{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T15:31:06Z","timestamp":1778254266566,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":79,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,9,28]]},"DOI":"10.1145\/3746059.3747673","type":"proceedings-article","created":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T07:49:12Z","timestamp":1758959352000},"page":"1-18","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["Can You Move These Over There? Exploring an LLM-based VR Mover to Support Natural Multi-object Manipulation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4772-7210","authenticated-orcid":false,"given":"Xiangzhi Eric","family":"Wang","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8377-0216","authenticated-orcid":false,"given":"Zackary P. T.","family":"Sin","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0457-8083","authenticated-orcid":false,"given":"Ye","family":"Jia","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2525-8054","authenticated-orcid":false,"given":"Dan","family":"Archer","sequence":"additional","affiliation":[{"name":"University College London, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-6625-4993","authenticated-orcid":false,"given":"Wynonna H. Y.","family":"Fong","sequence":"additional","affiliation":[{"name":"Heep Yunn School, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3370-471X","authenticated-orcid":false,"given":"Qing","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3782-0737","authenticated-orcid":false,"given":"Chen","family":"Li","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,27]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3661547"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Elizabeth\u00a0E Austin and Naomi Sweller. 2014. Presentation and production: The role of gesture in spatial communication. Journal of experimental child psychology 122 (2014) 92\u2013103.","DOI":"10.1016\/j.jecp.2013.12.008"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Edward Awh Brian Barton and Edward\u00a0K. Vogel. 2007. Visual Working Memory Represents a Fixed Number of Items Regardless of Complexity. Psychological Science 18 7 (2007) 622\u2013628.","DOI":"10.1111\/j.1467-9280.2007.01949.x"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3532106.3533452"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"crossref","unstructured":"Alan Baddeley. 2003. Working memory: looking back and looking forward. Nature reviews neuroscience 4 10 (2003) 829\u2013839.","DOI":"10.1038\/nrn1201"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/VR55154.2023.00018"},{"key":"e_1_3_3_2_8_2","unstructured":"Miguel\u00a0Angel Bautista Pengsheng Guo Samira Abnar Walter Talbott Alexander Toshev Zhuoyuan Chen Laurent Dinh Shuangfei Zhai Hanlin Goh Daniel Ulbricht et\u00a0al. 2022. GAUDI: A Neural Architect for Immersive 3D Scene Generation. Advances in Neural Information Processing Systems 35 (2022) 25102\u201325116."},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/GEM61861.2024.10585452"},{"key":"e_1_3_3_2_10_2","series-title":"(SIGGRAPH \u201980)","first-page":"262","volume-title":"Proceedings of the 7th Annual Conference on Computer Graphics and Interactive Techniques","author":"Bolt Richard\u00a0A.","year":"1980","unstructured":"Richard\u00a0A. Bolt. 1980. \u201cPut-that-there\u201d: Voice and gesture at the graphics interface. In Proceedings of the 7th Annual Conference on Computer Graphics and Interactive Techniques(SIGGRAPH \u201980). 262\u2013270."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Gunnar\u00a0A Borg. 1982. Psychophysical bases of perceived exertion. Medicine and science in sports and exercise 14 5 (1982) 377\u2013381.","DOI":"10.1249\/00005768-198205000-00012"},{"key":"e_1_3_3_2_12_2","unstructured":"J Brooke. 1996. SUS: A quick and dirty usability scale. Usability Evaluation in Industry (1996)."},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1145\/1640233.1640255"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642041"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Sharon\u00a0Rose Clay and Jane Wilhelms. 1996. Put: Language-based interactive manipulation of objects. IEEE Computer Graphics and Applications 16 2 (1996) 31\u201339.","DOI":"10.1109\/38.486678"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3489849.3489853"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642579"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-42293-5_11"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581004"},{"key":"e_1_3_3_2_20_2","unstructured":"Weixi Feng Wanrong Zhu Tsu-jui Fu Varun Jampani Arjun Akula Xuehai He Sugato Basu Xin\u00a0Eric Wang and William\u00a0Yang Wang. 2024. LayoutGPT: Compositional Visual Planning and Generation with Large Language Models. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_3_2_21_2","unstructured":"Jorge Askur\u00a0Vazquez Fernandez Jae\u00a0Joong Lee Santiago Andr\u00e9s\u00a0Serrano Vacca Alejandra Magana Bedrich Benes and Voicu Popescu. 2024. Hands-Free VR. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.15083 (2024)."},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Rachel\u00a0L. Franz Sasa Junuzovic and Martez Mott. 2024. A Virtual Reality Scene Taxonomy: Identifying and Designing Accessible Scene-Viewing Techniques. ACM Trans. Comput.-Hum. Interact. 31 2 Article 23 (2024) 44\u00a0pages.","DOI":"10.1145\/3635142"},{"key":"e_1_3_3_2_23_2","series-title":"(ECCV \u201924)","first-page":"52","volume-title":"European Conference on Computer Vision","author":"Fu Rao","year":"2024","unstructured":"Rao Fu, Zehao Wen, Zichen Liu, and Srinath Sridhar. 2024. AnyHome: Open-Vocabulary Generation of Structured and Textured 3D Homes. In European Conference on Computer Vision(ECCV \u201924). 52\u201370."},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Zaifeng Gao and Shlomo Bentin. 2011. Coarse-to-fine encoding of spatial frequency information into visual short-term memory for faces but impartial decay. Journal of Experimental Psychology: Human Perception and Performance 37 4 (2011) 1051.","DOI":"10.1037\/a0023091"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"crossref","unstructured":"Zaifeng Gao Xiaowei Ding Tong Yang Junying Liang and Rende Shui. 2013. Coarse-to-fine construction for high-resolution representation in visual working memory. PLoS One 8 2 (2013) e57913.","DOI":"10.1371\/journal.pone.0057913"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"publisher","DOI":"10.1109\/VR58804.2024.00078"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"crossref","unstructured":"P\u00a0Christopher Gloumeau Wolfgang Stuerzlinger and JungHyun Han. 2020. PinNPivot: Object Manipulation Using Pins in Immersive Virtual Environments. IEEE Transactions on Visualization and Computer Graphics 27 4 (2020) 2488\u20132494.","DOI":"10.1109\/TVCG.2020.2987834"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"Barbara G\u00f6bl Simone Kriglstein and Helmut Hlavacs. 2021. Conversational Interfaces in Serious Games: Identifying Potentials and Future Research Directions based on a Systematic Literature Review. CSEDU (1) (2021) 108\u2013115.","DOI":"10.5220\/0010447301080115"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487797"},{"key":"e_1_3_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-57987-0_41"},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1177\/154193120605000909"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Daniel Hepperle Yannick Wei\u00df Andreas Siess and Matthias W\u00f6lfel. 2019. 2D 3D or speech? A case study on which user interface is preferable for what kind of object interaction in immersive virtual reality. Computers & Graphics 82 (2019) 321\u2013331.","DOI":"10.1016\/j.cag.2019.06.003"},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Kenneth\u00a0P. Herndon Andries van Dam and Michael Gleicher. 1994. The challenges of 3D interaction: a CHI \u201994 workshop. SIGCHI Bull. 26 4 (Oct. 1994) 36\u201343.","DOI":"10.1145\/191642.191652"},{"key":"e_1_3_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/VR55154.2023.00028"},{"key":"e_1_3_3_2_35_2","unstructured":"Xiyun Hu Dizhi Ma Fengming He Zhengzhe Zhu Shao-Kang Hsia Chenfei Zhu Ziyi Liu and Karthik Ramani. 2025. GesPrompt: Leveraging Co-Speech Gestures to Augment LLM-Based Interaction in Virtual Reality. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.05441 (2025)."},{"key":"e_1_3_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/97243.97246"},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/3025453.3025523"},{"key":"e_1_3_3_2_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICTEST60614.2024.10576146"},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3631802.3631806"},{"key":"e_1_3_3_2_40_2","doi-asserted-by":"crossref","unstructured":"Daehwa Kim Vimal Mollyn and Chris Harrison. 2023. WorldPoint: Finger Pointing as a Rapid and Natural Trigger for In-the-Wild Mobile Interactions. Proceedings of the ACM on Human-Computer Interaction 7 ISS (2023) 357\u2013375.","DOI":"10.1145\/3626478"},{"key":"e_1_3_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/1240624.1240782"},{"key":"e_1_3_3_2_42_2","doi-asserted-by":"crossref","unstructured":"Ahmet\u00a0Baki Kocaballi Liliana Laranjo and Enrico Coiera. 2019. Understanding and measuring user experience in conversational interfaces. Interacting with Computers 31 2 (2019) 192\u2013207.","DOI":"10.1093\/iwc\/iwz015"},{"key":"e_1_3_3_2_43_2","volume-title":"3D user interfaces: theory and practice","author":"LaViola\u00a0Jr Joseph\u00a0J","year":"2017","unstructured":"Joseph\u00a0J LaViola\u00a0Jr, Ernst Kruijff, Ryan\u00a0P McMahan, Doug Bowman, and Ivan\u00a0P Poupyrev. 2017. 3D user interfaces: theory and practice. Addison-Wesley Professional."},{"key":"e_1_3_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642230"},{"key":"e_1_3_3_2_45_2","doi-asserted-by":"crossref","unstructured":"Xiaolong Liu Lili Wang Wei Ke and Sio-Kei Im. 2024. Object manipulation based on the head manipulation space in VR. International Journal of Human-Computer Studies (2024) 103346.","DOI":"10.1016\/j.ijhcs.2024.103346"},{"key":"e_1_3_3_2_46_2","first-page":"37","volume-title":"Psychology of Learning and Motivation","author":"Logie Robert\u00a0H","year":"2003","unstructured":"Robert\u00a0H Logie. 2003. Spatial and visual working memory: A mental workspace. In Psychology of Learning and Motivation. Vol.\u00a042. 37\u201378."},{"key":"e_1_3_3_2_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/2658537.2658541"},{"key":"e_1_3_3_2_48_2","doi-asserted-by":"crossref","unstructured":"Daniel Mendes Fabio\u00a0Marco Caputo Andrea Giachetti Alfredo Ferreira and Joaquim Jorge. 2019. A Survey on 3D Virtual Object Manipulation: From the Desktop to Immersive Virtual Environments. Computer Graphics Forum 38 1 21\u201345.","DOI":"10.1111\/cgf.13390"},{"key":"e_1_3_3_2_49_2","doi-asserted-by":"publisher","DOI":"10.1145\/3139131.3139157"},{"key":"e_1_3_3_2_50_2","unstructured":"Meta. 2024. Llama 3.1. https:\/\/llama.meta.com\/ Accessed: 2024-9-13."},{"key":"e_1_3_3_2_51_2","unstructured":"Microsoft. 2024. How to generate reproducible output with Azure OpenAI Service - Azure OpenAI. https:\/\/learn.microsoft.com\/en-us\/azure\/ai-services\/openai\/how-to\/reproducible-output Accessed: 2024-09-11."},{"key":"e_1_3_3_2_52_2","doi-asserted-by":"crossref","unstructured":"George\u00a0A Miller. 1956. The Magical Number Seven Plus or Minus Two: Some Limits on Our Capacity for Processing Information. Psychological Review 63 2 (1956) 81.","DOI":"10.1037\/h0043158"},{"key":"e_1_3_3_2_53_2","doi-asserted-by":"publisher","DOI":"10.1109\/VRW50115.2020.00074"},{"key":"e_1_3_3_2_54_2","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173580"},{"key":"e_1_3_3_2_55_2","doi-asserted-by":"publisher","DOI":"10.5555\/2821575"},{"key":"e_1_3_3_2_56_2","unstructured":"Ba\u015fak\u00a0Melis \u00d6cal Maxim Tatarchenko Sezer Karaoglu and Theo Gevers. 2024. SceneTeller: Language-to-3D Scene Generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.20727 (2024)."},{"key":"e_1_3_3_2_57_2","unstructured":"OpenAI. 2024. Hello GPT-4o. https:\/\/openai.com\/index\/hello-gpt-4o\/ Accessed: 2024-9-13."},{"key":"e_1_3_3_2_58_2","doi-asserted-by":"publisher","DOI":"10.1109\/VR58804.2024.00088"},{"key":"e_1_3_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1145\/237091.237102"},{"key":"e_1_3_3_2_60_2","doi-asserted-by":"crossref","unstructured":"Jesse Sargent Stephen Dopkins John Philbeck and David Chichka. 2010. Chunking in spatial memory. Journal of Experimental Psychology: Learning memory and cognition 36 3 (2010) 576.","DOI":"10.1037\/a0017528"},{"key":"e_1_3_3_2_61_2","volume-title":"Can You Use a Single Item to Predict SUS Scores?","author":"Sauro Jeff","year":"2018","unstructured":"Jeff Sauro. 2018. Can You Use a Single Item to Predict SUS Scores?Retrieved Sep 13, 2024 from https:\/\/measuringu.com\/single-item-sus\/"},{"key":"e_1_3_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-155860594-7\/50014-X"},{"key":"e_1_3_3_2_63_2","doi-asserted-by":"crossref","unstructured":"Martin Schrepp Andreas Hinderks et\u00a0al. 2017. Design and evaluation of a short version of the user experience questionnaire (UEQ-S). International Journal of Interactive Multimedia and Artificial Intelligence 4 6 (2017) 103\u2013108.","DOI":"10.9781\/ijimai.2017.09.001"},{"key":"e_1_3_3_2_64_2","doi-asserted-by":"publisher","DOI":"10.1145\/3570945.3607317"},{"key":"e_1_3_3_2_65_2","doi-asserted-by":"crossref","unstructured":"Yasuko Sugase Shigeru Yamane Shoogo Ueno and Kenji Kawano. 1999. Global and fine information coded by single neurons in the temporal visual cortex. Nature 400 6747 (1999) 869\u2013873.","DOI":"10.1038\/23703"},{"key":"e_1_3_3_2_66_2","doi-asserted-by":"publisher","DOI":"10.1145\/3290605.3300243"},{"key":"e_1_3_3_2_67_2","doi-asserted-by":"crossref","unstructured":"Mirko Thalmann Alessandra\u00a0S Souza and Klaus Oberauer. 2019. How does chunking help working memory? Journal of Experimental Psychology: Learning Memory and Cognition 45 1 (2019) 37.","DOI":"10.1037\/xlm0000578"},{"key":"e_1_3_3_2_68_2","doi-asserted-by":"crossref","unstructured":"Leslie\u00a0G Ungerleider Susan\u00a0M Courtney and James\u00a0V Haxby. 1998. A neural system for human visual working memory. Proceedings of the National Academy of Sciences 95 3 (1998) 883\u2013890.","DOI":"10.1073\/pnas.95.3.883"},{"key":"e_1_3_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613905.3651026"},{"key":"e_1_3_3_2_70_2","unstructured":"Can Wang Hongliang Zhong Menglei Chai Mingming He Dongdong Chen and Jing Liao. 2024. Chat2Layout: Interactive 3D Furniture Layout with a Multimodal LLM. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21333 (2024)."},{"key":"e_1_3_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643834.3661542"},{"key":"e_1_3_3_2_72_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642235"},{"key":"e_1_3_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01428"},{"key":"e_1_3_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2018.8446381"},{"key":"e_1_3_3_2_75_2","doi-asserted-by":"crossref","unstructured":"Bob\u00a0G Witmer Christian\u00a0J Jerome and Michael\u00a0J Singer. 2005. The factor structure of the presence questionnaire. Presence: Teleoperators & Virtual Environments 14 3 (2005) 298\u2013312.","DOI":"10.1162\/105474605323384654"},{"key":"e_1_3_3_2_76_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642517"},{"key":"e_1_3_3_2_77_2","doi-asserted-by":"crossref","unstructured":"Chaoxiong Ye Tengfei Liang Yin Zhang Qianru Xu Yongjie Zhu and Qiang Liu. 2020. The two-stage process in visual working memory consolidation. Scientific reports 10 1 (2020) 13564.","DOI":"10.1038\/s41598-020-70418-y"},{"key":"e_1_3_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1145\/3411764.3445343"},{"key":"e_1_3_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676451"},{"key":"e_1_3_3_2_80_2","doi-asserted-by":"publisher","DOI":"10.1145\/3562939.3565637"}],"event":{"name":"UIST '25: The 38th Annual ACM Symposium on User Interface Software and Technology","location":"Busan Republic of Korea","acronym":"UIST '25","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGGRAPH ACM Special Interest Group on Computer Graphics and Interactive Techniques"]},"container-title":["Proceedings of the 38th Annual ACM Symposium on User Interface Software and Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746059.3747673","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T22:09:14Z","timestamp":1759010954000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746059.3747673"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,27]]},"references-count":79,"alternative-id":["10.1145\/3746059.3747673","10.1145\/3746059"],"URL":"https:\/\/doi.org\/10.1145\/3746059.3747673","relation":{},"subject":[],"published":{"date-parts":[[2025,9,27]]},"assertion":[{"value":"2025-09-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}