{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:15Z","timestamp":1777888815867,"version":"3.51.4"},"reference-count":86,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2022ZD0161600"],"award-info":[{"award-number":["2022ZD0161600"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100023542","name":"Centre for Perceptual and Interactive Intelligence (CPII) Ltd","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100023542","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\/iccv51701.2025.01604","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17268-17280","source":"Crossref","is-referenced-by-count":0,"title":["X-Prompt: Generalizable Auto-Regressive Visual Learning with In-Context Prompting"],"prefix":"10.1109","author":[{"given":"Zeyi","family":"Sun","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyang","family":"Chu","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tong","family":"Wu","sequence":"additional","affiliation":[{"name":"Stanford Unviersity"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Zang","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanjun","family":"Xiong","sequence":"additional","affiliation":[{"name":"Adobe"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai Artificial Intelligence Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Palm 2 technical report","author":"Anil","year":"2023","journal-title":"ArXiv, abs\/2305.10403"},{"key":"ref2","article-title":"Openflamingo: An open-source framework for training large autoregressive vision-language models","author":"Awadalla","year":"2023","journal-title":"ArXiv, abs\/2308.01390"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02157"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1813"},{"issue":"3","key":"ref5","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Computer Science"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref7","author":"Brown","year":"2005","journal-title":"Language models are few-shot learners"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995413"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref10","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref12","article-title":"Dreamllm: Synergistic multimodal comprehension and creation","author":"Dong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","author":"Dong","year":"2024","journal-title":"Internlm-xcomposer2: Mastering free-form textimage composition and comprehension in vision-language large model"},{"key":"ref14","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref16","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.186"},{"key":"ref18","author":"Gan","year":"2023","journal-title":"Instructcv: Instructiontuned text-to-image diffusion models as vision generalists. arXiv preprint arXiv:2310.00390"},{"key":"ref19","article-title":"Making llama see and draw with seed tokenizer","author":"Ge","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Seed-x: Multimodal models with unified multi-granularity comprehension and generation","author":"Ge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01208"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2270"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref24","article-title":"Training compute-optimal large language models","author":"Hoffmann","year":"2022","journal-title":"ArXiv, abs\/2203.15556"},{"key":"ref25","article-title":"Group diffusion transformers are unsupervised multitask learners","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"In-context lora for diffusion transformers","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00799"},{"key":"ref28","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013","journal-title":"arXiv preprint"},{"key":"ref29","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive nlp tasks","volume":"33","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref30","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ArXiv, abs\/2301.12597"},{"key":"ref31","article-title":"Imagefolder: Autoregressive image generation with folded tokens","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Playground v3: Improving text-toimage alignment with deep-fusion large language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Lumina-mgpt: Illuminate flexible photorealistic text-to-image generation with multimodal generative pretraining","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Mia-dpo: Multi-image augmented di-rect preference optimization for large vision-language models","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Unified-io: A unified model for vision, language, and multi-modal tasks","volume-title":"The Eleventh International Conference on Learning Representations","author":"Lu","year":"2022"},{"key":"ref36","article-title":"Open-magvit2: An open-source project toward democratizing auto-regressive visual generation","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Star: Scale-wise text-toimage generation via auto-regressive representations","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Language models are few-shot learners","author":"Mann","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.35"},{"key":"ref40","article-title":"OpenAI","year":"2023","journal-title":"Gpt-4v(ision) system card"},{"key":"ref41","year":"2023","journal-title":"Gpt-4 technical report"},{"key":"ref42","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","volume-title":"arXiv preprint","author":"Podell","year":"2023"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02495"},{"key":"ref44","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":"ref45","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh","year":"2021"},{"issue":"2","key":"ref46","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref48","article-title":"Rb-modulation: Training-free personalization of diffusion models using stochastic optimal control","author":"Rout","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-33715-4_54"},{"key":"ref52","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Emu: Generative pretraining in multimodality","volume-title":"The Twelfth International Conference on Learning Representations","author":"Sun","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01365"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01237"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01458"},{"key":"ref58","article-title":"Hart: Efficient visual generation with hybrid autoregressive transformer","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Chameleon: Mixed-modal early-fusion foundation models","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Visual autoregressive modeling: Scalable im-age generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"ArXiv, abs\/2302.13971"},{"key":"ref62","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref64","article-title":"Neural discrete representation learning","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref65","article-title":"Instantstyle: Free lunch towards style-preserving in text-to-image generation","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00660"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00110"},{"key":"ref69","article-title":"Emu 3: Next-token prediction is all you need","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Deep retinex decomposition for low-light enhancement","author":"Wei","year":"2018","journal-title":"arXiv preprint"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01210"},{"key":"ref72","article-title":"Next-gpt: Any-to-any multimodal llm","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Vila-u: a unified foundation model integrating visual understanding and generation","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01241"},{"key":"ref75","article-title":"Show-o: One single transformer to unify multimodal understanding and generation","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref76","article-title":"Pyramiddrop: Accelerating your large vision-language models via pyramid visual redundancy reduction","author":"Xing","year":"2024","journal-title":"arXiv preprint"},{"key":"ref77","author":"Xing","journal-title":"Scalecap: Inference-time scalable image captioning via dual-modality debiasing"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.183"},{"key":"ref79","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint"},{"issue":"3","key":"ref80","article-title":"Scaling autoregressive multimodal models: Pretraining and instruction tuning","volume":"2","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1365"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref83","author":"Zhang","journal-title":"Internlm-xcomposer: A vision-language large model for advanced text-image comprehension and composition"},{"key":"ref84","article-title":"Var-clip: Text-to-image generator with visual auto-regressive modeling","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref85","article-title":"Ultraedit: Instruction-based fine-grained image editing at scale","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"}],"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\/11445403.pdf?arnumber=11445403","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:07Z","timestamp":1777611547000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445403\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01604","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}