{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:07:22Z","timestamp":1779944842399,"version":"3.53.1"},"reference-count":99,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:00:00Z","timestamp":1773964800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000002","name":"NIH","doi-asserted-by":"publisher","award":["R01AG089169"],"award-info":[{"award-number":["R01AG089169"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,20]]},"DOI":"10.1109\/3dv69130.2026.00175","type":"proceedings-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T19:40:49Z","timestamp":1779910849000},"page":"1-17","source":"Crossref","is-referenced-by-count":0,"title":["SocialGen: Modeling Multi-Human Social Interaction with Language Models"],"prefix":"10.1109","author":[{"given":"Heng","family":"Yu","sequence":"first","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juze","family":"Zhang","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changan","family":"Chen","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiange","family":"Xiang","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusu","family":"Fang","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan Carlos","family":"Niebles","sequence":"additional","affiliation":[{"name":"Stanford University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ehsan","family":"Adeli","sequence":"additional","affiliation":[{"name":"Stanford 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":"10.1109\/CVPR52729.2023.00843"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.173"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00062"},{"key":"ref5","article-title":"The language of motion: Unifying verbal and non-verbal language of 3d human motion","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"X-llm: Bootstrapping advanced large language models by treating multi-modalities as foreign languages","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3242152"},{"issue":"70","key":"ref10","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"ref12","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_6"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00204"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_24"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657447"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00912"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF02291478"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01271"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02510"},{"key":"ref28","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3155"},{"key":"ref30","article-title":"Interact: Capture and modelling of realistic, expressive and interactive activities between two persons in daily scenarios","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_11"},{"key":"ref32","article-title":"Intermask: 3d human interaction generation via collaborative masked modelling","author":"Gohar Javed","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01113"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref37","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International conference on machine learning","author":"Li","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02042-6"},{"key":"ref39","first-page":"1","article-title":"Generating animated videos of human activities from natural language descriptions","volume":"1","author":"Lin","year":"2018","journal-title":"Learning"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1099"},{"key":"ref41","article-title":"Chathuman: Language-driven 3d human understanding with retrieval-augmented tool reasoning","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref42","first-page":"arXiv-2402","article-title":"World model on million-length video and language with ringattention","author":"Liu","year":"2024","journal-title":"arXiv e-prints"},{"key":"ref43","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":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref45","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref46","article-title":"Humantomato: Text-aligned whole-body motion generation","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0879"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00799"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00132"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.497"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00991"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00101"},{"key":"ref55","article-title":"Gpt-4o-mini: Advancing cost-efficient intelligence","volume-title":"OpenAI","year":"2024"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2011"},{"key":"ref57","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01080"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2018.07.006"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"issue":"8","key":"ref64","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"issue":"140","key":"ref65","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref66","article-title":"Generating diverse high-fidelity images with vq-vae-2","volume":"32","author":"Razavi","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00200"},{"key":"ref68","article-title":"Laion- 400 m: Open dataset of clip-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Human motion diffusion as a generative prior","author":"Shafir","year":"2023","journal-title":"arXiv preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73650-6_5"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i11.37878"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01466"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1145\/3687951"},{"key":"ref74","article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet","year":"2023"},{"key":"ref75","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref77","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2011.6130396"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_3"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"ref82","article-title":"Motionllm: Multimodal motion-language learning with large language models","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref83","article-title":"Next-gpt: Any-to-any multimodal llm","author":"Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00173"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_20"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_36"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.521"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00056"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00140"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00338"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaaiss.v1i1.27474"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_2"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00545"}],"event":{"name":"2026 International Conference on 3D Vision (3DV)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2026,3,20]]},"end":{"date-parts":[[2026,3,23]]}},"container-title":["2026 International Conference on 3D Vision (3DV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11533157\/11533158\/11533191.pdf?arnumber=11533191","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T05:01:28Z","timestamp":1779944488000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11533191\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,20]]},"references-count":99,"URL":"https:\/\/doi.org\/10.1109\/3dv69130.2026.00175","relation":{},"subject":[],"published":{"date-parts":[[2026,3,20]]}}}