{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T02:30:28Z","timestamp":1783996228859,"version":"3.55.0"},"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\/iccv51701.2025.00342","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3585-3595","source":"Crossref","is-referenced-by-count":1,"title":["Knowledge Transfer from Interaction Learning"],"prefix":"10.1109","author":[{"given":"Yilin","family":"Gao","sequence":"first","affiliation":[{"name":"Shanghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kangyi","family":"Chen","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongxing","family":"Peng","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengjie","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shugong","family":"Xu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong-Liverpool University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The platonic representation hypothesis","journal-title":"arXiv preprint arXiv"},{"key":"ref2","article-title":"Frozen transformers in language models are effective visual encoder layers","journal-title":"arXiv preprint arXiv"},{"key":"ref3","article-title":"Can the inference logic of large language models be disentangled into symbolic concepts?","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"},{"key":"ref5","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref6","article-title":"Gemini: A family of highly capable multimodal models","author":"Anil","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01499"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2448"},{"key":"ref9","article-title":"Llavakd: A framework of distilling multimodal large language models","author":"Cai","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00045"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref13","article-title":"Interpreting and controlling vision foundation models via text explanations","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00497"},{"key":"ref15","first-page":"24185","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Chen","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref17","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref19","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.4140\/TCP.n.2015.249"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3557149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3357717"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06668-3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01325"},{"key":"ref25","article-title":"Blip-2 : Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning, pages 1973019742. PMLR","author":"Li","year":"2023"},{"key":"ref26","first-page":"20452","article-title":"Does a neural network really encode symbolic concepts?","volume-title":"International conference on machine learning","author":"Li","year":"2023"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3637265"},{"key":"ref28","article-title":"Advancing object goal navigation through llm-enhanced object affinities transfer","author":"Lin","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref30","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems, 36"},{"key":"ref31","article-title":"Dab-detr: Dynamic anchor boxes are better queries for detr","author":"Liu","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3514094.3534148"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3270479"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01368"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00363"},{"key":"ref38","article-title":"Large language models and cognitive science: A comprehensive review of similarities, differences, and challenges","author":"Niu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","article-title":"Frozen transformers in language models are effective visual encoder layers","author":"Pang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref40","article-title":"Ecor: Explainable clip for object recognition","author":"Rasekh","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Llava-mod: Making llava tiny via moe knowledge distillation","author":"Shu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Lvlm-intrepret: An interpretability tool for large vision-language models","author":"Ben","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","article-title":"Cogvlm: Visual expert for pretrained language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref45","article-title":"Seeing the image: Prioritizing visual correlation by contrastive alignment","author":"Xiao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","article-title":"Deco: Decoupling token compression from semantic abstraction in multimodal large language models","author":"Yao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref47","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","author":"Zagoruyko","year":"2016","journal-title":"arXiv preprint arXiv"},{"key":"ref48","article-title":"Dino: Detr with improved denoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref49","article-title":"Tip-adapter: Training-free clip-adapter for better visionlanguage modeling","author":"Zhang","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref50","article-title":"Sparsevlm: Visual token sparsification for efficient vision-language model inference","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref53","article-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref54","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","journal-title":"arXiv preprint arXiv"}],"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\/11445699.pdf?arnumber=11445699","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:02:48Z","timestamp":1777611768000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445699\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00342","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}