{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:03:52Z","timestamp":1777889032445,"version":"3.51.4"},"reference-count":58,"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\/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\/iccv51701.2025.00110","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"1099-1109","source":"Crossref","is-referenced-by-count":1,"title":["MM-IFEngine: Towards Multimodal Instruction Following"],"prefix":"10.1109","author":[{"given":"Shengyuan","family":"Ding","sequence":"first","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shenxi","family":"Wu","sequence":"additional","affiliation":[{"name":"Fudan University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangyu","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Zang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haodong","family":"Duan","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyi","family":"Dong","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhang","family":"Cao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dahua","family":"Lin","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","year":"2024","journal-title":"Anthropic. Claude 3.5 sonnet."},{"key":"ref2","article-title":"VisIT-Bench: A benchmark for visionlanguage instruction following inspired by real-world use","author":"Bitton","year":"2023","journal-title":"NeurIPS, Datasets and Benchmarks"},{"key":"ref3","article-title":"Allava: Harnessing gpt4v-synthesized data for lite vision-language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref5","article-title":"Are we on the right way for evaluating large visionlanguage models?","author":"Chen","year":"2024","journal-title":"NeurIPS"},{"key":"ref6","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":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3126594.3126651"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3685520"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00049"},{"key":"ref12","article-title":"G-llava: Solving geometric problem with multi-modal large language model","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.257"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref16","article-title":"LLaVA-OneVision: Easy visual task transfer","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.537"},{"key":"ref18","article-title":"A survey on benchmarks of multimodal large language models","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref20","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref21","author":"Liu","year":"2024","journal-title":"Llava-next: Improved reasoning, ocr, and world knowledge"},{"key":"ref22","author":"Liu","year":"2024","journal-title":"Harnessing webpage uis for text-rich visual understanding"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4187-3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref26","article-title":"MMDU: A multi-turn multi-image dialog understanding benchmark and instruction-tuning dataset for lvlms","author":"Liu","year":"2024","journal-title":"NeurIPS Datasets and Benchmarks Track"},{"key":"ref27","article-title":"A comprehensive survey on instruction following","author":"Lou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","article-title":"Wildvision: Evaluating vision-language models in the wild with human preferences","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Wizardcoder: Empowering code large language models with evol-instruct","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"MMLongBench-Doc: Benchmarking long-context document understanding with visualizations","author":"Ma","year":"2024","journal-title":"NeurIPS Datasets and Benchmarks Track"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref32","article-title":"GPT-4 technical report","year":"2023","journal-title":"arXiv preprint"},{"key":"ref33","year":"2023","journal-title":"GPT-4V(ision) System Card"},{"key":"ref34","article-title":"MIA-Bench: Towards better instruction following evaluation of multimodal 11 ms","author":"Qian","year":"2025","journal-title":"ICLR"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.772"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref38","article-title":"Hi Robot: Open-ended instruction following with hierarchical vision-language-action models","author":"Shi","year":"2025","journal-title":"arXiv preprint"},{"key":"ref39","author":"Song","year":"2024","journal-title":"Milebench: Benchmarking mllms in long context"},{"key":"ref40","author":"Wang","year":"2024","journal-title":"Muirbench: A comprehensive benchmark for robust multiimage understanding"},{"key":"ref41","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":"ref42","article-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"Videorope: What makes for good video rotary position embedding?","author":"Wei","year":"2025","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Wizardlm: Empowering large language models to follow complex instructions","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.641"},{"key":"ref46","author":"Xu","year":"2024","journal-title":"Visionflan: Scaling human-labeled tasks in visual instruction tuning"},{"key":"ref47","article-title":"MiniCPM-V: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","author":"Ying","year":"2024","journal-title":"Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi"},{"key":"ref49","article-title":"MM-Vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.340"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02214-4"},{"key":"ref53","article-title":"CFBench: A comprehensive constraints-following benchmark for 11 ms","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.1079"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.906"},{"key":"ref56","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","author":"Zheng","year":"2023","journal-title":"NeurIPS Datasets and Benchmarks Track"},{"key":"ref57","article-title":"Instruction-following evaluation for large language models","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Controlled text generation with natural language instructions","author":"Zhou","year":"2023","journal-title":"ICML"}],"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\/11446185.pdf?arnumber=11446185","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:05:43Z","timestamp":1777611943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446185\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00110","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}