{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:15:39Z","timestamp":1761894939059,"version":"build-2065373602"},"reference-count":19,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11208956","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":0,"title":["MLLM-DataEngine: Closing the Loop of Multimodal Instruction Tuning Data Generation"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Zhao","sequence":"first","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}]},{"given":"Bin","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}]},{"given":"Linke","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}]},{"given":"Yiqi","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}]},{"given":"Pan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}]},{"given":"Xiaoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}]},{"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}]},{"given":"Conghui","family":"He","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,Shanghai,China"}]}],"member":"263","reference":[{"article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","year":"2023","author":"Zhu","key":"ref1"},{"key":"ref2","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","year":"2023","author":"Dai","key":"ref3"},{"article-title":"Kosmos-2: Grounding multimodal large language models to the world","year":"2023","author":"Peng","key":"ref4"},{"key":"ref5","article-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022","journal-title":"NeurIPS"},{"article-title":"Internlm-xcomposer2: Mastering free-form text-image composition and comprehension in vision-language large model","year":"2024","author":"Dong","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"article-title":"Mimic-it: Multimodal in-context instruction tuning","year":"2023","author":"Li","key":"ref8"},{"article-title":"Chatgpt asks, blip-2 answers: Automatic questioning towards enriched visual descriptions","year":"2023","author":"Zhu","key":"ref9"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.755"},{"article-title":"Gpt-4 technical report","year":"2023","author":"Achiam","key":"ref11"},{"key":"ref12","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","author":"Liu","year":"2023","journal-title":"ICLR"},{"article-title":"Seed-bench: Benchmarking multimodal llms with generative comprehension","year":"2023","author":"Li","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"article-title":"Svit: Scaling up visual instruction tuning","year":"2023","author":"Zhao","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"article-title":"Pp-ocr: A practical ultra lightweight ocr system","year":"2020","author":"Du","key":"ref18"},{"article-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","year":"2023","author":"Chen","key":"ref19"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11208956.pdf?arnumber=11208956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:39:39Z","timestamp":1761889179000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11208956\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":19,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11208956","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}