{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:47:02Z","timestamp":1782546422130,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,5,19]],"date-time":"2026-05-19T00:00:00Z","timestamp":1779148800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,5,19]]},"DOI":"10.1145\/3801487.3801812","type":"proceedings-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:05:47Z","timestamp":1782543947000},"page":"280-289","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MKA: Memory-Keyed Attention for Efficient Long-Context Reasoning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-6815-8297","authenticated-orcid":false,"given":"Dong","family":"Liu","sequence":"first","affiliation":[{"name":"University of California - Los Angeles, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-7096-2438","authenticated-orcid":false,"given":"Yanxuan","family":"Yu","sequence":"additional","affiliation":[{"name":"Columbia University, New York, New York, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8690-9554","authenticated-orcid":false,"given":"Ben","family":"Lengerich","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, Wisconsin, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8029-3664","authenticated-orcid":false,"given":"Ying Nian","family":"Wu","sequence":"additional","affiliation":[{"name":"University of California - Los Angeles, Los Angeles, California, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,27]]},"reference":[{"key":"e_1_3_3_2_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. (2023). arxiv:https:\/\/arXiv.org\/abs\/2305.13245\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2305.13245","DOI":"10.18653\/v1\/2023.emnlp-main.298"},{"key":"e_1_3_3_2_3_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. 2024. LongBench: A Bilingual Multitask Benchmark for Long Context Understanding. (2024). arxiv:https:\/\/arXiv.org\/abs\/2408.13140\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2408.13140"},{"key":"e_1_3_3_2_4_2","unstructured":"Sebastian Borgeaud Arthur Mensch Jordan Hoffmann Trevor Cai Eliza Rutherford Katie Millican George van\u00a0den Driessche Jean-Baptiste Lespiau Bogdan Damoc Aidan Clark Diego de Las\u00a0Casas Aurelia Guy Jacob Menick Roman Ring Tom Hennigan Saffron Huang Loren Maggiore Chris Jones Albin Cassirer Andy Brock Michela Paganini Geoffrey Irving Oriol Vinyals Simon Osindero Karen Simonyan Jack\u00a0W. Rae Erich Elsen and Laurent Sifre. 2022. Improving language models by retrieving from trillions of tokens. (2022). arxiv:https:\/\/arXiv.org\/abs\/2112.04426\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2112.04426"},{"key":"e_1_3_3_2_5_2","unstructured":"Zefan Cai Yichi Zhang Bofei Gao Yuliang Liu Tianyu Liu Keming Lu Wayne Xiong Yue Dong Baobao Chang Junjie Hu and Wen Xiao. 2024. PyramidKV: Dynamic KV Cache Compression based on Pyramidal Information Funneling. (2024). arxiv:https:\/\/arXiv.org\/abs\/2406.02069\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2406.02069"},{"key":"e_1_3_3_2_6_2","volume-title":"The Fourteenth International Conference on Learning Representations","author":"Chen Zeming","year":"2026","unstructured":"Zeming Chen, Angelika Romanou, Gail Weiss, and Antoine Bosselut. 2026. PERK: Long-Context Reasoning as Parameter-Efficient Test-Time Learning. In The Fourteenth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=qxDTe8fIyA"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"e_1_3_3_2_8_2","unstructured":"Tri Dao. 2023. FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning. (2023). arxiv:https:\/\/arXiv.org\/abs\/2307.08691\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2307.08691"},{"key":"e_1_3_3_2_9_2","unstructured":"Tri Dao Daniel\u00a0Y. Fu Stefano Ermon Atri Rudra and Christopher R\u00e9. 2022. FlashAttention: Fast and Memory-Efficient Exact Attention with IO-Awareness. (2022). arxiv:https:\/\/arXiv.org\/abs\/2205.14135\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2205.14135"},{"key":"e_1_3_3_2_10_2","first-page":"1","volume-title":"Journal of Machine Learning Research","author":"Fedus William","year":"2022","unstructured":"William Fedus, Barret Zoph, and Noam Shazeer. 2022. Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity. In Journal of Machine Learning Research , Vol.\u00a023. 1\u201339."},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Alex Graves Greg Wayne Malcolm Reynolds Tim Harley Ivo Danihelka Agnieszka Grabska-Barwi\u0144ska Sergio\u00a0G\u00f3mez Colmenarejo Edward Grefenstette Tiago Ramalho John Agapiou et\u00a0al. 2016. Hybrid computing using a neural network with dynamic external memory. Nature 538 7626 (2016) 471\u2013476.","DOI":"10.1038\/nature20101"},{"key":"e_1_3_3_2_12_2","unstructured":"Huiqiang Jiang Qianhui Wu Xufang Luo Dongsheng Li Chin-Yew Lin Yuqing Yang and Lili Qiu. 2024. LongLLMLingua: Accelerating and Enhancing LLMs in Long Context Scenarios via Prompt Compression. (2024). arxiv:https:\/\/arXiv.org\/abs\/2310.06839\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2310.06839"},{"key":"e_1_3_3_2_13_2","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. InfiniGen: Efficient Generative Inference of Large Language Models with Dynamic KV Cache Management. In 18th USENIX Symposium on Operating Systems Design and Implementation (OSDI 24). https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/lee-wonbeom"},{"key":"e_1_3_3_2_14_2","volume-title":"International Conference on Learning Representations (ICLR)","author":"Lepikhin Dmitry","year":"2021","unstructured":"Dmitry Lepikhin, HyoukJoong Lee, Yuanzhong Xu, Dehao Chen, Orhan Firat, Yanping Huang, Maxim Krikun, Noam Shazeer, and Zhifeng Chen. 2021. GShard: Scaling giant models with conditional computation and automatic sharding. In International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_3_2_15_2","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. 2021. Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks. (2021). arxiv:https:\/\/arXiv.org\/abs\/2005.11401\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2005.11401"},{"key":"e_1_3_3_2_16_2","unstructured":"Xiabin Liu Yanan Zheng Zhenglin Wang et\u00a0al. 2024. DynamicKV: Task-Aware Adaptive KV Cache Compression for Long Context LLMs. (2024). arxiv:https:\/\/arXiv.org\/abs\/2412.14838\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2412.14838"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"crossref","unstructured":"Matanel Oren Michael Hassid Nir Yarden Yossi Adi and Roy Schwartz. 2024. Transformers are Multi-State RNNs. (2024). arxiv:https:\/\/arXiv.org\/abs\/2401.06104\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2401.06104","DOI":"10.18653\/v1\/2024.emnlp-main.1043"},{"key":"e_1_3_3_2_18_2","unstructured":"Bowen Peng Jeffrey Quesnelle Honglu Fan and Enrico Shippole. 2023. YaRN: Efficient Context Window Extension of Large Language Models. (2023). arxiv:https:\/\/arXiv.org\/abs\/2309.00071\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2309.00071"},{"key":"e_1_3_3_2_19_2","volume-title":"International Conference on Learning Representations","author":"Rae Jack\u00a0W.","year":"2020","unstructured":"Jack\u00a0W. Rae, Anna Potapenko, Siddhant\u00a0M. Jayakumar, Chloe Hillier, and Timothy\u00a0P. Lillicrap. 2020. Compressive Transformers for Long-Range Sequence Modelling. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=SylKikSYDH"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"crossref","unstructured":"Aurko Roy Mohammad Saffar Ashish Vaswani and David Grangier. 2021. Efficient content-based sparse attention with routing transformers. Transactions of the Association for Computational Linguistics 9 (2021) 53\u201368.","DOI":"10.1162\/tacl_a_00353"},{"key":"e_1_3_3_2_21_2","unstructured":"Noam Shazeer. 2019. Fast Transformer Decoding: One Write-Head is All You Need. (2019). arxiv:https:\/\/arXiv.org\/abs\/1911.02150\u00a0[cs.NE] https:\/\/arxiv.org\/abs\/1911.02150"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"crossref","unstructured":"Mustafa Shukor Enrico Fini Victor Guilherme\u00a0Turrisi da Costa Matthieu Cord Joshua Susskind and Alaaeldin El-Nouby. 2025. Scaling Laws for Native Multimodal Models. (2025). arxiv:https:\/\/arXiv.org\/abs\/2504.07951\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2504.07951","DOI":"10.1109\/ICCV51701.2025.00009"},{"key":"e_1_3_3_2_23_2","unstructured":"Simeng Sun Yang Liu Dan Iter Chenguang Zhu Michael Zeng and Mohit Iyyer. 2024. RULER: What\u2019s the Real Context Size of Your Long-Context Language Models? (2024). arxiv:https:\/\/arXiv.org\/abs\/2404.06654\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2404.06654"},{"key":"e_1_3_3_2_24_2","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. (2024). arxiv:https:\/\/arXiv.org\/abs\/2406.10774\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2406.10774"},{"key":"e_1_3_3_2_25_2","unstructured":"DeepSeek Team. 2024. DeepSeek-V2 Technical Report. https:\/\/github.com\/deepseek-ai\/deepseek-v2. (2024)."},{"key":"e_1_3_3_2_26_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. (2023). arxiv:https:\/\/arXiv.org\/abs\/2302.13971\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2302.13971"},{"key":"e_1_3_3_2_27_2","unstructured":"Szymon Tworkowski Konrad Staniszewski Miko\u0142aj Pacek Yuhuai Wu Henryk Michalewski and Piotr Mi\u0142o\u015b. 2023. Focused Transformer: Contrastive Training for Context Scaling. (2023). arxiv:https:\/\/arXiv.org\/abs\/2307.03170\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2307.03170"},{"key":"e_1_3_3_2_28_2","unstructured":"Jason Weston Sumit Chopra and Antoine Bordes. 2015. Memory Networks. (2015). arxiv:https:\/\/arXiv.org\/abs\/1410.3916\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/1410.3916"},{"key":"e_1_3_3_2_29_2","unstructured":"Xiaoju Ye Shi Han and Dongmei Zhang. 2024. Infinite Retrieval: Attention Enhanced LLMs in Long-Context Processing. (2024). arxiv:https:\/\/arXiv.org\/abs\/2407.19525\u00a0[cs.CL] https:\/\/arxiv.org\/abs\/2407.19525"}],"event":{"name":"CF '26: Proceedings of the 23rd ACM International Conference on Computing Frontiers","location":"Catania Italy","acronym":"CF '26","sponsor":["SIGMICRO ACM Special Interest Group on Microarchitectural Research and Processing"]},"container-title":["Proceedings of the 23rd ACM International Conference on Computing Frontiers"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3801487.3801812","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T07:07:42Z","timestamp":1782544062000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3801487.3801812"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,19]]},"references-count":28,"alternative-id":["10.1145\/3801487.3801812","10.1145\/3801487"],"URL":"https:\/\/doi.org\/10.1145\/3801487.3801812","relation":{},"subject":[],"published":{"date-parts":[[2026,5,19]]},"assertion":[{"value":"2026-06-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}