{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T13:15:22Z","timestamp":1785330922033,"version":"3.55.0"},"reference-count":59,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62232005,62202126"],"award-info":[{"award-number":["62232005,62202126"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021YFB3300502"],"award-info":[{"award-number":["2021YFB3300502"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00368","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3863-3873","source":"Crossref","is-referenced-by-count":1,"title":["Free-Merging: Fourier Transform for Efficient Model Merging"],"prefix":"10.1109","author":[{"given":"Shenghe","family":"Zheng","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongzhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"4","article-title":"Git re-basin: Merging models modulo permutation symmetries","volume-title":"The Eleventh International Conference on Learning Representations","author":"Ainsworth"},{"key":"ref2","first-page":"6","article-title":"Qwen technical report","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00201"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3663363"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02120"},{"issue":"70","key":"ref6","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73226-3_16"},{"key":"ref8","first-page":"6","article-title":"Della-merging: Reducing interference in model merging through magnitude-based sampling","author":"Tej Deep","year":"2024","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19\u20131423"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00626-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/s11704-019-8208-z"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2691"},{"key":"ref13","first-page":"3","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0165-1684(90)90158-U"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105151"},{"key":"ref16","first-page":"8","article-title":"Task singular vectors: Reducing task interference in model merging","author":"Gargiulo","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","first-page":"7","article-title":"Loss surfaces, mode connectivity, and fast ensembling of dnns","volume":"31","author":"Garipov","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref18","first-page":"2","article-title":"Digital image processing","author":"Gonzales","year":"1987","journal-title":"Addison-Wesley Longman Publishing Co., Inc."},{"key":"ref19","first-page":"6","article-title":"Lora: Lowrank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Edward"},{"key":"ref20","article-title":"Emr-merging: Tuningfree high-performance model merging","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Editing models with task arithmetic","author":"Ilharco","year":"2022","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.792"},{"key":"ref23","article-title":"Dataless knowledge fusion by merging weights of language models","author":"Jin","year":"2022","journal-title":"arXiv preprint"},{"key":"ref24","first-page":"5","article-title":"Gshard: Scaling giant models with conditional computation and automatic sharding","volume-title":"International Conference on Learning Representations","author":"Lepikhin"},{"key":"ref25","first-page":"7","article-title":"Visualizing the loss landscape of neural nets","volume":"31","author":"Li","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0142"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0434"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01048"},{"key":"ref29","article-title":"Twin-merging: Dynamic integration of modular expertise in model merging","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","first-page":"6","article-title":"Wizardmath: Empowering mathematical reasoning for large language models via reinforced evol-instruct","author":"Luo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","first-page":"6","article-title":"Wizardcoder: Empowering code large language models with evol-instruct","volume-title":"The Twelfth International Conference on Learning Representations","author":"Luo"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0950"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1287"},{"key":"ref34","first-page":"512","article-title":"What is being transferred in transfer learning?","volume":"33","author":"Neyshabur","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2126"},{"key":"ref36","first-page":"2","article-title":"Less is more: Efficient model merging with binary task switch","author":"Qi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref38","first-page":"6","article-title":"Multitask prompted training enables zero-shot task generalization","volume-title":"International Conference on Learning Representations","author":"Sanh"},{"key":"ref39","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"International Conference on Learning Representations","author":"Shazeer"},{"key":"ref40","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3054719"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref43","article-title":"Huggingface\u2019s transformers: State-of-the-art natural language processing","author":"Wolf","year":"2019","journal-title":"arXiv preprint"},{"key":"ref44","first-page":"23965","article-title":"Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","volume-title":"International conference on machine learning","author":"Wortsman"},{"key":"ref45","first-page":"37713","article-title":"$\\backslash \\pi$-tuning: Transferring multimodal foundation models with optimal multi-task interpolation","volume-title":"International Conference on Machine Learning","author":"Wu"},{"key":"ref46","first-page":"6","article-title":"Wizardlm: Empowering large pre-trained language models to follow complex instructions","volume-title":"The Twelfth International Conference on Learning Representations","author":"Xu"},{"key":"ref47","article-title":"Random masking finds winning tickets for parameter efficient fine-tuning","volume-title":"Forty-first International Conference on Machine Learning","author":"Xu"},{"key":"ref48","article-title":"Ties-merging: Resolving interference when merging models","volume":"36","author":"Yadav","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref49","first-page":"2","article-title":"Model merging in llms, mllms, and beyond: Methods, theories, applications and opportunities","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Representation surgery for multi-task model merging","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","first-page":"1","article-title":"Representation surgery for multi-task model merging","volume-title":"Forty-first International Conference on Machine Learning","author":"Yang"},{"key":"ref52","article-title":"Adamerging: Adaptive model merging for multi-task learning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Yang"},{"key":"ref53","article-title":"Language models are super mario: Absorbing abilities from homologous models as a free lunch","volume-title":"Forty-first International Conference on Machine Learning","author":"Yu"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.1045"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0552"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0515"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.102"},{"key":"ref59","first-page":"1218","article-title":"A robustly optimized BERT pre-training approach with post-training","volume-title":"Proceedings of the 20th Chinese National Conference on Computational Linguistics","author":"Zhuang"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445923.pdf?arnumber=11445923","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:33Z","timestamp":1777612473000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445923\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00368","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}