{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:28:31Z","timestamp":1777865311880,"version":"3.51.4"},"reference-count":74,"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\/iccv51701.2025.01782","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19174-19184","source":"Crossref","is-referenced-by-count":1,"title":["Fine-Tuning Visual Autoregressive Models for Subject-Driven Generation"],"prefix":"10.1109","author":[{"given":"Jiwoo","family":"Chung","sequence":"first","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangeek","family":"Hyun","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyunjun","family":"Kim","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Eunseo","family":"Koh","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"MinKyu","family":"Lee","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jae-Pil","family":"Heo","sequence":"additional","affiliation":[{"name":"Sungkyunkwan University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref2","volume-title":"Coyo-700m: Image-text pair dataset","author":"Byeon","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02106"},{"key":"ref5","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"In International conference on machine learning","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1318"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00840"},{"key":"ref8","article-title":"Diffedit: Diffusion-based semantic image editing with mask guidance","author":"Couairon","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first international conference on machine learning","author":"Esser"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680734"},{"key":"ref12","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","volume-title":"The Eleventh International Conference on Learning Representations","author":"Gal"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3592133"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.3"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00782"},{"key":"ref17","article-title":"Infinity: Scaling bitwise autoregressive modeling for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Han","year":"2024"},{"key":"ref18","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Prompt-to-prompt image editing with cross-attention control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref20","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications.","author":"Ho"},{"key":"ref21","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"2","key":"ref22","first-page":"3","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Hu","year":"2022","journal-title":"ICLR"},{"key":"ref23","article-title":"Taming encoder for zero fine-tuning image customization with text-to-image diffusion models","author":"Jia","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"25105","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"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00192"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref27","volume-title":"Flux","volume":"1","year":"2024"},{"key":"ref28","article-title":"Flux","author":"Forest Labs","year":"2025","journal-title":"1 kontext: Flow matching for in-context image generation and editing in latent space"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1447"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1312"},{"key":"ref32","article-title":"Get what you want, not what you don\u2019t: Image content suppression for text-to-image diffusion models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Controlvar: Exploring controllable visual autoregressive modeling","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Few-shot image generation with elastic weight consolidation","volume":"2","author":"Li","year":"2020","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Controlar: Controllable image generation with autoregressive models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations.","author":"Loshchilov"},{"key":"ref37","first-page":"6437","article-title":"Countering language drift with seeded iterated learning","volume-title":"International Conference on Machine Learning","author":"Lu"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00740"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00774"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"2","key":"ref42","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref43","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":"ref44","first-page":"2912","article-title":"Parallel multiscale autoregressive density estimation","volume-title":"International conference on machine learning","author":"Reed"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00624"},{"key":"ref48","article-title":"Pixelcnn++: Improving the pixelcnn with discretized logistic mixture likelihood and other modifications","volume-title":"International Conference on Learning Representations","author":"Salimans"},{"key":"ref49","article-title":"Laion400 m: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"NeurIPS Workshop Datacentric AI, number FZJ-2022\u201300923. J\u00fclich Supercomputing Center","author":"Schuhmann","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00816"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00844"},{"key":"ref52","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref53","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref54","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Chameleon: Mixed-modal early-fusion foundation models","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2694"},{"key":"ref57","first-page":"2","article-title":"Conditional image generation with pixelcnn decoders","volume":"29","author":"Oord","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref58","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"International conference on machine learning","author":"Van Den Oord"},{"key":"ref59","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref60","volume-title":"Diffusers: State-of-the-art diffusion models","author":"Platen","year":"2022"},{"key":"ref61","article-title":"Emu3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Loong: Generating minute-level long videos with autoregressive language models","author":"Wang","year":"2024","journal-title":"CoRR"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01461"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02227-z"},{"key":"ref65","article-title":"Imagereward: Learning and evaluating human preferences for text-to-image generation","volume":"36","author":"Xu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref66","article-title":"Car: Controllable autoregressive modeling for visual generation","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Inst-inpaint: Instructing to remove objects with diffusion models","author":"Burak Yildirim","year":"2023","journal-title":"arXiv preprint"},{"key":"ref68","article-title":"Vector-quantized image modeling with improved vqgan","volume-title":"International Conference on Learning Representations","author":"Yu"},{"key":"ref69","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref70","article-title":"Language model beats diffusion-tokenizer is key to visual generation","volume":"2","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref72","article-title":"Image and video tokenization with binary spherical quantization","volume":"2","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680912"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_7"}],"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\/11445193.pdf?arnumber=11445193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:14:10Z","timestamp":1777529650000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01782","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}