{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:29:25Z","timestamp":1777865365167,"version":"3.51.4"},"reference-count":38,"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 Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24A20327"],"award-info":[{"award-number":["U24A20327"]}],"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\/iccv51701.2025.01592","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17140-17149","source":"Crossref","is-referenced-by-count":0,"title":["Frequency-Aware Autoregressive Modeling for Efficient High-Resolution Image Synthesis"],"prefix":"10.1109","author":[{"given":"Zhuokun","family":"Chen","sequence":"first","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jugang","family":"Fan","sequence":"additional","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuowei","family":"Yu","sequence":"additional","affiliation":[{"name":"University of California,Davis"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bohan","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingkui","family":"Tan","sequence":"additional","affiliation":[{"name":"South China University of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Hired: Attention-guided token dropping for efficient inference of high-resolution vision-language models in resource-constrained environments","author":"Arif","year":"2024","journal-title":"arXiv preprint"},{"issue":"3","key":"ref2","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref3","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2023","journal-title":"ICLR. OpenReview.net"},{"key":"ref4","article-title":"Pixart-\u03b1: Fast training of diffusion transformer for photorealistic text-to-image synthesis","volume-title":"ICLR","author":"Chen","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73004-7_2"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_37"},{"key":"ref7","first-page":"19822","article-title":"Cogview: Mastering text-to-image generation via transformers","volume":"34","author":"Ding","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref10","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Han","year":"2024"},{"key":"ref11","article-title":"Zipar: Accelerating autoregressive im-age generation through spatial locality","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Zipvl: Efficient large vision-language models with dynamic token sparsification and kv cache compression","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Ella: Equip diffusion models with llm for enhanced semantic alignment","author":"Hu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref16","article-title":"Video token merging for long-form video understanding","author":"Lee","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","article-title":"Controllable text-to-image generation","volume":"32","author":"Li","year":"2019","journal-title":"NeurIPS"},{"key":"ref18","article-title":"Imagefolder: Autoregressive image generation with folded tokens","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Controlvar: Exploring controllable visual autoregressive modeling","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Finite scalar quantization: Vq-vae made simple","author":"Mentzer","journal-title":"ICLR"},{"key":"ref21","article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","volume-title":"ICLR","author":"Podell","year":"2024"},{"key":"ref22","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"ICML","author":"Ramesh","year":"2021"},{"key":"ref23","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"NeurIPS"},{"key":"ref24","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"ICML","author":"Reed","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","article-title":"Llavaprumerge: Adaptive token reduction for efficient large multimodal models","author":"Shang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Hart: Efficient visual generation with hybrid autoregressive transformer","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref30","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/404"},{"key":"ref32","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Human preference score v2: A solid benchmark for evaluating human preferences of text-to-image synthesis","volume-title":"arXiv preprint","author":"Wu","year":"2023"},{"key":"ref34","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"NeurIPS"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref36","article-title":"Vectorquantized image modeling with improved vqgan","author":"Yu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","journal-title":"ICLR"},{"key":"ref38","article-title":"Language model beats diffusion tokenizer is key to visual generation","author":"Yu","year":"2024","journal-title":"ICLR"}],"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\/11446301.pdf?arnumber=11446301","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:20:38Z","timestamp":1777530038000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446301\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01592","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}