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"NeurIPS"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01209"},{"key":"ref62","article-title":"Maskbit: Embedding-free image generation via bit tokens","author":"Weber","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"ref64","article-title":"1.58-bit flux","author":"Yang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref65","article-title":"Vector-quantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref66","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref67","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2024","journal-title":"ICLR"},{"key":"ref68","article-title":"An image is worth 32 tokens for reconstruction and generation","author":"Yu","year":"2024","journal-title":"NeurIPS"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01713"},{"key":"ref70","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","author":"Yu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref71","article-title":"Monoformer: One transformer for both diffusion and autoregression","author":"Zhao","year":"2024","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\/11446325.pdf?arnumber=11446325","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:43Z","timestamp":1777529803000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446325\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01464","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}