{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:28Z","timestamp":1777865488486,"version":"3.51.4"},"reference-count":60,"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\/iccv51701.2025.00450","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4732-4742","source":"Crossref","is-referenced-by-count":0,"title":["Taming the Untamed: Graph-Based Knowledge Retrieval and Reasoning for MLLMs to Conquer the Unknown"],"prefix":"10.1109","author":[{"given":"Bowen","family":"Wang","sequence":"first","affiliation":[{"name":"Osaka University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhouqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Osaka University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yasuaki","family":"Susumu","sequence":"additional","affiliation":[{"name":"Osaka University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shotaro","family":"Miwa","sequence":"additional","affiliation":[{"name":"Osaka University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianwei","family":"Chen","sequence":"additional","affiliation":[{"name":"Osaka University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuta","family":"Nakashima","sequence":"additional","affiliation":[{"name":"Osaka University,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"GPT-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","volume-title":"Anthropic. The claude 3 model family: Opus, sonnet, haiku","year":"2024"},{"key":"ref3","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3416292"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1376616.1376746"},{"key":"ref6","article-title":"Visual rag: Expanding mllm visual knowledge without fine-tuning","author":"Bonomo","year":"2025","journal-title":"arXiv preprint"},{"key":"ref7","first-page":"1818","article-title":"Wiki-llava: Hierarchical retrieval-augmented generation for multimodal 11 ms","volume-title":"CVPR","author":"Caffagni","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1189"},{"key":"ref9","article-title":"Can vlms play action role-playing games? take black myth wukong as a study case","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.375"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.925"},{"key":"ref12","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":"ref13","article-title":"Knowledge graphs meet multimodal learning: A comprehensive survey","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref15","article-title":"From local to global: A graph rag approach to queryfocused summarization","author":"Edge","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Karpa: A trainingfree method of adapting knowledge graph as references for large language model\u2019s reasoning path aggregation","author":"Fang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-68204-4_8"},{"key":"ref18","article-title":"Retrieval-augmented generation for large language models: A survey","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.70"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.132"},{"key":"ref22","article-title":"G-retriever: Retrieval-augmented generation for textual graph understanding and question answering","author":"He","year":"2024","journal-title":"NeurIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.597"},{"issue":"2","key":"ref24","first-page":"494","article-title":"A survey on knowledge graphs: Representation, acquisition, and applications","volume":"33","author":"Ji","year":"2021","journal-title":"TNNLS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.446"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.574"},{"key":"ref27","first-page":"2637","article-title":"Mmchatalign: A novel multimodal reasoning framework based on large language models for entity alignment","author":"Jiang","year":"2024","journal-title":"Findings of EMNLP"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3469578"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.579"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.70"},{"key":"ref32","article-title":"Videochat-flash: Hierarchical compression for long-context video modeling","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Benchmarking multimodal retrieval augmented generation with dynamic vqa dataset and selfadaptive planning agent","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.772"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21348-0_30"},{"key":"ref36","author":"Lu","year":"2024","journal-title":"Ovis: Structural embedding alignment for multimodal large language model"},{"key":"ref37","article-title":"Graph-constrained reasoning: Faithful reasoning on knowledge graphs with large language models","author":"Luo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-024-10825-z"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.217"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3777378"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00121"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_9"},{"key":"ref43","volume-title":"Stepfun. Step-1o","year":"2024"},{"key":"ref44","article-title":"Hybrid rag-empowered multi-modal 11 m for secure data management in internet of medical things: A diffusion-based contract approach","author":"Su","year":"2024","journal-title":"IEEE Internet of Things Journal"},{"key":"ref45","article-title":"Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph","volume-title":"ICLR","author":"Sun","year":"2025"},{"key":"ref46","article-title":"Multi-agent collaboration: Harnessing the power of intelligent 11 m agents","author":"Talebirad","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref48","first-page":"74999","article-title":"Direct: Diagnostic reasoning for clinical notes via large language models","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref49","article-title":"Exploring the reasoning abilities of multimodal large language models (mllms): A comprehensive survey on emerging trends in multimodal reasoning","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Internvideo2. 5: Empowering video mllms with long and rich context modeling","author":"Wang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.108"},{"key":"ref52","article-title":"Deepseek-vl2: Mixture-ofexperts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00913"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25445"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s41019-025-00335-5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.314"},{"key":"ref59","first-page":"46595","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","volume":"36","author":"Zheng","year":"2023","journal-title":"NeurIPS"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tkde.2022.3224228"}],"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\/11445544.pdf?arnumber=11445544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:39:16Z","timestamp":1777531156000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445544\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00450","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}