{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:24:00Z","timestamp":1787689440881,"version":"build-2784847793"},"publisher-location":"New York, NY, USA","reference-count":85,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770854.3780230","type":"proceedings-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T12:07:40Z","timestamp":1785499660000},"page":"2054-2065","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["PEANuT: Parameter-Efficient Adaptation with Weight-aware Neural Tweakers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-3697-2698","authenticated-orcid":false,"given":"Yibo","family":"Zhong","sequence":"first","affiliation":[{"name":"Independent Researcher, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5631-2559","authenticated-orcid":false,"given":"Haoxiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"University at Albany, Albany, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3797-4055","authenticated-orcid":false,"given":"Lincan","family":"Li","sequence":"additional","affiliation":[{"name":"Florida State University, Tallahassee, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-9888-7472","authenticated-orcid":false,"given":"Ryumei","family":"Nakada","sequence":"additional","affiliation":[{"name":"Rutgers University, New Brunswick, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8396-8564","authenticated-orcid":false,"given":"Tianci","family":"Liu","sequence":"additional","affiliation":[{"name":"Purdue University, West Lafayette, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8309-7164","authenticated-orcid":false,"given":"Linjun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Rutgers University, New Brunswick, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8691-9629","authenticated-orcid":false,"given":"Huaxiu","family":"Yao","sequence":"additional","affiliation":[{"name":"University of North Carolina at Chapel Hill, Chapel Hill, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7485-6213","authenticated-orcid":false,"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"University at Albany, Albany, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,20]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"AI@Meta. 2024. Llama 3 Model Card. (2024). https:\/\/github.com\/meta-llama\/llama3\/blob\/main\/MODEL_CARD.md"},{"key":"e_1_3_2_2_2_1","volume-title":"Anna Korhonen, and Ivan Vuli\u0107.","author":"Ansell Alan","year":"2021","unstructured":"Alan Ansell, Edoardo Maria Ponti, Anna Korhonen, and Ivan Vuli\u0107. 2021. Composable sparse fine-tuning for cross-lingual transfer. arXiv preprint arXiv:2110.07560 (2021)."},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Tom M Apostol. 1990. Modular Functions and Dirichlet Series in Number Theory. (1990).","DOI":"10.1007\/978-1-4612-0999-7"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01007"},{"key":"e_1_3_2_2_5_1","volume-title":"Jianfeng Gao, and Yejin Choi.","author":"Bisk Yonatan","year":"2020","unstructured":"Yonatan Bisk, Rowan Zellers, Ronan Le Bras, Jianfeng Gao, and Yejin Choi. 2020. PIQA: Reasoning about Physical Commonsense in Natural Language. arXiv preprint arXiv:1911.11641 (2020)."},{"key":"e_1_3_2_2_6_1","volume-title":"Proc. of the IEEE\/CVF international conference on computer vision. 357-366","author":"Richard Chen Chun-Fu","year":"2021","unstructured":"Chun-Fu Richard Chen, Quanfu Fan, and Rameswar Panda. 2021. Crossvit: Cross-attention multi-scale vision transformer for image classification. In Proc. of the IEEE\/CVF international conference on computer vision. 357-366."},{"key":"e_1_3_2_2_7_1","volume-title":"Parameter-efficient fine-tuning design spaces. arXiv preprint arXiv:2301.01821","author":"Chen Jiaao","year":"2023","unstructured":"Jiaao Chen, Aston Zhang, Xingjian Shi, Mu Li, Alex Smola, and Diyi Yang. 2023. Parameter-efficient fine-tuning design spaces. arXiv preprint arXiv:2301.01821 (2023)."},{"key":"e_1_3_2_2_8_1","volume-title":"Large convolutional model tuning via filter subspace. arXiv preprint arXiv:2403.00269","author":"Chen Wei","year":"2024","unstructured":"Wei Chen, Zichen Miao, and Qiang Qiu. 2024. Large convolutional model tuning via filter subspace. arXiv preprint arXiv:2403.00269 (2024)."},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01738"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"e_1_3_2_2_11_1","volume-title":"Adaptersoup: Weight averaging to improve generalization of pretrained language models. arXiv preprint arXiv:2302.07027","author":"Chronopoulou Alexandra","year":"2023","unstructured":"Alexandra Chronopoulou, Matthew E Peters, Alexander Fraser, and Jesse Dodge. 2023. Adaptersoup: Weight averaging to improve generalization of pretrained language models. arXiv preprint arXiv:2302.07027 (2023)."},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_2_2_13_1","volume-title":"BoolQ: Exploring the Surprising Difficulty of Natural Yes\/No Questions. arXiv preprint arXiv:1905.10044","author":"Clark Christopher","year":"2019","unstructured":"Christopher Clark, Kenton Lee, Ming-Wei Chang, Tom Kwiatkowski, Michael Collins, and Kristina Toutanova. 2019. BoolQ: Exploring the Surprising Difficulty of Natural Yes\/No Questions. arXiv preprint arXiv:1905.10044 (2019)."},{"key":"e_1_3_2_2_14_1","volume-title":"Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge. arXiv preprint arXiv:1803.05457","author":"Clark Peter","year":"2018","unstructured":"Peter Clark, Isaac Cowhey, Oren Etzioni, Tushar Khot, Ashish Sabharwal, Carissa Schoenick, and Oyvind Tafjord. 2018. Think you have Solved Question Answering? Try ARC, the AI2 Reasoning Challenge. arXiv preprint arXiv:1803.05457 (2018)."},{"key":"e_1_3_2_2_15_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_2_16_1","volume-title":"Peng Shi, Wenpeng Yin, and Rui Zhang.","author":"Sarathi Das Sarkar Snigdha","year":"2023","unstructured":"Sarkar Snigdha Sarathi Das, Ranran Haoran Zhang, Peng Shi, Wenpeng Yin, and Rui Zhang. 2023. Unified low-resource sequence labeling by sample-aware dynamic sparse finetuning. arXiv preprint arXiv:2311.03748 (2023)."},{"key":"e_1_3_2_2_17_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"e_1_3_2_2_19_1","volume-title":"International Conference on Learning Representations.","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et al., 2020. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations."},{"key":"e_1_3_2_2_20_1","volume-title":"International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_2_2_21_1","volume-title":"James J Clark, and Mehdi Rezagholizadeh.","author":"Edalati Ali","year":"2022","unstructured":"Ali Edalati, Marzieh Tahaei, Ivan Kobyzev, Vahid Partovi Nia, James J Clark, and Mehdi Rezagholizadeh. 2022. Krona: Parameter efficient tuning with kronecker adapter. arXiv preprint arXiv:2212.10650 (2022)."},{"key":"e_1_3_2_2_22_1","volume-title":"Parameter-Efficient Fine-Tuning with Discrete Fourier Transform. In Forty-first International Conference on Machine Learning.","author":"Gao Ziqi","unstructured":"Ziqi Gao, Qichao Wang, Aochuan Chen, Zijing Liu, Bingzhe Wu, Liang Chen, and Jia Li. [n.d.]. Parameter-Efficient Fine-Tuning with Discrete Fourier Transform. In Forty-first International Conference on Machine Learning."},{"key":"e_1_3_2_2_23_1","volume-title":"Parameter-Efficient Fine-Tuning with Discrete Fourier Transform. arXiv preprint arXiv:2405.03003","author":"Gao Ziqi","year":"2024","unstructured":"Ziqi Gao, Qichao Wang, Aochuan Chen, Zijing Liu, Bingzhe Wu, Liang Chen, and Jia Li. 2024. Parameter-Efficient Fine-Tuning with Discrete Fourier Transform. arXiv preprint arXiv:2405.03003 (2024)."},{"key":"e_1_3_2_2_24_1","volume-title":"Parameter-efficient transfer learning with diff pruning. arXiv preprint arXiv:2012.07463","author":"Guo Demi","year":"2020","unstructured":"Demi Guo, Alexander M Rush, and Yoon Kim. 2020. Parameter-efficient transfer learning with diff pruning. arXiv preprint arXiv:2012.07463 (2020)."},{"key":"e_1_3_2_2_25_1","volume-title":"Sai Qian Zhang, et al","author":"Han Zeyu","year":"2024","unstructured":"Zeyu Han, Chao Gao, Jinyang Liu, Sai Qian Zhang, et al., 2024. Parameter-efficient fine-tuning for large models: A comprehensive survey. arXiv preprint arXiv:2403.14608 (2024)."},{"key":"e_1_3_2_2_26_1","volume-title":"Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366","author":"He Junxian","year":"2021","unstructured":"Junxian He, Chunting Zhou, Xuezhe Ma, Taylor Berg-Kirkpatrick, and Graham Neubig. 2021. Towards a unified view of parameter-efficient transfer learning. arXiv preprint arXiv:2110.04366 (2021)."},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_2_2_28_1","volume-title":"Measuring Mathematical Problem Solving With the MATH Dataset. arXiv preprint arXiv:2103.03874","author":"Hendrycks Dan","year":"2021","unstructured":"Dan Hendrycks, Collin Burns, Saurav Kadavath, Akul Arora, Steven Basart, Eric Tang, Dawn Song, and Jacob Steinhardt. 2021. Measuring Mathematical Problem Solving With the MATH Dataset. arXiv preprint arXiv:2103.03874 (2021)."},{"key":"e_1_3_2_2_29_1","volume-title":"International conference on machine learning. PMLR, 2790-2799","author":"Houlsby Neil","year":"2019","unstructured":"Neil Houlsby, Andrei Giurgiu, Stanislaw Jastrzebski, Bruna Morrone, Quentin De Laroussilhe, Andrea Gesmundo, Mona Attariyan, and Sylvain Gelly. 2019. Parameter-efficient transfer learning for NLP. In International conference on machine learning. PMLR, 2790-2799."},{"key":"e_1_3_2_2_30_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_2_31_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021a. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_2_32_1","volume-title":"Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2021b. Lora: Low-rank adaptation of large language models. arXiv preprint arXiv:2106.09685 (2021)."},{"key":"e_1_3_2_2_33_1","volume-title":"LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models. arXiv preprint arXiv:2304.01933","author":"Hu Zhiqiang","year":"2023","unstructured":"Zhiqiang Hu, Lei Wang, Yihuai Lan, Wanyu Xu, Ee-Peng Lim, Lidong Bing, Xing Xu, Soujanya Poria, and Roy Lee. 2023. LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models. arXiv preprint arXiv:2304.01933 (2023)."},{"key":"e_1_3_2_2_34_1","first-page":"1022","article-title":"Compacter: Efficient low-rank hypercomplex adapter layers","volume":"34","author":"Mahabadi Rabeeh Karimi","year":"2021","unstructured":"Rabeeh Karimi Mahabadi, James Henderson, and Sebastian Ruder. 2021. Compacter: Efficient low-rank hypercomplex adapter layers. Advances in Neural Information Processing Systems, Vol. 34 (2021), 1022-1035.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_35_1","volume-title":"Vera: Vector-based random matrix adaptation. arXiv preprint arXiv:2310.11454","author":"Kopiczko Dawid Jan","year":"2023","unstructured":"Dawid Jan Kopiczko, Tijmen Blankevoort, and Yuki Markus Asano. 2023. Vera: Vector-based random matrix adaptation. arXiv preprint arXiv:2310.11454 (2023)."},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_2_37_1","volume-title":"Learning Multiple Layers of Features from Tiny Images. Master's thesis","author":"Krizhevsky A","unstructured":"A Krizhevsky. 2009. Learning Multiple Layers of Features from Tiny Images. Master's thesis, University of Tront (2009)."},{"key":"e_1_3_2_2_38_1","volume-title":"The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691","author":"Lester Brian","year":"2021","unstructured":"Brian Lester, Rami Al-Rfou, and Noah Constant. 2021. The power of scale for parameter-efficient prompt tuning. arXiv preprint arXiv:2104.08691 (2021)."},{"key":"e_1_3_2_2_39_1","unstructured":"Patrick Lewis Ethan Perez Aleksandra Piktus Fabio Petroni Vladimir Karpukhin Naman Goyal Heinrich K\u00fcttler Mike Lewis Wen-tau Yih Tim Rockt\u00e4schel et al. 2020. Retrieval-augmented generation for knowledge-intensive nlp tasks. Advances in neural information processing systems Vol. 33 (2020) 9459-9474."},{"key":"e_1_3_2_2_40_1","volume-title":"Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190","author":"Li Xiang Lisa","year":"2021","unstructured":"Xiang Lisa Li and Percy Liang. 2021. Prefix-tuning: Optimizing continuous prompts for generation. arXiv preprint arXiv:2101.00190 (2021)."},{"key":"e_1_3_2_2_41_1","first-page":"87","article-title":"AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration","volume":"6","author":"Lin Ji","year":"2024","unstructured":"Ji Lin, Jiaming Tang, Haotian Tang, Shang Yang, Wei-Ming Chen, Wei-Chen Wang, Guangxuan Xiao, Xingyu Dang, Chuang Gan, and Song Han. 2024. AWQ: Activation-aware Weight Quantization for On-Device LLM Compression and Acceleration. Proc. of Machine Learning and Systems, Vol. 6 (2024), 87-100.","journal-title":"Proc. of Machine Learning and Systems"},{"key":"e_1_3_2_2_42_1","volume-title":"Kwang-Ting Cheng, and Min-Hung Chen.","author":"Liu Shih-Yang","year":"2024","unstructured":"Shih-Yang Liu, Chien-Yi Wang, Hongxu Yin, Pavlo Molchanov, Yu-Chiang Frank Wang, Kwang-Ting Cheng, and Min-Hung Chen. 2024. DoRA: Weight-Decomposed Low-Rank Adaptation. arXiv:2402.09353 (2024). https:\/\/arxiv.org\/abs\/2402.09353"},{"key":"e_1_3_2_2_43_1","volume-title":"Roserag: Robust retrieval-augmented generation with small-scale llms via margin-aware preference optimization. arXiv preprint arXiv:2502.10993","author":"Liu Tianci","year":"2025","unstructured":"Tianci Liu, Haoxiang Jiang, Tianze Wang, Ran Xu, Yue Yu, Linjun Zhang, Tuo Zhao, and Haoyu Wang. 2025a. Roserag: Robust retrieval-augmented generation with small-scale llms via margin-aware preference optimization. arXiv preprint arXiv:2502.10993 (2025)."},{"key":"e_1_3_2_2_44_1","volume-title":"Jun Huan, Haoyu Wang, et al.","author":"Liu Tianci","year":"2025","unstructured":"Tianci Liu, Ruirui Li, Yunzhe Qi, Hui Liu, Xianfeng Tang, Tianqi Zheng, Qingyu Yin, Monica Xiao Cheng, Jun Huan, Haoyu Wang, et al., 2025b. Unlocking efficient, scalable, and continual knowledge editing with basis-level representation fine-tuning. arXiv preprint arXiv:2503.00306 (2025)."},{"key":"e_1_3_2_2_45_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_2_46_1","volume-title":"Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151","author":"Maji Subhransu","year":"2013","unstructured":"Subhransu Maji, Esa Rahtu, Juho Kannala, Matthew Blaschko, and Andrea Vedaldi. 2013. Fine-grained visual classification of aircraft. arXiv preprint arXiv:1306.5151 (2013)."},{"key":"e_1_3_2_2_47_1","volume-title":"Unipelt: A unified framework for parameter-efficient language model tuning. arXiv preprint arXiv:2110.07577","author":"Mao Yuning","year":"2021","unstructured":"Yuning Mao, Lambert Mathias, Rui Hou, Amjad Almahairi, Hao Ma, Jiawei Han, Wen-tau Yih, and Madian Khabsa. 2021. Unipelt: A unified framework for parameter-efficient language model tuning. arXiv preprint arXiv:2110.07577 (2021)."},{"key":"e_1_3_2_2_48_1","volume-title":"PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models. arXiv preprint arXiv:2404.02948","author":"Meng Fanxu","year":"2024","unstructured":"Fanxu Meng, Zhaohui Wang, and Muhan Zhang. 2024. PiSSA: Principal Singular Values and Singular Vectors Adaptation of Large Language Models. arXiv preprint arXiv:2404.02948 (2024)."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01876"},{"key":"e_1_3_2_2_50_1","volume-title":"Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering. arXiv preprint arXiv:1809.02789","author":"Mihaylov Todor","year":"2018","unstructured":"Todor Mihaylov, Peter Clark, Tushar Khot, and Ashish Sabharwal. 2018. Can a Suit of Armor Conduct Electricity? A New Dataset for Open Book Question Answering. arXiv preprint arXiv:1809.02789 (2018)."},{"key":"e_1_3_2_2_51_1","volume-title":"LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning. arXiv preprint arXiv:2403.17919","author":"Pan Rui","year":"2024","unstructured":"Rui Pan, Xiang Liu, Shizhe Diao, Renjie Pi, Jipeng Zhang, Chi Han, and Tong Zhang. 2024. LISA: Layerwise Importance Sampling for Memory-Efficient Large Language Model Fine-Tuning. arXiv preprint arXiv:2403.17919 (2024)."},{"key":"e_1_3_2_2_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"e_1_3_2_2_53_1","volume-title":"Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices. arXiv preprint arXiv:2406.03777","author":"Qin Ruiyang","year":"2024","unstructured":"Ruiyang Qin, Dancheng Liu, Zheyu Yan, Zhaoxuan Tan, Zixuan Pan, Zhenge Jia, Meng Jiang, Ahmed Abbasi, Jinjun Xiong, and Yiyu Shi. 2024. Empirical Guidelines for Deploying LLMs onto Resource-constrained Edge Devices. arXiv preprint arXiv:2406.03777 (2024)."},{"key":"e_1_3_2_2_54_1","volume-title":"international conference on machine learning. PMLR, 2847-2854","author":"Raghu Maithra","year":"2017","unstructured":"Maithra Raghu, Ben Poole, Jon Kleinberg, Surya Ganguli, and Jascha Sohl-Dickstein. 2017. On the expressive power of deep neural networks. In international conference on machine learning. PMLR, 2847-2854."},{"key":"e_1_3_2_2_55_1","volume-title":"Chandra Bhagavatula, and Yejin Choi.","author":"Sakaguchi Keisuke","year":"2019","unstructured":"Keisuke Sakaguchi, Ronan Le Bras, Chandra Bhagavatula, and Yejin Choi. 2019. WinoGrande: An Adversarial Winograd Schema Challenge at Scale. arXiv preprint arXiv:1907.10641 (2019)."},{"key":"e_1_3_2_2_56_1","volume-title":"SocialIQA: Commonsense Reasoning about Social Interactions. arXiv preprint arXiv:1904.09728","author":"Sap Maarten","year":"2019","unstructured":"Maarten Sap, Hannah Rashkin, Derek Chen, Ronan LeBras, and Yejin Choi. 2019. SocialIQA: Commonsense Reasoning about Social Interactions. arXiv preprint arXiv:1904.09728 (2019)."},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01306"},{"key":"e_1_3_2_2_58_1","volume-title":"Text classification via large language models. arXiv preprint arXiv:2305.08377","author":"Sun Xiaofei","year":"2023","unstructured":"Xiaofei Sun, Xiaoya Li, Jiwei Li, Fei Wu, Shangwei Guo, Tianwei Zhang, and Guoyin Wang. 2023. Text classification via large language models. arXiv preprint arXiv:2305.08377 (2023)."},{"key":"e_1_3_2_2_59_1","first-page":"24193","article-title":"Training neural networks with fixed sparse masks","volume":"34","author":"Sung Yi-Lin","year":"2021","unstructured":"Yi-Lin Sung, Varun Nair, and Colin A Raffel. 2021. Training neural networks with fixed sparse masks. Advances in Neural Information Processing Systems, Vol. 34 (2021), 24193-24205.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_60_1","unstructured":"Qwen Team. 2025. Qwen3 Technical Report. arXiv preprint arXiv:2505.09388 (2025)."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00458"},{"key":"e_1_3_2_2_62_1","unstructured":"Hugo Touvron Louis Martin Kevin Stone Peter Albert Amjad Almahairi Yasmine Babaei Nikolay Bashlykov Soumya Batra and et al. 2023. Llama 2: Open Foundation and Fine-Tuned Chat Models. arXiv preprint arXiv:2307.09288 (2023)."},{"key":"e_1_3_2_2_63_1","volume-title":"Dylora: Parameter efficient tuning of pre-trained models using dynamic search-free low-rank adaptation. arXiv preprint arXiv:2210.07558","author":"Valipour Mojtaba","year":"2022","unstructured":"Mojtaba Valipour, Mehdi Rezagholizadeh, Ivan Kobyzev, and Ali Ghodsi. 2022. Dylora: Parameter efficient tuning of pre-trained models using dynamic search-free low-rank adaptation. arXiv preprint arXiv:2210.07558 (2022)."},{"key":"e_1_3_2_2_64_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_2_65_1","volume-title":"Spot: Better frozen model adaptation through soft prompt transfer. arXiv preprint arXiv:2110.07904","author":"Vu Tu","year":"2021","unstructured":"Tu Vu, Brian Lester, Noah Constant, Rami Al-Rfou, and Daniel Cer. 2021. Spot: Better frozen model adaptation through soft prompt transfer. arXiv preprint arXiv:2110.07904 (2021)."},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS48785.2022.9937567"},{"key":"e_1_3_2_2_67_1","volume-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461","author":"Wang Alex","year":"2018","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R Bowman. 2018. GLUE: A multi-task benchmark and analysis platform for natural language understanding. arXiv preprint arXiv:1804.07461 (2018)."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.58"},{"key":"e_1_3_2_2_69_1","volume-title":"RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning. arXiv preprint arXiv:2406.10777","author":"Wang Haoyu","year":"2024","unstructured":"Haoyu Wang, Tianci Liu, Tuo Zhao, and Jing Gao. 2024c. RoseLoRA: Row and Column-wise Sparse Low-rank Adaptation of Pre-trained Language Model for Knowledge Editing and Fine-tuning. arXiv preprint arXiv:2406.10777 (2024)."},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.72"},{"key":"e_1_3_2_2_71_1","volume-title":"MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning. arXiv preprint arXiv:2406.09044","author":"Wang Hanqing","year":"2024","unstructured":"Hanqing Wang, Zeguan Xiao, Yixia Li, Shuo Wang, Guanhua Chen, and Yun Chen. 2024d. MiLoRA: Harnessing Minor Singular Components for Parameter-Efficient LLM Finetuning. arXiv preprint arXiv:2406.09044 (2024)."},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3511988"},{"key":"e_1_3_2_2_73_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Wang Yihan","year":"2024","unstructured":"Yihan Wang, Jatin Chauhan, Wei Wang, and Cho-Jui Hsieh. 2024a. Universality and limitations of prompt tuning. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_2_74_1","volume-title":"Advancing Parameter Efficiency in Fine-tuning via Representation Editing. arXiv:2402.15179","author":"Wu Muling","year":"2024","unstructured":"Muling Wu, Wenhao Liu, Xiaohua Wang, Tianlong Li, Changze Lv, Zixuan Ling, Jianhao Zhu, Cenyuan Zhang, Xiaoqing Zheng, and Xuanjing Huang. 2024b. Advancing Parameter Efficiency in Fine-tuning via Representation Editing. arXiv:2402.15179 (2024). https:\/\/arxiv.org\/abs\/2402.15179"},{"key":"e_1_3_2_2_75_1","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3358119"},{"key":"e_1_3_2_2_76_1","unstructured":"Zhengxuan Wu Aryaman Arora Zheng Wang Atticus Geiger Dan Jurafsky Christopher D. Manning and Christopher Potts. 2024a. ReFT: Representation Finetuning for Language Models. (2024). arxiv.org\/abs\/2404.03592"},{"key":"e_1_3_2_2_77_1","volume-title":"Collab-rag: Boosting retrieval-augmented generation for complex question answering via white-box and black-box llm collaboration. arXiv preprint arXiv:2504.04915","author":"Xu Ran","year":"2025","unstructured":"Ran Xu, Wenqi Shi, Yuchen Zhuang, Yue Yu, Joyce C Ho, Haoyu Wang, and Carl Yang. 2025. Collab-rag: Boosting retrieval-augmented generation for complex question answering via white-box and black-box llm collaboration. arXiv preprint arXiv:2504.04915 (2025)."},{"key":"e_1_3_2_2_78_1","volume-title":"React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations.","author":"Yao Shunyu","year":"2022","unstructured":"Shunyu Yao, Jeffrey Zhao, Dian Yu, Nan Du, Izhak Shafran, Karthik R Narasimhan, and Yuan Cao. 2022. React: Synergizing reasoning and acting in language models. In The eleventh international conference on learning representations."},{"key":"e_1_3_2_2_79_1","volume-title":"MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models. arXiv preprint arXiv:2309.12284","author":"Yu Longhui","year":"2023","unstructured":"Longhui Yu, Weisen Jiang, Han Shi, Jincheng Yu, Zhengying Liu, Yu Zhang, James T. Kwok, Zhenguo Li, Adrian Weller, and Weiyang Liu. 2023. MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Models. arXiv preprint arXiv:2309.12284 (2023)."},{"key":"e_1_3_2_2_80_1","volume-title":"Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199","author":"Zaken Elad Ben","year":"2021","unstructured":"Elad Ben Zaken, Shauli Ravfogel, and Yoav Goldberg. 2021. Bitfit: Simple parameter-efficient fine-tuning for transformer-based masked language-models. arXiv preprint arXiv:2106.10199 (2021)."},{"key":"e_1_3_2_2_81_1","volume-title":"HellaSwag: Can a Machine Really Finish Your Sentence? arXiv preprint arXiv:1905.07830","author":"Zellers Rowan","year":"2019","unstructured":"Rowan Zellers, Ari Holtzman, Yonatan Bisk, Ali Farhadi, and Yejin Choi. 2019. HellaSwag: Can a Machine Really Finish Your Sentence? arXiv preprint arXiv:1905.07830 (2019)."},{"key":"e_1_3_2_2_82_1","volume-title":"AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning. arXiv preprint arXiv:2303.10512","author":"Zhang Qingru","year":"2023","unstructured":"Qingru Zhang, Minshuo Chen, Alexander Bukharin, Nikos Karampatziakis, Pengcheng He, Yu Cheng, Weizhu Chen, and Tuo Zhao. 2023. AdaLoRA: Adaptive budget allocation for parameter-efficient fine-tuning. arXiv preprint arXiv:2303.10512 (2023)."},{"key":"e_1_3_2_2_83_1","volume-title":"Tiny-attention adapter: Contexts are more important than the number of parameters. arXiv preprint arXiv:2211.01979","author":"Zhao Hongyu","year":"2022","unstructured":"Hongyu Zhao, Hao Tan, and Hongyuan Mei. 2022. Tiny-attention adapter: Contexts are more important than the number of parameters. arXiv preprint arXiv:2211.01979 (2022)."},{"key":"e_1_3_2_2_84_1","volume-title":"Galore: Memory-efficient llm training by gradient low-rank projection. arXiv preprint arXiv:2403.03507","author":"Zhao Jiawei","year":"2024","unstructured":"Jiawei Zhao, Zhenyu Zhang, Beidi Chen, Zhangyang Wang, Anima Anandkumar, and Yuandong Tian. 2024. Galore: Memory-efficient llm training by gradient low-rank projection. arXiv preprint arXiv:2403.03507 (2024)."},{"key":"e_1_3_2_2_85_1","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00662"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.1"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3770854.3780230","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T20:10:17Z","timestamp":1787688617000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770854.3780230"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,20]]},"references-count":85,"alternative-id":["10.1145\/3770854.3780230","10.1145\/3770854"],"URL":"https:\/\/doi.org\/10.1145\/3770854.3780230","relation":{},"subject":[],"published":{"date-parts":[[2026,4,20]]},"assertion":[{"value":"2026-04-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}