{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:30:15Z","timestamp":1777865415818,"version":"3.51.4"},"reference-count":61,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62436007"],"award-info":[{"award-number":["62436007"]}],"id":[{"id":"10.13039\/501100001809","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\/iccv51701.2025.00022","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"155-165","source":"Crossref","is-referenced-by-count":0,"title":["Mastering Collaborative Multi-Modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness"],"prefix":"10.1109","author":[{"given":"Qifan","family":"Yu","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhebei","family":"Shen","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongqi","family":"Yue","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Wu","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bosheng","family":"Qin","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqiao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yunfei","family":"Li","sequence":"additional","affiliation":[{"name":"Ant Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juncheng","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siliang","family":"Tang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueting","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00904"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref3","article-title":"Perplexed by perplexity: Perplexity-based data pruning with small reference models","author":"Ankner","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref5","article-title":"What limits virtual agent application? omnibench: A scalable multi-dimensional benchmark for essential virtual agent capabilities","author":"Bu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Instruction mining: High-quality instruction data selection for large language models","author":"Cao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Understanding and mitigating the label noise in pre-training on downstream tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"1081","article-title":"Transferability vs. discriminability: Batch spectral penalization for adversarial domain adaptation","volume-title":"International conference on machine learning","author":"Chen","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref10","article-title":"Mods: Model-oriented data selection for instruction tuning","author":"Du","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Gio: Gradient information optimization for training dataset selection","author":"Everaert","year":"2023","journal-title":"arXiv preprint"},{"key":"ref12","author":"Fu","year":"2024","journal-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681082"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681488"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01046"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00380"},{"key":"ref17","article-title":"Efficient multimodal learning from data-centric perspective","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Multi-if: Benchmarking llms on multiturn and multilingual instructions following","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Align2 llava: Cascaded human and large language model preference alignment for multi-modal instruction curation","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref21","first-page":"1885","article-title":"Understanding black-box predictions via influence functions","volume-title":"International conference on machine learning","author":"Koh","year":"2017"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.291"},{"key":"ref23","article-title":"Mimicit: Multi-modal in-context instruction tuning","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0529"},{"key":"ref26","article-title":"Fine-tuning multimodal 11 ms to follow zero-shot demonstrative instructions","volume-title":"The Twelfth International Conference on Learning Representations","author":"Li","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3274139"},{"key":"ref28","article-title":"From quantity to quality: Boosting llm performance with self-guided data selection for instruction tuning","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref31","article-title":"Data-efficient fine-tuning for 11 m -based recommendation","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Mitigating hallucination in large multi-modal models via robust instruction tuning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Liu","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref34","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref35","article-title":"Less is more: Data value estimation for visual instruction tuning","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"# instag: Instruction tagging for analyzing supervised fine-tuning of large language models","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lu","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.4135\/9780857020123.n242"},{"key":"ref38","article-title":"Towards unified multimodal editing with enhanced knowledge collaboration","author":"Pan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Auto-encoding morph-tokens for multimodal 11 m","author":"Pan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","first-page":"20596","article-title":"Deep learning on a data diet: Finding important examples early in training","volume":"34","author":"Paul","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref41","article-title":"Momentor: Advancing video large language model with fine-grained temporal reasoning","author":"Qian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00312"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-022-00329-y"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref45","article-title":"Data pruning via moving-one-sample-out","author":"Tan","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"issue":"11","key":"ref46","article-title":"Visualizing data using t -sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref47","article-title":"Instructiongpt-4: A 200-instruction paradigm for fine-tuning minigpt-4","author":"Wei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Curriculum learning with quality-driven data selection","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Self-evolved diverse data sampling for efficient instruction tuning","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Icons: Influence consensus for vision-language data selection","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Less: Selecting influential data for targeted instruction tuning","author":"Xia","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","first-page":"24851","article-title":"Investigating why contrastive learning benefits robustness against label noise","volume-title":"International Conference on Machine Learning","author":"Xue","year":"2022"},{"key":"ref53","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01971"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01230"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02433"},{"key":"ref58","article-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref60","article-title":"Lima: Less is more for alignment","author":"Zhou","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref61","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\/11443618.pdf?arnumber=11443618","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:29:28Z","timestamp":1777530568000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443618\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00022","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}