{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T15:00:25Z","timestamp":1780066825882,"version":"3.54.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Scientific and Technological Research Council of T\u00fcrkiye","award":["124E055"],"award-info":[{"award-number":["124E055"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3582015","type":"journal-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T17:28:39Z","timestamp":1750699719000},"page":"108743-108755","source":"Crossref","is-referenced-by-count":2,"title":["KAFA-Merge: Model Merging Method With Layer-Based Bayes+Linear Search"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2094-4358","authenticated-orcid":false,"given":"Muzaffer Kaan","family":"Yuce","sequence":"first","affiliation":[{"name":"Department of Computer Engineering, Yıldız Technical University, Istanbul, Türkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0404-5973","authenticated-orcid":false,"given":"Mehmet Fatih","family":"Amasyali","sequence":"additional","affiliation":[{"name":"Department of Computer Engineering, Yıldız Technical University, Istanbul, Türkiye"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1452"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00349"},{"key":"ref4","article-title":"Merging models with Fisher-weighted averaging","author":"Matena","year":"2021","journal-title":"arXiv:2111.09832"},{"key":"ref5","first-page":"2441","article-title":"Analyzing hidden representations in end-to-end automatic speech recognition systems","volume-title":"Proc. NeurIPS","volume":"30","author":"Belinkov"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.blackboxnlp-1.4"},{"key":"ref7","first-page":"23965","article-title":"Model soups: Averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","author":"Wortsman","year":"2022","journal-title":"Proc. ICML"},{"key":"ref8","article-title":"Temperature-independent optical cavities for laser frequency stabilization","author":"Zhadnov","year":"2022","journal-title":"arXiv:2202.10557"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-025-03843-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49357.2023.10097156"},{"key":"ref11","article-title":"Checkpoint merging via Bayesian optimization in LLM pretraining","author":"Liu","year":"2024","journal-title":"arXiv:2403.19390"},{"key":"ref12","article-title":"Model fusion through Bayesian optimization in language model fine-tuning","author":"Jang","year":"2024","journal-title":"arXiv:2411.06710"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.36"},{"key":"ref14","article-title":"StableRep: Synthetic images from text-to-image models make strong visual representation learners","author":"Tian","year":"2023","journal-title":"arXiv:2306.00984"},{"key":"ref15","article-title":"TIES-merging: Resolving interference when merging models","author":"Yadav","year":"2023","journal-title":"arXiv:2306.01708"},{"key":"ref16","article-title":"Editing models with task arithmetic","author":"Ilharco","year":"2022","journal-title":"arXiv:2212.04089"},{"key":"ref17","article-title":"Language models are super mario: Absorbing abilities from homologous models as a free lunch","author":"Yu","year":"2023","journal-title":"arXiv:2311.03099"},{"key":"ref18","article-title":"Model breadcrumbs: Scaling multi-task model merging with sparse masks","author":"Davari","year":"2023","journal-title":"arXiv:2312.06795"},{"key":"ref19","first-page":"1","article-title":"MergeDistill: Merging pretrained models efficiently via knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Ainsworth"},{"key":"ref20","first-page":"1","article-title":"Flat fusion: Training-free weight fusion for efficient model deployment","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dong"},{"key":"ref21","first-page":"1","article-title":"AdaMerge: Adaptive model merging for efficient transfer learning","volume-title":"Proc. ICLR","author":"Wu"},{"key":"ref22","first-page":"16640","article-title":"Merged models for continual learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Borsos"},{"key":"ref23","article-title":"A tutorial on Bayesian optimization of expensive cost functions, with application to active user modeling and hierarchical reinforcement learning","author":"Brochu","year":"2010","journal-title":"arXiv:1012.2599"},{"key":"ref24","first-page":"2951","article-title":"Practical Bayesian optimization of machine learning algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Snoek"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2494218"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1008306431147"},{"key":"ref27","article-title":"Think you have solved question answering? Try ARC, the AI2 reasoning challenge","author":"Clark","year":"2018","journal-title":"arXiv:1803.05457"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref29","article-title":"Measuring massive multitask language understanding","author":"Hendrycks","year":"2020","journal-title":"arXiv:2009.03300"},{"key":"ref30","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021","journal-title":"arXiv:2110.14168"},{"key":"ref31","volume-title":"ARC-TR V0.2 Dataset","author":"Alhajar","year":"2025"},{"key":"ref32","volume-title":"Hellaswag Turkish V0.2","author":"Alhajar","year":"2024"},{"key":"ref33","volume-title":"MMLU Turkish V0.2","author":"Alhajar","year":"2024"},{"key":"ref34","volume-title":"GSM8K Turkish V0.2","author":"Alhajar","year":"2024"},{"key":"ref35","volume-title":"Open LLM Turkish Leaderboard V0.2","author":"Alhajar","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/INISTA62901.2024.10683863"},{"key":"ref37","volume-title":"Cosmopedia","author":"Ben Allal"},{"key":"ref38","volume-title":"OpenOrca: An Open Dataset of GPT Augmented FLAN Reasoning Traces","author":"Lian","year":"2023"},{"key":"ref39","volume-title":"Llama 3.2-1B: A Multilingual Large Language Model","year":"2024"},{"key":"ref40","volume-title":"Llama 3.2-1B-Instruct: An Instruction-Tuned Multilingual LLM","year":"2024"},{"key":"ref41","volume-title":"Llama 3.2-3B","year":"2024"},{"key":"ref42","volume-title":"Llama 3.2-3B-Instruct","year":"2024"},{"key":"ref43","volume-title":"Llama 3.1-8B","year":"2024"},{"key":"ref44","volume-title":"Llama 3.1-8B-Instruct","year":"2024"},{"key":"ref45","volume-title":"Gemma","year":"2024"},{"key":"ref46","volume-title":"Metin\/Gemma-2-9b-it-TR-DPO-V1","author":"Usta","year":"2024"},{"key":"ref47","volume-title":"Gemma-2-9b-it-tr","year":"2024"},{"key":"ref48","article-title":"Model merging in LLMs, MLLMs, and beyond: Methods, theories, applications and opportunities","author":"Yang","year":"2024","journal-title":"arXiv:2408.07666"},{"key":"ref49","article-title":"LoRA: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv:2106.09685"},{"key":"ref50","article-title":"FFT: Towards harmlessness evaluation and analysis for LLMs with factuality, fairness, toxicity","author":"Cui","year":"2023","journal-title":"arXiv:2311.18580"},{"key":"ref51","article-title":"Composing parameter-efficient modules with arithmetic operations","author":"Zhang","year":"2023","journal-title":"arXiv:2306.14870"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1251"},{"key":"ref53","first-page":"372","article-title":"Learning to select data for transfer learning with Bayesian optimization","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Ruder"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00344"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.38016\/jista.815823"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.28978\/nesciences.833188"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11048544.pdf?arnumber=11048544","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,28]],"date-time":"2025-06-28T06:32:30Z","timestamp":1751092350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11048544\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3582015","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}