{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T13:04:51Z","timestamp":1776085491780,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":42,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China","award":["62372298"],"award-info":[{"award-number":["62372298"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3772363.3798936","type":"proceedings-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T01:55:24Z","timestamp":1776045324000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Just-in-Time Tokens: Adaptive Token Pacing for Cognitive-Friendly LLM Streaming"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4550-3826","authenticated-orcid":false,"given":"Hailiang","family":"Zhu","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-5987-9545","authenticated-orcid":false,"given":"Junye","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7748-2971","authenticated-orcid":false,"given":"Laixin","family":"Xie","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0841-7251","authenticated-orcid":false,"given":"Ruofei","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1600-2758","authenticated-orcid":false,"given":"Yingbin","family":"Sun","sequence":"additional","affiliation":[{"name":"Library and IT Services, ShanghaiTech University, Shanghai, China\/Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8769-293X","authenticated-orcid":false,"given":"Fangxin","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0226-9399","authenticated-orcid":false,"given":"Chengbo","family":"Zheng","sequence":"additional","affiliation":[{"name":"The University of Queensland, Brisbane, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2249-0728","authenticated-orcid":false,"given":"Quan","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, ShanghaiTech University, Shanghai, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,4,13]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"Jimmy\u00a0Lei Ba Jamie\u00a0Ryan Kiros and Geoffrey\u00a0E. Hinton. 2016. Layer Normalization. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1607.06450 (2016)."},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","unstructured":"Dami\u00e1n\u00a0E. Blasi Joseph Henrich Evangelia Adamou David Kemmerer and Asifa Majid. 2022. Over-reliance on English hinders cognitive science. Trends in Cognitive Sciences 26 (2022) 1153\u20131170. 10.1016\/j.tics.2022.09.014","DOI":"10.1016\/j.tics.2022.09.014"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPC.2015.36"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","unstructured":"Uschi Cop Denis Drieghe and Wouter Duyck. 2017. Presenting GECO: An Eye-Tracking Corpus of Monolingual and Bilingual Sentence Reading. Behavior Research Methods 49 2 (2017) 602\u2013615. 10.3758\/s13428-016-0734-0","DOI":"10.3758\/s13428-016-0734-0"},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"publisher","unstructured":"Shuwen Deng David\u00a0R. Reich Paul Prasse Patrick Haller Tobias Scheffer and Lena\u00a0A. J\u00e4ger. 2023. Eyettention: An Attention-based Dual-Sequence Model for Predicting Human Scanpaths during Reading. Proceedings of the ACM on Human-Computer Interaction 7 Article 162 (2023) 24\u00a0pages. 10.1145\/3591131","DOI":"10.1145\/3591131"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Ralf Engbert Antje Nuthmann Eike\u00a0M. Richter and Reinhold Kliegl. 2005. SWIFT: A dynamical model of saccade generation during reading. Psychological Review 112 4 (2005) 777\u2013813.","DOI":"10.1037\/0033-295X.112.4.777"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"crossref","unstructured":"Lan Fang Yiyang Xie Keke Yu Ruiming Wang and John\u00a0W. Schwieter. 2021. An examination of prosody and second language sentence processing through pause insertion. International Journal of Bilingualism 25 5 (2021) 1473\u20131485.","DOI":"10.1177\/13670069211018753"},{"key":"e_1_3_3_1_10_2","unstructured":"Leo Gao Stella Biderman Sid Black Laurence Golding Travis Hoppe Charles Foster Jason Phang Horace He Anish Thite Noa Nabeshima et\u00a0al. 2020. The pile: An 800gb dataset of diverse text for language modeling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2101.00027 (2020)."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Muhammad\u00a0Usman Hadi Qasem Al-Tashi Rizwan Qureshi Abbas Shah Amgad Muneer Muhammad Irfan Anas Zafar Muhammad Shaikh Naveed Akhtar Jia Wu and Seyedali Mirjalili. 2023. Large Language Models: A Comprehensive Survey of Its Applications Challenges Limitations and Future Prospects. TechRxiv (July 2023). 10.36227\/techrxiv.23589741.v1Preprint.","DOI":"10.36227\/techrxiv.23589741.v1"},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","unstructured":"Michael Hahn and Frank Keller. 2023. Modeling task effects in human reading with neural network-based attention. Cognition 230 (2023) 105289. 10.1016\/j.cognition.2022.105289","DOI":"10.1016\/j.cognition.2022.105289"},{"key":"e_1_3_3_1_13_2","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1502.03167 (2015)."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1145\/3586183.3606737"},{"key":"e_1_3_3_1_15_2","series-title":"(NeurIPS \u201923)","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","author":"Jin Yunho","year":"2023","unstructured":"Yunho Jin, Chun-Feng Wu, David Brooks, and Gu-Yeon Wei. 2023. S3: Increasing GPU Utilization During Generative Inference for Higher Throughput. In Proceedings of the 37th International Conference on Neural Information Processing Systems(NeurIPS \u201923). Curran Associates, Inc., Red Hook, NY, USA, Article 791, 13\u00a0pages. https:\/\/papers.nips.cc\/paper_files\/paper\/2023\/hash\/9bdb2f09f78d5ed38bcf9ef9a3577e57-Abstract-Conference.html"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","unstructured":"Marcel\u00a0A. Just and Patricia\u00a0A. Carpenter. 1992. A Capacity Theory of Comprehension: Individual Differences in Working Memory. Psychological Review 99 1 (1992) 122\u2013149. 10.1037\/0033-295X.99.1.122","DOI":"10.1037\/0033-295X.99.1.122"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3640543.3645148"},{"key":"e_1_3_3_1_18_2","doi-asserted-by":"publisher","unstructured":"Victor Kuperman Michal Siegelman Martin Paczynski et\u00a0al. 2020. Text Reading in English and Russian: Evidence from the Multilingual Eye-Movement Corpus (MECO). Behavior Research Methods 52 6 (2020) 2362\u20132379. 10.3758\/s13428-020-01374-0","DOI":"10.3758\/s13428-020-01374-0"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"publisher","unstructured":"Marta Kutas and Kara\u00a0D. Federmeier. 2011. Thirty Years and Counting: Finding Meaning in the N400 Component of the Event-Related Brain Potential (ERP). Annual Review of Psychology 62 (2011) 621\u2013647. 10.1146\/annurev.psych.093008.131123","DOI":"10.1146\/annurev.psych.093008.131123"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Tom Kwiatkowski Jennimaria Palomaki Olivia Redfield Michael Collins Ankur Parikh Chris Alberti Danielle Epstein Illia Polosukhin Jacob Devlin Kenton Lee et\u00a0al. 2019. Natural questions: a benchmark for question answering research. Transactions of the Association for Computational Linguistics 7 (2019) 453\u2013466.","DOI":"10.1162\/tacl_a_00276"},{"key":"e_1_3_3_1_21_2","unstructured":"Woosuk Kwon Zhuohan Li Siyuan Zhuang Ying Sheng Lianmin Zheng Cody\u00a0Hao Yu Joseph\u00a0E. Gonzalez Hao Zhang and Ion Stoica. 2023. Efficient Memory Management for Large Language Model Serving with PagedAttention. arxiv:https:\/\/arXiv.org\/abs\/2309.06180\u00a0[cs.LG] https:\/\/arxiv.org\/abs\/2309.06180"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3672198.3673797"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","unstructured":"Xingshan Li Linjieqiong Huang Panpan Yao and Jukka Hy\u00f6n\u00e4. 2022. Universal and specific reading mechanisms across different writing systems. Nature Reviews Psychology 1 (2022) 133\u2013144. 10.1038\/s44159-022-00014-5","DOI":"10.1038\/s44159-022-00014-5"},{"key":"e_1_3_3_1_24_2","unstructured":"Jiachen Liu Jae-Won Chung Zhiyu Wu Fan Lai Myungjin Lee and Mosharaf Chowdhury. 2024. Andes: Defining and Enhancing Quality-of-Experience in LLM-Based Text Streaming Services. arxiv:https:\/\/arXiv.org\/abs\/2404.16283\u00a0[cs.DC] https:\/\/arxiv.org\/abs\/2404.16283"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"publisher","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 Article 195 (Sept. 2023) 35\u00a0pages. 10.1145\/3560815","DOI":"10.1145\/3560815"},{"key":"e_1_3_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1145\/1357054.1357072"},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"crossref","unstructured":"Keith Rayner. 1998. Eye movements in reading and information processing: 20 years of research. Psychological Bulletin 124 3 (1998) 372\u2013422.","DOI":"10.1037\/0033-2909.124.3.372"},{"key":"e_1_3_3_1_28_2","doi-asserted-by":"crossref","unstructured":"Erik\u00a0D. Reichle Keith Rayner and Alexander Pollatsek. 2003. The EZ Reader model of eye-movement control in reading: Comparisons to other models. Behavioral and Brain Sciences 26 4 (2003) 445\u2013476.","DOI":"10.1017\/S0140525X03000104"},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","unstructured":"Joshua\u00a0S. Rubinstein David\u00a0E. Meyer and Jeffrey\u00a0E. Evans. 2001. Executive Control of Cognitive Processes in Task Switching. Journal of Experimental Psychology: Human Perception and Performance 27 4 (2001) 763\u2013797. 10.1037\/0096-1523.27.4.763","DOI":"10.1037\/0096-1523.27.4.763"},{"key":"e_1_3_3_1_30_2","doi-asserted-by":"publisher","unstructured":"Nadia Salem Amjad Hudaib Khawla Al-Tarawneh Hamza Salem Afaf Tareef Hadi Salloum and Manuel Mazzara. 2024. A Survey on the Application of Large Language Models in Software Engineering. Computer Research and Modeling 16 7 (Dec. 2024) 1715\u20131726. 10.20537\/2076-7633-2024-16-7-1715-1726","DOI":"10.20537\/2076-7633-2024-16-7-1715-1726"},{"key":"e_1_3_3_1_31_2","first-page":"6854","volume-title":"Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC 2022)","author":"S\u00e4lev\u00e4 Simo","year":"2022","unstructured":"Simo S\u00e4lev\u00e4 et\u00a0al. 2022. The Turku Eye-Tracking Corpus of Reading (TECO). In Proceedings of the Thirteenth Language Resources and Evaluation Conference (LREC 2022). European Language Resources Association (ELRA), Marseille, France, 6854\u20136863. https:\/\/aclanthology.org\/2022.lrec-1.737"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","unstructured":"Mike Scaife and Yvonne Rogers. 1996. External Cognition: How Do Graphical Representations Work? International Journal of Human-Computer Studies 45 2 (Aug. 1996) 185\u2013213. 10.1006\/ijhc.1996.0048","DOI":"10.1006\/ijhc.1996.0048"},{"key":"e_1_3_3_1_33_2","unstructured":"Ying Sheng Shiyi Cao Dacheng Li Banghua Zhu Zhuohan Li Danyang Zhuo Joseph\u00a0E. Gonzalez and Ion Stoica. 2024. Fairness in Serving Large Language Models. arxiv:https:\/\/arXiv.org\/abs\/2401.00588\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2401.00588"},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"publisher","unstructured":"Alexander Skulmowski and Kate\u00a0Man Xu. 2022. Understanding Cognitive Load in Digital and Online Learning: A New Perspective on Extraneous Cognitive Load. Educational Psychology Review 34 1 (2022) 171\u2013196. 10.1007\/s10648-021-09624-7","DOI":"10.1007\/s10648-021-09624-7"},{"key":"e_1_3_3_1_35_2","doi-asserted-by":"publisher","unstructured":"Alexander Skulmowski and Ke\u00a0M. Xu. 2022. Understanding Cognitive Load in Digital and Online Learning: A New Perspective on Extraneous Cognitive Load. Educational Psychology Review 34 (2022) 171\u2013196. 10.1007\/s10648-021-09624-7","DOI":"10.1007\/s10648-021-09624-7"},{"key":"e_1_3_3_1_36_2","series-title":"(OSDI \u201924)","volume-title":"Proceedings of the 18th USENIX Conference on Operating Systems Design and Implementation","author":"Sun Biao","year":"2024","unstructured":"Biao Sun, Ziming Huang, Hanyu Zhao, Wencong Xiao, Xinyi Zhang, Yong Li, and Wei Lin. 2024. Llumnix: Dynamic Scheduling for Large Language Model Serving. In Proceedings of the 18th USENIX Conference on Operating Systems Design and Implementation(OSDI \u201924). USENIX Association, Santa Clara, CA, USA, Article 10, 19\u00a0pages. https:\/\/www.usenix.org\/conference\/osdi24\/presentation\/sun-biao"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","unstructured":"John Sweller. 1988. Cognitive Load During Problem Solving: Effects on Learning. Cognitive Science 12 2 (1988) 257\u2013285. 10.1016\/0364-0213(88)90023-7","DOI":"10.1016\/0364-0213(88)90023-7"},{"key":"e_1_3_3_1_38_2","unstructured":"Simon Torka and Sahin Albayrak. 2024. ALPACA\u2013Adaptive Learning Pipeline for Comprehensive AI. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.10950 (2024)."},{"key":"e_1_3_3_1_39_2","volume-title":"What is LLM Streaming and How to Use It?","author":"AI Vellum","year":"2025","unstructured":"Vellum AI. 2025. What is LLM Streaming and How to Use It?Retrieved September 11, 2025 from https:\/\/www.vellum.ai\/llm-parameters\/llm-streaming"},{"key":"e_1_3_3_1_40_2","unstructured":"Jiayin Wang Weizhi Ma Peijie Sun Min Zhang and Jian-Yun Nie. 2024. Understanding User Experience in Large Language Model Interactions. arxiv:https:\/\/arXiv.org\/abs\/2401.08329https:\/\/arxiv.org\/abs\/2401.08329"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","unstructured":"Xiaoming Wang Xinbo Zhao and Yanning Zhang. 2021. Deep-learning-based reading eye-movement analysis for aiding biometric recognition. Neurocomputing 444 (2021) 390\u2013398. 10.1016\/j.neucom.2020.06.137","DOI":"10.1016\/j.neucom.2020.06.137"},{"key":"e_1_3_3_1_42_2","unstructured":"Chang Xiao and Brenda\u00a0Z. Yang. 2025. Streaming Fast and Slow: Cognitive Load-Aware Streaming for Efficient LLM Serving. arxiv:https:\/\/arXiv.org\/abs\/2504.17999https:\/\/arxiv.org\/abs\/2504.17999"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676374"}],"event":{"name":"CHI EA '26: Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems","location":"Barcelona , Spain","acronym":"CHI EA '26","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the Extended Abstracts of the 2026 CHI Conference on Human Factors in Computing Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3772363.3798936","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T12:26:48Z","timestamp":1776083208000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3772363.3798936"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,13]]},"references-count":42,"alternative-id":["10.1145\/3772363.3798936","10.1145\/3772363"],"URL":"https:\/\/doi.org\/10.1145\/3772363.3798936","relation":{},"subject":[],"published":{"date-parts":[[2026,4,13]]},"assertion":[{"value":"2026-04-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}