{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T17:13:25Z","timestamp":1780420405120,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T00:00:00Z","timestamp":1781913600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Hong Kong General Research Fund","award":["15206123"],"award-info":[{"award-number":["15206123"]}]},{"name":"Hong Kong General Research Fund","award":["15211924"],"award-info":[{"award-number":["15211924"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,21]]},"DOI":"10.1145\/3812836.3814754","type":"proceedings-article","created":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:54:53Z","timestamp":1780419293000},"page":"188-194","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Automating Model Deployment on Mobile Devices"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7661-6432","authenticated-orcid":false,"given":"Leming","family":"Shen","sequence":"first","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"},{"name":"University College London, Londno, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5202-7892","authenticated-orcid":false,"given":"Qiang","family":"Yang","sequence":"additional","affiliation":[{"name":"University of Cambridge, Cambridge, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3125-0411","authenticated-orcid":false,"given":"Xinyu","family":"Huang","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4868-5750","authenticated-orcid":false,"given":"Zijing","family":"Ma","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3096-687X","authenticated-orcid":false,"given":"Yuanqing","family":"Zheng","sequence":"additional","affiliation":[{"name":"The Hong Kong Polytechnic University, Hong Kong, Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3733-4480","authenticated-orcid":false,"given":"Chris Xiaoxuan","family":"Lu","sequence":"additional","affiliation":[{"name":"University College London (UCL), London, United Kingdom"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,20]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2021. ONNX Runtime. https:\/\/onnxruntime.ai\/."},{"key":"e_1_3_2_1_2_1","unstructured":"2021. TensorRT. https:\/\/github.com\/NVIDIA\/TensorRT."},{"key":"e_1_3_2_1_3_1","unstructured":"2022. LangChain. https:\/\/www.langchain.com\/."},{"key":"e_1_3_2_1_4_1","unstructured":"2023. OpenVINO. https:\/\/github.com\/openvinotoolkit\/openvino."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330701"},{"key":"e_1_3_2_1_6_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan et al. 2020. Language models are few-shot learners. NeurIPS (2020)."},{"key":"e_1_3_2_1_7_1","unstructured":"Tianqi Chen Thierry Moreau et al. 2018. {TVM} : An automated {End-to-End} optimizing compiler for deep learning. In USENIX OSDI."},{"key":"e_1_3_2_1_8_1","unstructured":"Gaole Dai Shiqi Jiang Ting Cao Yuanchun Li Yuqing Yang Rui Tan Mo Li and Lili Qiu. 2026. V-Droid: Advancing Mobile GUI Agent Through Generative Verifiers. (2026)."},{"key":"e_1_3_2_1_9_1","volume-title":"Pal: Program-aided language models. In ICML. 10764\u201310799.","author":"Gao Luyu","year":"2023","unstructured":"Luyu Gao, Aman Madaan, Shuyan Zhou, Uri Alon, Pengfei Liu, Yiming Yang, Jamie Callan, and Graham Neubig. 2023. Pal: Program-aided language models. In ICML. 10764\u201310799."},{"key":"e_1_3_2_1_10_1","unstructured":"Aaron Hurst Adam Lerer Adam P Goucher Adam Perelman Aditya Ramesh Aidan Clark AJ Ostrow Akila Welihinda Alan Hayes Alec Radford et al. 2024. Gpt-4o system card. arXiv preprint arXiv:2410.21276 (2024)."},{"key":"e_1_3_2_1_11_1","unstructured":"Md Ashraful Islam et al. 2024. MapCoder: Multi-Agent Code Generation for Competitive Problem Solving. arXiv preprint arXiv:2405.11403 (2024)."},{"key":"e_1_3_2_1_12_1","unstructured":"Tian Jin Gheorghe-Teodor Bercea et al. 2020. Compiling onnx neural network models using mlir. arXiv preprint arXiv:2008.08272 (2020)."},{"key":"e_1_3_2_1_13_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. NeurIPS","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, et al. 2019. Pytorch: An imperative style, high-performance deep learning library. NeurIPS (2019)."},{"key":"e_1_3_2_1_14_1","volume-title":"Fedconv: A learning-on-model paradigm for heterogeneous federated clients. In ACM MobiSys. 398\u2013411.","author":"Shen Leming","year":"2024","unstructured":"Leming Shen, Qiang Yang, Kaiyan Cui, Yuanqing Zheng, Xiao-Yong Wei, Jianwei Liu, and Jinsong Han. 2024. Fedconv: A learning-on-model paradigm for heterogeneous federated clients. In ACM MobiSys. 398\u2013411."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","unstructured":"Leming Shen Qiang Yang Xinyu Huang Zijing Ma and Yuanqing Zheng. 2025. GPIoT: Tailoring Small Language Models for IoT Program Synthesis and Development. In ACM SenSys. 199\u2013212.","DOI":"10.1145\/3715014.3722064"},{"key":"e_1_3_2_1_16_1","volume-title":"Autoiot: Llm-driven automated natural language programming for aiot applications. In ACM MobiCom. 468\u2013482.","author":"Shen Leming","year":"2025","unstructured":"Leming Shen, Qiang Yang, Yuanqing Zheng, and Mo Li. 2025. Autoiot: Llm-driven automated natural language programming for aiot applications. In ACM MobiCom. 468\u2013482."},{"key":"e_1_3_2_1_17_1","volume-title":"Iotcoder: A copilot for iot application development. In ACM MobiCom. 1647\u20131649.","author":"Shen Leming","year":"2024","unstructured":"Leming Shen and Yuanqing Zheng. 2024. Iotcoder: A copilot for iot application development. In ACM MobiCom. 1647\u20131649."},{"key":"e_1_3_2_1_18_1","volume-title":"Reflexion: Language agents with verbal reinforcement learning. Advances in neural information processing systems 36","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in neural information processing systems 36 (2023), 8634\u20138652."},{"key":"e_1_3_2_1_19_1","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"35","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Xuezhi Wang, et al. 2022. Chain-of-thought prompting elicits reasoning in large language models. NeurIPS 35 (2022), 24824\u201324837.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_20_1","volume-title":"Penetrative AI: Making LLMs Comprehend the Physical World. In ACL.","author":"Xu Huatao","year":"2024","unstructured":"Huatao Xu, Liying Han, Qirui Yang, Mo Li, and Mani Srivastava. 2024. Penetrative AI: Making LLMs Comprehend the Physical World. In ACL."},{"key":"e_1_3_2_1_21_1","first-page":"11809","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume":"36","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. NeurIPS 36 (2023), 11809\u201311822.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_22_1","volume-title":"React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. arXiv preprint arXiv:2210.03629 (2022)."}],"event":{"name":"MobiSys Workshop '26: 24th Annual International Conference on Mobile Systems, Applications and Services Workshops","location":"University of Cambridge Cambridge United Kingdom","acronym":"MobiSys Workshop '26","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing","SIGOPS ACM Special Interest Group on Operating Systems"]},"container-title":["Proceedings of the 24th Annual International Conference on Mobile Systems, Applications and Services Workshops"],"original-title":[],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:55:40Z","timestamp":1780419340000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3812836.3814754"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,20]]},"references-count":22,"alternative-id":["10.1145\/3812836.3814754","10.1145\/3812836"],"URL":"https:\/\/doi.org\/10.1145\/3812836.3814754","relation":{},"subject":[],"published":{"date-parts":[[2026,6,20]]},"assertion":[{"value":"2026-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}