{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:11Z","timestamp":1777889651204,"version":"3.51.4"},"reference-count":54,"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\/iccv51701.2025.02205","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"23752-23762","source":"Crossref","is-referenced-by-count":0,"title":["LangBridge: Interpreting Image as a Combination of Language Embeddings"],"prefix":"10.1109","author":[{"given":"Jiaqi","family":"Liao","sequence":"first","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuwei","family":"Niu","sequence":"additional","affiliation":[{"name":"Peking University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanqing","family":"Meng","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changyao","family":"Tian","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinuo","family":"Du Yuwen Xiong","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dianqi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xizhou","family":"Zhu","sequence":"additional","affiliation":[{"name":"Tsinghua University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Yuan","sequence":"additional","affiliation":[{"name":"Peking University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jifeng","family":"Dai","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong,Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"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":"Rt-2: Vision-language-action models transfer web knowledge to robotic control","author":"Brohan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Ict: Image-object cross-level trusted intervention for mitigating object hallucination in large vision-language models","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref7","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","article-title":"Llama-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"ref10","article-title":"Deciphering cross-modal alignment in large vision-language models with modality integration rate","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref12","article-title":"What\u2019s in the image? a deep-dive into the vision of vision language models","author":"Kaduri","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","first-page":"19730","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":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.20"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.342"},{"key":"ref17","article-title":"Moe-llava: Mixture of experts for large visionlanguage models","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref19","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72658-3_13"},{"key":"ref21","article-title":"Deepseek-vl: towards real-world visionlanguage understanding","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Ovis: Structural embedding alignment for multimodal large language model","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/info16080688"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/979-8-8688-0583-7_10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3744746"},{"key":"ref26","article-title":"Wise: A world knowledge-informed semantic evaluation for text-toimage generation","author":"Niu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","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":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-022-00329-y"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72943-0_15"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref33","article-title":"How to bridge the gap between modalities: A comprehensive survey on multimodal large language model","author":"Song","year":"2023","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Eva-clip: Improved training techniques for clip at scale","author":"Sun","year":"2023","journal-title":"arXiv preprint"},{"key":"ref35","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal 11 ms","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","first-page":"9568","article-title":"Eyes wide shut? exploring the visual shortcomings of multimodal 11 ms","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Tong","year":"2024"},{"key":"ref37","article-title":"Pargo: Bridging vision-language with partial and global views","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Lanp: Rethinking the impact of language priors in large vision-language models","author":"Wu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Qwen 2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Qwen 2.5 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","article-title":"Law of vision representation in mllms","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","article-title":"Dense connector for mllms","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref43","article-title":"A survey on multimodal large language models","author":"Yin","year":"2023","journal-title":"arXiv preprint"},{"key":"ref44","article-title":"Sea: Supervised embedding alignment for token-level visual-textual integration in mllms","author":"Yin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref45","article-title":"Kola: Carefully benchmarking world knowledge of large language models","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Mm-vet: Evaluating large multimodal models for integrated capabilities","author":"Yu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.738"},{"key":"ref49","article-title":"Large multi-modal models can interpret features in large multimodal models","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"A survey of large language models","author":"Xin Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_24"},{"key":"ref52","article-title":"Llmbind: A unified modality-task integration framework","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2025\/1202"}],"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\/11443363.pdf?arnumber=11443363","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:15:03Z","timestamp":1777612503000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443363\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02205","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}