{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:04:41Z","timestamp":1784268281309,"version":"3.55.0"},"reference-count":48,"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\/iccv51701.2025.00338","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3542-3551","source":"Crossref","is-referenced-by-count":1,"title":["Oasis: One Image is All You Need for Multimodal Instruction Data Synthesis"],"prefix":"10.1109","author":[{"given":"Letian","family":"Zhang","sequence":"first","affiliation":[{"name":"Tongji University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quan","family":"Cui","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingchen","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng","family":"Yang","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Mllm-as-a-judge: Assessing multimodal llm-as-a-judge with vision-language benchmark","author":"Chen","year":"2024","journal-title":"ICML"},{"key":"ref4","article-title":"Allava: Harnessing gpt4v-synthesized data for a lite vision-language model","author":"Hardy Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref7","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref9","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2024","journal-title":"CVPR"},{"key":"ref10","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref11","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Vila2: Vila augmented vila","author":"Fang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11023-020-09548-1"},{"key":"ref14","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref17","article-title":"Seed-bench-2-plus: Benchmarking multimodal large language models with text-rich visual comprehension","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref19","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Densefusion-1m: Merging vision experts for comprehensive multimodal perception","author":"Li","year":"2024","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref23","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref24","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4187-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref28","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Mmevol: Empowering multimodal large language models with evol-instruct","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref33","article-title":"Simpo: Simple preference optimization with a reference-free reward","author":"Meng","year":"2024","journal-title":"NeurIPS"},{"key":"ref34","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-022-00329-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref37","volume-title":"Stanford alpaca: An instruction-following llama model","author":"Taori","year":"2023"},{"key":"ref38","year":"2024","journal-title":"Qwen2.5: A party of foundation models"},{"key":"ref39","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal 11 ms","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","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":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref42","article-title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","author":"Xu","year":"2024","journal-title":"ICLR"},{"key":"ref43","article-title":"Magpie: Alignment data synthesis from scratch by prompting aligned 11 ms with nothing","volume-title":"arXiv preprint","author":"Xu","year":"2024"},{"key":"ref44","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.736"},{"key":"ref47","article-title":"Judging 11m-as-a-judge with mt-bench and chatbot arena","author":"Zheng","year":"2023","journal-title":"NeurIPS"},{"key":"ref48","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"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\/11445889.pdf?arnumber=11445889","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:29Z","timestamp":1777529969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445889\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00338","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}