{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T05:43:08Z","timestamp":1780724588055,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":112,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,8,4]],"date-time":"2024-08-04T00:00:00Z","timestamp":1722729600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,8,4]]},"DOI":"10.1145\/3651890.3672268","type":"proceedings-article","created":{"date-parts":[[2024,7,31]],"date-time":"2024-07-31T13:11:43Z","timestamp":1722431503000},"page":"661-678","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":129,"title":["NetLLM: Adapting Large Language Models for Networking"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2790-7484","authenticated-orcid":false,"given":"Duo","family":"Wu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-3811-1341","authenticated-orcid":false,"given":"Xianda","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8801-4827","authenticated-orcid":false,"given":"Yaqi","family":"Qiao","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5462-6178","authenticated-orcid":false,"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6877-1683","authenticated-orcid":false,"given":"Junchen","family":"Jiang","sequence":"additional","affiliation":[{"name":"University of Chicago, Chicago, United States of America"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2608-775X","authenticated-orcid":false,"given":"Shuguang","family":"Cui","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2559-045X","authenticated-orcid":false,"given":"Fangxin","family":"Wang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,8,4]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405892"},{"key":"e_1_3_2_1_2_1","volume-title":"Wanna make your tcp scheme great for cellular networks? Let machines do it for you! IEEE Journal on Selected Areas in Communications 39, 1","author":"Abbasloo Soheil","year":"2021","unstructured":"Soheil Abbasloo, Chen-Yu Yen, and H. Jonathan Chao. 2021. Wanna make your tcp scheme great for cellular networks? Let machines do it for you! IEEE Journal on Selected Areas in Communications 39, 1 (2021), 265--279."},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the 2020 International Conference on Machine Learning. PMLR, 104--114","author":"Agarwal Rishabh","year":"2020","unstructured":"Rishabh Agarwal, Dale Schuurmans, and Mohammad Norouzi. 2020. An optimistic perspective on offline reinforcement learning. In Proceedings of the 2020 International Conference on Machine Learning. PMLR, 104--114."},{"key":"e_1_3_2_1_4_1","volume-title":"Intrinsic dimensionality explains the effectiveness of language model fine-tuning. arXiv preprint arXiv:2012.13255","author":"Aghajanyan Armen","year":"2020","unstructured":"Armen Aghajanyan, Luke Zettlemoyer, and Sonal Gupta. 2020. Intrinsic dimensionality explains the effectiveness of language model fine-tuning. arXiv preprint arXiv:2012.13255 (2020)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","unstructured":"J Alammar. 2021. Ecco: An open source library for the explainability of transformer language models. In Proceedings of the 59th Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstrations. 249--257.","DOI":"10.18653\/v1\/2021.acl-demo.30"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3232755.3232783"},{"key":"e_1_3_2_1_7_1","volume-title":"Jamie Ryan Kiros, and Geoffrey E. Hinton","author":"Ba Jimmy Lei","year":"2016","unstructured":"Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E. Hinton. 2016. Layer Normalization. arXiv preprint arXiv:1607.06450 (2016)."},{"key":"e_1_3_2_1_8_1","volume-title":"2015 USENIX Symposium on Networked Systems Design and Implementation (NSDI). 455--468","author":"Bai Wei","year":"2015","unstructured":"Wei Bai, Li Chen, Kai Chen, Dongsu Han, Chen Tian, and Hao Wang. 2015. Information-agnostic flow scheduling for commodity data centers. In 2015 USENIX Symposium on Networked Systems Design and Implementation (NSDI). 455--468."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3304112.3325611"},{"key":"e_1_3_2_1_10_1","first-page":"1877","article-title":"Language Models are Few-Shot Learners","volume":"33","author":"Brown Tom","year":"2020","unstructured":"Tom Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah, Jared D Kaplan, Prafulla Dhariwal, Arvind Neelakantan, Pranav Shyam, Girish Sastry, Amanda Askell, Sandhini Agarwal, Ariel Herbert-Voss, Gretchen Krueger, Tom Henighan, Rewon Child, Aditya Ramesh, Daniel Ziegler, Jeffrey Wu, Clemens Winter, Chris Hesse, Mark Chen, Eric Sigler, Mateusz Litwin, Scott Gray, Benjamin Chess, Jack Clark, Christopher Berner, Sam McCandlish, Alec Radford, Ilya Sutskever, and Dario Amodei. 2020. Language Models are Few-Shot Learners. In Advances in Neural Information Processing Systems, Vol. 33. 1877--1901.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3230543.3230551"},{"key":"e_1_3_2_1_12_1","first-page":"15084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen Lili","year":"2021","unstructured":"Lili Chen, Kevin Lu, Aravind Rajeswaran, Kimin Lee, Aditya Grover, Misha Laskin, Pieter Abbeel, Aravind Srinivas, and Igor Mordatch. 2021. Decision transformer: Reinforcement learning via sequence modeling. Advances in Neural Information Processing Systems 34 (2021), 15084--15097.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_13_1","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique Ponde de Oliveira Pinto Jared Kaplan Harri Edwards Yuri Burda Nicholas Joseph Greg Brockman Alex Ray Raul Puri Gretchen Krueger Michael Petrov Heidy Khlaaf Girish Sastry Pamela Mishkin Brooke Chan Scott Gray Nick Ryder Mikhail Pavlov Alethea Power Lukasz Kaiser Mohammad Bavarian Clemens Winter Philippe Tillet Felipe Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew N. Carr Jan Leike Josh Achiam Vedant Misra Evan Morikawa Alec Radford Matthew Knight Miles Brundage Mira Murati Katie Mayer Peter Welinder Bob McGrew Dario Amodei Sam McCandlish Ilya Sutskever and Wojciech Zaremba. 2021. Evaluating Large Language Models Trained on Code. arXiv preprint arXiv:2107.03374 (2021)."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2016.7482079"},{"key":"e_1_3_2_1_15_1","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery Aakanksha","year":"2023","unstructured":"Aakanksha Chowdhery, Sharan Narang, Jacob Devlin, Maarten Bosma, Gaurav Mishra, Adam Roberts, Paul Barham, Hyung Won Chung, Charles Sutton, Sebastian Gehrmann, Parker Schuh, Kensen Shi, Sasha Tsvyashchenko, Joshua Maynez, Abhishek Rao, Parker Barnes, Yi Tay, Noam Shazeer, Vinodkumar Prabhakaran, Emily Reif, Nan Du, Ben Hutchinson, Reiner Pope, James Bradbury, Jacob Austin, Michael Isard, Guy Gur-Ari, Pengcheng Yin, Toju Duke, Anselm Levskaya, Sanjay Ghemawat, Sunipa Dev, Henryk Michalewski, Xavier Garcia, Vedant Misra, Kevin Robinson, Liam Fedus, Denny Zhou, Daphne Ippolito, David Luan, Hyeontaek Lim, Barret Zoph, Alexander Spiridonov, Ryan Sepassi, David Dohan, Shivani Agrawal, Mark Omernick, Andrew M. Dai, Thanumalayan Sankaranarayana Pillai, Marie Pellat, Aitor Lewkowycz, Erica Moreira, Rewon Child, Oleksandr Polozov, Katherine Lee, Zongwei Zhou, Xuezhi Wang, Brennan Saeta, Mark Diaz, Orhan Firat, Michele Catasta, Jason Wei, Kathy Meier-Hellstern, Douglas Eck, Jeff Dean, Slav Petrov, and Noah Fiedel. 2023. Palm: Scaling language modeling with pathways. Journal of Machine Learning Research 24, 240 (2023), 1--113.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_16_1","unstructured":"Hyung Won Chung Le Hou Shayne Longpre Barret Zoph Yi Tay William Fedus Yunxuan Li Xuezhi Wang Mostafa Dehghani Siddhartha Brahma Albert Webson Shixiang Shane Gu Zhuyun Dai Mirac Suzgun Xinyun Chen Aakanksha Chowdhery Alex Castro-Ros Marie Pellat Kevin Robinson Dasha Valter Sharan Narang Gaurav Mishra Adams Yu Vincent Zhao Yanping Huang Andrew Dai Hongkun Yu Slav Petrov Ed H. Chi Jeff Dean Jacob Devlin Adam Roberts Denny Zhou Quoc V. Le and Jason Wei. 2022. Scaling instruction-finetuned language models. arXiv preprint arXiv:2210.11416 (2022)."},{"key":"e_1_3_2_1_17_1","volume-title":"Zunamys I Carrero, Jan-Niklas Eckardt, Narmin Ghaffari Laleh, Chiara Maria Lavinia L\u00f6ffler, SophieCaroline Schwarzkopf, Michaela Unger, Gregory P Veldhuizen, et al.","author":"Clusmann Jan","year":"2023","unstructured":"Jan Clusmann, Fiona R Kolbinger, Hannah Sophie Muti, Zunamys I Carrero, Jan-Niklas Eckardt, Narmin Ghaffari Laleh, Chiara Maria Lavinia L\u00f6ffler, SophieCaroline Schwarzkopf, Michaela Unger, Gregory P Veldhuizen, et al. 2023. The future landscape of large language models in medicine. Communications medicine 3, 1 (2023), 141."},{"key":"e_1_3_2_1_18_1","unstructured":"Federal Communications Commission. 2016. Raw data - measuring broadband america. (2016). https:\/\/www.fcc.gov\/reports-research\/reports\/measuring-broadband-america\/raw-data-measuring-broadband-america-2016"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-demo.10"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_2_1_22_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2021)."},{"key":"e_1_3_2_1_23_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 S. M. Sajjadi, Corey Lynch, Aakanksha Chowdhery, Brian Ichter, Ayzaan Wahid, Jonathan Tompson, Quan Vuong, Tianhe Yu, Wenlong Huang, Yevgen Chebotar, Pierre Sermanet, Daniel Duckworth, Sergey Levine, Vincent Vanhoucke, Karol Hausman, Marc Toussaint, Klaus Greff, Andy Zeng, Igor Mordatch, and Pete Florence. 2023. Palm-e: An embodied multimodal language model. arXiv preprint arXiv:2303.03378 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3067686"},{"key":"e_1_3_2_1_25_1","unstructured":"DASH Industry Form. 2016. Reference Client 2.4.0. (2016). http:\/\/mediapm.edgesuite.net\/dash\/public\/nightly\/samples\/dash-if-reference-player\/index.html."},{"key":"e_1_3_2_1_26_1","volume-title":"Proceedings of the 2023 International Conference on Machine Learning. PMLR, 10323--10337","author":"Frantar Elias","year":"2023","unstructured":"Elias Frantar and Dan Alistarh. 2023. Sparsegpt: Massive language models can be accurately pruned in one-shot. In Proceedings of the 2023 International Conference on Machine Learning. PMLR, 10323--10337."},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the 2022 International Conference on Learning Representations.","author":"Frantar Elias","year":"2022","unstructured":"Elias Frantar, Saleh Ashkboos, Torsten Hoefler, and Dan Alistarh. 2022. Optq: Accurate quantization for generative pre-trained transformers. In Proceedings of the 2022 International Conference on Learning Representations."},{"key":"e_1_3_2_1_28_1","volume-title":"Mme: A comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394","author":"Fu Chaoyou","year":"2023","unstructured":"Chaoyou Fu, Peixian Chen, Yunhang Shen, Yulei Qin, Mengdan Zhang, Xu Lin, Jinrui Yang, Xiawu Zheng, Ke Li, Xing Sun, et al. 2023. Mme: A comprehensive evaluation benchmark for multimodal large language models. arXiv preprint arXiv:2306.13394 (2023)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26505"},{"key":"e_1_3_2_1_30_1","unstructured":"Archie Gertsman. 2024. spark-sched-sim: An apache spark job scheduling simulator implemented as a Gymnasium environment. (2024). https:\/\/github.com\/ArchieGertsman\/spark-sched-sim"},{"key":"e_1_3_2_1_31_1","unstructured":"Amelia Glaese Nat McAleese Maja Tr\u0119bacz John Aslanides Vlad Firoiu Timo Ewalds Maribeth Rauh Laura Weidinger Martin Chadwick Phoebe Thacker et al. 2022. Improving alignment of dialogue agents via targeted human judgements. arXiv preprint arXiv:2209.14375 (2022)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626334"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342063"},{"key":"e_1_3_2_1_34_1","volume-title":"Proceedings of the 2022 ACM Multimedia Systems Conference. 12--26","author":"Guimard Quentin","year":"2022","unstructured":"Quentin Guimard, Lucile Sassatelli, Francesco Marchetti, Federico Becattini, Lorenzo Seidenari, and Alberto Del Bimbo. 2022. Deep variational learning for multiple trajectory prediction of 360\u00b0 head movements. In Proceedings of the 2022 ACM Multimedia Systems Conference. 12--26."},{"key":"e_1_3_2_1_35_1","volume-title":"Deep learning with Keras","author":"Gulli Antonio","unstructured":"Antonio Gulli and Sujit Pal. 2017. Deep learning with Keras. Packt Publishing Ltd."},{"key":"e_1_3_2_1_36_1","volume-title":"netFound: Foundation Model for Network Security. arXiv preprint arXiv:2310.17025","author":"Guthula Satyandra","year":"2023","unstructured":"Satyandra Guthula, Navya Battula, Roman Beltiukov, Wenbo Guo, and Arpit Gupta. 2023. netFound: Foundation Model for Network Security. arXiv preprint arXiv:2310.17025 (2023)."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3380888"},{"key":"e_1_3_2_1_38_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J.","year":"2021","unstructured":"Edward J. Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1145\/2619239.2626296"},{"key":"e_1_3_2_1_40_1","first-page":"1273","article-title":"Offline reinforcement learning as one big sequence modeling problem","volume":"34","author":"Janner Michael","year":"2021","unstructured":"Michael Janner, Qiyang Li, and Sergey Levine. 2021. Offline reinforcement learning as one big sequence modeling problem. Advances in Neural Information Processing Systems 34 (2021), 1273--1286.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_41_1","volume-title":"Andrea Madotto, and Pascale Fung.","author":"Ji Ziwei","year":"2023","unstructured":"Ziwei Ji, Nayeon Lee, Rita Frieske, Tiezheng Yu, Dan Su, Yan Xu, Etsuko Ishii, Ye Jin Bang, Andrea Madotto, and Pascale Fung. 2023. Survey of hallucination in natural language generation. Comput. Surveys 55, 12, Article 248 (2023), 38 pages."},{"key":"e_1_3_2_1_42_1","unstructured":"Albert Q. Jiang Alexandre Sablayrolles Arthur Mensch Chris Bamford Devendra Singh Chaplot Diego de las Casas Florian Bressand Gianna Lengyel Guillaume Lample Lucile Saulnier L\u00e9lio Renard Lavaud Marie-Anne Lachaux Pierre Stock Teven Le Scao Thibaut Lavril Thomas Wang Timoth\u00e9e Lacroix and William El Sayed. 2023. Mistral 7b. arXiv preprint arXiv:2310.06825 (2023)."},{"key":"e_1_3_2_1_43_1","volume-title":"Proceedings of the 2022 ACM International Conference on Multimedia. 1025--1034","author":"Jin Yili","year":"2022","unstructured":"Yili Jin, Junhua Liu, Fangxin Wang, and Shuguang Cui. 2022. Where are you looking? A large-scale dataset of head and gaze behavior for 360-degree videos and a pilot study. In Proceedings of the 2022 ACM International Conference on Multimedia. 1025--1034."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548331"},{"key":"e_1_3_2_1_45_1","first-page":"22199","article-title":"Large language models are zero-shot reasoners","volume":"35","author":"Kojima Takeshi","year":"2022","unstructured":"Takeshi Kojima, Shixiang Shane Gu, Machel Reid, Yutaka Matsuo, and Yusuke Iwasawa. 2022. Large language models are zero-shot reasoners. Advances in Neural Information Processing Systems 35 (2022), 22199--22213.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_47_1","volume-title":"Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643","author":"Levine Sergey","year":"2020","unstructured":"Sergey Levine, Aviral Kumar, George Tucker, and Justin Fu. 2020. Offline reinforcement learning: Tutorial, review, and perspectives on open problems. arXiv preprint arXiv:2005.01643 (2020)."},{"key":"e_1_3_2_1_48_1","first-page":"9459","article-title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","volume":"33","author":"Lewis Patrick","year":"2020","unstructured":"Patrick Lewis, Ethan Perez, Aleksandra Piktus, Fabio Petroni, Vladimir Karpukhin, Naman Goyal, Heinrich K\u00fcttler, Mike Lewis, Wen-tau Yih, Tim Rockt\u00e4schel, Sebastian Riedel, and Douwe Kiela. 2020. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. In Advances in Neural Information Processing Systems, Vol. 33. 9459--9474.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.397"},{"key":"e_1_3_2_1_50_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600100.3623719"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3604237.3626869"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2014.140405"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512217"},{"key":"e_1_3_2_1_55_1","volume-title":"Maryam Fazel-Zarandi, Tom Sercu, Salvatore Candido, and Alexander Rives.","author":"Lin Zeming","year":"2023","unstructured":"Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting Lu, Nikita Smetanin, Robert Verkuil, Ori Kabeli, Yaniv Shmueli, Allan dos Santos Costa, Maryam Fazel-Zarandi, Tom Sercu, Salvatore Candido, and Alexander Rives. 2023. Evolutionary-scale prediction of atomic-level protein structure with a language model. Science 379, 6637 (2023), 1123--1130."},{"key":"e_1_3_2_1_56_1","volume-title":"Visual instruction tuning. arXiv preprint arXiv:2304.08485","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/VR55154.2023.00033"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3066410"},{"key":"e_1_3_2_1_59_1","volume-title":"Chipnemo: Domain-adapted llms for chip design. arXiv preprint arXiv:2311.00176","author":"Liu Mingjie","year":"2023","unstructured":"Mingjie Liu, Teodor-Dumitru Ene, Robert Kirby, Chris Cheng, Nathaniel Pinckney, Rongjian Liang, Jonah Alben, Himyanshu Anand, Sanmitra Banerjee, Ismet Bayraktaroglu, Bonita Bhaskaran, Bryan Catanzaro, Arjun Chaudhuri, Sharon Clay, Bill Dally, Laura Dang, Parikshit Deshpande, Siddhanth Dhodhi, Sameer Halepete, Eric Hill, Jiashang Hu, Sumit Jain, Brucek Khailany, George Kokai, Kishor Kunal, Xiaowei Li, Charley Lind, Hao Liu, Stuart Oberman, Sujeet Omar, Sreedhar Pratty, Jonathan Raiman, Ambar Sarkar, Zhengjiang Shao, Hanfei Sun, Pratik P Suthar, Varun Tej, Walker Turner, Kaizhe Xu, and Haoxing Ren. 2023. Chipnemo: Domain-adapted llms for chip design. arXiv preprint arXiv:2311.00176 (2023)."},{"key":"e_1_3_2_1_60_1","first-page":"1","article-title":"Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing","volume":"55","author":"Liu Pengfei","year":"2023","unstructured":"Pengfei Liu, Weizhe Yuan, Jinlan Fu, Zhengbao Jiang, Hiroaki Hayashi, and Graham Neubig. 2023. Pre-train, prompt, and predict: A systematic survey of prompting methods in natural language processing. Comput. Surveys 55, 9 (2023), 1--35.","journal-title":"Comput. Surveys"},{"key":"e_1_3_2_1_61_1","volume-title":"CacheGen: Fast Context Loading for Language Model Applications. arXiv preprint arXiv:2310.07240","author":"Liu Yuhan","year":"2023","unstructured":"Yuhan Liu, Hanchen Li, Kuntai Du, Jiayi Yao, Yihua Cheng, Yuyang Huang, Shan Lu, Michael Maire, Henry Hoffmann, Ari Holtzman, Ganesh Ananthanarayanan, and Junchen Jiang. 2023. CacheGen: Fast Context Loading for Language Model Applications. arXiv preprint arXiv:2310.07240 (2023)."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3098822.3098843"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1145\/3341302.3342080"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2020.107515"},{"key":"e_1_3_2_1_65_1","volume-title":"Netgpt: Generative pretrained transformer for network traffic. arXiv preprint arXiv:2304.09513","author":"Meng Xuying","year":"2023","unstructured":"Xuying Meng, Chungang Lin, Yequan Wang, and Yujun Zhang. 2023. Netgpt: Generative pretrained transformer for network traffic. arXiv preprint arXiv:2304.09513 (2023)."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405859"},{"key":"e_1_3_2_1_67_1","volume-title":"Artificial Intelligence in the Age of Neural Networks and Brain Computing","author":"Miikkulainen Risto","unstructured":"Risto Miikkulainen, Jason Liang, Elliot Meyerson, Aditya Rawal, Dan Fink, Olivier Francon, Bala Raju, Hormoz Shahrzad, Arshak Navruzyan, Nigel Duffy, and Babak Hodjat. 2024. Evolving deep neural networks. In Artificial Intelligence in the Age of Neural Networks and Brain Computing (Second Edition) (second edition ed.), Robert Kozma, Cesare Alippi, Yoonsuck Choe, and Francesco Carlo Morabito (Eds.). Academic Press, 269--287."},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"publisher","DOI":"10.1145\/3605943"},{"key":"e_1_3_2_1_69_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_1_70_1","volume-title":"2015 USENIX Annual Technical Conference (USENIX ATC). 417--429","author":"Netravali Ravi","year":"2015","unstructured":"Ravi Netravali, Anirudh Sivaraman, Somak Das, Ameesh Goyal, Keith Winstein, James Mickens, and Hari Balakrishnan. 2015. Mahimahi: accurate record-andreplay for http. In 2015 USENIX Annual Technical Conference (USENIX ATC). 417--429."},{"key":"e_1_3_2_1_71_1","volume-title":"Gpt-4 technical report. arXiv preprint arXiv:2303.08774","author":"AI.","year":"2023","unstructured":"OpenAI. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_72_1","volume-title":"https:\/\/chat.openai.com\/chat","author":"Chatgpt AI.","year":"2024","unstructured":"OpenAI. 2024. Chatgpt. (2024). https:\/\/chat.openai.com\/chat"},{"key":"e_1_3_2_1_73_1","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2018.2883147"},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3352100"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"e_1_3_2_1_76_1","volume-title":"Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems 32","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga, Alban Desmaison, Andreas Kopf, Edward Yang, Zachary DeVito, Martin Raison, Alykhan Tejani, Sasank Chilamkurthy, Benoit Steiner, Lu Fang, Junjie Bai, and Soumith Chintala. 2019. Pytorch: An imperative style, high-performance deep learning library. Advances in Neural Information Processing Systems 32 (2019)."},{"key":"e_1_3_2_1_77_1","volume-title":"The refinedweb dataset for falcon llm: Outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116","author":"Penedo Guilherme","year":"2023","unstructured":"Guilherme Penedo, Quentin Malartic, Daniel Hesslow, Ruxandra Cojocaru, Alessandro Cappelli, Hamza Alobeidli, Baptiste Pannier, Ebtesam Almazrouei, and Julien Launay. 2023. The refinedweb dataset for falcon llm: Outperforming curated corpora with web data, and web data only. arXiv preprint arXiv:2306.01116 (2023)."},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3052895"},{"key":"e_1_3_2_1_79_1","volume-title":"A survey on offline reinforcement learning: Taxonomy, review, and open problems","author":"Prudencio Rafael Figueiredo","year":"2023","unstructured":"Rafael Figueiredo Prudencio, Marcos R. O. A. Maximo, and Esther Luna Colombini. 2023. A survey on offline reinforcement learning: Taxonomy, review, and open problems. IEEE Transactions on Neural Networks and Learning Systems (2023), 1--21."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241565"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.5555\/3455716.3455856"},{"key":"e_1_3_2_1_82_1","unstructured":"Scott Reed Konrad Zolna Emilio Parisotto Sergio Gomez Colmenarejo Alexander Novikov Gabriel Barth-Maron Mai Gimenez Yury Sulsky Jackie Kay Jost Tobias Springenberg Tom Eccles Jake Bruce Ali Razavi Ashley Edwards Nicolas Heess Yutian Chen Raia Hadsell Oriol Vinyals Mahyar Bordbar and Nando de Freitas. 2022. A generalist agent. arXiv preprint arXiv:2205.06175 (2022)."},{"key":"e_1_3_2_1_83_1","volume-title":"Article 76 (may","author":"Ren Pengzhen","year":"2021","unstructured":"Pengzhen Ren, Yun Xiao, Xiaojun Chang, Po-yao Huang, Zhihui Li, Xiaojiang Chen, and Xin Wang. 2021. A Comprehensive Survey of Neural Architecture Search: Challenges and Solutions. ACM Comput. Surv. 54, 4, Article 76 (may 2021), 34 pages."},{"key":"e_1_3_2_1_84_1","doi-asserted-by":"publisher","DOI":"10.1145\/2483977.2483991"},{"key":"e_1_3_2_1_85_1","first-page":"5681","article-title":"Track: A new method from a re-examination of deep architectures for head motion prediction in 360\u00b0 videos","volume":"44","author":"Romero Rond\u00f3n Miguel Fabi\u00e1n","year":"2022","unstructured":"Miguel Fabi\u00e1n Romero Rond\u00f3n, Lucile Sassatelli, Ram\u00f3n Aparicio-Pardo, and Fr\u00e9d\u00e9ric Precioso. 2022. Track: A new method from a re-examination of deep architectures for head motion prediction in 360\u00b0 videos. IEEE Transactions on Pattern Analysis and Machine Intelligence 44, 9 (2022), 5681--5699.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"e_1_3_2_1_86_1","volume-title":"Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347","author":"Schulman John","year":"2017","unstructured":"John Schulman, Filip Wolski, Prafulla Dhariwal, Alec Radford, and Oleg Klimov. 2017. Proximal policy optimization algorithms. arXiv preprint arXiv:1707.06347 (2017)."},{"key":"e_1_3_2_1_87_1","unstructured":"Apache Spark. 2024. Job Scheduling - Spark 3.5.0 Documentation. (2024). https:\/\/spark.apache.org\/docs\/latest\/job-scheduling.html Accessed: 2024-01-08."},{"key":"e_1_3_2_1_88_1","volume-title":"Reinforcement learning: An introduction","author":"Sutton Richard S","unstructured":"Richard S Sutton and Andrew G Barto. 2018. Reinforcement learning: An introduction. MIT press."},{"key":"e_1_3_2_1_89_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_16"},{"key":"e_1_3_2_1_90_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548001"},{"key":"e_1_3_2_1_91_1","unstructured":"Gemini Team Rohan Anil Sebastian Borgeaud Yonghui Wu Jean-Baptiste Alayrac Jiahui Yu Radu Soricut Johan Schalkwyk Andrew M Dai Anja Hauth et al. 2023. Gemini: a family of highly capable multimodal models. arXiv preprint arXiv:2312.11805 (2023)."},{"key":"e_1_3_2_1_92_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale Dan Bikel Lukas Blecher Cristian Canton Ferrer Moya Chen Guillem Cucurull David Esiobu Jude Fernandes Jeremy Fu Wenyin Fu Brian Fuller Cynthia Gao Vedanuj Goswami Naman Goyal Anthony Hartshorn Saghar Hosseini Rui Hou Hakan Inan Marcin Kardas Viktor Kerkez Madian Khabsa Isabel Kloumann Artem Korenev Punit Singh Koura Marie-Anne Lachaux Thibaut Lavril Jenya Lee Diana Liskovich Yinghai Lu Yuning Mao Xavier Martinet Todor Mihaylov Pushkar Mishra Igor Molybog Yixin Nie Andrew Poulton Jeremy Reizenstein Rashi Rungta Kalyan Saladi Alan Schelten Ruan Silva Eric Michael Smith Ranjan Subramanian Xiaoqing Ellen Tan Binh Tang Ross Taylor Adina Williams Jian Xiang Kuan Puxin Xu Zheng Yan Iliyan Zarov Yuchen Zhang Angela Fan Melanie Kambadur Sharan Narang Aurelien Rodriguez Robert Stojnic Sergey Edunov and Thomas Scialom. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_93_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10295"},{"key":"e_1_3_2_1_94_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems 30","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. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_95_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.02.011"},{"key":"e_1_3_2_1_96_1","volume-title":"Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le.","author":"Wei Jason","year":"2022","unstructured":"Jason Wei, Maarten Bosma, Vincent Y Zhao, Kelvin Guu, Adams Wei Yu, Brian Lester, Nan Du, Andrew M Dai, and Quoc V Le. 2022. Finetuned language models are zero-shot learners. arXiv preprint arXiv:2109.01652 (2022)."},{"key":"e_1_3_2_1_97_1","doi-asserted-by":"publisher","DOI":"10.1145\/3083187.3083210"},{"key":"e_1_3_2_1_98_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.7377"},{"key":"e_1_3_2_1_99_1","volume-title":"Mansy: Generalizing neural adaptive immersive video streaming with ensemble and representation learning. arXiv preprint arXiv:2311.06812","author":"Wu Duo","year":"2023","unstructured":"Duo Wu, Panlong Wu, Miao Zhang, and Fangxin Wang. 2023. Mansy: Generalizing neural adaptive immersive video streaming with ensemble and representation learning. arXiv preprint arXiv:2311.06812 (2023)."},{"key":"e_1_3_2_1_100_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.346"},{"key":"e_1_3_2_1_101_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"e_1_3_2_1_102_1","unstructured":"Zhiheng Xi Wenxiang Chen Xin Guo Wei He Yiwen Ding Boyang Hong Ming Zhang Junzhe Wang Senjie Jin Enyu Zhou et al. 2023. The rise and potential of large language model based agents: A survey. arXiv preprint arXiv:2309.07864 (2023)."},{"key":"e_1_3_2_1_103_1","doi-asserted-by":"publisher","DOI":"10.1145\/3544216.3544243"},{"key":"e_1_3_2_1_104_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i9.26255"},{"key":"e_1_3_2_1_105_1","volume-title":"2020 USENIX Symposium on Networked Systems Design and Implementation (NSDI). 495--511","author":"Yan Francis Y","year":"2020","unstructured":"Francis Y Yan, Hudson Ayers, Chenzhi Zhu, Sadjad Fouladi, James Hong, Keyi Zhang, Philip Levis, and Keith Winstein. 2020. Learning in situ: A randomized experiment in video streaming. In 2020 USENIX Symposium on Networked Systems Design and Implementation (NSDI). 495--511."},{"key":"e_1_3_2_1_106_1","doi-asserted-by":"publisher","DOI":"10.1145\/3603269.3604838"},{"key":"e_1_3_2_1_107_1","doi-asserted-by":"publisher","DOI":"10.1145\/2785956.2787486"},{"key":"e_1_3_2_1_108_1","volume-title":"Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer.","author":"Zhang Susan","year":"2022","unstructured":"Susan Zhang, Stephen Roller, Naman Goyal, Mikel Artetxe, Moya Chen, Shuohui Chen, Christopher Dewan, Mona Diab, Xian Li, Xi Victoria Lin, Todor Mihaylov, Myle Ott, Sam Shleifer, Kurt Shuster, Daniel Simig, Punit Singh Koura, Anjali Sridhar, Tianlu Wang, and Luke Zettlemoyer. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:2205.01068 (2022)."},{"key":"e_1_3_2_1_109_1","first-page":"18309","article-title":"Advancing model pruning via bi-level optimization","volume":"35","author":"Zhang Yihua","year":"2022","unstructured":"Yihua Zhang, Yuguang Yao, Parikshit Ram, Pu Zhao, Tianlong Chen, Mingyi Hong, Yanzhi Wang, and Sijia Liu. 2022. Advancing model pruning via bi-level optimization. Advances in Neural Information Processing Systems 35 (2022), 18309--18326.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_110_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658673"},{"key":"e_1_3_2_1_111_1","doi-asserted-by":"crossref","unstructured":"Hao Zhou Chengming Hu Ye Yuan Yufei Cui Yili Jin Can Chen Haolun Wu Dun Yuan Li Jiang Di Wu et al. 2024. Large Language Model (LLM) for Telecommunications: A Comprehensive Survey on Principles Key Techniques and Opportunities. arXiv preprint arXiv:2405.10825 (2024).","DOI":"10.1109\/COMST.2024.3465447"},{"key":"e_1_3_2_1_112_1","volume-title":"Proceedings of the 2023 PMLR Conference on Robot Learning (CoRL). 2165--2183","author":"Zitkovich Brianna","year":"2023","unstructured":"Brianna Zitkovich, Tianhe Yu, Sichun Xu, Peng Xu, Ted Xiao, Fei Xia, Jialin Wu, Paul Wohlhart, Stefan Welker, Ayzaan Wahid, Quan Vuong, Vincent Vanhoucke, Huong Tran, Radu Soricut, Anikait Singh, Jaspiar Singh, Pierre Sermanet, Pannag R. Sanketi, Grecia Salazar, Michael S. Ryoo, Krista Reymann, Kanishka Rao, Karl Pertsch, Igor Mordatch, Henryk Michalewski, Yao Lu, Sergey Levine, Lisa Lee, Tsang-Wei Edward Lee, Isabel Leal, Yuheng Kuang, Dmitry Kalashnikov, Ryan Julian, Nikhil J. Joshi, Alex Irpan, Brian Ichter, Jasmine Hsu, Alexander Herzog, Karol Hausman, Keerthana Gopalakrishnan, Chuyuan Fu, Pete Florence, Chelsea Finn, Kumar Avinava Dubey, Danny Driess, Tianli Ding, Krzysztof Marcin Choromanski, Xi Chen, Yevgen Chebotar, Justice Carbajal, Noah Brown, Anthony Brohan, Montserrat Gonzalez Arenas, and Kehang Han. 2023. Rt-2: Vision-language-action models transfer web knowledge to robotic control. In Proceedings of the 2023 PMLR Conference on Robot Learning (CoRL). 2165--2183."}],"event":{"name":"ACM SIGCOMM '24: ACM SIGCOMM 2024 Conference","location":"Sydney NSW Australia","acronym":"ACM SIGCOMM '24","sponsor":["SIGCOMM ACM Special Interest Group on Data Communication"]},"container-title":["Proceedings of the ACM SIGCOMM 2024 Conference"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651890.3672268","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3651890.3672268","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T17:49:13Z","timestamp":1750268953000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3651890.3672268"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,4]]},"references-count":112,"alternative-id":["10.1145\/3651890.3672268","10.1145\/3651890"],"URL":"https:\/\/doi.org\/10.1145\/3651890.3672268","relation":{},"subject":[],"published":{"date-parts":[[2024,8,4]]},"assertion":[{"value":"2024-08-04","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}