{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T21:07:39Z","timestamp":1760044059490,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,4,28]]},"DOI":"10.1145\/3696410.3714737","type":"proceedings-article","created":{"date-parts":[[2025,5,5]],"date-time":"2025-05-05T16:42:02Z","timestamp":1746463322000},"page":"4699-4709","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["AI Model Modulation with Logits Redistribution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6536-2948","authenticated-orcid":false,"given":"Zihan","family":"Wang","sequence":"first","affiliation":[{"name":"University of Queensland, Brisbane, Australia and CSIRO's Data61, Brisbane, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2392-3751","authenticated-orcid":false,"given":"Zhongkui","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Queensland, Brisbane, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2307-2771","authenticated-orcid":false,"given":"Xinguo","family":"Feng","sequence":"additional","affiliation":[{"name":"University of Queensland, Brisbane, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9990-009X","authenticated-orcid":false,"given":"Zhiyang","family":"Mei","sequence":"additional","affiliation":[{"name":"University of Queensland, Brisbane, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8672-4251","authenticated-orcid":false,"given":"Ethan","family":"Ma","sequence":"additional","affiliation":[{"name":"University of Queensland, Brisbane, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1388-7715","authenticated-orcid":false,"given":"Derui","family":"Wang","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, Melbourne, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9172-4252","authenticated-orcid":false,"given":"Minhui","family":"Xue","sequence":"additional","affiliation":[{"name":"CSIRO's Data61, Adelaide, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6390-9890","authenticated-orcid":false,"given":"Guangdong","family":"Bai","sequence":"additional","affiliation":[{"name":"University of Queensland, Brisbane, Australia"}]}],"member":"320","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2018. cutout.pro. https:\/\/www.cutout.pro."},{"key":"e_1_3_2_1_2_1","unstructured":"2023. together.ai. https:\/\/www.together.ai."},{"key":"e_1_3_2_1_3_1","unstructured":"Tom Brown Benjamin Mann Nick Ryder Melanie Subbiah Jared D Kaplan Prafulla Dhariwal Arvind Neelakantan Pranav Shyam Girish Sastry Amanda Askell et al. 2020. Language models are few-shot learners. In Advances in neural information processing systems (NeurIPS). 1877--1901."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11280-024-01276-1"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108218"},{"key":"e_1_3_2_1_6_1","unstructured":"Li Chuan. 2023. OpenAI's GPT-3 Language Model: A Technical Overview. https: \/\/lambdalabs.com\/blog\/demystifying-gpt-3."},{"key":"e_1_3_2_1_7_1","volume-title":"Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168","author":"Cobbe Karl","year":"2021","unstructured":"Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, and John Schulman. 2021. Training Verifiers to Solve Math Word Problems. arXiv preprint arXiv:2110.14168 (2021)."},{"key":"e_1_3_2_1_8_1","volume-title":"Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems 36","author":"Dettmers Tim","year":"2024","unstructured":"Tim Dettmers, Artidoro Pagnoni, Ari Holtzman, and Luke Zettlemoyer. 2024. Qlora: Efficient finetuning of quantized llms. Advances in Neural Information Processing Systems 36 (2024)."},{"key":"e_1_3_2_1_9_1","volume-title":"The KITTI Vision Benchmark Suite. In Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Geiger Andreas","year":"2012","unstructured":"Andreas Geiger, Philip Lenz, and Raquel Urtasun. 2012. Are we ready for Autonomous Driving? The KITTI Vision Benchmark Suite. In Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 1321--1330","author":"Guo Chuan","year":"2017","unstructured":"Chuan Guo, Geoff Pleiss, Yu Sun, and Kilian QWeinberger. 2017. On calibration of modern neural networks. In International conference on machine learning. PMLR, 1321--1330."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-13-7139-4_27"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_22"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317803"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_15_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2021. Measuring Massive Multitask Language Understanding. Proceedings of the International Conference on Learning Representations (ICLR) (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146","author":"Howard Jeremy","year":"2018","unstructured":"Jeremy Howard and Sebastian Ruder. 2018. Universal language model fine-tuning for text classification. arXiv preprint arXiv:1801.06146 (2018)."},{"key":"e_1_3_2_1_17_1","volume-title":"Nataraj Dasgupta, Sayee Natarajan, Larry A Pickett, and Varun Dutt.","author":"Kaushik Shruti","year":"2020","unstructured":"Shruti Kaushik, Abhinav Choudhury, Pankaj Kumar Sheron, Nataraj Dasgupta, Sayee Natarajan, Larry A Pickett, and Varun Dutt. 2020. AI in healthcare: timeseries forecasting using statistical, neural, and ensemble architectures. Frontiers in big data 3 (2020), 4."},{"key":"e_1_3_2_1_18_1","volume-title":"Proceedings of the 36th International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research","volume":"3310","author":"Kaya Yigitcan","year":"2019","unstructured":"Yigitcan Kaya, Sanghyun Hong, and Tudor Dumitras. 2019. Shallow-Deep Networks: Understanding and Mitigating Network Overthinking. In Proceedings of the 36th International Conference on Machine Learning (ICML) (Proceedings of Machine Learning Research, Vol. 97), Kamalika Chaudhuri and Ruslan Salakhutdinov (Eds.). PMLR, 3301--3310. https:\/\/proceedings.mlr.press\/v97\/kaya19a.html"},{"key":"e_1_3_2_1_19_1","unstructured":"Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. (2009)."},{"key":"e_1_3_2_1_20_1","volume-title":"Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E Hinton. 2012. Imagenet classification with deep convolutional neural networks. Advances in neural information processing systems 25 (2012)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.05.103"},{"key":"e_1_3_2_1_22_1","volume-title":"Deep learning. nature 521, 7553","author":"LeCun Yann","year":"2015","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. 2015. Deep learning. nature 521, 7553 (2015), 436--444."},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.26042"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.162"},{"key":"e_1_3_2_1_25_1","first-page":"1950","article-title":"Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning","volume":"35","author":"Liu Haokun","year":"2022","unstructured":"Haokun Liu, Derek Tam, Mohammed Muqeeth, Jay Mohta, Tenghao Huang, Mohit Bansal, and Colin A Raffel. 2022. Few-shot parameter-efficient fine-tuning is better and cheaper than in-context learning. Advances in Neural Information Processing Systems 35 (2022), 1950--1965.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jmsy.2022.01.010"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.222"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2024.109237"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2020.3041615"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2015.152"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7123"},{"key":"e_1_3_2_1_33_1","volume-title":"Early exiting with ensemble internal classifiers. arXiv preprint arXiv:2105.13792","author":"Sun Tianxiang","year":"2021","unstructured":"Tianxiang Sun, Yunhua Zhou, Xiangyang Liu, Xinyu Zhang, Hao Jiang, Zhao Cao, Xuanjing Huang, and Xipeng Qiu. 2021. Early exiting with ensemble internal classifiers. arXiv preprint arXiv:2105.13792 (2021)."},{"key":"e_1_3_2_1_34_1","unstructured":"Chloe Taylor. 2023. ChatGPT creator OpenAI earnings: $80 million a month $1 billion annual revenue $540 million loss: Sam Altman. https:\/\/fortune.com\/2023\/08\/30\/chatgpt-creator-openai-earnings-80-million-amonth- 1-billion-annual-revenue-540-million-loss-sam-altman\/."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Lisa Torrey and Jude Shavlik. 2010. Transfer learning. In Handbook of research on machine learning applications and trends: algorithms methods and techniques. IGI global 242--264.","DOI":"10.4018\/978-1-60566-766-9.ch011"},{"key":"e_1_3_2_1_37_1","volume-title":"Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971","author":"Touvron Hugo","year":"2023","unstructured":"Hugo Touvron, Thibaut Lavril, Gautier Izacard, Xavier Martinet, Marie-Anne Lachaux, Timoth\u00e9e Lacroix, Baptiste Rozi\u00e8re, Naman Goyal, Eric Hambro, Faisal Azhar, et al. 2023. Llama: Open and efficient foundation language models. arXiv preprint arXiv:2302.13971 (2023)."},{"key":"e_1_3_2_1_38_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems","author":"Vaswani A","year":"2017","unstructured":"A Vaswani. 2017. Attention is all you need. Advances in Neural Information Processing Systems (2017)."},{"key":"e_1_3_2_1_39_1","volume-title":"Data hiding with deep learning: a survey unifying digital watermarking and steganography","author":"Wang Zihan","year":"2023","unstructured":"Zihan Wang, Olivia Byrnes, Hu Wang, Ruoxi Sun, Congbo Ma, Huaming Chen, QiWu, and Minhui Xue. 2023. Data hiding with deep learning: a survey unifying digital watermarking and steganography. IEEE Transactions on Computational Social Systems (2023)."},{"key":"e_1_3_2_1_40_1","volume-title":"CoreLocker: Neuron-level Usage Control. In 2024 IEEE Symposium on Security and Privacy (SP). IEEE Computer Society, 2497--2514","author":"Ma Zhongkui","year":"2024","unstructured":"ZihanWang, Zhongkui Ma, Xinguo Feng, Ruoxi Sun, HuWang, Minhui Xue, and Guangdong Bai. 2024. CoreLocker: Neuron-level Usage Control. In 2024 IEEE Symposium on Security and Privacy (SP). IEEE Computer Society, 2497--2514."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2023.10.003"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01593"},{"key":"e_1_3_2_1_44_1","volume-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems 34","author":"Xie Enze","year":"2021","unstructured":"Enze Xie, Wenhai Wang, Zhiding Yu, Anima Anandkumar, Jose M Alvarez, and Ping Luo. 2021. SegFormer: Simple and efficient design for semantic segmentation with transformers. Advances in neural information processing systems 34 (2021), 12077--12090."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3691620.3695510"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"e_1_3_2_1_47_1","first-page":"18330","article-title":"Bert loses patience: Fast and robust inference with early exit","volume":"33","author":"Zhou Wangchunshu","year":"2020","unstructured":"Wangchunshu Zhou, Canwen Xu, Tao Ge, Julian McAuley, Ke Xu, and Furu Wei. 2020. Bert loses patience: Fast and robust inference with early exit. Advances in Neural Information Processing Systems (NeurIPS) 33 (2020), 18330--18341.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"}],"event":{"name":"WWW '25: The ACM Web Conference 2025","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"],"location":"Sydney NSW Australia","acronym":"WWW '25"},"container-title":["Proceedings of the ACM on Web Conference 2025"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714737","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696410.3714737","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:41Z","timestamp":1750295921000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696410.3714737"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":47,"alternative-id":["10.1145\/3696410.3714737","10.1145\/3696410"],"URL":"https:\/\/doi.org\/10.1145\/3696410.3714737","relation":{},"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"2025-04-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}