{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T23:40:54Z","timestamp":1783035654910,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":92,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62032001"],"award-info":[{"award-number":["62032001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"111 Project","award":["B18001"],"award-info":[{"award-number":["B18001"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,21]]},"DOI":"10.1145\/3695053.3731008","type":"proceedings-article","created":{"date-parts":[[2025,6,20]],"date-time":"2025-06-20T16:43:11Z","timestamp":1750437791000},"page":"194-210","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":18,"title":["H\n            <sup>2<\/sup>\n            -LLM: Hardware-Dataflow Co-Exploration for Heterogeneous Hybrid-Bonding-based Low-Batch LLM Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7760-3254","authenticated-orcid":false,"given":"Cong","family":"Li","sequence":"first","affiliation":[{"name":"School of Integrated Circuits, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3848-3426","authenticated-orcid":false,"given":"Yihan","family":"Yin","sequence":"additional","affiliation":[{"name":"School of EECS, Peking university, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9971-2413","authenticated-orcid":false,"given":"Xintong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of EECS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4321-7694","authenticated-orcid":false,"given":"Jingchen","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1013-5781","authenticated-orcid":false,"given":"Zhutianya","family":"Gao","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8440-3875","authenticated-orcid":false,"given":"Dimin","family":"Niu","sequence":"additional","affiliation":[{"name":"Alibaba Group Inc., Sunnyvale, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8981-2876","authenticated-orcid":false,"given":"Qiang","family":"Wu","sequence":"additional","affiliation":[{"name":"Houmo AI, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4993-0087","authenticated-orcid":false,"given":"Xin","family":"Si","sequence":"additional","affiliation":[{"name":"SouthEast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2093-1788","authenticated-orcid":false,"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"HKUST, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2762-2726","authenticated-orcid":false,"given":"Chen","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7315-6589","authenticated-orcid":false,"given":"Guangyu","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Integrated Circuits, Peking University, Beijing, China and Beijing Advanced Innovation Center for Integrated Circuits, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,20]]},"reference":[{"key":"e_1_3_3_4_2_2","doi-asserted-by":"crossref","unstructured":"Joshua Ainslie James Lee-Thorp Michiel de Jong Yury Zemlyanskiy Federico Lebr\u00f3n and Sumit Sanghai. 2023. Gqa: Training generalized multi-query transformer models from multi-head checkpoints. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2305.13245 (2023).","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"e_1_3_3_4_3_2","unstructured":"Ebtesam Almazrouei Hamza Alobeidli Abdulaziz Alshamsi Alessandro Cappelli Ruxandra Cojocaru M\u00e9rouane Debbah \u00c9tienne Goffinet Daniel Hesslow Julien Launay Quentin Malartic Daniele Mazzotta Badreddine Noune Baptiste Pannier and Guilherme Penedo. 2023. The Falcon Series of Open Language Models. arxiv:https:\/\/arXiv.org\/abs\/2311.16867\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2311.16867"},{"key":"e_1_3_3_4_4_2","unstructured":"Amazon. [n. d.]. Bedrock. https:\/\/aws.amazon.com\/bedrock\/."},{"key":"e_1_3_3_4_5_2","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2309.16609\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2309.16609"},{"key":"e_1_3_3_4_6_2","unstructured":"Yushi Bai Xin Lv Jiajie Zhang Hongchang Lyu Jiankai Tang Zhidian Huang Zhengxiao Du Xiao Liu Aohan Zeng Lei Hou Yuxiao Dong Jie Tang and Juanzi Li. 2023. Longbench: A bilingual multitask benchmark for long context understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2308.14508 (2023)."},{"key":"e_1_3_3_4_7_2","unstructured":"Tom\u00a0B. Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared 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\u00a0M. Ziegler Jeffrey Wu Clemens Winter Christopher 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. Advances in neural information processing systems 33 (2020) 1877\u20131901."},{"key":"e_1_3_3_4_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731678"},{"key":"e_1_3_3_4_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00022"},{"key":"e_1_3_3_4_10_2","unstructured":"Mark Chen Jerry Tworek Heewoo Jun Qiming Yuan Henrique\u00a0Ponde de Oliveira\u00a0Pinto 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\u00a0Petroski Such Dave Cummings Matthias Plappert Fotios Chantzis Elizabeth Barnes Ariel Herbert-Voss William\u00a0Hebgen Guss Alex Nichol Alex Paino Nikolas Tezak Jie Tang Igor Babuschkin Suchir Balaji Shantanu Jain William Saunders Christopher Hesse Andrew\u00a0N. 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:https:\/\/arXiv.org\/abs\/2107.03374 (2021)."},{"key":"e_1_3_3_4_11_2","unstructured":"Tianqi Chen Lianmin Zheng Eddie Yan Ziheng Jiang Thierry Moreau Luis Ceze Carlos Guestrin and Arvind Krishnamurthy. 2018. Learning to optimize tensor programs. Advances in Neural Information Processing Systems 31 (2018)."},{"key":"e_1_3_3_4_12_2","unstructured":"Aakanksha Chowdhery Sharan Narang Jacob Devlin Maarten Bosma Gaurav Mishra Adam Roberts Paul Barham Hyung\u00a0Won 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\u00a0M. Dai Thanumalayan\u00a0Sankaranarayana 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. 2022. PaLM: Scaling Language Modeling with Pathways. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2204.02311 (2022)."},{"key":"e_1_3_3_4_13_2","doi-asserted-by":"crossref","unstructured":"Guohao Dai Tianhao Huang Yuze Chi Jishen Zhao Guangyu Sun Yongpan Liu Yu Wang Yuan Xie and Huazhong Yang. 2018. Graphh: A processing-in-memory architecture for large-scale graph processing. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 38 4 (2018) 640\u2013653.","DOI":"10.1109\/TCAD.2018.2821565"},{"key":"e_1_3_3_4_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2019.8875680"},{"key":"e_1_3_3_4_15_2","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan Anirudh Goyal Anthony Hartshorn Aobo Yang Archi Mitra Archie Sravankumar Artem Korenev Arthur Hinsvark Arun Rao Aston Zhang Aurelien Rodriguez Austen Gregerson Ava Spataru Baptiste Roziere Bethany Biron Binh Tang Bobbie Chern Charlotte Caucheteux Chaya Nayak Chloe Bi Chris Marra Chris McConnell Christian Keller Christophe Touret Chunyang Wu Corinne Wong Cristian\u00a0Canton Ferrer Cyrus Nikolaidis Damien Allonsius Daniel Song Danielle Pintz Danny Livshits David Esiobu Dhruv Choudhary Dhruv Mahajan Diego Garcia-Olano Diego Perino Dieuwke Hupkes Egor Lakomkin Ehab AlBadawy Elina Lobanova Emily Dinan Eric\u00a0Michael Smith Filip Radenovic Frank Zhang Gabriel Synnaeve Gabrielle Lee Georgia\u00a0Lewis Anderson Graeme Nail Gregoire Mialon Guan Pang Guillem Cucurell Hailey Nguyen Hannah Korevaar Hu Xu Hugo Touvron Iliyan Zarov Imanol\u00a0Arrieta Ibarra Isabel Kloumann Ishan Misra Ivan Evtimov Jade Copet Jaewon Lee Jan Geffert Jana Vranes Jason Park Jay Mahadeokar Jeet Shah Jelmer van\u00a0der Linde Jennifer Billock Jenny Hong Jenya Lee Jeremy Fu Jianfeng Chi Jianyu Huang Jiawen Liu Jie Wang Jiecao Yu Joanna Bitton Joe Spisak Jongsoo Park Joseph Rocca Joshua Johnstun Joshua Saxe Junteng Jia Kalyan\u00a0Vasuden Alwala Kartikeya Upasani Kate Plawiak Ke Li Kenneth Heafield Kevin Stone Khalid El-Arini Krithika Iyer Kshitiz Malik Kuenley Chiu Kunal Bhalla Lauren Rantala-Yeary Laurens van\u00a0der Maaten Lawrence Chen Liang Tan Liz Jenkins Louis Martin Lovish Madaan Lubo Malo Lukas Blecher Lukas Landzaat Luke de Oliveira Madeline Muzzi Mahesh Pasupuleti Mannat Singh Manohar Paluri Marcin Kardas Mathew Oldham Mathieu Rita Maya Pavlova Melanie Kambadur Mike Lewis Min Si Mitesh\u00a0Kumar Singh Mona Hassan Naman Goyal Narjes Torabi Nikolay Bashlykov Nikolay Bogoychev Niladri Chatterji Olivier Duchenne Onur \u00c7elebi Patrick Alrassy Pengchuan Zhang Pengwei Li Petar Vasic Peter Weng Prajjwal Bhargava Pratik Dubal Praveen Krishnan Punit\u00a0Singh Koura Puxin Xu Qing He Qingxiao Dong Ragavan Srinivasan Raj Ganapathy Ramon Calderer Ricardo\u00a0Silveira Cabral Robert Stojnic Roberta Raileanu Rohit Girdhar Rohit Patel Romain Sauvestre Ronnie Polidoro Roshan Sumbaly Ross Taylor Ruan Silva Rui Hou Rui Wang Saghar Hosseini Sahana Chennabasappa Sanjay Singh Sean Bell Seohyun\u00a0Sonia Kim Sergey Edunov Shaoliang Nie Sharan Narang Sharath Raparthy Sheng Shen Shengye Wan Shruti Bhosale Shun Zhang Simon Vandenhende Soumya Batra Spencer Whitman Sten Sootla Stephane Collot Suchin Gururangan Sydney Borodinsky Tamar Herman Tara Fowler Tarek Sheasha Thomas Georgiou Thomas Scialom Tobias Speckbacher Todor Mihaylov Tong Xiao Ujjwal Karn Vedanuj Goswami Vibhor Gupta Vignesh Ramanathan Viktor Kerkez Vincent Gonguet Virginie Do Vish Vogeti Vladan Petrovic Weiwei Chu Wenhan Xiong Wenyin Fu Whitney Meers Xavier Martinet Xiaodong Wang Xiaoqing\u00a0Ellen Tan Xinfeng Xie Xuchao Jia Xuewei Wang Yaelle Goldschlag Yashesh Gaur Yasmine Babaei Yi Wen Yiwen Song Yuchen Zhang Yue Li Yuning Mao Zacharie\u00a0Delpierre Coudert Zheng Yan Zhengxing Chen Zoe Papakipos Aaditya Singh Aaron Grattafiori Abha Jain Adam Kelsey Adam Shajnfeld Adithya Gangidi Adolfo Victoria Ahuva Goldstand Ajay Menon Ajay Sharma Alex Boesenberg Alex Vaughan Alexei Baevski Allie Feinstein Amanda Kallet Amit Sangani Anam Yunus Andrei Lupu Andres Alvarado Andrew Caples Andrew Gu Andrew Ho Andrew Poulton Andrew Ryan Ankit Ramchandani Annie Franco Aparajita Saraf Arkabandhu Chowdhury Ashley Gabriel Ashwin Bharambe Assaf Eisenman Azadeh Yazdan Beau James Ben Maurer Benjamin Leonhardi Bernie Huang Beth Loyd Beto\u00a0De Paola Bhargavi Paranjape Bing Liu Bo Wu Boyu Ni Braden Hancock Bram Wasti Brandon Spence Brani Stojkovic Brian Gamido Britt Montalvo Carl Parker Carly Burton Catalina Mejia Changhan Wang Changkyu Kim Chao Zhou Chester Hu Ching-Hsiang Chu Chris Cai Chris Tindal Christoph Feichtenhofer Damon Civin Dana Beaty Daniel Kreymer Daniel Li Danny Wyatt David Adkins David Xu Davide Testuggine Delia David Devi Parikh Diana Liskovich Didem Foss Dingkang Wang Duc Le Dustin Holland Edward Dowling Eissa Jamil Elaine Montgomery Eleonora Presani Emily Hahn Emily Wood Erik Brinkman Esteban Arcaute Evan Dunbar Evan Smothers Fei Sun Felix Kreuk Feng Tian Firat Ozgenel Francesco Caggioni Francisco Guzm\u00e1n Frank Kanayet Frank Seide Gabriela\u00a0Medina Florez Gabriella Schwarz Gada Badeer Georgia Swee Gil Halpern Govind Thattai Grant Herman Grigory Sizov Guangyi Zhang Guna Lakshminarayanan Hamid Shojanazeri Han Zou Hannah Wang Hanwen Zha Haroun Habeeb Harrison Rudolph Helen Suk Henry Aspegren Hunter Goldman Ibrahim Damlaj Igor Molybog Igor Tufanov Irina-Elena Veliche Itai Gat Jake Weissman James Geboski James Kohli Japhet Asher Jean-Baptiste Gaya Jeff Marcus Jeff Tang Jennifer Chan Jenny Zhen Jeremy Reizenstein Jeremy Teboul Jessica Zhong Jian Jin Jingyi Yang Joe Cummings Jon Carvill Jon Shepard Jonathan McPhie Jonathan Torres Josh Ginsburg Junjie Wang Kai Wu Kam\u00a0Hou U Karan Saxena Karthik Prasad Kartikay Khandelwal Katayoun Zand Kathy Matosich Kaushik Veeraraghavan Kelly Michelena Keqian Li Kun Huang Kunal Chawla Kushal Lakhotia Kyle Huang Lailin Chen Lakshya Garg Lavender A Leandro Silva Lee Bell Lei Zhang Liangpeng Guo Licheng Yu Liron Moshkovich Luca Wehrstedt Madian Khabsa Manav Avalani Manish Bhatt Maria Tsimpoukelli Martynas Mankus Matan Hasson Matthew Lennie Matthias Reso Maxim Groshev Maxim Naumov Maya Lathi Meghan Keneally Michael\u00a0L. Seltzer Michal Valko Michelle Restrepo Mihir Patel Mik Vyatskov Mikayel Samvelyan Mike Clark Mike Macey Mike Wang Miquel\u00a0Jubert Hermoso Mo Metanat Mohammad Rastegari Munish Bansal Nandhini Santhanam Natascha Parks Natasha White Navyata Bawa Nayan Singhal Nick Egebo Nicolas Usunier Nikolay\u00a0Pavlovich Laptev Ning Dong Ning Zhang Norman Cheng Oleg Chernoguz Olivia Hart Omkar Salpekar Ozlem Kalinli Parkin Kent Parth Parekh Paul Saab Pavan Balaji Pedro Rittner Philip Bontrager Pierre Roux Piotr Dollar Polina Zvyagina Prashant Ratanchandani Pritish Yuvraj Qian Liang Rachad Alao Rachel Rodriguez Rafi Ayub Raghotham Murthy Raghu Nayani Rahul Mitra Raymond Li Rebekkah Hogan Robin Battey Rocky Wang Rohan Maheswari Russ Howes Ruty Rinott Sai\u00a0Jayesh Bondu Samyak Datta Sara Chugh Sara Hunt Sargun Dhillon Sasha Sidorov Satadru Pan Saurabh Verma Seiji Yamamoto Sharadh Ramaswamy Shaun Lindsay Shaun Lindsay Sheng Feng Shenghao Lin Shengxin\u00a0Cindy Zha Shiva Shankar Shuqiang Zhang Shuqiang Zhang Sinong Wang Sneha Agarwal Soji Sajuyigbe Soumith Chintala Stephanie Max Stephen Chen Steve Kehoe Steve Satterfield Sudarshan Govindaprasad Sumit Gupta Sungmin Cho Sunny Virk Suraj Subramanian Sy Choudhury Sydney Goldman Tal Remez Tamar Glaser Tamara Best Thilo Kohler Thomas Robinson Tianhe Li Tianjun Zhang Tim Matthews Timothy Chou Tzook Shaked Varun Vontimitta Victoria Ajayi Victoria Montanez Vijai Mohan Vinay\u00a0Satish Kumar Vishal Mangla V\u00edtor Albiero Vlad Ionescu Vlad Poenaru Vlad\u00a0Tiberiu Mihailescu Vladimir Ivanov Wei Li Wenchen Wang Wenwen Jiang Wes Bouaziz Will Constable Xiaocheng Tang Xiaofang Wang Xiaojian Wu Xiaolan Wang Xide Xia Xilun Wu Xinbo Gao Yanjun Chen Ye Hu Ye Jia Ye Qi Yenda Li Yilin Zhang Ying Zhang Yossi Adi Youngjin Nam Yu Wang Yuchen Hao Yundi Qian Yuzi He Zach Rait Zachary DeVito Zef Rosnbrick Zhaoduo Wen Zhenyu Yang and Zhiwei Zhao. 2024. The llama 3 herd of models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.21783 (2024)."},{"key":"e_1_3_3_4_16_2","unstructured":"Zane Durante Qiuyuan Huang Naoki Wake Ran Gong Jae\u00a0Sung Park Bidipta Sarkar Rohan Taori Yusuke Noda Demetri Terzopoulos Yejin Choi Katsushi Ikeuchi Hoi Vo Li Fei-Fei and Jianfeng Gao. 2024. Agent ai: Surveying the horizons of multimodal interaction. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.03568 (2024)."},{"key":"e_1_3_3_4_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/IEDM13553.2020.9372039"},{"key":"e_1_3_3_4_18_2","unstructured":"Github. 2025. Copilot. https:\/\/github.com\/features\/copilot."},{"key":"e_1_3_3_4_19_2","unstructured":"Team GLM Aohan Zeng Bin Xu Bowen Wang Chenhui Zhang Da Yin Diego Rojas Guanyu Feng Hanlin Zhao Hanyu Lai Hao Yu Hongning Wang Jiadai Sun Jiajie Zhang Jiale Cheng Jiayi Gui Jie Tang Jing Zhang Juanzi Li Lei Zhao Lindong Wu Lucen Zhong Mingdao Liu Minlie Huang Peng Zhang Qinkai Zheng Rui Lu Shuaiqi Duan Shudan Zhang Shulin Cao Shuxun Yang Weng\u00a0Lam Tam Wenyi Zhao Xiao Liu Xiao Xia Xiaohan Zhang Xiaotao Gu Xin Lv Xinghan Liu Xinyi Liu Xinyue Yang Xixuan Song Xunkai Zhang Yifan An Yifan Xu Yilin Niu Yuantao Yang Yueyan Li Yushi Bai Yuxiao Dong Zehan Qi Zhaoyu Wang Zhen Yang Zhengxiao Du Zhenyu Hou and Zihan Wang. 2024. ChatGLM: A Family of Large Language Models from GLM-130B to GLM-4 All Tools. arxiv:https:\/\/arXiv.org\/abs\/2406.12793"},{"key":"e_1_3_3_4_20_2","unstructured":"Google. 2023. Bard. https:\/\/bard.google.com\/."},{"key":"e_1_3_3_4_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00071"},{"key":"e_1_3_3_4_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"e_1_3_3_4_23_2","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1606.08415 (2016)."},{"key":"e_1_3_3_4_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3577190.3614158"},{"key":"e_1_3_3_4_25_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"e_1_3_3_4_26_2","doi-asserted-by":"crossref","unstructured":"JH Holland. 1992. Genetic Algorithms. Scientific American (1992).","DOI":"10.1038\/scientificamerican0792-66"},{"key":"e_1_3_3_4_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO56248.2022.00051"},{"key":"e_1_3_3_4_28_2","unstructured":"Cunchen Hu Heyang Huang Junhao Hu Jiang Xu Xusheng Chen Tao Xie Chenxi Wang Sa Wang Yungang Bao Ninghui Sun and Yizhou Shan. 2024. Memserve: Context caching for disaggregated llm serving with elastic memory pool. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.17565 (2024)."},{"key":"e_1_3_3_4_29_2","unstructured":"Cunchen Hu Heyang Huang Liangliang Xu Xusheng Chen Jiang Xu Shuang Chen Hao Feng Chenxi Wang Sa Wang Yungang Bao Ninghui Sun and Yizhou Shan. 2024. Inference without interference: Disaggregate llm inference for mixed downstream workloads. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.11181 (2024)."},{"key":"e_1_3_3_4_30_2","first-page":"9118","volume-title":"International conference on machine learning","author":"Huang Wenlong","year":"2022","unstructured":"Wenlong Huang, Pieter Abbeel, Deepak Pathak, and Igor Mordatch. 2022. Language models as zero-shot planners: Extracting actionable knowledge for embodied agents. In International conference on machine learning. PMLR, 9118\u20139147."},{"key":"e_1_3_3_4_31_2","unstructured":"Wenlong Huang Fei Xia Ted Xiao Harris Chan Jacky Liang Pete Florence Andy Zeng Jonathan Tompson Igor Mordatch Yevgen Chebotar Pierre Sermanet Tomas Jackson Noah Brown Linda Luu Sergey Levine Karol Hausman and Brian Ichter. 2022. Inner monologue: Embodied reasoning through planning with language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2207.05608 (2022)."},{"key":"e_1_3_3_4_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358329"},{"key":"e_1_3_3_4_33_2","unstructured":"Mohamed Ibrahim Shaizeen Aga Ada Li Suchita Pati and Mahzabeen Islam. 2024. JIT-Q: Just-in-time Quantization with Processing-In-Memory for Efficient ML Training. Proceedings of Machine Learning and Systems 6 (2024) 46\u201359."},{"key":"e_1_3_3_4_34_2","doi-asserted-by":"crossref","unstructured":"Xiping Jiang Fengguo Zuo Song Wang Xiaofeng Zhou Yubing Wang Qi Liu Qiwei Ren and Ming Liu. 2022. A 1596-GB\/s 48-Gb stacked embedded DRAM 384-core SoC with hybrid bonding integration. IEEE Solid-State Circuits Letters 5 (2022) 110\u2013113.","DOI":"10.1109\/LSSC.2022.3171862"},{"key":"e_1_3_3_4_35_2","first-page":"745","volume-title":"21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24)","author":"Jiang Ziheng","year":"2024","unstructured":"Ziheng Jiang, Haibin Lin, Yinmin Zhong, Qi Huang, Yangrui Chen, Zhi Zhang, Yanghua Peng, Xiang Li, Cong Xie, Shibiao Nong, Yulu Jia, Sun He, Hongmin Chen, Zhihao Bai, Qi Hou, Shipeng Yan, Ding Zhou, Yiyao Sheng, Zhuo Jiang, Haohan Xu, Haoran Wei, Zhang Zhang, Pengfei Nie, Leqi Zou, Sida Zhao, Liang Xiang, Zherui Liu, Zhe Li, Xiaoying Jia, Jianxi Ye, Xin Jin, and Xin Liu. 2024. { MegaScale} : Scaling large language model training to more than 10,000 { GPUs}. In 21st USENIX Symposium on Networked Systems Design and Implementation (NSDI 24). 745\u2013760."},{"key":"e_1_3_3_4_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00010"},{"key":"e_1_3_3_4_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA45697.2020.00070"},{"key":"e_1_3_3_4_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS61935.2024.10664793"},{"key":"e_1_3_3_4_39_2","unstructured":"Hyungyo Kim Gaohan Ye Nachuan Wang Amir Yazdanbakhsh and Nam\u00a0Sung Kim. 2024. Exploiting Intel\u00ae Advanced Matrix Extensions (AMX) for Large Language Model Inference. IEEE Computer Architecture Letters (2024)."},{"key":"e_1_3_3_4_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS59251.2023.10254711"},{"key":"e_1_3_3_4_41_2","doi-asserted-by":"crossref","unstructured":"Hyoukjun Kwon Prasanth Chatarasi Vivek Sarkar Tushar Krishna Michael Pellauer and Angshuman Parashar. 2020. Maestro: A data-centric approach to understand reuse performance and hardware cost of dnn mappings. IEEE micro 40 3 (2020) 20\u201329.","DOI":"10.1109\/MM.2020.2985963"},{"key":"e_1_3_3_4_42_2","doi-asserted-by":"publisher","DOI":"10.1109\/HCS59251.2023.10254717"},{"key":"e_1_3_3_4_43_2","unstructured":"Jeston\u00a0AI Lab. 2025. Text Generation Webui. https:\/\/www.jetson-ai-lab.com\/tutorial_text-generation.html."},{"key":"e_1_3_3_4_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00013"},{"key":"e_1_3_3_4_45_2","first-page":"1","volume-title":"2022 IEEE International Solid-State Circuits Conference (ISSCC)","volume":"65","author":"Lee Seong\u00a0Ju","year":"2022","unstructured":"Seong\u00a0Ju Lee, Kyu-Young Kim, Sanghoon Oh, Joonhong Park, Gimoon Hong, Dong\u00a0Yoon Ka, Kyu-Dong Hwang, Jeongje Park, Kyeong\u00a0Pil Kang, Jungyeon Kim, Junyeol Jeon, Nahsung Kim, Yongkee Kwon, Kornijcuk Vladimir, Woojae Shin, Jongsoon Won, Minkyu Lee, Hyunha Joo, Haerang Choi, Jaewook Lee, Donguc Ko, Younggun Jun, Keewon Cho, Ilwoong Kim, Choungki Song, Chunseok Jeong, Dae-Han Kwon, Jieun Jang, Il Park, Junhyun Chun, and Joohwan Cho. 2022. A 1ynm 1.25 V 8Gb, 16Gb\/s\/pin GDDR6-based accelerator-in-memory supporting 1TFLOPS MAC operation and various activation functions for deep-learning applications. In 2022 IEEE International Solid-State Circuits Conference (ISSCC), Vol.\u00a065. IEEE, 1\u20133."},{"key":"e_1_3_3_4_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/DAC56929.2023.10247764"},{"key":"e_1_3_3_4_47_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640376"},{"key":"e_1_3_3_4_48_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651352"},{"key":"e_1_3_3_4_49_2","unstructured":"Jiaqi Li Mengmeng Wang Zilong Zheng and Muhan Zhang. 2023. LooGLE: Can Long-Context Language Models Understand Long Contexts? arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.04939 (2023)."},{"key":"e_1_3_3_4_50_2","unstructured":"Yuanchun Li Hao Wen Weijun Wang Xiangyu Li Yizhen Yuan Guohong Liu Jiacheng Liu Wenxing Xu Xiang Wang Yi Sun Rui Kong Yile Wang Hanfei Geng Jian Luan Xuefeng Jin Zilong Ye Guanjing Xiong Fan Zhang Xiang Li Mengwei Xu Zhijun Li Peng Li Yang Liu Ya-Qin Zhang and Yunxin Liu. 2024. Personal llm agents: Insights and survey about the capability efficiency and security. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.05459 (2024)."},{"key":"e_1_3_3_4_51_2","doi-asserted-by":"publisher","DOI":"10.1145\/3466752.3480090"},{"key":"e_1_3_3_4_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA52012.2021.00062"},{"key":"e_1_3_3_4_53_2","unstructured":"Haocong Luo Yahya\u00a0Can Tu F\u00a0Nisa Bostanc\u0131 Ataberk Olgun A\u00a0Giray Ya and Onur Mutlu. 2023. Ramulator 2.0: A Modern Modular and Extensible DRAM Simulator. IEEE Computer Architecture Letters (2023)."},{"key":"e_1_3_3_4_54_2","unstructured":"Kai Mei Zelong Li Shuyuan Xu Ruosong Ye Yingqiang Ge and Yongfeng Zhang. 2024. AIOS: LLM agent operating system. arXiv e-prints pp. arXiv\u20132403 (2024)."},{"key":"e_1_3_3_4_55_2","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:https:\/\/arXiv.org\/abs\/2203.13474 (2022)."},{"key":"e_1_3_3_4_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731694"},{"key":"e_1_3_3_4_57_2","unstructured":"NVIDIA. 2025. Jetson Modules. https:\/\/developer.nvidia.com\/embedded\/jetson-modules."},{"key":"e_1_3_3_4_58_2","unstructured":"OpenAI. 2022. Chatgpt. https:\/\/openai.com\/blog\/chatgpt."},{"key":"e_1_3_3_4_59_2","unstructured":"OpenAI. 2023. GPT-4 Technical Report. arxiv:https:\/\/arXiv.org\/abs\/2303.08774\u00a0[cs.CL]"},{"key":"e_1_3_3_4_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISPASS.2019.00042"},{"key":"e_1_3_3_4_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"e_1_3_3_4_62_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00019"},{"key":"e_1_3_3_4_63_2","unstructured":"J.\u00a0Thomas Pawlowski. 2019. Prospects for Memory."},{"key":"e_1_3_3_4_64_2","unstructured":"Baolin Peng Michel Galley Pengcheng He Hao Cheng Yujia Xie Yu Hu Qiuyuan Huang Lars Liden Zhou Yu Weizhu Chen and Jianfeng Gao. 2023. Check your facts and try again: Improving large language models with external knowledge and automated feedback. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.12813 (2023)."},{"key":"e_1_3_3_4_65_2","unstructured":"Ruoyu Qin Zheming Li Weiran He Mingxing Zhang Yongwei Wu Weimin Zheng and Xinran Xu. 2024. Mooncake: Kimi\u2019s KVCache-centric Architecture for LLM Serving. arXiv e-prints (2024) arXiv\u20132407."},{"key":"e_1_3_3_4_66_2","unstructured":"Alec Radford Jeffrey Wu Rewon Child David Luan Dario Amodei and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog 1 8 (2019) 9."},{"key":"e_1_3_3_4_67_2","unstructured":"Teven\u00a0Le Scao Angela Fan Christopher Akiki Ellie Pavlick Suzana Ili\u0107 Daniel Hesslow Roman Castagn\u00e9 Alexandra\u00a0Sasha Luccioni Fran\u00e7ois Yvon and Matthias Gall\u00e9. 2022. Bloom: A 176b-parameter open-access multilingual language model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2211.05100 (2022)."},{"key":"e_1_3_3_4_68_2","unstructured":"Noam Shazeer. 2019. Fast transformer decoding: One write-head is all you need 2019. URL https:\/\/arxiv. org\/abs (2019) 23."},{"key":"e_1_3_3_4_69_2","unstructured":"Noam Shazeer. 2020. Glu variants improve transformer. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2002.05202 (2020)."},{"key":"e_1_3_3_4_70_2","doi-asserted-by":"crossref","unstructured":"Hyunsung Shin Dongyoung Kim Eunhyeok Park Sungho Park Yongsik Park and Sungjoo Yoo. 2018. McDRAM: Low latency and energy-efficient matrix computations in DRAM. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems 37 11 (2018) 2613\u20132622.","DOI":"10.1109\/TCAD.2018.2857044"},{"key":"e_1_3_3_4_71_2","unstructured":"Sharegpt teams. 2023. ShareGPT Vicuna unfiltered. https:\/\/huggingface.co\/datasets\/anon8231489123\/ShareGPT_Vicuna_unfiltered."},{"key":"e_1_3_3_4_72_2","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2302.13971 (2023)."},{"key":"e_1_3_3_4_73_2","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\u00a0Canton 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\u00a0Singh 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\u00a0Michael Smith Ranjan Subramanian Xiaoqing\u00a0Ellen Tan Binh Tang Ross Taylor Adina Williams Jian\u00a0Xiang 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:https:\/\/arXiv.org\/abs\/2307.09288 (2023)."},{"key":"e_1_3_3_4_74_2","unstructured":"Ashish Vaswani Noam Shazeer Niki Parmar Jakob Uszkoreit Llion Jones Aidan\u00a0N. Gomez Lukasz Kaiser and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_3_4_75_2","unstructured":"Ben Wang. 2021. Mesh-Transformer-JAX: Model-Parallel Implementation of Transformer Language Model with JAX. https:\/\/github.com\/kingoflolz\/mesh-transformer-jax."},{"key":"e_1_3_3_4_76_2","doi-asserted-by":"crossref","unstructured":"Dingmin Wang Qiuyuan Huang Matthew Jackson and Jianfeng Gao. 2024. Retrieve What You Need: A Mutual Learning Framework for Open-domain Question Answering. Transactions of the Association for Computational Linguistics 12 (2024) 247\u2013263.","DOI":"10.1162\/tacl_a_00646"},{"key":"e_1_3_3_4_77_2","unstructured":"Yuxin Wang Yuhan Chen Zeyu Li Zhenheng Tang Rui Guo Xin Wang Qiang Wang Amelie\u00a0Chi Zhou and Xiaowen Chu. 2024. Towards Efficient and Reliable LLM Serving: A Real-World Workload Study. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.17644 (2024)."},{"key":"e_1_3_3_4_78_2","unstructured":"Yiming Wang Yu Lin Xiaodong Zeng and Guannan Zhang. 2023. Privatelora for efficient privacy preserving llm. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2311.14030 (2023)."},{"key":"e_1_3_3_4_79_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD45719.2019.8942149"},{"key":"e_1_3_3_4_80_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISSCC42614.2022.9731565"},{"key":"e_1_3_3_4_81_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00054"},{"key":"e_1_3_3_4_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA51647.2021.00055"},{"key":"e_1_3_3_4_83_2","unstructured":"Haoyan Yang Zhitao Li Yong Zhang Jianzong Wang Ning Cheng Ming Li and Jing Xiao. 2024. PFID: Privacy First Inference Delegation Framework for LLMs. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.12238 (2024)."},{"key":"e_1_3_3_4_84_2","doi-asserted-by":"publisher","unstructured":"Shouyi Yin Shibin Tang Xinhan Lin Peng Ouyang Fengbin Tu Leibo Liu Jishen Zhao Cong Xu Shuangchen Li Yuan Xie and Shaojun Wei. 2019. Parana: A Parallel Neural Architecture Considering Thermal Problem of 3D Stacked Memory. IEEE Trans. Parallel Distributed Syst. 30 1 (2019) 146\u2013160. 10.1109\/TPDS.2018.2858230","DOI":"10.1109\/TPDS.2018.2858230"},{"key":"e_1_3_3_4_85_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISCA59077.2024.00037"},{"key":"e_1_3_3_4_86_2","unstructured":"Sungmin Yun Kwanhee Kyung Juhwan Cho Jaewan Choi Jongmin Kim Byeongho Kim Sukhan Lee Kyomin Sohn and Jung\u00a0Ho Ahn. 2024. Duplex: A Device for Large Language Models with Mixture of Experts Grouped Query Attention and Continuous Batching. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2409.01141 (2024)."},{"key":"e_1_3_3_4_87_2","unstructured":"Susan Zhang Stephen Roller Naman Goyal Mikel Artetxe Moya Chen Shuohui Chen Christopher Dewan Mona Diab Xian Li Xi\u00a0Victoria Lin Todor Mihaylov Myle Ott Sam Shleifer Kurt Shuster Daniel Simig Punit\u00a0Singh Koura Anjali Sridhar Tianlu Wang and Luke Zettlemoyer. 2022. Opt: Open pre-trained transformer language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2205.01068 (2022)."},{"key":"e_1_3_3_4_88_2","first-page":"863","volume-title":"14th USENIX symposium on operating systems design and implementation (OSDI 20)","author":"Zheng Lianmin","year":"2020","unstructured":"Lianmin Zheng, Chengfan Jia, Minmin Sun, Zhao Wu, Cody\u00a0Hao Yu, Ameer Haj-Ali, Yida Wang, Jun Yang, Danyang Zhuo, Koushik Sen, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2020. Ansor: Generating { High-Performance} tensor programs for deep learning. In 14th USENIX symposium on operating systems design and implementation (OSDI 20). 863\u2013879."},{"key":"e_1_3_3_4_89_2","doi-asserted-by":"publisher","DOI":"10.1145\/3470496.3527440"},{"key":"e_1_3_3_4_90_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3623792"},{"key":"e_1_3_3_4_91_2","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. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2401.09670 (2024)."},{"key":"e_1_3_3_4_92_2","doi-asserted-by":"publisher","DOI":"10.1145\/3559009.3569670"},{"key":"e_1_3_3_4_93_2","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA56546.2023.10071005"}],"event":{"name":"ISCA '25: Proceedings of the 52nd Annual International Symposium on Computer Architecture","location":"Tokyo Japan","acronym":"SIGARCH '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 52nd Annual International Symposium on Computer Architecture"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3695053.3731008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,21]],"date-time":"2025-06-21T11:07:28Z","timestamp":1750504048000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3695053.3731008"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,20]]},"references-count":92,"alternative-id":["10.1145\/3695053.3731008","10.1145\/3695053"],"URL":"https:\/\/doi.org\/10.1145\/3695053.3731008","relation":{},"subject":[],"published":{"date-parts":[[2025,6,20]]},"assertion":[{"value":"2025-06-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}