{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T15:57:06Z","timestamp":1763740626833,"version":"3.45.0"},"publisher-location":"New York, NY, USA","reference-count":122,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,28]]},"DOI":"10.1145\/3730567.3764441","type":"proceedings-article","created":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T15:22:38Z","timestamp":1763738558000},"page":"308-324","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Hello, GenAI? Dissecting Human to Generative AI Calling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3942-5167","authenticated-orcid":false,"given":"Ruizhi","family":"Cheng","sequence":"first","affiliation":[{"name":"Meta Platforms, Inc., Menlo Park, USA and George Mason University, Fairfax, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9087-2483","authenticated-orcid":false,"given":"Surendra","family":"Pathak","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8756-8327","authenticated-orcid":false,"given":"Guowu","family":"Xie","sequence":"additional","affiliation":[{"name":"Meta Platforms Inc., Menlo Park, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8500-4630","authenticated-orcid":false,"given":"Matteo","family":"Varvello","sequence":"additional","affiliation":[{"name":"Nokia Bell Labs, Murray Hill, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4650-7125","authenticated-orcid":false,"given":"Songqing","family":"Chen","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7042-3322","authenticated-orcid":false,"given":"Bo","family":"Han","sequence":"additional","affiliation":[{"name":"George Mason University, Fairfax, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,11,21]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906412"},{"key":"e_1_3_2_1_2_1","volume-title":"Proceedings of USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/agrawal","author":"Agrawal Amey","year":"2024","unstructured":"Amey Agrawal, Nitin Kedia, Ashish Panwar, Jayashree Mohan, Nipun Kwatra, Bhargav Gulavani, Alexey Tumanov, and Ramachandran Ramjee. 2024. Taming Throughput-Latency Tradeoff in LLM Inference With Sarathi-Serve. In Proceedings of USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/agrawal"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of USENIX Security Symposium (USENIX Security). https:\/\/www.usenix.org\/conference\/usenixsecurity23\/presentation\/ahmed-dilawer","author":"Ahmed Dilawer","year":"2023","unstructured":"Dilawer Ahmed, Aafaq Sabir, and Anupam Das. 2023. Spying Through Your Voice Assistants: Realistic Voice Command Fingerprinting. In Proceedings of USENIX Security Symposium (USENIX Security). https:\/\/www.usenix.org\/conference\/usenixsecurity23\/presentation\/ahmed-dilawer"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/NTMS49979.2021.9432677"},{"key":"e_1_3_2_1_5_1","volume-title":"Proceedings of IEEE International Conference on Distributed Computing Systems Workshops (ICDCS Workshops).","author":"Alhilal Ahmad","year":"2023","unstructured":"Ahmad Alhilal, Kirill Shatilov, Gareth Tyson, Tristan Braud, and Pan Hui. 2023. Network Traffic in the Metaverse: The Case of Social VR. In Proceedings of IEEE International Conference on Distributed Computing Systems Workshops (ICDCS Workshops)."},{"key":"e_1_3_2_1_6_1","volume-title":"Proceedings of ACM International Conference for High Performance Computing, Networking, Storage and Analysis (SC).","author":"Aminabadi Reza Yazdani","year":"2022","unstructured":"Reza Yazdani Aminabadi, Samyam Rajbhandari, Ammar Ahmad Awan, Cheng Li, Du Li, Elton Zheng, Olatunji Ruwase, Shaden Smith, Minjia Zhang, Jeff Rasley, et al., 2022. Deepspeed-Inference: Enabling Efficient Inference of Transformer Models at Unprecedented Scale. In Proceedings of ACM International Conference for High Performance Computing, Networking, Storage and Analysis (SC)."},{"key":"e_1_3_2_1_7_1","volume-title":"Android Developers: SpeechRecognizer. https:\/\/developer.android.com\/reference\/android\/speech\/SpeechRecognizer. [accessed on accessdate].","year":"2025","unstructured":"Android. 2025a. Android Developers: SpeechRecognizer. https:\/\/developer.android.com\/reference\/android\/speech\/SpeechRecognizer. [accessed on accessdate]."},{"key":"e_1_3_2_1_8_1","volume-title":"Android Developers: TextToSpeech. https:\/\/developer.android.com\/reference\/android\/speech\/tts\/package-summary. [accessed on accessdate].","year":"2025","unstructured":"Android. 2025b. Android Developers: TextToSpeech. https:\/\/developer.android.com\/reference\/android\/speech\/tts\/package-summary. [accessed on accessdate]."},{"key":"e_1_3_2_1_9_1","unstructured":"Anthropic. 2025. Claude. https:\/\/claude.ai. [accessed on accessdate]."},{"key":"e_1_3_2_1_10_1","unstructured":"Apple. 2025. Siri. https:\/\/www.apple.com\/siri\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_11_1","unstructured":"Apple Inc. 2025. Siri. https:\/\/www.apple.com\/siri\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCN.2015.7288417"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Marcelo Bagnulo Philip Matthews and Iljitsch van Beijnum. 2011. RFC 6146: Stateful NAT64: Network Address and Protocol Translation from IPv6 Clients to IPv4 Servers. https:\/\/www.rfc-editor.org\/rfc\/rfc6146. [accessed on accessdate].","DOI":"10.17487\/rfc6146"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","unstructured":"Shuai Bai Keqin Chen Xuejing Liu Jialin Wang Wenbin Ge Sibo Song Kai Dang Peng Wang Shijie Wang Jun Tang et al. 2025. Qwen2. 5-VL Technical Report. https:\/\/doi.org\/10.48550\/arXiv.2502.13923. [accessed on accessdate].","DOI":"10.48550\/arXiv.2502.13923"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.ijcnlp-main.45"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/1282380.1282386"},{"key":"e_1_3_2_1_17_1","volume-title":"Proceedings of ACM IMC. https:\/\/dl.acm.org\/doi\/abs\/10","author":"Chang Hyunseok","year":"2021","unstructured":"Hyunseok Chang, Matteo Varvello, Fang Hao, and Sarit Mukherjee. 2021. Can You See Me Now? A Measurement Study of Zoom, Webex, and Meet. In Proceedings of ACM IMC. https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3487552.3487847"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/1151659.1159959"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of Machine Learning and Systems (MLSys). https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/054de805fcceb78a201f5e9d53c85908-Paper-Conference.pdf","author":"Chen Lequn","year":"2024","unstructured":"Lequn Chen, Zihao Ye, Yongji Wu, Danyang Zhuo, Luis Ceze, and Arvind Krishnamurthy. 2024. Punica: Multi-Tenant LoRA Serving. In Proceedings of Machine Learning and Systems (MLSys). https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2024\/file\/054de805fcceb78a201f5e9d53c85908-Paper-Conference.pdf"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","unstructured":"Lingjiao Chen Matei Zaharia and James Zou. 2023. FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance. https:\/\/doi.org\/10.48550\/arXiv.2305.05176. [accessed on accessdate].","DOI":"10.48550\/arXiv.2305.05176"},{"key":"e_1_3_2_1_21_1","unstructured":"Qian Chen Yafeng Chen Yanni Chen Mengzhe Chen Yingda Chen Chong Deng Zhihao Du Ruize Gao Changfeng Gao Zhifu Gao et al. 2025a. MinMo: A Multimodal Large Language Model for Seamless Voice Interaction. https:\/\/arxiv.org\/abs\/2501.06282. [accessed on accessdate]."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714553"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/VRW55335.2022.00040"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.117.2200055"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3646547.3689006"},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of ACM IMC.","author":"Cheng Ruizhi","year":"2022","unstructured":"Ruizhi Cheng, Nan Wu, Matteo Varvello, Songqing Chen, and Bo Han. 2022c. Are We Ready for Metaverse? A Measurement Study of Social Virtual Reality Platforms. In Proceedings of ACM IMC."},{"key":"e_1_3_2_1_27_1","unstructured":"Ruizhi Cheng Guowu Xie and Bo Han. 2025. Real-time Human and Generative AI Interaction: Network Challenges and Opportunities. In arXiv."},{"key":"e_1_3_2_1_28_1","volume-title":"Apple delays Siri AI improvements to","author":"CNBC.","year":"2026","unstructured":"CNBC. 2025. Apple delays Siri AI improvements to 2026. https:\/\/www.cnbc.com\/2025\/03\/07\/apple-delays-siri-ai-improvements-to-2026.html. [accessed on accessdate]."},{"key":"e_1_3_2_1_29_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/67d57c32e20fd0a7a302cb81d36e40d5-Paper-Conference.pdf","author":"Dao Tri","year":"2022","unstructured":"Tri Dao, Dan Fu, Stefano Ermon, Atri Rudra, and Christopher R\u00e9. 2022. Flashattention: Fast and Memory-Efficient Exact Attention With IO-Awareness. In Proceedings of Advances in Neural Information Processing Systems (NeurIPS). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/67d57c32e20fd0a7a302cb81d36e40d5-Paper-Conference.pdf"},{"key":"e_1_3_2_1_30_1","unstructured":"Google DeepMind. 2025. Gemini 2.5. https:\/\/blog.google\/technology\/google-deepmind\/gemini-model-thinking-updates-march-2025\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_31_1","volume-title":"Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining. https:\/\/dl.acm.org\/doi\/abs\/10","author":"Dong Xin Luna","year":"2023","unstructured":"Xin Luna Dong, Seungwhan Moon, Yifan Ethan Xu, Kshitiz Malik, and Zhou Yu. 2023. Towards Next-Generation Intelligent Assistants Leveraging LLM Techniques. In Proceedings of ACM SIGKDD Conference on Knowledge Discovery and Data Mining. https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3580305.3599572"},{"key":"e_1_3_2_1_32_1","unstructured":"ElevenLabs. 2025. ElevenLabs: Text to Speech & AI Voice Generator. https:\/\/elevenlabs.io\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_33_1","unstructured":"Hugging Face. 2024. Everyday Conversations for LLMs. https:\/\/huggingface.co\/datasets\/HuggingFaceTB\/everyday-conversations-llama3.1-2k."},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/fu","author":"Fu Yao","year":"2024","unstructured":"Yao Fu, Leyang Xue, Yeqi Huang, Andrei-Octavian Brabete, Dmitrii Ustiugov, Yuvraj Patel, and Luo Mai. 2024. ServerlessLLM: Low-Latency Serverless Inference for Large Language Models. In Proceedings of USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/fu"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of USENIX Annual Technical Conference (USENIX ATC).","author":"Gao Bin","year":"2024","unstructured":"Bin Gao, Zhuomin He, Puru Sharma, Qingxuan Kang, Djordje Jevdjic, Junbo Deng, Xingkun Yang, Zhou Yu, and Pengfei Zuo. 2024. Cost-Efficient Large Language Model Serving for Multi-Turn Conversations With CachedAttention. In Proceedings of USENIX Annual Technical Conference (USENIX ATC)."},{"key":"e_1_3_2_1_36_1","unstructured":"Google. 2024. Gemini 2.0 Flash. https:\/\/cloud.google.com\/vertex-ai\/generative-ai\/docs\/models\/gemini\/2-0-flash. [accessed on accessdate]."},{"key":"e_1_3_2_1_37_1","unstructured":"Google. 2025a. Gemini. https:\/\/gemini.google.com\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_38_1","unstructured":"Google. 2025b. Gemini 2.5 Flash. https:\/\/cloud.google.com\/vertex-ai\/generative-ai\/docs\/models\/gemini\/2-5-flash. [accessed on accessdate]."},{"key":"e_1_3_2_1_39_1","unstructured":"Google. 2025c. Google Assistant. https:\/\/assistant.google.com\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_40_1","unstructured":"Google DeepMind. 2024. Gemini. https:\/\/gemini.google.com\/app. Accessed: 2025-05-01."},{"key":"e_1_3_2_1_41_1","unstructured":"hagezi. 2023. VS Code Telemetry. https:\/\/github.com\/StevenBlack\/hosts\/issues\/2301#issuecomment-1518564889. [accessed on accessdate]."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626296"},{"key":"e_1_3_2_1_43_1","unstructured":"ipinfo.io. 2024. https:\/\/ipinfo.io\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of ACM Measurement and Analysis of Computing Systems (SIGMETRICS).","author":"Iqbal Hassan","year":"2021","unstructured":"Hassan Iqbal, Ayesha Khalid, and Muhammad Shahzad. 2021. Dissecting Cloud Gaming Performance with DECAF. In Proceedings of ACM Measurement and Analysis of Computing Systems (SIGMETRICS)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618257.3624803"},{"key":"e_1_3_2_1_46_1","unstructured":"The International Telecommunication Union Telecommunication Standardization Sector (ITU-T). 2003. One-way Transmission Time for the General Recommendations on the Transmission Quality for an Entire International Telephone Connection. https:\/\/www.itu.int\/rec\/t-rec-g.114-200305-i."},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of USENIX NSDI.","author":"Jiang Junchen","year":"2017","unstructured":"Junchen Jiang, Shijie Sun, Vyas Sekar, and Hui Zhang. 2017. Pytheas: Enabling Data-Driven Quality of Experience Optimization Using Group-Based Exploration-Exploitation. In Proceedings of USENIX NSDI."},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3131365.3131368"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.diin.2015.09.002"},{"key":"e_1_3_2_1_50_1","unstructured":"Michael Kerrisk. 2000. tc-netem(8) \u2014 Linux manual page. https:\/\/man7.org\/linux\/man-pages\/man8\/tc-netem.8.html. [accessed on accessdate]."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of ACM Annual International Conference on Mobile Computing and Networking (MobiCom). https:\/\/dl.acm.org\/doi\/10","author":"Lee Sunjae","year":"2024","unstructured":"Sunjae Lee, Junyoung Choi, Jungjae Lee, Munim Hasan Wasi, Hojun Choi, Steve Ko, Sangeun Oh, and Insik Shin. 2024. MobileGPT: Augmenting LLM with Human-Like App Memory for Mobile Task Automation. In Proceedings of ACM Annual International Conference on Mobile Computing and Networking (MobiCom). https:\/\/dl.acm.org\/doi\/10.1145\/3636534.3690682"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/IWQoS.2017.7969110"},{"key":"e_1_3_2_1_54_1","first-page":"5662","article-title":"RAV: Learning-Based Adaptive Streaming to Coordinate the Audio and Video Bitrate Selections","volume":"25","author":"Li Weihe","year":"2022","unstructured":"Weihe Li, Jiawei Huang, Wenjun Lyu, Baoshen Guo, Wanchun Jiang, and Jianxin Wang. 2022. RAV: Learning-Based Adaptive Streaming to Coordinate the Audio and Video Bitrate Selections. IEEE Transactions on Multimedia, Vol. 25 (2022), 5662-5675.","journal-title":"IEEE Transactions on Multimedia"},{"key":"e_1_3_2_1_55_1","volume-title":"Proceedings of ACM SIGCOMM.","author":"Li Zhihao","year":"2018","unstructured":"Zhihao Li, Dave Levin, Neil Spring, and Bobby Bhattacharjee. 2018. Internet Anycast: Performance, Problems, & Potential. In Proceedings of ACM SIGCOMM."},{"key":"e_1_3_2_1_56_1","volume-title":"Proceedings of IEEE\/ACM International Conference on Software Engineering (ICSE). https:\/\/www.computer.org\/csdl\/proceedings-article\/icse\/2025\/056900a204\/215aWCaXlSg","author":"Lian Xinyu","year":"2024","unstructured":"Xinyu Lian, Yinfang Chen, Runxiang Cheng, Jie Huang, Parth Thakkar, Minjia Zhang, and Tianyin Xu. 2024. Large Language Models as Configuration Validators. In Proceedings of IEEE\/ACM International Conference on Software Engineering (ICSE). https:\/\/www.computer.org\/csdl\/proceedings-article\/icse\/2025\/056900a204\/215aWCaXlSg"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1145\/3427228.3427250"},{"key":"e_1_3_2_1_58_1","volume-title":"Proceedings of Text Summarization Branches Out. https:\/\/aclanthology.org\/W04-1013\/","author":"Lin Chin-Yew","year":"2004","unstructured":"Chin-Yew Lin. 2004. ROUGE: A Package for Automatic Evaluation of Summaries. In Proceedings of Text Summarization Branches Out. https:\/\/aclanthology.org\/W04-1013\/"},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual Instruction Tuning. In Proceedings of Advances in Neural Information Processing Systems (NeurIPS). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2023\/file\/6dcf277ea32ce3288914faf369fe6de0-Paper-Conference.pdf"},{"key":"e_1_3_2_1_60_1","volume-title":"Proceedings of ACM SIGCOMM.","author":"Liu Yuhan","year":"2024","unstructured":"Yuhan Liu, Hanchen Li, Yihua Cheng, Siddhant Ray, Yuyang Huang, Qizheng Zhang, Kuntai Du, Jiayi Yao, Shan Lu, Ganesh Ananthanarayanan, et al., 2024. CacheGen: KV Cache Compression and Streaming for Fast Large Language Model Serving. In Proceedings of ACM SIGCOMM."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626786"},{"key":"e_1_3_2_1_62_1","volume-title":"Proceedings of Advances in Neural Information Processing Systems (NeurIPS).","author":"Ma Xinyin","year":"2023","unstructured":"Xinyin Ma, Gongfan Fang, and Xinchao Wang. 2023. LLM-Pruner: On the Structural Pruning of Large Language Models. Proceedings of Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"crossref","unstructured":"Rohan Mahy Philip Matthews and Jonathan Rosenberg. 2010. RFC 5766: Traversal Using Relays around NAT (TURN): Relay Extensions to Session Traversal Utilities for NAT (STUN). https:\/\/www.rfc-editor.org\/rfc\/rfc5766. [accessed on accessdate].","DOI":"10.17487\/rfc5766"},{"key":"e_1_3_2_1_64_1","volume-title":"Proceedings of ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement. https:\/\/dl.acm.org\/doi\/abs\/10","author":"Majdoub Yacine","year":"2024","unstructured":"Yacine Majdoub and Eya Ben Charrada. 2024. Debugging With Open-Source Large Language Models: An Evaluation. In Proceedings of ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement. https:\/\/dl.acm.org\/doi\/abs\/10.1145\/3674805.3690758"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2010.04.029"},{"key":"e_1_3_2_1_66_1","unstructured":"MaxMind. 2024. https:\/\/www.maxmind.com\/en\/home. [accessed on accessdate]."},{"key":"e_1_3_2_1_67_1","unstructured":"Trevor Mendez Walter Milliken and Dr. Craig Partridge. 1993. Host Anycasting Service. RFC 1546. https:\/\/www.rfc-editor.org\/info\/rfc1546 [accessed on accessdate]."},{"key":"e_1_3_2_1_68_1","volume-title":"Proceedings of ACM IMC.","author":"Meng Jiayi","year":"2023","unstructured":"Jiayi Meng, Jingqi Huang, Y Charlie Hu, Yaron Koral, Xiaojun Lin, Muhammad Shahbaz, and Abhigyan Sharma. 2023. Modeling and Generating Control-Plane Traffic for Cellular Networks. In Proceedings of ACM IMC."},{"key":"e_1_3_2_1_69_1","unstructured":"Meta. 2024. MLow: Meta's low bitrate audio codec. https:\/\/engineering.fb.com\/2024\/06\/13\/web\/mlow-metas-low-bitrate-audio-codec\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_70_1","unstructured":"Meta. 2025a. Instagram. https:\/\/www.instagram.com\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_71_1","unstructured":"Meta. 2025b. Introducing the Meta AI App: A New Way to Access Your AI Assistant. https:\/\/about.fb.com\/news\/2025\/04\/introducing-meta-ai-app-new-way-access-ai-assistant\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_72_1","unstructured":"Meta. 2025c. Messenger. https:\/\/www.messenger.com\/."},{"key":"e_1_3_2_1_73_1","unstructured":"Meta. 2025d. WhatsApp. https:\/\/whatsapp.com\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_74_1","volume-title":"Herd: The Beginning of a New Era of Natively Multimodal AI Innovation. https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/. [accessed on accessdate].","author":"Platforms Meta","year":"2025","unstructured":"Meta Platforms, Inc., 2025. The Llama 4 Herd: The Beginning of a New Era of Natively Multimodal AI Innovation. https:\/\/ai.meta.com\/blog\/llama-4-multimodal-intelligence\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517745.3561414"},{"key":"e_1_3_2_1_76_1","unstructured":"Microsoft. 2022. AltspaceVR. https:\/\/altvr.com\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_77_1","unstructured":"Microsoft. 2024. Teams. https:\/\/www.microsoft.com\/en-us\/microsoft-teams\/group-chat-software. [accessed on accessdate]."},{"key":"e_1_3_2_1_78_1","unstructured":"Microsoft. 2025. Copilot. https:\/\/copilot.microsoft.com\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_79_1","unstructured":"Microsoft Corporation. 2025. Skype. https:\/\/www.skype.com\/en\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_80_1","unstructured":"OpenAI. 2023. Gpt-4 Technical Report. https:\/\/arxiv.org\/abs\/2303.08774. [accessed on accessdate]."},{"key":"e_1_3_2_1_81_1","unstructured":"OpenAI. 2024. ChatGPT. https:\/\/openai.com\/. Accessed: 2025-05-01."},{"key":"e_1_3_2_1_82_1","unstructured":"OpenAI. 2024. Gpt-4o System Card. https:\/\/arxiv.org\/abs\/2410.21276. [accessed on accessdate]."},{"key":"e_1_3_2_1_83_1","unstructured":"OpenAI. 2025a. ChatGPT. https:\/\/openai.com\/index\/chatgpt\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_84_1","unstructured":"OpenAI. 2025b. What is the ChatGPT model selector? https:\/\/help.openai.com\/en\/articles\/7864572-what-is-the-chatgpt-model-selector. [accessed on accessdate]."},{"key":"e_1_3_2_1_85_1","volume-title":"Proceedings of ACM Technical Symposium on Computer Science Education. https:\/\/dl.acm.org\/doi\/10","author":"Padurean Victor Alexandru","year":"2025","unstructured":"Victor Alexandru Padurean, Paul Denny, and Adish Singla. 2025. BugSpotter: Automated Generation of Code Debugging Exercises. In Proceedings of ACM Technical Symposium on Computer Science Education. https:\/\/dl.acm.org\/doi\/10.1145\/3641554.3701974"},{"key":"e_1_3_2_1_86_1","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"e_1_3_2_1_87_1","doi-asserted-by":"publisher","DOI":"10.1109\/ATNAC.2018.8615445"},{"key":"e_1_3_2_1_88_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2022.100087"},{"key":"e_1_3_2_1_89_1","unstructured":"Anthropic PBC. 2024. Claude 3.5 Sonnet. https:\/\/www.anthropic.com\/news\/claude-3-5-sonnet. [accessed on accessdate]."},{"key":"e_1_3_2_1_90_1","unstructured":"Android Police. 2025. Google Gemini vs. Gemini Advanced: All the key differences explained. https:\/\/www.androidpolice.com\/google-gemini-vs-gemini-advanced\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_91_1","volume-title":"Proceedings of Machine Learning and Systems (MLSys). https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/file\/c4be71ab8d24cdfb45e3d06dbfca2780-Paper-mlsys2023","author":"Pope Reiner","year":"2023","unstructured":"Reiner Pope, Sholto Douglas, Aakanksha Chowdhery, Jacob Devlin, James Bradbury, Jonathan Heek, Kefan Xiao, Shivani Agrawal, and Jeff Dean. 2023. Efficiently Scaling Transformer Inference. In Proceedings of Machine Learning and Systems (MLSys). https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2023\/file\/c4be71ab8d24cdfb45e3d06dbfca2780-Paper-mlsys2023.pdf"},{"key":"e_1_3_2_1_92_1","volume-title":"Proceedings of ACM SIGCOMM.","author":"Qian Kun","year":"2024","unstructured":"Kun Qian, Yongqing Xi, Jiamin Cao, Jiaqi Gao, Yichi Xu, Yu Guan, Binzhang Fu, Xuemei Shi, Fangbo Zhu, Rui Miao, et al., 2024. Alibaba HPN: A Data Center Network for Large Language Model Training. In Proceedings of ACM SIGCOMM."},{"key":"e_1_3_2_1_93_1","volume-title":"Proceedings of ACM International Conference on Emerging Networking Experiments And Technologies (CoNEXT).","author":"Qin Yanyuan","year":"2019","unstructured":"Yanyuan Qin, Subhabrata Sen, and Bing Wang. 2019. ABR Streaming with Separate Audio and Video Tracks: Measurements and Best Practices. In Proceedings of ACM International Conference on Emerging Networking Experiments And Technologies (CoNEXT)."},{"key":"e_1_3_2_1_94_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173574.3173900"},{"key":"e_1_3_2_1_95_1","volume-title":"Proceedings of Conference on Neural Information Processing Systems (NeurIPS).","author":"Ren Yi","year":"2019","unstructured":"Yi Ren, Yangjun Ruan, Xu Tan, Tao Qin, Sheng Zhao, Zhou Zhao, and Tie-Yan Liu. 2019. FastSpeech: Fast, Robust and Controllable Text to Speech. In Proceedings of Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_96_1","unstructured":"Charlie F Ruan Yucheng Qin Xun Zhou Ruihang Lai Hongyi Jin Yixin Dong Bohan Hou Meng-Shiun Yu Yiyan Zhai Sudeep Agarwal et al. 2024. WebLLM: A High-Performance In-Browser LLM Inference Engine. https:\/\/arxiv.org\/abs\/2412.15803. [accessed on accessdate]."},{"key":"e_1_3_2_1_97_1","unstructured":"Rusty Russell. [n.d.]. iptables - administration tool for IPv4 packet filtering and NAT."},{"key":"e_1_3_2_1_98_1","volume-title":"Proceedings of International Conference on Electrical, Computer and Energy Technologies (ICECET). https:\/\/ieeexplore.ieee.org\/abstract\/document\/10698405","author":"Sakib Fardin Ahsan","year":"2024","unstructured":"Fardin Ahsan Sakib, Saadat Hasan Khan, and AHM Rezaul Karim. 2024. Extending the Frontier of ChatGPT: Code Generation and Debugging. In Proceedings of International Conference on Electrical, Computer and Energy Technologies (ICECET). https:\/\/ieeexplore.ieee.org\/abstract\/document\/10698405"},{"key":"e_1_3_2_1_99_1","volume-title":"RTP: A Transport Protocol for Real-Time Applications. RFC 3550. https:\/\/rfc-editor","author":"Schulzrinne Henning","year":"2003","unstructured":"Henning Schulzrinne, Stephen L. Casner, Ron Frederick, and Van Jacobson. 2003. RTP: A Transport Protocol for Real-Time Applications. RFC 3550. https:\/\/rfc-editor.org\/rfc\/rfc3550.txt [accessed on accessdate]."},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604679"},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.1145\/3618257.3624828"},{"key":"e_1_3_2_1_102_1","doi-asserted-by":"crossref","unstructured":"Yaron Sheffer P Saint-Andre and T Fossati. 2022. RFC 9325: Recommendations for Secure Use of Transport Layer Security (TLS) and Datagram Transport Layer Security (DTLS). https:\/\/www.rfc-editor.org\/rfc\/rfc9325.html. [accessed on accessdate].","DOI":"10.17487\/RFC9325"},{"key":"e_1_3_2_1_103_1","unstructured":"Ying Sheng Shiyi Cao Dacheng Li Coleman Hooper Nicholas Lee Shuo Yang Christopher Chou Banghua Zhu Lianmin Zheng Kurt Keutzer Joseph E. Gonzalez and Ion Stoica. 2024. S-LoRA: Serving Thousands of Concurrent LoRA Adapters. https:\/\/arxiv.org\/abs\/2311.03285. [accessed on accessdate]."},{"key":"e_1_3_2_1_104_1","volume-title":"Proceedings of International Conference on Machine Learning (ICML). https:\/\/proceedings.mlr.press\/v202\/sheng23a.html","author":"Sheng Ying","year":"2023","unstructured":"Ying Sheng, Lianmin Zheng, Binhang Yuan, Zhuohan Li, Max Ryabinin, Beidi Chen, Percy Liang, Christopher R\u00e9, Ion Stoica, and Ce Zhang. 2023. Flexgen: High-Throughput Generative Inference of Large Language Models With a Single GPU. In Proceedings of International Conference on Machine Learning (ICML). https:\/\/proceedings.mlr.press\/v202\/sheng23a.html"},{"key":"e_1_3_2_1_105_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIT47043.2019.8987315"},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517384"},{"key":"e_1_3_2_1_107_1","volume-title":"Llama: Open and Efficient Foundation Language Models. https:\/\/arxiv.org\/pdf\/2302.13971. [accessed on accessdate].","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al., 2023. Llama: Open and Efficient Foundation Language Models. https:\/\/arxiv.org\/pdf\/2302.13971. [accessed on accessdate]."},{"key":"e_1_3_2_1_108_1","unstructured":"Jean-Marc Valin and Cary Bran. 2016. RFC7874: WebRTC Audio Codec and Processing Requirements. https:\/\/datatracker.ietf.org\/doc\/html\/rfc7874. [accessed on accessdate]."},{"key":"e_1_3_2_1_109_1","unstructured":"Jean-Marc Valin Koen Vos and Tim Terriberry. 2012. Definition of the Opus Audio Codec. RFC 6716. https:\/\/rfc-editor.org\/rfc\/rfc6716.txt [accessed on accessdate]."},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517745.3561442"},{"key":"e_1_3_2_1_111_1","volume-title":"Proceedings of Conference on Neural Information Processing Systems (NeurIPS).","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is All You Need. In Proceedings of Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_112_1","volume-title":"Proceedings of ACM Annual International Conference on Mobile Computing and Networking (MobiCom). https:\/\/dl.acm.org\/doi\/10","author":"Wen Hao","year":"2024","unstructured":"Hao Wen, Yuanchun Li, Guohong Liu, Shanhui Zhao, Tao Yu, Toby Jia-Jun Li, Shiqi Jiang, Yunhao Liu, Yaqin Zhang, and Yunxin Liu. 2024. Autodroid: LLM-Powered Task Automation in Android. In Proceedings of ACM Annual International Conference on Mobile Computing and Networking (MobiCom). https:\/\/dl.acm.org\/doi\/10.1145\/3636534.3649379"},{"key":"e_1_3_2_1_113_1","unstructured":"Wireshark. 1998. https:\/\/www.wireshark.org\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_114_1","doi-asserted-by":"publisher","DOI":"10.1145\/3715014.3722069"},{"key":"e_1_3_2_1_115_1","doi-asserted-by":"publisher","DOI":"10.1145\/3551349.3560416"},{"key":"e_1_3_2_1_116_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517745.3561464"},{"key":"e_1_3_2_1_117_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i16.17674"},{"key":"e_1_3_2_1_118_1","doi-asserted-by":"publisher","DOI":"10.1145\/3689031.3696098"},{"key":"e_1_3_2_1_119_1","volume-title":"Automatic Speech Recognition","author":"Yu Dong","unstructured":"Dong Yu and Lin Deng. 2016. Automatic Speech Recognition. Vol. 1. Springer."},{"key":"e_1_3_2_1_120_1","volume-title":"Proceedings of USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu","author":"Yu Gyeong-In","year":"2022","unstructured":"Gyeong-In Yu, Joo Seong Jeong, Geon-Woo Kim, Soojeong Kim, and Byung-Gon Chun. 2022. Orca: A Distributed Serving System for Transformer-Based Generative Models. In Proceedings of USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi22\/presentation\/yu"},{"key":"e_1_3_2_1_121_1","volume-title":"The best large language models (LLMs)","year":"2025","unstructured":"Zapier. 2025. The best large language models (LLMs) in 2025. https:\/\/zapier.com\/blog\/best-llm\/. [accessed on accessdate]."},{"key":"e_1_3_2_1_122_1","volume-title":"Proceedings of USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/zhong-yinmin","author":"Zhong Yinmin","year":"2024","unstructured":"Yinmin Zhong, Shengyu Liu, Junda Chen, Jianbo Hu, Yibo Zhu, Xuanzhe Liu, Xin Jin, and Hao Zhang. 2024. DistServe: Disaggregating Prefill and Decoding for Goodput-Optimized Large Language Model Serving. In Proceedings of USENIX Symposium on Operating Systems Design and Implementation (OSDI). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/zhong-yinmin"}],"event":{"name":"IMC '25:ACM Internet Measurement Conference","location":"Madison WI USA","sponsor":["SIGMETRICS ACM Special Interest Group on Measurement and Evaluation","SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the 2025 ACM Internet Measurement Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3730567.3764441","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,21]],"date-time":"2025-11-21T15:30:51Z","timestamp":1763739051000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3730567.3764441"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,28]]},"references-count":122,"alternative-id":["10.1145\/3730567.3764441","10.1145\/3730567"],"URL":"https:\/\/doi.org\/10.1145\/3730567.3764441","relation":{},"subject":[],"published":{"date-parts":[[2025,10,28]]},"assertion":[{"value":"2025-11-21","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}