{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:00:24Z","timestamp":1777888824506,"version":"3.51.4"},"reference-count":43,"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":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62121002,U2336206,62372423,62102386"],"award-info":[{"award-number":["62121002,U2336206,62372423,62102386"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00028","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"218-227","source":"Crossref","is-referenced-by-count":0,"title":["Deciphering Cross-Modal Alignment in Large Vision-Language Models Via Modality Integration Rate"],"prefix":"10.1109","author":[{"given":"Qidong","family":"Huang","sequence":"first","affiliation":[{"name":"Alibaba Cloud"}],"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":"Zang","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":"Jiaqi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nenghai","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btl242"},{"key":"ref3","article-title":"Allava: Harnessing gpt4v-synthesized data for a lite vision-language model","author":"Hardy Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_22"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0850"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref8","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models","author":"Fu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"When attention sink emerges in language models: An empirical view","author":"Gu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref12","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref14","article-title":"Codesearchnet challenge: Evaluating the state of semantic code search","author":"Husain","year":"2019","journal-title":"arXiv preprint"},{"key":"ref15","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"International conference on machine learning","author":"Kornblith","year":"2019"},{"key":"ref16","article-title":"Seed-bench: Benchmarking multimodal 11 ms with generative comprehension","author":"Li","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02520"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"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","doi-asserted-by":"publisher","DOI":"10.52202\/079017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref26","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0182"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref31","article-title":"Mm1: Methods, analysis & insights from multimodal 11 m pre-training","author":"McKinzie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref33","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref35","article-title":"Massive activations in large language models","author":"Sun","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal llms","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Efficient streaming language models with attention sinks","author":"Xiao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref40","article-title":"A survey on multimodal large language models","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Mm -vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref43","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\/11444053.pdf?arnumber=11444053","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:59:17Z","timestamp":1777611557000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444053\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00028","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}