{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:34:54Z","timestamp":1783107294762,"version":"3.54.6"},"reference-count":75,"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\/iccv51701.2025.00948","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10173-10183","source":"Crossref","is-referenced-by-count":1,"title":["Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis"],"prefix":"10.1109","author":[{"given":"Kaiyang","family":"Ji","sequence":"first","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ye","family":"Shi","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zichen","family":"Jin","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kangyi","family":"Chen","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Xu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuexin","family":"Ma","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingyi","family":"Yu","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingya","family":"Wang","sequence":"additional","affiliation":[{"name":"ShanghaiTech University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref3","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"Bengio","year":"2015","journal-title":"Advances in neural information processing systems, 28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"ref5","article-title":"Symbiosim: Human-in-the-loop simulation platform for bidirectional continuing learning in human-robot interaction","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Rhino: Learning real-time humanoid-human-object interaction from human demonstrations","author":"Chen","year":"2025","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657440"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3242152"},{"key":"ref9","article-title":"Human-object interaction via automatically designed vlm-guided motion policy","author":"Deng","year":"2025","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref11","first-page":"8469","article-title":"Palme: an embodied multimodal language model","volume-title":"Proceedings of the 40th International Conference on Machine Learning","author":"Driess","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00054"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref15","article-title":"Omnih2o: Universal and dexterous human-to-humanoid whole-body teleoperation and learning","author":"He","year":"2024","journal-title":"arXiv preprint"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iros58592.2024.10801984"},{"key":"ref17","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems, 30"},{"key":"ref18","article-title":"Generative adversarial imitation learning","author":"Ho","year":"2016","journal-title":"Advances in neural information processing systems, 29"},{"key":"ref19","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0628"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"ref23","article-title":"Intermask: 3d human interaction generation via collaborative masked modelling","author":"Gohar Javed","year":"2024","journal-title":"arXiv preprint"},{"key":"ref24","article-title":"Exbody2: Advanced expressive humanoid whole-body control","author":"Ji","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02504"},{"key":"ref27","article-title":"Arflow: Human action-reaction flow matching with physical guidance","author":"Jiang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref28","author":"Kingma","year":"2013","journal-title":"Auto-encoding variational bayes"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01644"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3528979"},{"key":"ref31","article-title":"Interdance: Reactive 3d dance generation with realistic duet interactions","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref33","article-title":"Chathuman: Language-driven 3d human understanding with retrieval-augmented tool reasoning","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/770"},{"key":"ref35","article-title":"Interactive humanoid: Online full-body motion reaction synthesis with social affordance canonicalization and forecasting","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680636"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"ref39","article-title":"Universal humanoid motion representations for physics-based control","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00061"},{"key":"ref41","article-title":"Isaac gym: High performance gpu-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv preprint"},{"key":"ref42","author":"Park","year":"2024","journal-title":"Using apple vision pro to train and control robots"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201311"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459670"},{"key":"ref47","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01129"},{"key":"ref49","volume-title":"Unitree h1 robot","author":"Robotics","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130883"},{"key":"ref51","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Duolando: Follower gpt with off-policy reinforcement learning for dance accompaniment","author":"Siyao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Denoising diffusion implicit models","author":"Song","journal-title":"arXiv preprint"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392450"},{"key":"ref55","article-title":"Think then react: Towards unconstrained action-to-reaction motion generation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Tan","year":"2025"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01466"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02008"},{"key":"ref58","article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet","year":"2023"},{"key":"ref59","article-title":"Closd: Closing the loop between simulation and diffusion for multi-task character control","author":"Tevet","year":"2024","journal-title":"arXiv preprint"},{"key":"ref60","article-title":"Gaze-guided handobject interaction synthesis: Dataset and method","author":"Tian","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref62","article-title":"Thor: Text to human-object interaction diffusion via relation intervention","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","article-title":"Human-object interaction from human-level instructions","author":"Wu","year":"2024","journal-title":"CoRR"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00212"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00173"},{"key":"ref67","first-page":"56071","article-title":"Guidance with spherical gaussian constraint for conditional diffusion","volume-title":"Proceedings of the 41st International Conference on Machine Learning","author":"Yang","year":"2024"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3592408"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref72","article-title":"Openhoi: Open-world hand-object interaction synthesis with multimodal large language model","author":"Zhang","year":"2025","journal-title":"arXiv preprint"},{"key":"ref73","article-title":"Dart: A diffusion-based autoregressive motion model for real-time text-driven motion control","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref75","article-title":"Unidb: A unified diffusion bridge framework via stochastic optimal control","author":"Zhu","year":"2025","journal-title":"arXiv preprint"}],"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\/11443579.pdf?arnumber=11443579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:00:58Z","timestamp":1777611658000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00948","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}