{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T16:18:43Z","timestamp":1774628323318,"version":"3.50.1"},"reference-count":54,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T00:00:00Z","timestamp":1749513600000},"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":[[2025,6,10]]},"DOI":"10.1109\/cvpr52734.2025.00242","type":"proceedings-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:26:42Z","timestamp":1755106002000},"page":"2535-2544","source":"Crossref","is-referenced-by-count":1,"title":["HMAR: Efficient Hierarchical Masked Auto-Regressive Image Generation"],"prefix":"10.1109","author":[{"given":"Hermann","family":"Kumbong","sequence":"first","affiliation":[{"name":"Stanford University"}]},{"given":"Xian","family":"Liu","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Tsung-Yi","family":"Lin","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Ming-Yu","family":"Liu","sequence":"additional","affiliation":[{"name":"NVIDIA"}]},{"given":"Xihui","family":"Liu","sequence":"additional","affiliation":[{"name":"HKU"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"NTU"}]},{"given":"Daniel Y.","family":"Fu","sequence":"additional","affiliation":[{"name":"UCSD"}]},{"given":"Christopher","family":"R\u00e9","sequence":"additional","affiliation":[{"name":"Stanford University"}]},{"given":"David W.","family":"Romero","sequence":"additional","affiliation":[{"name":"NVIDIA"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref2","volume-title":"Image data compression with the Laplacian pyramid","author":"Adelson","year":"1980"},{"key":"ref3","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2022"},{"key":"ref4","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-08-051581-6.50065-9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref7","article-title":"Muse: Text-to-image generation via masked generative transformers","author":"Chang","year":"2023"},{"key":"ref8","article-title":"Collaborative decoding makes visual auto-regressive modeling efficient","author":"Chen","year":"2024"},{"key":"ref9","article-title":"FlashAttention-2: Faster attention with better parallelism and work partitioning","volume-title":"International Conference on Learning Representations (ICLR)","author":"Dao"},{"key":"ref10","article-title":"FlashAttention: Fast and memory-efficient exact attention with IO-awareness","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Dao"},{"key":"ref11","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019"},{"key":"ref12","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref13","article-title":"Noise schedules considered harmful","author":"Dieleman","year":"2024"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref15","article-title":"Depthart: Monocular depth estimation as autoregressive refinement task","author":"Gabdullin","year":"2024"},{"key":"ref16","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref17","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","author":"Han","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024"},{"key":"ref21","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01123"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref24","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024"},{"key":"ref25","article-title":"Imagefolder: Autoregressive image generation with folded tokens","author":"Li","year":"2024"},{"key":"ref26","article-title":"Controlvar: Exploring controllable visual autoregressive modeling","author":"Li","year":"2024"},{"key":"ref27","article-title":"Hyperhuman: Hyper-realistic human generation with latent structural diffusion","author":"Liu","year":"2023"},{"key":"ref28","article-title":"Star: Scale-wise text-to-image generation via auto-regressive representations","author":"Ma","year":"2024"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref30","article-title":"Flexattention: The flexibility of py-torch with the performance of flashattention","year":"2024"},{"key":"ref31","article-title":"Self-attention does not need o(n\u02c62) memory","author":"Rabe","year":"2021"},{"key":"ref32","article-title":"Improving language understanding by generative pre-training","author":"Radford","year":"2018"},{"issue":"8","key":"ref33","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"issue":"2","key":"ref34","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref35","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref38","article-title":"Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications","author":"Salimans","year":"2017"},{"key":"ref39","article-title":"Flashattention-3: Fast and accurate attention with asynchrony and low-precision","author":"Shah","year":"2024"},{"key":"ref40","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref41","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref42","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024"},{"key":"ref43","article-title":"Hart: Efficient visual generation with hybrid autoregressive transformer","author":"Tang","year":"2024"},{"key":"ref44","article-title":"Accelerating auto-regressive text-to-image generation with training-free speculative jacobi decoding","author":"Teng","year":"2024"},{"key":"ref45","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3315508.3329973"},{"key":"ref47","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref48","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"International conference on machine learning","author":"Oord"},{"key":"ref49","article-title":"Conditional image generation with pixelcnn decoders","author":"van den Oord","year":"2016"},{"key":"ref50","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2018"},{"key":"ref51","article-title":"Switti: Designing scale-wise transformers for text-to-image synthesis","author":"Voronov","year":"2024"},{"key":"ref52","article-title":"Maskbit: Embedding-free image generation via bit tokens","author":"Weber","year":"2024"},{"key":"ref53","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022"},{"key":"ref54","article-title":"Var-clip: Text-to-image generator with visual auto-regressive modeling","author":"Zhang","year":"2024"}],"event":{"name":"2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Nashville, TN, USA","start":{"date-parts":[[2025,6,10]]},"end":{"date-parts":[[2025,6,17]]}},"container-title":["2025 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11091818\/11091608\/11091878.pdf?arnumber=11091878","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,15]],"date-time":"2025-08-15T04:55:52Z","timestamp":1755233752000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11091878\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,10]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/cvpr52734.2025.00242","relation":{},"subject":[],"published":{"date-parts":[[2025,6,10]]}}}