{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T22:13:56Z","timestamp":1784240036884,"version":"3.55.0"},"reference-count":46,"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\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"publisher","award":["2022ZD0114904,NSFC6247070125"],"award-info":[{"award-number":["2022ZD0114904,NSFC6247070125"]}],"id":[{"id":"10.13039\/501100018537","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\/iccv51701.2025.01111","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11948-11957","source":"Crossref","is-referenced-by-count":0,"title":["Embodied Representation Alignment with Mirror Neurons"],"prefix":"10.1109","author":[{"given":"Wentao","family":"Zhu","sequence":"first","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Compter Science, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhining","family":"Zhang","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Compter Science, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuwei","family":"Ren","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yin","family":"Huang","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Xu","sequence":"additional","affiliation":[{"name":"Qualcomm AI Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yizhou","family":"Wang","sequence":"additional","affiliation":[{"name":"Center on Frontiers of Computing Studies, School of Compter Science, Peking University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.59.103006.093639"},{"key":"ref2","volume-title":"Polarnet: 3d point clouds for language-guided robotic manipulation","author":"Chen","year":"2023"},{"key":"ref3","article-title":"Being there: Putting brain, body, and world together again","author":"Clark","year":"1998","journal-title":"MIT press"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/BF00230027"},{"key":"ref5","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2021","journal-title":"ICLR"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.brainres.2006.01.114"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1152\/jn.1995.73.6.2608"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1080\/02643290442000310"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1093\/brain\/119.2.593"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhn181"},{"key":"ref11","article-title":"Act3d: 3d feature field transformers for multi-task robotic manipulation","volume-title":"7th Annual Conference on Robot Learning","author":"Gervet"},{"key":"ref12","article-title":"Rvt: Robotic view transformer for 3d object manipulation","author":"Goyal","year":"2023","journal-title":"CoRL"},{"key":"ref13","doi-asserted-by":"crossref","DOI":"10.15607\/RSS.2024.XX.055","article-title":"Rvt2: Learning precise manipulation from few demonstrations","author":"Goyal","year":"2024","journal-title":"RSS"},{"key":"ref14","article-title":"Instruction-driven history-aware policies for robotic manipulations","volume-title":"6th Annual Conference on Robot Learning","author":"Guhur"},{"key":"ref15","article-title":"Position: The platonic representation hypothesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Huh"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1126\/science.286.5449.2526"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pbio.0030079"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01337"},{"key":"ref20","article-title":"BC-z: Zero-shot task generalization with robotic imitation learning","volume-title":"5th Annual Conference on Robot Learning","author":"Jang"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1006\/nimg.2001.0832"},{"key":"ref22","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.conb.2009.10.006"},{"key":"ref24","first-page":"3519","article-title":"Similarity of neural network representations revisited","volume-title":"International conference on machine learning","author":"Kornblith"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018025"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8624.2012.01735.x"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00725"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01359"},{"key":"ref29","article-title":"Insights on representational similarity in neural networks with canonical correlation","volume":"31","author":"Morcos","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/s00422-002-0318-1"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proceedings of the 38th International Conference on Machine Learning","author":"Radford"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.27.070203.144230"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780199217984.001.0001"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/iros.2013.6696520"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.11.004"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.4324\/9780203850664"},{"key":"ref37","article-title":"Perceiveractor: A multi-task transformer for robotic manipulation","volume-title":"Proceedings of the 6th Conference on Robot Learning (CoRL)","author":"Shridhar"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/S0896-6273(01)00337-3"},{"issue":"86","key":"ref39","first-page":"2579","article-title":"Visualizing data using t -sne","volume":"9","author":"van der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/9780262529365.001.0001","volume-title":"The embodied mind, revised edition: Cognitive science and human experience","author":"Varela","year":"2017"},{"key":"ref41","article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref42","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Yu"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01361"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2025.3550849"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-21738-8_43"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01385"}],"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\/11445341.pdf?arnumber=11445341","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T21:50:56Z","timestamp":1784238656000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445341\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01111","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}