{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,2]],"date-time":"2025-08-02T19:01:38Z","timestamp":1754161298941,"version":"3.41.2"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,23]]},"DOI":"10.1145\/3696630.3730571","type":"proceedings-article","created":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:10:43Z","timestamp":1753729843000},"page":"1768-1773","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["AI Model Genome"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8793-5367","authenticated-orcid":false,"given":"Yanjie","family":"Zhao","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1100-8633","authenticated-orcid":false,"given":"Haoyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,7,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Mergekit: A toolkit for merging large language models. https:\/\/github.com\/arcee-ai\/mergekit","author":"Arcee","year":"2024","unstructured":"Arcee AI. Mergekit: A toolkit for merging large language models. https:\/\/github.com\/arcee-ai\/mergekit, 2024. Accessed: 2025-03-10."},{"volume-title":"https:\/\/anthropic.com","year":"2025","key":"e_1_3_2_1_2_1","unstructured":"Anthropic. Claude. https:\/\/anthropic.com, 2025. Accessed: 2025-03-10."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"crossref","first-page":"345","DOI":"10.1007\/s00530-010-0182-0","article-title":"Multimodal fusion for multimedia analysis: a survey","volume":"16","author":"Atrey Pradeep K","year":"2010","unstructured":"Pradeep K Atrey, M Anwar Hossain, Abdulmotaleb El Saddik, and Mohan S Kankanhalli. Multimodal fusion for multimedia analysis: a survey. Multimedia systems, 16:345\u2013379, 2010.","journal-title":"Multimedia systems"},{"key":"e_1_3_2_1_4_1","volume-title":"Deep learning architect: Classification for architectural design. arXiv preprint, arXiv:1812.01714","author":"Author Unknown","year":"2021","unstructured":"Unknown Author. Deep learning architect: Classification for architectural design. arXiv preprint, arXiv:1812.01714, 2021. Accessed: 2025-03-10."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"crossref","first-page":"133","DOI":"10.1007\/s10994-013-5335-x","article-title":"From machine learning to machine reasoning: An essay","volume":"94","author":"Bottou L\u00e9on","year":"2014","unstructured":"L\u00e9on Bottou. From machine learning to machine reasoning: An essay. Machine learning, 94:133\u2013149, 2014.","journal-title":"Machine learning"},{"key":"e_1_3_2_1_6_1","volume-title":"Symbolic mixture-of-experts: Adaptive skill-based routing for heterogeneous reasoning","author":"Chih-Yao Chen Justin","year":"2025","unstructured":"Justin Chih-Yao Chen, Sukwon Yun, Elias Stengel-Eskin, Tianlong Chen, and Mohit Bansal. Symbolic mixture-of-experts: Adaptive skill-based routing for heterogeneous reasoning, 2025."},{"issue":"9","key":"e_1_3_2_1_7_1","doi-asserted-by":"crossref","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","article-title":"Diffusion models in vision: A survey","volume":"45","author":"Croitoru Florinel-Alin","year":"2023","unstructured":"Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, and Mubarak Shah. Diffusion models in vision: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9):10850\u201310869, 2023.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"volume-title":"What is ai training data? examples, datasets and providers. https:\/\/datarade.ai\/data-categories\/ai-ml-training-data","year":"2025","key":"e_1_3_2_1_8_1","unstructured":"Datarade. What is ai training data? examples, datasets and providers. https:\/\/datarade.ai\/data-categories\/ai-ml-training-data, 2025. Accessed: 2025-03-10."},{"volume-title":"https:\/\/deepseek.ai","year":"2025","key":"e_1_3_2_1_9_1","unstructured":"DeepSeek. Deepseek. https:\/\/deepseek.ai, 2025. Accessed: 2025-03-10."},{"key":"e_1_3_2_1_10_1","volume-title":"Accessed","author":"Science Elite Data","year":"2025","unstructured":"Elite Data Science. The 5 levels of machine learning iteration. https:\/\/elitedatascience.com\/machine-learning-iteration, July 2022. Accessed: April 25, 2025."},{"issue":"55","key":"e_1_3_2_1_11_1","first-page":"1","article-title":"Neural architecture search: A survey","volume":"20","author":"Elsken Thomas","year":"2019","unstructured":"Thomas Elsken, Jan Hendrik Metzen, and Frank Hutter. Neural architecture search: A survey. Journal of Machine Learning Research, 20(55):1\u201321, 2019.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_1_12_1","first-page":"894","volume-title":"A brief review of domain adaptation. Advances in data science and information engineering: proceedings from ICDATA 2020 and IKE","author":"Farahani Abolfazl","year":"2020","unstructured":"Abolfazl Farahani, Sahar Voghoei, Khaled Rasheed, and Hamid R Arabnia. A brief review of domain adaptation. Advances in data science and information engineering: proceedings from ICDATA 2020 and IKE 2020, pages 877\u2013894, 2021."},{"key":"e_1_3_2_1_13_1","volume-title":"The Stanford encyclopedia of philosophy","author":"Friederich Simon","year":"2017","unstructured":"Simon Friederich. Fine-tuning. The Stanford encyclopedia of philosophy, 2017."},{"key":"e_1_3_2_1_14_1","volume-title":"Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752","author":"Gu Albert","year":"2023","unstructured":"Albert Gu and Tri Dao. Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752, 2023."},{"issue":"1","key":"e_1_3_2_1_15_1","doi-asserted-by":"crossref","first-page":"5721","DOI":"10.1038\/s41467-021-25874-z","article-title":"Embodied intelligence via learning and evolution","volume":"12","author":"Gupta Agrim","year":"2021","unstructured":"Agrim Gupta, Silvio Savarese, Surya Ganguli, and Li Fei-Fei. Embodied intelligence via learning and evolution. Nature communications, 12(1):5721, 2021.","journal-title":"Nature communications"},{"key":"e_1_3_2_1_16_1","volume-title":"On model expansion, model contraction, identifiability and prior information: two illustrative scenarios involving mismeasured variables","author":"Gustafson Paul","year":"2005","unstructured":"Paul Gustafson. On model expansion, model contraction, identifiability and prior information: two illustrative scenarios involving mismeasured variables. 2005."},{"key":"e_1_3_2_1_17_1","volume-title":"Machine psychology: Investigating emergent capabilities and behavior in large language models using psychological methods. arXiv preprint arXiv:2303.13988, 1","author":"Hagendorff Thilo","year":"2023","unstructured":"Thilo Hagendorff. Machine psychology: Investigating emergent capabilities and behavior in large language models using psychological methods. arXiv preprint arXiv:2303.13988, 1, 2023."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","first-page":"3039","DOI":"10.1016\/S1573-4412(05)80019-4","article-title":"State-space models","volume":"4","author":"Hamilton James D","year":"1994","unstructured":"James D Hamilton. State-space models. Handbook of econometrics, 4:3039\u20133080, 1994.","journal-title":"Handbook of econometrics"},{"issue":"8","key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. Long short-term memory. Neural computation, 9(8):1735\u20131780, 1997.","journal-title":"Neural computation"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","first-page":"249","DOI":"10.1016\/j.neucom.2021.04.112","article-title":"A comprehensive survey","volume":"459","author":"Hoi Steven CH","year":"2021","unstructured":"Steven CH Hoi, Doyen Sahoo, Jing Lu, and Peilin Zhao. Online learning: A comprehensive survey. Neurocomputing, 459:249\u2013289, 2021.","journal-title":"Neurocomputing"},{"issue":"8","key":"e_1_3_2_1_21_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3695988","article-title":"Large language models for software engineering: A systematic literature review","volume":"33","author":"Hou Xinyi","year":"2024","unstructured":"Xinyi Hou, Yanjie Zhao, Yue Liu, Zhou Yang, Kailong Wang, Li Li, Xiapu Luo, David Lo, John Grundy, and Haoyu Wang. Large language models for software engineering: A systematic literature review. ACM Transactions on Software Engineering and Methodology, 33(8):1\u201379, 2024.","journal-title":"ACM Transactions on Software Engineering and Methodology"},{"key":"e_1_3_2_1_22_1","unstructured":"IBM. What is knowledge distillation? https:\/\/www.ibm.com\/think\/topics\/knowledge-distillation 2024. Accessed: 2025-03-10."},{"key":"e_1_3_2_1_23_1","first-page":"38887","article-title":"The emergence of essential sparsity in large pre-trained models: The weights that matter","volume":"36","author":"Jaiswal Ajay","year":"2023","unstructured":"Ajay Jaiswal, Shiwei Liu, Tianlong Chen, Zhangyang Wang, et al. The emergence of essential sparsity in large pre-trained models: The weights that matter. Advances in Neural Information Processing Systems, 36:38887\u201338901, 2023.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_24_1","volume-title":"Fairness-aware low-rank adaptation under demographic privacy constraints","author":"Kamalaruban Parameswaran","year":"2025","unstructured":"Parameswaran Kamalaruban, Mark Anderson, Stuart Burrell, Maeve Madigan, Piotr Skalski, and David Sutton. Fairness-aware low-rank adaptation under demographic privacy constraints, 2025."},{"volume-title":"Finding the best training data for your ai model. https:\/\/keylabs.ai\/blog\/finding-the-best-training-data-for-your-ai-model\/","year":"2024","key":"e_1_3_2_1_25_1","unstructured":"Keylabs. Finding the best training data for your ai model. https:\/\/keylabs.ai\/blog\/finding-the-best-training-data-for-your-ai-model\/, 2024. Accessed: 2025-03-10."},{"issue":"11","key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","first-page":"2278","DOI":"10.1109\/5.726791","article-title":"Gradient-based learning applied to document recognition","volume":"86","author":"LeCun Yann","year":"1998","unstructured":"Yann LeCun, Yoshua Bengio, and Geoffrey Hinton. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278\u20132324, 1998.","journal-title":"Proceedings of the IEEE"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1016\/j.compchemeng.2019.03.040","article-title":"Understanding the effect of specialization on hospital performance through knowledge-guided machine learning","volume":"125","author":"Lee Jangwon","year":"2019","unstructured":"Jangwon Lee and Q Peter He. Understanding the effect of specialization on hospital performance through knowledge-guided machine learning. Computers & Chemical Engineering, 125:490\u2013498, 2019.","journal-title":"Computers & Chemical Engineering"},{"key":"e_1_3_2_1_28_1","volume-title":"Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities. npj Computational Materials, 11(1):84","author":"Lu Wei","year":"2025","unstructured":"Wei Lu, Rachel K Luu, and Markus J Buehler. Fine-tuning large language models for domain adaptation: Exploration of training strategies, scaling, model merging and synergistic capabilities. npj Computational Materials, 11(1):84, 2025."},{"key":"e_1_3_2_1_29_1","first-page":"9","volume-title":"Proceedings of the Conference on Fairness, Accountability, and Transparency","author":"Milli Smitha","year":"2019","unstructured":"Smitha Milli, Ludwig Schmidt, Anca D Dragan, and Moritz Hardt. Model reconstruction from model explanations. In Proceedings of the Conference on Fairness, Accountability, and Transparency, pages 1\u20139, 2019."},{"key":"e_1_3_2_1_30_1","volume-title":"https:\/\/openai.com","author":"AI.","year":"2025","unstructured":"OpenAI. Gpt-4.5. https:\/\/openai.com, 2025. Accessed: 2025-03-10."},{"issue":"53","key":"e_1_3_2_1_31_1","first-page":"1","article-title":"Importance of hyperparameters of machine learning algorithms","volume":"20","author":"Probst Philipp","year":"2019","unstructured":"Philipp Probst, Anne-Laure Boulesteix, and Bernd Bischl. Tunability: Importance of hyperparameters of machine learning algorithms. Journal of Machine Learning Research, 20(53):1\u201332, 2019.","journal-title":"Journal of Machine Learning Research"},{"volume-title":"Comparison of ai model architectures. https:\/\/www.restack.io\/p\/ai-model-answer-comparison-of-architectures-cat-ai","year":"2025","key":"e_1_3_2_1_32_1","unstructured":"Restackio. Comparison of ai model architectures. https:\/\/www.restack.io\/p\/ai-model-answer-comparison-of-architectures-cat-ai, 2025. Accessed: 2025-03-10."},{"key":"e_1_3_2_1_33_1","volume-title":"Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy","author":"Shao Zhihong","year":"2023","unstructured":"Zhihong Shao, Yeyun Gong, Yelong Shen, Minlie Huang, Nan Duan, and Weizhu Chen. Enhancing retrieval-augmented large language models with iterative retrieval-generation synergy, 2023."},{"key":"e_1_3_2_1_34_1","first-page":"6114","volume-title":"International conference on machine learning","author":"Tan Mingxing","unstructured":"Mingxing Tan and Quoc Le. Efficientnet: Rethinking model scaling for convolutional neural networks. In International conference on machine learning, pages 6105\u20136114. PMLR, 2019."},{"key":"e_1_3_2_1_35_1","volume-title":"Attention is all you need. arXiv preprint arXiv:1706.03762","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. Attention is all you need. arXiv preprint arXiv:1706.03762, 2017."},{"key":"e_1_3_2_1_36_1","volume-title":"et al. K-adapter: Infusing knowledge into pre-trained models with adapters. arXiv preprint arXiv:2002.01808","author":"Wang Ruize","year":"2020","unstructured":"Ruize Wang, Duyu Tang, Nan Duan, Zhongyu Wei, Xuanjing Huang, Guihong Cao, Daxin Jiang, Ming Zhou, et al. K-adapter: Infusing knowledge into pre-trained models with adapters. arXiv preprint arXiv:2002.01808, 2020."},{"key":"e_1_3_2_1_37_1","volume-title":"A code knowledge graph-enhanced system for llm-based fuzz driver generation. arXiv preprint arXiv:2411.11532","author":"Xu Hanxiang","year":"2024","unstructured":"Hanxiang Xu, Wei Ma, Ting Zhou, Yanjie Zhao, Kai Chen, Qiang Hu, Yang Liu, and Haoyu Wang. A code knowledge graph-enhanced system for llm-based fuzz driver generation. arXiv preprint arXiv:2411.11532, 2024."},{"key":"e_1_3_2_1_38_1","volume-title":"Athanasios Mouchtaris, Sravan Babu Bodapati, Nathan Susanj, Zheng Zhang, Jack FitzGerald, and Abhishek Kumar. Wanda++: Pruning large language models via regional gradients","author":"Yang Yifan","year":"2025","unstructured":"Yifan Yang, Kai Zhen, Bhavana Ganesh, Aram Galstyan, Goeric Huybrechts, Markus M\u00fcller, Jonas M. K\u00fcbler, Rupak Vignesh Swaminathan, Athanasios Mouchtaris, Sravan Babu Bodapati, Nathan Susanj, Zheng Zhang, Jack FitzGerald, and Abhishek Kumar. Wanda++: Pruning large language models via regional gradients, 2025."},{"key":"e_1_3_2_1_39_1","volume-title":"Instruction tuning for large language models: A survey. arXiv preprint arXiv:2308.10792","author":"Zhang Shengyu","year":"2023","unstructured":"Shengyu Zhang, Linfeng Dong, Xiaoya Li, Sen Zhang, Xiaofei Sun, Shuhe Wang, Jiwei Li, Runyi Hu, Tianwei Zhang, Fei Wu, et al. Instruction tuning for large language models: A survey. arXiv preprint arXiv:2308.10792, 2023."},{"key":"e_1_3_2_1_40_1","volume-title":"Qartsr: Quantization via reverse-module and timestep-retraining in one-step diffusion based image super-resolution","author":"Zhu Libo","year":"2025","unstructured":"Libo Zhu, Haotong Qin, Kaicheng Yang, Wenbo Li, Yong Guo, Yulun Zhang, Susanto Rahardja, and Xiaokang Yang. Qartsr: Quantization via reverse-module and timestep-retraining in one-step diffusion based image super-resolution, 2025."}],"event":{"name":"FSE Companion '25: 33rd ACM International Conference on the Foundations of Software Engineering","sponsor":["SIGSOFT ACM Special Interest Group on Software Engineering"],"location":"Clarion Hotel Trondheim Trondheim Norway","acronym":"FSE Companion '25"},"container-title":["Proceedings of the 33rd ACM International Conference on the Foundations of Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3696630.3730571","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,28]],"date-time":"2025-07-28T19:14:06Z","timestamp":1753730046000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3696630.3730571"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,23]]},"references-count":40,"alternative-id":["10.1145\/3696630.3730571","10.1145\/3696630"],"URL":"https:\/\/doi.org\/10.1145\/3696630.3730571","relation":{},"subject":[],"published":{"date-parts":[[2025,6,23]]},"assertion":[{"value":"2025-07-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}