{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:29:24Z","timestamp":1776889764767,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","funder":[{"name":"The Hong Kong University of Science and Technology","award":["R9911"],"award-info":[{"award-number":["R9911"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3754894","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:55:00Z","timestamp":1761375300000},"page":"1032-1041","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Outlier-Aware Model Merging for Efficient Multitask Inference"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9251-2711","authenticated-orcid":false,"given":"Qiyuan","family":"Zhu","sequence":"first","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4329-2707","authenticated-orcid":false,"given":"Lujun","family":"Li","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0530-1512","authenticated-orcid":false,"given":"Dezhi","family":"Li","sequence":"additional","affiliation":[{"name":"Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0378-2311","authenticated-orcid":false,"given":"Jiacheng","family":"Liu","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-7540-8704","authenticated-orcid":false,"given":"Pengyu","family":"Cheng","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University, Xi'an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6353-2632","authenticated-orcid":false,"given":"Yucheng","family":"Xu","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7303-0671","authenticated-orcid":false,"given":"Sirui","family":"Han","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8401-282X","authenticated-orcid":false,"given":"Yike","family":"Guo","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang Binyuan Hui Luo Ji Mei Li Junyang Lin Runji Lin Dayiheng Liu Gao Liu Chengqiang Lu Keming Lu Jianxin Ma Rui Men Xingzhang Ren Xuancheng Ren Chuanqi Tan Sinan Tan Jianhong Tu Peng Wang Shijie Wang Wei Wang Shengguang Wu Benfeng Xu Jin Xu An Yang Hao Yang Jian Yang Shusheng Yang Yang Yao Bowen Yu Hongyi Yuan Zheng Yuan Jianwei Zhang Xingxuan Zhang Yichang Zhang Zhenru Zhang Chang Zhou Jingren Zhou Xiaohuan Zhou and Tianhang Zhu. 2023. Qwen Technical Report. arXiv:2309.16609 [cs.CL]"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"e_1_3_2_1_4_1","volume-title":"Revisiting Weight Averaging for Model Merging. arXiv preprint arXiv:2412.12153","author":"Choi Jiho","year":"2024","unstructured":"Jiho Choi, Donggyun Kim, Chanhyuk Lee, and Seunghoon Hong. 2024. Revisiting Weight Averaging for Model Merging. arXiv preprint arXiv:2412.12153 (2024). arXiv:2412.12153"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"e_1_3_2_1_6_1","volume-title":"Deep Learning for Classical Japanese Literature. CoRR","author":"Clanuwat Tarin","year":"2018","unstructured":"Tarin Clanuwat, Mikel Bober-Irizar, Asanobu Kitamoto, Alex Lamb, Kazuaki Yamamoto, and David Ha. 2018. Deep Learning for Classical Japanese Literature. CoRR, Vol. abs\/1812.01718 (2018). arXiv:1812.01718 http:\/\/arxiv.org\/abs\/1812.01718"},{"key":"e_1_3_2_1_7_1","volume-title":"Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, . JMLR Workshop and Conference Proceedings, 215-223","author":"Coates Adam","year":"2011","unstructured":"Adam Coates, Andrew Ng, and Honglak Lee. 2011. An Analysis of Single-Layer Networks in Unsupervised Feature Learning. In Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, . JMLR Workshop and Conference Proceedings, 215-223. https:\/\/proceedings.mlr.press\/v15\/coates11a.html ISSN: 1938-7228."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2017.7966217"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the 2019 Conference of the North American, Chapter of the Association for Computational Linguistics: Human Language Technologies","volume":"1","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. Bert: Pre-training, of Deep Bidirectional Transformers for Language Understanding. In Proceedings of the 2019 Conference of the North American, Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171-4186."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1166"},{"key":"e_1_3_2_1_11_1","unstructured":"Peijie Dong Lujun Li Zhenheng Tang Xiang Liu Xinglin Pan Qiang Wang and Xiaowen Chu. 2024. Pruner-Zero: Evolving Symbolic Pruning Metric from Scratch for Large Language Models. In ICML."},{"key":"e_1_3_2_1_12_1","volume-title":"STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs. In ICLR.","author":"Dong Peijie","year":"2025","unstructured":"Peijie Dong, Lujun Li, Yuedong Zhong, Dayou Du, Ruibo Fan, Yuhan Chen, Zhenheng Tang, Qiang Wang, Wei Xue, Yike Guo, et al., 2025. STBLLM: Breaking the 1-Bit Barrier with Structured Binary LLMs. In ICLR."},{"key":"e_1_3_2_1_13_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_1_14_1","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. arXiv:2010.11929 [cs.CV] https:\/\/arxiv.org\/abs\/2010.11929"},{"key":"e_1_3_2_1_15_1","volume-title":"Catastrophic forgetting in connectionist networks. Trends in cognitive sciences","author":"French Robert M","year":"1999","unstructured":"Robert M French. 1999. Catastrophic forgetting in connectionist networks. Trends in cognitive sciences, Vol. 3, 4 (1999), 128-135."},{"key":"e_1_3_2_1_16_1","volume-title":"Simone Scardapane, Fabrizio Silvestri, and Emanuele Rodol\u00e0.","author":"Gargiulo Antonio Andrea","year":"2024","unstructured":"Antonio Andrea Gargiulo, Donato Crisostomi, Maria Sofia Bucarelli, Simone Scardapane, Fabrizio Silvestri, and Emanuele Rodol\u00e0. 2024. Task Singular Vectors: Reducing, Task Interference in Model Merging. arXiv preprint arXiv:2412.00081 (2024). arXiv:2412.00081"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"e_1_3_2_1_18_1","volume-title":"Delta Decompression for MoE-based LLMs Compression. arXiv preprint arXiv:2502.17298","author":"Gu Hao","year":"2025","unstructured":"Hao Gu, Wei Li, Lujun Li, Zhu Qiyuan, Mark Lee, Shengjie Sun, Wei Xue, and Yike Guo. 2025. Delta Decompression for MoE-based LLMs Compression. arXiv preprint arXiv:2502.17298 (2025)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"e_1_3_2_1_20_1","volume-title":"Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations.","author":"Hendrycks Dan","year":"2020","unstructured":"Dan Hendrycks, Collin Burns, Steven Basart, Andy Zou, Mantas Mazeika, Dawn Song, and Jacob Steinhardt. 2020. Measuring Massive Multitask Language Understanding. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_21_1","volume-title":"LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations.","author":"Hu Edward J","year":"2021","unstructured":"Edward J Hu, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, Weizhu Chen, et al., 2021. LoRA: Low-Rank Adaptation of Large Language Models. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Chenyu Huang Peng Ye Tao Chen Tong He Xiangyu Yue and Wanli Ouyang. 2024. EMR-merging : Tuning-free High-Performance Model Merging. In Advances in Neural Information Processing Systems .","DOI":"10.52202\/079017-3900"},{"key":"e_1_3_2_1_23_1","volume-title":"Editing Models with Task Arithmetic. In International Conference, on Learning Representations, .","author":"Ilharco Gabriel","year":"2023","unstructured":"Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2023a. Editing Models with Task Arithmetic. In International Conference, on Learning Representations, ."},{"key":"e_1_3_2_1_24_1","volume-title":"The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6t0Kwf8-jrj","author":"Ilharco Gabriel","year":"2023","unstructured":"Gabriel Ilharco, Marco Tulio Ribeiro, Mitchell Wortsman, Ludwig Schmidt, Hannaneh Hajishirzi, and Ali Farhadi. 2023b. Editing models with task arithmetic. In The Eleventh International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=6t0Kwf8-jrj"},{"key":"e_1_3_2_1_25_1","volume-title":"International Conference, on Learning Representations, .","author":"Jin Xisen","year":"2023","unstructured":"Xisen Jin, Xiang Ren, Daniel Preotiuc-Pietro, and Pengxiang Cheng. 2023. Dataless Knowledge Fusion by Merging Weights of Language Models. In International Conference, on Learning Representations, ."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"e_1_3_2_1_27_1","unstructured":"Alex Krizhevsky and Geoffrey Hinton. 2009. Learning multiple layers of features from tiny images. Technical Report 0. University of Toronto Toronto Ontario. https:\/\/www.cs.toronto.edu\/ kriz\/learning-features-2009-TR.pdf"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_1_29_1","unstructured":"Yu-Ang Lee Ching-Yun Ko Tejaswini Pedapati I Chung Mi-Yen Yeh Pin-Yu Chen et al. 2025. STAR : Spectral Truncation and Rescale for Model Merging. arXiv preprint arXiv:2502.10339 (2025). arXiv:2502.10339"},{"key":"e_1_3_2_1_30_1","unstructured":"Lujun Li Yufan Bao Peijie Dong Chuanguang Yang Anggeng Li Wenhan Luo Qifeng Liu Wei Xue and Yike Guo. 2024a. DetKDS: Knowledge Distillation Search for Object Detectors. In ICML."},{"key":"e_1_3_2_1_31_1","unstructured":"Lujun Li Peijie Dong Zimian Wei and Ya Yang. 2023. Automated knowledge distillation via monte carlo tree search. In ICCV."},{"key":"e_1_3_2_1_32_1","unstructured":"Lujun Li and Zhe Jin. 2022. Shadow Knowledge Distillation: Bridging Offline and Online Knowledge Transfer. In NeuIPS."},{"key":"e_1_3_2_1_33_1","unstructured":"Lujun Li Peijie Zhenheng Tang Xiang Liu Qiang Wang Wenhan Luo Wei Xue Qifeng Liu Xiaowen Chu and Yike Guo. 2024c. Discovering Sparsity Allocation for Layer-wise Pruning of Large Language Models. In NeuIPS."},{"key":"e_1_3_2_1_34_1","volume-title":"Auto-gas: Automated proxy discovery for training-free generative architecture search. ECCV.","author":"Li Lujun","year":"2024","unstructured":"Lujun Li, Haosen Sun, Shiwen Li, Peijie Dong, Wenhan Luo, Wei Xue, Qifeng Liu, and Yike Guo. 2024d. Auto-gas: Automated proxy discovery for training-free generative architecture search. ECCV."},{"key":"e_1_3_2_1_35_1","unstructured":"Lujun Li Zimian Wei Peijie Dong Wenhan Luo Wei Xue Qifeng Liu and Yike Guo. 2024 e. Attnzero: efficient attention discovery for vision transformers. In ECCV."},{"key":"e_1_3_2_1_36_1","unstructured":"Wei Li Lujun Li You-Liang Huang Mark G. Lee Shengjie Sun Wei Xue and Yike Guo. 2025. Structured Mixture-of-Experts LLMs Compression via Singular Value Decomposition. In ICML."},{"key":"e_1_3_2_1_37_1","volume-title":"ALS: Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment. In NeuIPS.","author":"Li Wei","year":"2024","unstructured":"Wei Li, Lujun Li, Mark Lee, and Shengjie Sun. 2024b. ALS: Adaptive Layer Sparsity for Large Language Models via Activation Correlation Assessment. In NeuIPS."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"e_1_3_2_1_39_1","volume-title":"Conflict-averse gradient descent for multi-task learning. Advances in Neural Information Processing Systems","author":"Liu Bo","year":"2021","unstructured":"Bo Liu, Xingchao Liu, Xiaojie Jin, Peter Stone, and Qiang Liu. 2021. Conflict-averse gradient descent for multi-task learning. Advances in Neural Information Processing Systems (2021)."},{"key":"e_1_3_2_1_40_1","volume-title":"Roberta: A, Robustly Optimized Bert Pretraining Approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A, Robustly Optimized Bert Pretraining Approach. arXiv preprint arXiv:1907.11692 (2019). arXiv:1907.11692"},{"key":"e_1_3_2_1_41_1","first-page":"78905","article-title":"Twin-merging: Dynamic integration of modular expertise in model merging","volume":"37","author":"Lu Zhenyi","year":"2024","unstructured":"Zhenyi Lu, Chenghao Fan, Wei Wei, Xiaoye Qu, Dangyang Chen, and Yu Cheng. 2024a. Twin-merging: Dynamic integration of modular expertise in model merging. Advances in Neural Information Processing Systems, Vol. 37 (2024), 78905-78935.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Zhenyi Lu Chenghao Fan Wei Wei Xiaoye Qu Dangyang Chen and Yu Cheng. 2024b. Twin-Merging: Dynamic Integration of Modular Expertise in Model Merging. In Advances in Neural Information Processing Systems .","DOI":"10.52202\/079017-2505"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00195"},{"key":"e_1_3_2_1_44_1","first-page":"17703","article-title":"Merging Models with Fisher-Weighted Averaging","volume":"35","author":"Matena Michael S","year":"2022","unstructured":"Michael S Matena and Colin A Raffel. 2022. Merging Models with Fisher-Weighted Averaging. Advances in Neural Information Processing Systems, Vol. 35 (2022), 17703-17716.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"crossref","unstructured":"Ramesh Nallapati Bowen Zhou Caglar Gulcehre Bing Xiang et al. 2016. Abstractive text summarization using sequence-to-sequence rnns and beyond. arXiv preprint arXiv:1602.06023 (2016).","DOI":"10.18653\/v1\/K16-1028"},{"key":"e_1_3_2_1_46_1","volume-title":"Reading Digits in Natural Images with Unsupervised Feature Learning. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011","author":"Netzer Yuval","year":"2011","unstructured":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. 2011. Reading Digits in Natural Images with Unsupervised Feature Learning. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011. http:\/\/ufldl.stanford.edu\/housenumbers\/nips2011_housenumbers.pdf"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"e_1_3_2_1_49_1","volume-title":"Phu Mon Htut, and Samuel Bowman","author":"Parrish Alicia","year":"2022","unstructured":"Alicia Parrish, Angelica Chen, Nikita Nangia, Vishakh Padmakumar, Jason Phang, Jana Thompson, Phu Mon Htut, and Samuel Bowman. 2022. BBQ: A hand-built bias benchmark for question answering. In Findings of the Association for Computational Linguistics: ACL 2022."},{"key":"e_1_3_2_1_50_1","volume-title":"International conference on machine learning. PMLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PMLR, 8748-8763."},{"key":"e_1_3_2_1_51_1","volume-title":"Multitask Prompted Training Enables Zero-Shot Task Generalization. In International Conference on Learning Representations.","author":"Sanh Victor","year":"2022","unstructured":"Victor Sanh, Albert Webson, Colin Raffel, Stephen H Bach, Lintang Sutawika, Zaid Alyafeai, Antoine Chaffin, Arnaud Stiegler, Teven Le Scao, Arun Raja, et al., 2022. Multitask Prompted Training Enables Zero-Shot Task Generalization. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_52_1","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","author":"Socher Richard","unstructured":"Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Ng, and Christopher Potts. 2013. Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, David Yarowsky, Timothy Baldwin, Anna Korhonen, Karen Livescu, and Steven Bethard (Eds.). Association for Computational Linguistics, Seattle, Washington, USA, 1631-1642. https:\/\/aclanthology.org\/D13-1170"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_24"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-5446"},{"key":"e_1_3_2_1_56_1","volume-title":"Localizing Task Information for Improved Model Merging and Compression. In International Conference, on Machine Learning, .","author":"Wang Ke","year":"2024","unstructured":"Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez, Franc cois Fleuret, and Pascal Frossard. 2024a. Localizing Task Information for Improved Model Merging and Compression. In International Conference, on Machine Learning, ."},{"key":"e_1_3_2_1_57_1","volume-title":"Localizing Task Information for Improved Model Merging and Compression. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=DWT9uiGjxT","author":"Wang Ke","year":"2024","unstructured":"Ke Wang, Nikolaos Dimitriadis, Guillermo Ortiz-Jimenez, Fran\u00e7ois Fleuret, and Pascal Frossard. 2024b. Localizing Task Information for Improved Model Merging and Compression. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=DWT9uiGjxT"},{"key":"e_1_3_2_1_58_1","unstructured":"Han Xiao Kashif Rasul and Roland Vollgraf. 2017. Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms. http:\/\/arxiv.org\/abs\/1708.07747 arXiv:1708.07747 [cs stat]."},{"key":"e_1_3_2_1_59_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0748-y"},{"key":"e_1_3_2_1_60_1","volume-title":"TIES-Merging: Resolving Interference When Merging Models. In Thirty-seventh Conference on Neural Information Processing Systems.","author":"Yadav Prateek","year":"2023","unstructured":"Prateek Yadav, Derek Tam, Leshem Choshen, Colin Raffel, and Mohit Bansal. 2023a. TIES-Merging: Resolving Interference When Merging Models. In Thirty-seventh Conference on Neural Information Processing Systems."},{"key":"e_1_3_2_1_61_1","first-page":"7093","article-title":"Ties-Merging: Resolving, Interference When Merging Models","volume":"36","author":"Yadav Prateek","year":"2023","unstructured":"Prateek Yadav, Derek Tam, Leshem Choshen, Colin A Raffel, and Mohit Bansal. 2023b. Ties-Merging: Resolving, Interference When Merging Models. Advances in Neural Information Processing Systems, Vol. 36 (2023), 7093-7115.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_62_1","volume-title":"Advances in Neural Information Processing Systems","volume":"36","author":"Yadav Prateek","year":"2024","unstructured":"Prateek Yadav, Derek Tam, Leshem Choshen, Colin A Raffel, and Mohit Bansal. 2024. Ties-merging: Resolving interference when merging models. Advances in Neural Information Processing Systems, Vol. 36 (2024)."},{"key":"e_1_3_2_1_63_1","unstructured":"Le Yu Bowen Yu Haiyang Yu Fei Huang and Yongbin Li. 2024. Language Models are Super Mario: Absorbing Abilities from Homologous Models as a Free Lunch. arXiv:2311.03099 [cs.CL]"}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3754894","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T03:57:58Z","timestamp":1765339078000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3754894"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":63,"alternative-id":["10.1145\/3746027.3754894","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3754894","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}