{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T04:23:16Z","timestamp":1783225396754,"version":"3.54.6"},"reference-count":57,"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 (NSFC)","doi-asserted-by":"publisher","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\/iccv51701.2025.00012","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"48-58","source":"Crossref","is-referenced-by-count":2,"title":["Token Activation Map to Visually Explain Multimodal LLMs"],"prefix":"10.1109","author":[{"given":"Yi","family":"Li","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hualiang","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinpeng","family":"Ding","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haonan","family":"Wang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaomeng","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology,Department of Electronic and Computer Engineering,Hong Kong SAR,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref2","first-page":"135168","article-title":"Attnlrp: Attentionaware layer-wise relevance propagation for transformers","volume-title":"International Conference on Machine Learning","author":"Achtibat","year":"2024"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02072"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref5","first-page":"435","article-title":"Xai for transformers: Better explanations through conservative propagation","volume-title":"International Conference on Machine Learning","author":"Ali","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref7","first-page":"8182","article-title":"Lvlm-intrepret: An interpretability tool for large vision-language models","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ben","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IITA.2008.259"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00045"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref12","article-title":"Less is more: Fewer interpretable region via submodular subset selection","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen"},{"key":"ref13","article-title":"Microsoft coco captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-9003-6_2"},{"key":"ref15","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00106"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref19","article-title":"Vision transformers need registers","volume-title":"The Twelfth International Conference on Learning Representations","author":"Darcet"},{"key":"ref20","first-page":"41714186","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 conference of the North American chapter of the association for computational linguistics: human language technologies","volume":"1","author":"Devlin","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72390-2_54"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01297"},{"key":"ref23","article-title":"An image is worth 16 16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy","year":"2020"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref25","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3089943"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.34133\/research.0467"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-08987-4"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.caeai.2024.100297"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref31","article-title":"Exploring visual interpretability for contrastive language-image pre-training","author":"Li","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2025.111409"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-023-00952-2"},{"key":"ref35","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3321\/j.issn:0529-6579.2007.z1.029"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref38","article-title":"Smooth grad-cam++: An enhanced inference level visualization technique for deep convolutional neural network models","author":"Omeiza","year":"2019","journal-title":"arXiv preprint arXiv"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00307"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1163\/_afco_asc_2206"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-3020"},{"key":"ref44","article-title":"Causal interpretation of self-attention in pre-trained transformers","volume":"36","author":"Raanan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/wacv57701.2024.00039"},{"key":"ref47","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref48","volume-title":"Understanding how vision-language models reason when solving visual math problems","author":"Tey"},{"key":"ref49","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","article-title":"Interpretable bilingual multimodal large language model for diverse biomedical tasks","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Wang","year":"2025"},{"key":"ref51","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref52","article-title":"Star: A benchmark for situated reasoning in real-world videos","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Wu"},{"key":"ref53","article-title":"Efficient streaming language models with attention sinks","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xiao"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.4135\/9781412952637.n77"},{"key":"ref55","article-title":"From redundancy to relevance: Enhancing explainability in multimodal large language models","volume-title":"Annual Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics","author":"Zhang","year":"2025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_12"}],"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\/11446156.pdf?arnumber=11446156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:16:31Z","timestamp":1777529791000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00012","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}