{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T21:30:24Z","timestamp":1778103024891,"version":"3.51.4"},"reference-count":79,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100009950","name":"Ministry of Education","doi-asserted-by":"publisher","award":["MOET2EP20221-0012"],"award-info":[{"award-number":["MOET2EP20221-0012"]}],"id":[{"id":"10.13039\/100009950","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,16]]},"DOI":"10.1109\/cvpr52733.2024.00062","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T17:34:53Z","timestamp":1726508093000},"page":"582-592","source":"Crossref","is-referenced-by-count":24,"title":["Digital Life Project: Autonomous 3D Characters with Social Intelligence"],"prefix":"10.1109","author":[{"given":"Zhongang","family":"Cai","sequence":"first","affiliation":[{"name":"S-Lab, Nanyang Technological University"}]},{"given":"Jianping","family":"Jiang","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Zhongfei","family":"Qing","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Xinying","family":"Guo","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University"}]},{"given":"Mingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University"}]},{"given":"Zhengyu","family":"Lin","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Haiyi","family":"Mei","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Chen","family":"Wei","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Ruisi","family":"Wang","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University"}]},{"given":"Wanqi","family":"Yin","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Liang","family":"Pan","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University"}]},{"given":"Xiangyu","family":"Fan","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Han","family":"Du","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Peng","family":"Gao","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Zhitao","family":"Yang","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Yang","family":"Gao","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Jiaqi","family":"Li","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Tianxiang","family":"Ren","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Yukun","family":"Wei","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Xiaogang","family":"Wang","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University"}]},{"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"Sense Time Research"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University"}]}],"member":"263","reference":[{"key":"ref1","first-page":"337","article-title":"Using large language models to simulate multiple humans and replicate human subject studies","volume-title":"International Conference on Machine Learning","author":"Aher"},{"key":"ref2","article-title":"Do as i can, not as i say: Grounding language in robotic affordances","author":"Ahn","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref4","volume-title":"Social penetration: The development of interpersonal relationships","author":"Altman","year":"1973"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1017\/pan.2023.2"},{"key":"ref6","volume-title":"Social learning theory","author":"Bandura","year":"1977"},{"key":"ref7","doi-asserted-by":"crossref","DOI":"10.4135\/9781412982818","volume-title":"The handbook of communication science. Sage","author":"Berger","year":"2010"},{"key":"ref8","article-title":"Smpler-x: Scaling up expressive human pose and shape estimation","author":"Cai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.73.1.19"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.55.090902.142015"},{"key":"ref12","article-title":"Motion matching and the road to next-gen animation","volume-title":"Proc. of GDC","author":"Clavet","year":"2016"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1037\/0003-066X.59.8.676"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1037\/0033-2909.98.2.310"},{"key":"ref15","first-page":"179","article-title":"The revised neo person-ality inventory (neo-pi-r)","author":"Costa","year":"2008","journal-title":"The SAGE handbook of personal-ity theory and assessment"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1037\/0022-3514.93.5.880"},{"key":"ref17","article-title":"Glm: General language model pretraining with autoregressive blank infilling","author":"Du","year":"2021","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1080\/14330237.2015.1124603"},{"key":"ref19","article-title":"Manual of the Eysenck Personality Questionnaire (junior & adult)","author":"Jurgen Eysenck","year":"1975","journal-title":"Hodder and Stoughton Educational"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4607026"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref22","article-title":"Remos: Reactive 3d motion synthesis for two-person interactions","volume-title":"arXiv, 2023","author":"Ghosh"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref25","volume-title":"The hidden dimension","author":"Hall","year":"1966"},{"key":"ref26","volume-title":"The silent language","author":"Hall","year":"1973"},{"key":"ref27","article-title":"A multipha-sic personality schedule (minnesota): I. construction of the schedule","volume-title":"The Journal of Psychology","author":"Hathaway","year":"1940"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.4324\/9780203781159"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.94.3.319"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392440"},{"key":"ref31","article-title":"Inner monologue: Em-bodied reasoning through planning with language models","author":"Huang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref32","volume-title":"The principles of psychology","author":"James","year":"2007"},{"key":"ref33","volume-title":"The big-five trait taxonomy: History, measurement, and theoretical perspectives","author":"Oliver","year":"1999"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref35","article-title":"Intergen: Diffusion-based multi-human motion generation under complex interactions","author":"Liang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref37","article-title":"Manual: A guide to the development and use of the myers-briggs type indicator","author":"Myers","year":"1985","journal-title":"(No Title)"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1037\/h0046141"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21236\/ADA222909"},{"key":"ref40","article-title":"Gpt-4 technical report","year":"2023","journal-title":"OpenAI"},{"key":"ref41","article-title":"Social simulacra: Creating populated prototypes for social computing systems","author":"Sung Park","year":"2022","journal-title":"UIST"},{"key":"ref42","article-title":"Generative agents: Interactive simulacra of human behavior","volume-title":"the 36th Annual ACM Symposium on User Interface Software and Technology (UIST 23)","author":"Sung Park","year":"2023"},{"key":"ref43","article-title":"Generative agents: Interactive simulacra of human behavior","author":"Sung Park","year":"2023","journal-title":"UIST"},{"key":"ref44","article-title":"Gorilla: Large language model connected with massive apis","author":"Patil","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3610543.3626176"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1037\/\/0022-3514.49.1.95"},{"key":"ref49","article-title":"Insactor: Instruction-driven physics-based characters","volume":"36","author":"Ren","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-6494.1967.tb01454.x"},{"key":"ref51","article-title":"Personality traits in large language models","author":"Safdari","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Toolformer: Language models can teach themselves to use tools","author":"Schick","year":"2023","journal-title":"arXiv preprint"},{"key":"ref53","volume-title":"Chatgpt: Optimizing language models for dialogue","author":"Schulman","year":"2022"},{"key":"ref54","article-title":"Human motion diffusion as a generative prior","author":"Shafir","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","first-page":"40","article-title":"Conflict-based search for optimal multi-agent pathfinding","volume":"219","author":"Sharon","year":"2015","journal-title":"AI"},{"key":"ref56","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in huggingface","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1080\/00223891.2011.577475"},{"key":"ref58","volume-title":"Duolando: Follower gpt with off-policy reinforcement learning for dance accompaniment","author":"Siyao","year":"2024"},{"key":"ref59","article-title":"Cognitive architectures for language agents","author":"Sumers","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref61","article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","author":"Tevet"},{"key":"ref62","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1037\/0033-295X.94.1.3"},{"key":"ref64","article-title":"Voyager: An open-ended embodied agent with large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"ref66","article-title":"Emergent abilities of large language models","author":"Wei","year":"2022","journal-title":"arXiv preprint"},{"key":"ref67","article-title":"Chain-of-thought prompting elicits reasoning in large language models","author":"Wei","year":"2022","journal-title":"NeurIPS"},{"key":"ref68","article-title":"Inter-x: Towards versatile human-human interaction analysis","volume-title":"arXiv preprint","author":"Xu","year":"2023"},{"key":"ref69","article-title":"Exploring large language models for communication games: An empirical study on werewolf","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref70","article-title":"Tree of thoughts: Deliberate problem solving with large language models","author":"Yao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref71","article-title":"React: Synergizing reasoning and acting in language models","author":"Yao","year":"2023","journal-title":"ICLR"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref73","article-title":"Building cooperative embodied agents modularly with large language models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref74","article-title":"T2m-gpt: Generating human motion from textual de-scriptions with discrete representations","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhang"},{"key":"ref75","article-title":"Motiondif-fuse: Text-driven human motion generation with diffusion model","author":"Zhang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref77","article-title":"Finemogen: Fine-grained spatiotemporal motion generation and editing","volume":"36","author":"Zhang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref79","article-title":"Ghost in the minecraft: Generally capable agents for open-world enviroments via large language models with text-based knowledge and memory","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Seattle, WA, USA","start":{"date-parts":[[2024,6,16]]},"end":{"date-parts":[[2024,6,22]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10654794\/10654797\/10658043.pdf?arnumber=10658043","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,20]],"date-time":"2024-09-20T06:12:26Z","timestamp":1726812746000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10658043\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,16]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.00062","relation":{},"subject":[],"published":{"date-parts":[[2024,6,16]]}}}