{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T15:31:12Z","timestamp":1773588672762,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":61,"publisher":"ACM","funder":[{"name":"NSF (National Science Foundation)","award":["2442271"],"award-info":[{"award-number":["2442271"]}]},{"name":"RPI-IBM Future of Computing Research Collaboration","award":["A25-0057-007"],"award-info":[{"award-number":["A25-0057-007"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,3,22]]},"DOI":"10.1145\/3779212.3790226","type":"proceedings-article","created":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T13:55:26Z","timestamp":1773150926000},"page":"1863-1879","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["STARC: Selective Token Access with Remapping and Clustering for Efficient LLM Decoding on PIM Systems"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0021-2578","authenticated-orcid":false,"given":"Zehao","family":"Fan","sequence":"first","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2445-5765","authenticated-orcid":false,"given":"Yunzhen","family":"Liu","sequence":"additional","affiliation":[{"name":"University of Massachusetts, Amherst, Amherst, MA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-0754-9518","authenticated-orcid":false,"given":"Garrett","family":"Gagnon","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0047-7026","authenticated-orcid":false,"given":"Zhenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-6780-076X","authenticated-orcid":false,"given":"Yayue","family":"Hou","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5259-0749","authenticated-orcid":false,"given":"Hadjer","family":"Benmeziane","sequence":"additional","affiliation":[{"name":"IBM Research -- Ruschlikon, Ruschlikon, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1967-8749","authenticated-orcid":false,"given":"Kaoutar El","family":"Maghraoui","sequence":"additional","affiliation":[{"name":"IBM T. J. Watson Research Center, Yorktown Heights, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0792-8146","authenticated-orcid":false,"given":"Liu","family":"Liu","sequence":"additional","affiliation":[{"name":"Rensselaer Polytechnic Institute, Troy, NY, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,22]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al., 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.172"},{"key":"e_1_3_2_1_3_1","volume-title":"RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression. arXiv preprint arXiv:2502.14051","author":"Behnam Payman","year":"2025","unstructured":"Payman Behnam, Yaosheng Fu, Ritchie Zhao, Po-An Tsai, Zhiding Yu, and Alexey Tumanov. 2025. RocketKV: Accelerating Long-Context LLM Inference via Two-Stage KV Cache Compression. arXiv preprint arXiv:2502.14051 (2025)."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3458817.3476146"},{"key":"e_1_3_2_1_5_1","volume-title":"A dataset of information-seeking questions and answers anchored in research papers. arXiv preprint arXiv:2105.03011","author":"Dasigi Pradeep","year":"2021","unstructured":"Pradeep Dasigi, Kyle Lo, Iz Beltagy, Arman Cohan, Noah A Smith, and Matt Gardner. 2021. A dataset of information-seeking questions and answers anchored in research papers. arXiv preprint arXiv:2105.03011 (2021)."},{"key":"e_1_3_2_1_6_1","unstructured":"Abhimanyu Dubey Abhinav Jauhri Abhinav Pandey Abhishek Kadian Ahmad Al-Dahle Aiesha Letman Akhil Mathur Alan Schelten Amy Yang Angela Fan et al. 2024. The llama 3 herd of models. arXiv e-prints (2024) arXiv-2407."},{"key":"e_1_3_2_1_7_1","volume-title":"Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model. arXiv preprint arXiv:1906.01749","author":"Fabbri Alexander R","year":"2019","unstructured":"Alexander R Fabbri, Irene Li, Tianwei She, Suyi Li, and Dragomir R Radev. 2019. Multi-news: A large-scale multi-document summarization dataset and abstractive hierarchical model. arXiv preprint arXiv:1906.01749 (2019)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3352460.3358260"},{"key":"e_1_3_2_1_9_1","volume-title":"Model tells you what to discard: Adaptive kv cache compression for llms. arXiv preprint arXiv:2310.01801","author":"Ge Suyu","year":"2023","unstructured":"Suyu Ge, Yunan Zhang, Liyuan Liu, Minjia Zhang, Jiawei Han, and Jianfeng Gao. 2023. Model tells you what to discard: Adaptive kv cache compression for llms. arXiv preprint arXiv:2310.01801 (2023)."},{"key":"e_1_3_2_1_10_1","volume-title":"Dialogue without limits: Constant-sized kv caches for extended responses in llms. arXiv preprint arXiv:2503.00979","author":"Ghadia Ravi","year":"2025","unstructured":"Ravi Ghadia, Avinash Kumar, Gaurav Jain, Prashant Nair, and Poulami Das. 2025. Dialogue without limits: Constant-sized kv caches for extended responses in llms. arXiv preprint arXiv:2503.00979 (2025)."},{"key":"e_1_3_2_1_11_1","volume-title":"SAMSum corpus: A human-annotated dialogue dataset for abstractive summarization. arXiv preprint arXiv:1911.12237","author":"Gliwa Bogdan","year":"2019","unstructured":"Bogdan Gliwa, Iwona Mochol, Maciej Biesek, and Aleksander Wawer. 2019. SAMSum corpus: A human-annotated dialogue dataset for abstractive summarization. arXiv preprint arXiv:1911.12237 (2019)."},{"key":"e_1_3_2_1_12_1","volume-title":"International Conference on Machine Learning. PMLR, 12098-12107","author":"Guo Daya","year":"2023","unstructured":"Daya Guo, Canwen Xu, Nan Duan, Jian Yin, and Julian McAuley. 2023. Longcoder: A long-range pre-trained language model for code completion. In International Conference on Machine Learning. PMLR, 12098-12107."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO50266.2020.00040"},{"key":"e_1_3_2_1_14_1","volume-title":"PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System. arXiv preprint arXiv:2502.15470","author":"He Yintao","year":"2025","unstructured":"Yintao He, Haiyu Mao, Christina Giannoula, Mohammad Sadrosadati, Juan G\u00f3mez-Luna, Huawei Li, Xiaowei Li, Ying Wang, and Onur Mutlu. 2025. PAPI: Exploiting Dynamic Parallelism in Large Language Model Decoding with a Processing-In-Memory-Enabled Computing System. arXiv preprint arXiv:2502.15470 (2025)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651380"},{"key":"e_1_3_2_1_16_1","volume-title":"Squeezed attention: Accelerating long context length llm inference. arXiv preprint arXiv:2411.09688","author":"Hooper Coleman","year":"2024","unstructured":"Coleman Hooper, Sehoon Kim, Hiva Mohammadzadeh, Monishwaran Maheswaran, June Paik, Michael W Mahoney, Kurt Keutzer, and Amir Gholami. 2024. Squeezed attention: Accelerating long context length llm inference. arXiv preprint arXiv:2411.09688 (2024)."},{"key":"e_1_3_2_1_17_1","volume-title":"RULER: What's the Real Context Size of Your Long-Context Language Models? arXiv preprint arXiv:2404.06654","author":"Hsieh Cheng-Ping","year":"2024","unstructured":"Cheng-Ping Hsieh, Simeng Sun, Samuel Kriman, Shantanu Acharya, Dima Rekesh, Fei Jia, Yang Zhang, and Boris Ginsburg. 2024. RULER: What's the Real Context Size of Your Long-Context Language Models? arXiv preprint arXiv:2404.06654 (2024)."},{"key":"e_1_3_2_1_18_1","volume-title":"Efficient attentions for long document summarization. arXiv preprint arXiv:2104.02112","author":"Huang Luyang","year":"2021","unstructured":"Luyang Huang, Shuyang Cao, Nikolaus Parulian, Heng Ji, and Lu Wang. 2021. Efficient attentions for long document summarization. arXiv preprint arXiv:2104.02112 (2021)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA57654.2024.00029"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3307650.3322237"},{"key":"e_1_3_2_1_21_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:2310.06825 [cs.CL] https:\/\/arxiv.org\/abs\/2310.06825"},{"key":"e_1_3_2_1_22_1","volume-title":"Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. arXiv preprint arXiv:1705.03551","author":"Joshi Mandar","year":"2017","unstructured":"Mandar Joshi, Eunsol Choi, Daniel S Weld, and Luke Zettlemoyer. 2017. Triviaqa: A large scale distantly supervised challenge dataset for reading comprehension. arXiv preprint arXiv:1705.03551 (2017)."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00023"},{"key":"e_1_3_2_1_24_1","unstructured":"Hyucksung Kwon Kyungmo Koo Janghyeon Kim Woongkyu Lee Minjae Lee Hyungdeok Lee Yousub Jung Jaehan Park Yosub Song Byeongsu Yang et al. 2024. LoL-PIM: Long-Context LLM Decoding with Scalable DRAM-PIM System. arXiv preprint arXiv:2412.20166 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3600006.3613165"},{"key":"e_1_3_2_1_26_1","first-page":"155","volume-title":"18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24)","author":"Lee Wonbeom","year":"2024","unstructured":"Wonbeom Lee, Jungi Lee, Junghwan Seo, and Jaewoong Sim. 2024. : Efficient generative inference of large language models with dynamic cache management. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). 155-172."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3695053.3731008"},{"key":"e_1_3_2_1_28_1","unstructured":"Dacheng Li Rulin Shao Anze Xie Ying Sheng Lianmin Zheng Joseph E. Gonzalez Ion Stoica Xuezhe Ma and Hao Zhang. 2023. How Long Can Open-Source LLMs Truly Promise on Context Length? https:\/\/lmsys.org\/blog\/2023-06-29-longchat"},{"key":"e_1_3_2_1_29_1","first-page":"31199","article-title":"Pre-trained language models for interactive decision-making","volume":"35","author":"Li Shuang","year":"2022","unstructured":"Shuang Li, Xavier Puig, Chris Paxton, Yilun Du, Clinton Wang, Linxi Fan, Tao Chen, De-An Huang, Ekin Aky\u00fcrek, Anima Anandkumar, et al., 2022. Pre-trained language models for interactive decision-making. Advances in Neural Information Processing Systems, Vol. 35 (2022), 31199-31212.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.3115\/1072228.1072378"},{"key":"e_1_3_2_1_31_1","unstructured":"Aixin Liu Bei Feng Bing Xue Bingxuan Wang Bochao Wu Chengda Lu Chenggang Zhao Chengqi Deng Chenyu Zhang Chong Ruan et al. 2024a. Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)."},{"key":"e_1_3_2_1_32_1","volume-title":"Clusterkv: Manipulating llm kv cache in semantic space for recallable compression. arXiv preprint arXiv:2412.03213","author":"Liu Guangda","year":"2024","unstructured":"Guangda Liu, Chengwei Li, Jieru Zhao, Chenqi Zhang, and Minyi Guo. 2024b. Clusterkv: Manipulating llm kv cache in semantic space for recallable compression. arXiv preprint arXiv:2412.03213 (2024)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA61900.2025.00129"},{"key":"e_1_3_2_1_34_1","volume-title":"Repobench: Benchmarking repository-level code auto-completion systems. arXiv preprint arXiv:2306.03091","author":"Liu Tianyang","year":"2023","unstructured":"Tianyang Liu, Canwen Xu, and Julian McAuley. 2023b. Repobench: Benchmarking repository-level code auto-completion systems. arXiv preprint arXiv:2306.03091 (2023)."},{"key":"e_1_3_2_1_35_1","first-page":"52342","article-title":"Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time","volume":"36","author":"Liu Zichang","year":"2023","unstructured":"Zichang Liu, Aditya Desai, Fangshuo Liao, Weitao Wang, Victor Xie, Zhaozhuo Xu, Anastasios Kyrillidis, and Anshumali Shrivastava. 2023a. Scissorhands: Exploiting the persistence of importance hypothesis for llm kv cache compression at test time. Advances in Neural Information Processing Systems, Vol. 36 (2023), 52342-52364.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/LCA.2023.3333759"},{"key":"e_1_3_2_1_37_1","volume-title":"Mohammed E Elbtity, and Ramtin Zand.","author":"Malekar Jinendra","year":"2025","unstructured":"Jinendra Malekar, Peyton Chandarana, Md Hasibul Amin, Mohammed E Elbtity, and Ramtin Zand. 2025. PIM-LLM: A High-Throughput Hybrid PIM Architecture for 1-bit LLMs. arXiv preprint arXiv:2504.01994 (2025)."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3597503.3639187"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2022.3202350"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620665.3640422"},{"key":"e_1_3_2_1_41_1","first-page":"606","article-title":"Efficiently scaling transformer inference","volume":"5","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. Proceedings of Machine Learning and Systems, Vol. 5 (2023), 606-624.","journal-title":"Proceedings of Machine Learning and Systems"},{"key":"e_1_3_2_1_42_1","volume-title":"Compressive transformers for long-range sequence modelling. arXiv preprint arXiv:1911.05507","author":"Rae Jack W","year":"2019","unstructured":"Jack W Rae, Anna Potapenko, Siddhant M Jayakumar, and Timothy P Lillicrap. 2019. Compressive transformers for long-range sequence modelling. arXiv preprint arXiv:1911.05507 (2019)."},{"key":"e_1_3_2_1_43_1","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel Colin","year":"2020","unstructured":"Colin Raffel, Noam Shazeer, Adam Roberts, Katherine Lee, Sharan Narang, Michael Matena, Yanqi Zhou, Wei Li, and Peter J Liu. 2020. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, Vol. 21, 140 (2020), 1-67.","journal-title":"Journal of machine learning research"},{"key":"e_1_3_2_1_44_1","volume-title":"Carlo Luschi, and Douglas Orr","author":"Ribar Luka","year":"2023","unstructured":"Luka Ribar, Ivan Chelombiev, Luke Hudlass-Galley, Charlie Blake, Carlo Luschi, and Douglas Orr. 2023. Sparq attention: Bandwidth-efficient llm inference. arXiv preprint arXiv:2312.04985 (2023)."},{"key":"e_1_3_2_1_45_1","volume-title":"Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, et al.","author":"Roziere Baptiste","year":"2023","unstructured":"Baptiste Roziere, Jonas Gehring, Fabian Gloeckle, Sten Sootla, Itai Gat, Xiaoqing Ellen Tan, Yossi Adi, Jingyu Liu, Tal Remez, J\u00e9r\u00e9my Rapin, et al., 2023. Code llama: Open foundation models for code. arXiv preprint arXiv:2308.12950 (2023)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1145\/3620666.3651324"},{"key":"e_1_3_2_1_47_1","first-page":"8634","article-title":"Reflexion: Language agents with verbal reinforcement learning","volume":"36","author":"Shinn Noah","year":"2023","unstructured":"Noah Shinn, Federico Cassano, Ashwin Gopinath, Karthik Narasimhan, and Shunyu Yao. 2023. Reflexion: Language agents with verbal reinforcement learning. Advances in Neural Information Processing Systems, Vol. 36 (2023), 8634-8652.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330699"},{"key":"e_1_3_2_1_49_1","volume-title":"Quest: Query-aware sparsity for efficient long-context llm inference. arXiv preprint arXiv:2406.10774","author":"Tang Jiaming","year":"2024","unstructured":"Jiaming Tang, Yilong Zhao, Kan Zhu, Guangxuan Xiao, Baris Kasikci, and Song Han. 2024. Quest: Query-aware sparsity for efficient long-context llm inference. arXiv preprint arXiv:2406.10774 (2024)."},{"key":"e_1_3_2_1_50_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra Prajjwal Bhargava Shruti Bhosale et al. 2023. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00475"},{"key":"e_1_3_2_1_52_1","volume-title":"Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453","author":"Xiao Guangxuan","year":"2023","unstructured":"Guangxuan Xiao, Yuandong Tian, Beidi Chen, Song Han, and Mike Lewis. 2023. Efficient streaming language models with attention sinks. arXiv preprint arXiv:2309.17453 (2023)."},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1237"},{"key":"e_1_3_2_1_54_1","volume-title":"HotpotQA: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600","author":"Yang Zhilin","year":"2018","unstructured":"Zhilin Yang, Peng Qi, Saizheng Zhang, Yoshua Bengio, William W Cohen, Ruslan Salakhutdinov, and Christopher D Manning. 2018. HotpotQA: A dataset for diverse, explainable multi-hop question answering. arXiv preprint arXiv:1809.09600 (2018)."},{"key":"e_1_3_2_1_55_1","volume-title":"Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems","author":"Yao Shunyu","year":"2023","unstructured":"Shunyu Yao, Dian Yu, Jeffrey Zhao, Izhak Shafran, Tom Griffiths, Yuan Cao, and Karthik Narasimhan. 2023. Tree of thoughts: Deliberate problem solving with large language models. Advances in neural information processing systems, Vol. 36 (2023), 11809-11822."},{"key":"e_1_3_2_1_56_1","first-page":"34661","article-title":"H2o: Heavy-hitter oracle for efficient generative inference of large language models","volume":"36","author":"Zhang Zhenyu","year":"2023","unstructured":"Zhenyu Zhang, Ying Sheng, Tianyi Zhou, Tianlong Chen, Lianmin Zheng, Ruisi Cai, Zhao Song, Yuandong Tian, Christopher R\u00e9, Clark Barrett, et al., 2023. H2o: Heavy-hitter oracle for efficient generative inference of large language models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 34661-34710.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_57_1","unstructured":"Lianmin Zheng Wei-Lin Chiang Ying Sheng Tianle Li Siyuan Zhuang Zhanghao Wu Yonghao Zhuang Zhuohan Li Zi Lin Eric P Xing et al. 2023. Lmsys-chat-1m: A large-scale real-world llm conversation dataset. arXiv preprint arXiv:2309.11998 (2023)."},{"key":"e_1_3_2_1_58_1","volume-title":"Asli Celikyilmaz, Yang Liu, Xipeng Qiu, et al.","author":"Zhong Ming","year":"2021","unstructured":"Ming Zhong, Da Yin, Tao Yu, Ahmad Zaidi, Mutethia Mutuma, Rahul Jha, Ahmed Hassan Awadallah, Asli Celikyilmaz, Yang Liu, Xipeng Qiu, et al., 2021. QMSum: A new benchmark for query-based multi-domain meeting summarization. arXiv preprint arXiv:2104.05938 (2021)."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/HPCA53966.2022.00082"},{"key":"e_1_3_2_1_60_1","volume-title":"SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching. arXiv preprint arXiv:2504.00970","author":"Zhu Yuxuan","year":"2025","unstructured":"Yuxuan Zhu, Ali Falahati, David H Yang, and Mohammad Mohammadi Amiri. 2025. SentenceKV: Efficient LLM Inference via Sentence-Level Semantic KV Caching. arXiv preprint arXiv:2504.00970 (2025)."},{"key":"e_1_3_2_1_61_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Zhuang Yuchen","year":"2024","unstructured":"Yuchen Zhuang, Yue Yu, Kuan Wang, Haotian Sun, and Chao Zhang. 2024. Toolqa: A dataset for llm question answering with external tools. Advances in Neural Information Processing Systems, Vol. 36 (2024)."}],"event":{"name":"ASPLOS '26: 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems","location":"Pittsburgh PA USA","sponsor":["SIGOPS ACM Special Interest Group on Operating Systems","SIGPLAN ACM Special Interest Group on Programming Languages","SIGARCH ACM Special Interest Group on Computer Architecture","SIGBED ACM Special Interest Group on Embedded Systems"]},"container-title":["Proceedings of the 31st ACM International Conference on Architectural Support for Programming Languages and Operating Systems, Volume 2"],"original-title":[],"deposited":{"date-parts":[[2026,3,15]],"date-time":"2026-03-15T14:04:43Z","timestamp":1773583483000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3779212.3790226"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,22]]},"references-count":61,"alternative-id":["10.1145\/3779212.3790226","10.1145\/3779212"],"URL":"https:\/\/doi.org\/10.1145\/3779212.3790226","relation":{},"subject":[],"published":{"date-parts":[[2026,3,22]]},"assertion":[{"value":"2026-03-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}