{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:38:50Z","timestamp":1775230730042,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T00:00:00Z","timestamp":1715385600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,5,11]]},"DOI":"10.1145\/3613904.3642579","type":"proceedings-article","created":{"date-parts":[[2024,5,11]],"date-time":"2024-05-11T08:37:41Z","timestamp":1715416661000},"page":"1-22","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":74,"title":["LLMR: Real-time Prompting of Interactive Worlds using Large Language Models"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4818-4158","authenticated-orcid":false,"given":"Fernanda","family":"De La Torre","sequence":"first","affiliation":[{"name":"BCS, MIT, United States and Microsoft, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4684-7058","authenticated-orcid":false,"given":"Cathy Mengying","family":"Fang","sequence":"additional","affiliation":[{"name":"MIT Media Lab, United States and Microsoft, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9447-835X","authenticated-orcid":false,"given":"Han","family":"Huang","sequence":"additional","affiliation":[{"name":"Mathematics, Rensselaer Polytechnic Institute, United States and Microsoft, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3360-4121","authenticated-orcid":false,"given":"Andrzej","family":"Banburski-Fahey","sequence":"additional","affiliation":[{"name":"Microsoft, United States"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1285-6909","authenticated-orcid":false,"given":"Judith","family":"Amores Fernandez","sequence":"additional","affiliation":[{"name":"Microsoft Research, Microsoft, United States"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7659-2797","authenticated-orcid":false,"given":"Jaron","family":"Lanier","sequence":"additional","affiliation":[{"name":"Microsoft, United States"}]}],"member":"320","published-online":{"date-parts":[[2024,5,11]]},"reference":[{"key":"e_1_3_3_3_1_1","volume-title":"Program Synthesis With Large Language Models. ArXiv Preprint ArXiv:2108.07732","author":"Austin Jacob","year":"2021","unstructured":"Jacob Austin, Augustus Odena, Maxwell Nye, Maarten Bosma, Henryk Michalewski, David Dohan, Ellen Jiang, Carrie Cai, Michael Terry, Quoc Le, 2021. Program Synthesis With Large Language Models. ArXiv Preprint ArXiv:2108.07732 (2021). https:\/\/arxiv.org\/pdf\/2108.07732"},{"key":"e_1_3_3_3_2_1","volume-title":"Keep Me Updated! Memory Management in Long-Term Conversations. ArXiv Preprint ArXiv:2210.08750","author":"Bae Sanghwan","year":"2022","unstructured":"Sanghwan Bae, Donghyun Kwak, Soyoung Kang, Min\u00a0Young Lee, Sungdong Kim, Yuin Jeong, Hyeri Kim, Sang-Woo Lee, Woomyoung Park, and Nako Sung. 2022. Keep Me Updated! Memory Management in Long-Term Conversations. ArXiv Preprint ArXiv:2210.08750 (2022). https:\/\/arxiv.org\/pdf\/2402.11975"},{"key":"e_1_3_3_3_3_1","volume-title":"Game Development and Production","author":"Bethke Erik","unstructured":"Erik Bethke. 2003. Game Development and Production. Wordware Publishing, Inc."},{"key":"e_1_3_3_3_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"e_1_3_3_3_5_1","doi-asserted-by":"publisher","unstructured":"Yifei Cheng Yukang Yan Xin Yi Yuanchun Shi and David Lindlbauer. 2021. Semanticadapt: Optimization-Based Adaptation of Mixed Reality Layouts Leveraging Virtual-Physical Semantic Connections. In The 34th Annual ACM Symposium on User Interface Software and Technology. 282\u2013297. https:\/\/doi.org\/10.1145\/3472749.3474750","DOI":"10.1145\/3472749.3474750"},{"key":"e_1_3_3_3_6_1","volume-title":"Pangu-Coder: Program Synthesis With Function-Level Language Modeling. ArXiv Preprint ArXiv:2207.11280","author":"Christopoulou Fenia","year":"2022","unstructured":"Fenia Christopoulou, Gerasimos Lampouras, Milan Gritta, Guchun Zhang, Yinpeng Guo, Zhongqi Li, Qi Zhang, Meng Xiao, Bo Shen, Lin Li, 2022. Pangu-Coder: Program Synthesis With Function-Level Language Modeling. ArXiv Preprint ArXiv:2207.11280 (2022). https:\/\/arxiv.org\/pdf\/2207.11280"},{"key":"e_1_3_3_3_7_1","unstructured":"Stephanie\u00a0Claudino Daffara Federico Saldarini Balasaravanan\u00a0Thoravi Kumaravel and Bj\u00f8rn Hartmann. 2020. AuthorIVE: Authoring Interactions for Virtual Environments Through Disambiguating Demonstrations. (2020)."},{"key":"e_1_3_3_3_8_1","volume-title":"Palm-E: An Embodied Multimodal Language Model. ArXiv Preprint ArXiv:2303.03378","author":"Driess Danny","year":"2023","unstructured":"Danny Driess, Fei Xia, Mehdi\u00a0SM Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, 2023. Palm-E: An Embodied Multimodal Language Model. ArXiv Preprint ArXiv:2303.03378 (2023). https:\/\/arxiv.org\/pdf\/2303.03378."},{"key":"e_1_3_3_3_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3533376"},{"key":"e_1_3_3_3_10_1","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.12276"},{"key":"e_1_3_3_3_11_1","volume-title":"Nerf: Neural Radiance Field in 3d Vision, a Comprehensive Review. ArXiv Preprint ArXiv:2210.00379","author":"Gao Kyle","year":"2022","unstructured":"Kyle Gao, Yina Gao, Hongjie He, Denning Lu, Linlin Xu, and Jonathan Li. 2022. Nerf: Neural Radiance Field in 3d Vision, a Comprehensive Review. ArXiv Preprint ArXiv:2210.00379 (2022). https:\/\/arxiv.org\/pdf\/2210.00379"},{"key":"e_1_3_3_3_12_1","unstructured":"Google. 2016. Tilt Brush. https:\/\/www.tiltbrush.com\/"},{"key":"e_1_3_3_3_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130804"},{"key":"e_1_3_3_3_14_1","volume-title":"Mustafa Safdari, Yutaka Matsuo, Douglas Eck, and Aleksandra Faust.","author":"Gur Izzeddin","year":"2023","unstructured":"Izzeddin Gur, Hiroki Furuta, Austin Huang, Mustafa Safdari, Yutaka Matsuo, Douglas Eck, and Aleksandra Faust. 2023. A Real-World Webagent With Planning, Long Context Understanding, and Program Synthesis. ArXiv Preprint ArXiv:2307.12856 (2023)."},{"key":"e_1_3_3_3_15_1","volume-title":"Instruct-Nerf2nerf: Editing 3d Scenes With Instructions. ArXiv Preprint ArXiv:2303.12789","author":"Haque Ayaan","year":"2023","unstructured":"Ayaan Haque, Matthew Tancik, Alexei\u00a0A Efros, Aleksander Holynski, and Angjoo Kanazawa. 2023. Instruct-Nerf2nerf: Editing 3d Scenes With Instructions. ArXiv Preprint ArXiv:2303.12789 (2023)."},{"key":"e_1_3_3_3_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581072"},{"key":"e_1_3_3_3_17_1","volume-title":"Text2room: Extracting Textured 3d Meshes From 2d Text-to-Image Models. ArXiv Preprint ArXiv:2303.11989","author":"H\u00f6llein Lukas","year":"2023","unstructured":"Lukas H\u00f6llein, Ang Cao, Andrew Owens, Justin Johnson, and Matthias Nie\u00dfner. 2023. Text2room: Extracting Textured 3d Meshes From 2d Text-to-Image Models. ArXiv Preprint ArXiv:2303.11989 (2023)."},{"key":"e_1_3_3_3_18_1","volume-title":"3D-LLM: Injecting the 3D World Into Large Language Models. ArXiv Preprint ArXiv:2307.12981","author":"Hong Yining","year":"2023","unstructured":"Yining Hong, Haoyu Zhen, Peihao Chen, Shuhong Zheng, Yilun Du, Zhenfang Chen, and Chuang Gan. 2023. 3D-LLM: Injecting the 3D World Into Large Language Models. ArXiv Preprint ArXiv:2307.12981 (2023)."},{"key":"e_1_3_3_3_19_1","volume-title":"Real-time Animation Generation and Control on Rigged Models via Large Language Models. arXiv preprint arXiv:2310.17838","author":"Huang Han","year":"2023","unstructured":"Han Huang, Fernanda De\u00a0La\u00a0Torre, Cathy\u00a0Mengying Fang, Andrzej Banburski-Fahey, Judith Amores, and Jaron Lanier. 2023. Real-time Animation Generation and Control on Rigged Models via Large Language Models. arXiv preprint arXiv:2310.17838 (2023)."},{"key":"e_1_3_3_3_20_1","volume-title":"Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents. ArXiv Preprint ArXiv:2308.01542","author":"Huang Ziheng","year":"2023","unstructured":"Ziheng Huang, Sebastian Gutierrez, Hemanth Kamana, and Stephen MacNeil. 2023. Memory Sandbox: Transparent and Interactive Memory Management for Conversational Agents. ArXiv Preprint ArXiv:2308.01542 (2023). https:\/\/arxiv.org\/pdf\/2308.01542"},{"key":"e_1_3_3_3_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3510003.3510203"},{"key":"e_1_3_3_3_22_1","volume-title":"Shap-E: Generating Conditional 3d Implicit Functions. ArXiv Preprint ArXiv:2305.02463","author":"Jun Heewoo","year":"2023","unstructured":"Heewoo Jun and Alex Nichol. 2023. Shap-E: Generating Conditional 3d Implicit Functions. ArXiv Preprint ArXiv:2305.02463 (2023). https:\/\/arxiv.org\/pdf\/2305.02463"},{"key":"e_1_3_3_3_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01767"},{"key":"e_1_3_3_3_24_1","volume-title":"Ai2-Thor: An Interactive 3d Environment for Visual Ai. ArXiv Preprint ArXiv:1712.05474","author":"Kolve Eric","year":"2017","unstructured":"Eric Kolve, Roozbeh Mottaghi, Winson Han, Eli VanderBilt, Luca Weihs, Alvaro Herrasti, Matt Deitke, Kiana Ehsani, Daniel Gordon, Yuke Zhu, 2017. Ai2-Thor: An Interactive 3d Environment for Visual Ai. ArXiv Preprint ArXiv:1712.05474 (2017). https:\/\/arxiv.org\/pdf\/1712.05474"},{"key":"e_1_3_3_3_25_1","volume-title":"3ddesigner: Towards Photorealistic 3d Object Generation and Editing With Text-Guided Diffusion Models. ArXiv Preprint ArXiv:2211.14108","author":"Li Gang","year":"2022","unstructured":"Gang Li, Heliang Zheng, Chaoyue Wang, Chang Li, Changwen Zheng, and Dacheng Tao. 2022. 3ddesigner: Towards Photorealistic 3d Object Generation and Editing With Text-Guided Diffusion Models. ArXiv Preprint ArXiv:2211.14108 (2022)."},{"key":"e_1_3_3_3_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00037"},{"key":"e_1_3_3_3_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347945"},{"key":"e_1_3_3_3_28_1","volume-title":"Large Language Models are Few-Shot Health Learners. arXiv preprint arXiv:2305.15525","author":"Liu Xin","year":"2023","unstructured":"Xin Liu, Daniel McDuff, Geza Kovacs, Isaac Galatzer-Levy, Jacob Sunshine, Jiening Zhan, Ming-Zher Poh, Shun Liao, Paolo Di\u00a0Achille, and Shwetak Patel. 2023. Large Language Models are Few-Shot Health Learners. arXiv preprint arXiv:2305.15525 (2023)."},{"key":"e_1_3_3_3_29_1","volume-title":"Jailbreaking Chatgpt via Prompt Engineering: An Empirical Study. ArXiv Preprint ArXiv:2305.13860","author":"Liu Yi","year":"2023","unstructured":"Yi Liu, Gelei Deng, Zhengzi Xu, Yuekang Li, Yaowen Zheng, Ying Zhang, Lida Zhao, Tianwei Zhang, and Yang Liu. 2023. Jailbreaking Chatgpt via Prompt Engineering: An Empirical Study. ArXiv Preprint ArXiv:2305.13860 (2023). https:\/\/arxiv.org\/pdf\/2305.13860"},{"key":"e_1_3_3_3_30_1","volume-title":"RoCo: Dialectic Multi-Robot Collaboration With Large Language Models. ArXiv Preprint ArXiv:2307.04738","author":"Mandi Zhao","year":"2023","unstructured":"Zhao Mandi, Shreeya Jain, and Shuran Song. 2023. RoCo: Dialectic Multi-Robot Collaboration With Large Language Models. ArXiv Preprint ArXiv:2307.04738 (2023). https:\/\/arxiv.org\/pdf\/2307.04738"},{"key":"e_1_3_3_3_31_1","unstructured":"Microsoft. 2017. Mixed Reality Toolkit. https:\/\/github.com\/microsoft\/MixedRealityToolkit-Unity"},{"key":"e_1_3_3_3_32_1","unstructured":"Microsoft. 2023. Mixed Reality Mobile Remoting. https:\/\/github.com\/microsoft\/Mixed-Reality-Remoting-Unity"},{"key":"e_1_3_3_3_33_1","volume-title":"Codegen: An Open Large Language Model for Code With Multi-Turn Program Synthesis. ArXiv Preprint ArXiv:2203.13474","author":"Nijkamp Erik","year":"2022","unstructured":"Erik Nijkamp, Bo Pang, Hiroaki Hayashi, Lifu Tu, Huan Wang, Yingbo Zhou, Silvio Savarese, and Caiming Xiong. 2022. Codegen: An Open Large Language Model for Code With Multi-Turn Program Synthesis. ArXiv Preprint ArXiv:2203.13474 (2022). https:\/\/arxiv.org\/pdf\/2203.13474"},{"key":"e_1_3_3_3_35_1","volume-title":"Dreamfusion: Text-to-3d Using 2d Diffusion. ArXiv Preprint ArXiv:2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan\u00a0T Barron, and Ben Mildenhall. 2022. Dreamfusion: Text-to-3d Using 2d Diffusion. ArXiv Preprint ArXiv:2209.14988 (2022). https:\/\/arxiv.org\/pdf\/2209.14988"},{"key":"e_1_3_3_3_36_1","doi-asserted-by":"publisher","unstructured":"Alec Radford Jong\u00a0Wook Kim Chris Hallacy Aditya Ramesh Gabriel Goh Sandhini Agarwal Girish Sastry Amanda Askell Pamela Mishkin Jack Clark Gretchen Krueger and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. https:\/\/doi.org\/10.1109\/CVPR52688.2022.00101 arxiv:2103.00020\u00a0[cs.CV]","DOI":"10.1109\/CVPR52688.2022.00101"},{"key":"e_1_3_3_3_37_1","volume-title":"SayPlan: Grounding Large Language Models Using 3D Scene Graphs for Scalable Task Planning. ArXiv Preprint ArXiv:2307.06135","author":"Rana Krishan","year":"2023","unstructured":"Krishan Rana, Jesse Haviland, Sourav Garg, Jad Abou-Chakra, Ian Reid, and Niko Suenderhauf. 2023. SayPlan: Grounding Large Language Models Using 3D Scene Graphs for Scalable Task Planning. ArXiv Preprint ArXiv:2307.06135 (2023). https:\/\/arxiv.org\/pdf\/2307.06135"},{"key":"e_1_3_3_3_38_1","volume-title":"Texture: Text-Guided Texturing of 3d Shapes. ArXiv Preprint ArXiv:2302.01721","author":"Richardson Elad","year":"2023","unstructured":"Elad Richardson, Gal Metzer, Yuval Alaluf, Raja Giryes, and Daniel Cohen-Or. 2023. Texture: Text-Guided Texturing of 3d Shapes. ArXiv Preprint ArXiv:2302.01721 (2023). https:\/\/arxiv.org\/pdf\/2302.01721"},{"key":"e_1_3_3_3_39_1","volume-title":"Steps Towards Prompt-Based Creation of Virtual Worlds. ArXiv Preprint ArXiv:2211.05875","author":"Roberts Jasmine","year":"2022","unstructured":"Jasmine Roberts, Andrzej Banburski-Fahey, and Jaron Lanier. 2022. Steps Towards Prompt-Based Creation of Virtual Worlds. ArXiv Preprint ArXiv:2211.05875 (2022). https:\/\/arxiv.org\/pdf\/2211.05875"},{"key":"e_1_3_3_3_40_1","volume-title":"36th Conference on Neural Information Processing Systems (NeurIPS","author":"Roberts Jasmine","year":"2022","unstructured":"Jasmine Roberts, Andrzej Banburski-Fahey, and Jaron Lanier. 2022. Surreal VR Pong: LLM Approach to Game Design. In 36th Conference on Neural Information Processing Systems (NeurIPS 2022). https:\/\/www.microsoft.com\/en-us\/research\/publication\/surreal-vr-pong-llm-approach-to-game-design\/"},{"key":"e_1_3_3_3_41_1","volume-title":"Text-to-4d Dynamic Scene Generation. ArXiv Preprint ArXiv:2301.11280","author":"Singer Uriel","year":"2023","unstructured":"Uriel Singer, Shelly Sheynin, Adam Polyak, Oron Ashual, Iurii Makarov, Filippos Kokkinos, Naman Goyal, Andrea Vedaldi, Devi Parikh, Justin Johnson, 2023. Text-to-4d Dynamic Scene Generation. ArXiv Preprint ArXiv:2301.11280 (2023)."},{"key":"e_1_3_3_3_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_3_3_43_1","doi-asserted-by":"publisher","DOI":"10.1007\/978"},{"key":"e_1_3_3_3_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/2993369.2993372"},{"key":"e_1_3_3_3_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.283"},{"key":"e_1_3_3_3_46_1","unstructured":"Unity Technologies. 2019. Unity Render Streaming. https:\/\/docs.unity3d.com\/Packages\/com.unity.renderstreaming@2.0\/manual\/index.html"},{"key":"e_1_3_3_3_47_1","unstructured":"OpenAI. 2022. DALL\u00b7E 2. https:\/\/openai.com\/dall-e-2"},{"key":"e_1_3_3_3_48_1","unstructured":"Sketchfab Inc.2023. Sketchfab. https:\/\/sketchfab.com\/"},{"key":"e_1_3_3_3_49_1","unstructured":"Trivial Interactive. 2019. Roslyn C# - Runtime C# Compiler. https:\/\/forum.unity.com\/threads\/released-roslyn-c-runtime-c-compiler.651505\/"},{"key":"e_1_3_3_3_50_1","unstructured":"Unity Technologies. 2005. Unity Game Engine. https:\/\/unity.com\/"},{"key":"e_1_3_3_3_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3332165.3347872"},{"key":"e_1_3_3_3_52_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wordplay-1.3"},{"key":"e_1_3_3_3_53_1","volume-title":"Voyager: An Open-Ended Embodied Agent With Large Language Models. ArXiv Preprint ArXiv:2305.16291","author":"Wang Guanzhi","year":"2023","unstructured":"Guanzhi Wang, Yuqi Xie, Yunfan Jiang, Ajay Mandlekar, Chaowei Xiao, Yuke Zhu, Linxi Fan, and Anima Anandkumar. 2023. Voyager: An Open-Ended Embodied Agent With Large Language Models. ArXiv Preprint ArXiv:2305.16291 (2023). https:\/\/arxiv.org\/pdf\/2305.16291"},{"key":"e_1_3_3_3_54_1","volume-title":"Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models. ArXiv Preprint ArXiv:2308.15022","author":"Wang Qingyue","year":"2023","unstructured":"Qingyue Wang, Liang Ding, Yanan Cao, Zhiliang Tian, Shi Wang, Dacheng Tao, and Li Guo. 2023. Recursively Summarizing Enables Long-Term Dialogue Memory in Large Language Models. ArXiv Preprint ArXiv:2308.15022 (2023). https:\/\/arxiv.org\/pdf\/2308.15022"},{"key":"e_1_3_3_3_55_1","volume-title":"Augmenting Language Models With Long-Term Memory. ArXiv Preprint ArXiv:2306.07174","author":"Wang Weizhi","year":"2023","unstructured":"Weizhi Wang, Li Dong, Hao Cheng, Xiaodong Liu, Xifeng Yan, Jianfeng Gao, and Furu Wei. 2023. Augmenting Language Models With Long-Term Memory. ArXiv Preprint ArXiv:2306.07174 (2023)."},{"key":"e_1_3_3_3_56_1","volume-title":"Chat-3D: Data-Efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes. ArXiv Preprint ArXiv:2308.08769","author":"Wang Zehan","year":"2023","unstructured":"Zehan Wang, Haifeng Huang, Yang Zhao, Ziang Zhang, and Zhou Zhao. 2023. Chat-3D: Data-Efficiently Tuning Large Language Model for Universal Dialogue of 3D Scenes. ArXiv Preprint ArXiv:2308.08769 (2023). https:\/\/arxiv.org\/pdf\/2308.08769"},{"key":"e_1_3_3_3_57_1","volume-title":"Embodied Task Planning With Large Language Models. ArXiv Preprint ArXiv:2307.01848","author":"Wu Zhenyu","year":"2023","unstructured":"Zhenyu Wu, Ziwei Wang, Xiuwei Xu, Jiwen Lu, and Haibin Yan. 2023. Embodied Task Planning With Large Language Models. ArXiv Preprint ArXiv:2307.01848 (2023). https:\/\/arxiv.org\/pdf\/2307.01848"},{"key":"e_1_3_3_3_58_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544548.3581500"},{"key":"e_1_3_3_3_59_1","doi-asserted-by":"crossref","unstructured":"Lvmin Zhang Anyi Rao and Maneesh Agrawala. 2023. Adding Conditional Control to Text-to-Image Diffusion Models. arxiv:2302.05543\u00a0[cs.CV]","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_3_3_60_1","volume-title":"MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators. ArXiv Preprint ArXiv:2306.10900","author":"Zhang Yaqi","year":"2023","unstructured":"Yaqi Zhang, Di Huang, Bin Liu, Shixiang Tang, Yan Lu, Lu Chen, Lei Bai, Qi Chu, Nenghai Yu, and Wanli Ouyang. 2023. MotionGPT: Finetuned LLMs Are General-Purpose Motion Generators. ArXiv Preprint ArXiv:2306.10900 (2023)."},{"key":"e_1_3_3_3_61_1","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525992"},{"key":"e_1_3_3_3_62_1","volume-title":"A Survey of Large Language Models. ArXiv Preprint ArXiv:2303.18223","author":"Zhao Wayne\u00a0Xin","year":"2023","unstructured":"Wayne\u00a0Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang, Xiaolei Wang, Yupeng Hou, Yingqian Min, Beichen Zhang, Junjie Zhang, Zican Dong, 2023. A Survey of Large Language Models. ArXiv Preprint ArXiv:2303.18223 (2023). https:\/\/arxiv.org\/pdf\/2303.18223."},{"key":"e_1_3_3_3_63_1","volume-title":"MemoryBank: Enhancing Large Language Models With Long-Term Memory. ArXiv Preprint ArXiv:2305.10250","author":"Zhong Wanjun","year":"2023","unstructured":"Wanjun Zhong, Lianghong Guo, Qiqi Gao, and Yanlin Wang. 2023. MemoryBank: Enhancing Large Language Models With Long-Term Memory. ArXiv Preprint ArXiv:2305.10250 (2023). https:\/\/arxiv.org\/pdf\/2305.10250"},{"key":"e_1_3_3_3_64_1","volume-title":"InstructPipe: Building Visual Programming Pipelines with Human Instructions. arXiv preprint arXiv:2312.09672","author":"Zhou Zhongyi","year":"2023","unstructured":"Zhongyi Zhou, Jing Jin, Vrushank Phadnis, Xiuxiu Yuan, Jun Jiang, Xun Qian, Jingtao Zhou, Yiyi Huang, Zheng Xu, Yinda Zhang, 2023. InstructPipe: Building Visual Programming Pipelines with Human Instructions. arXiv preprint arXiv:2312.09672 (2023)."},{"key":"e_1_3_3_3_65_1","doi-asserted-by":"publisher","unstructured":"Xiangyang Zhu Renrui Zhang Bowei He Ziyu Guo Ziyao Zeng Zipeng Qin Shanghang Zhang and Peng Gao. 2023. Pointclip V2: Prompting Clip and Gpt for Powerful 3d Open-World Learning. In ICCV Vol.\u00a02. 5. https:\/\/doi.org\/10.1109\/ICCV51070.2023.00249","DOI":"10.1109\/ICCV51070.2023.00249"}],"event":{"name":"CHI '24: CHI Conference on Human Factors in Computing Systems","location":"Honolulu HI USA","acronym":"CHI '24","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction","SIGACCESS ACM Special Interest Group on Accessible Computing"]},"container-title":["Proceedings of the CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642579","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3613904.3642579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T23:44:10Z","timestamp":1750290250000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3613904.3642579"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5,11]]},"references-count":64,"alternative-id":["10.1145\/3613904.3642579","10.1145\/3613904"],"URL":"https:\/\/doi.org\/10.1145\/3613904.3642579","relation":{},"subject":[],"published":{"date-parts":[[2024,5,11]]},"assertion":[{"value":"2024-05-11","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}