{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T18:39:26Z","timestamp":1771958366140,"version":"3.50.1"},"publisher-location":"Cham","reference-count":61,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732256","type":"print"},{"value":"9783031732263","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73226-3_16","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T15:02:57Z","timestamp":1730386977000},"page":"270-287","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Model Breadcrumbs: Scaling Multi-task Model Merging with\u00a0Sparse Masks"],"prefix":"10.1007","author":[{"given":"MohammadReza","family":"Davari","sequence":"first","affiliation":[]},{"given":"Eugene","family":"Belilovsky","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"key":"16_CR1","unstructured":"Ainsworth, S.K., Hayase, J., Srinivasa, S.: Git re-basin: merging models modulo permutation symmetries. arXiv preprint arXiv:2209.04836 (2022)"},{"key":"16_CR2","unstructured":"Asadi, N., Davari, M., Mudur, S., Aljundi, R., Belilovsky, E.: Prototype-sample relation distillation: towards replay-free continual learning. In: International Conference on Machine Learning, pp. 1093\u20131106. PMLR (2023)"},{"key":"16_CR3","unstructured":"Bommasani, R., et\u00a0al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)"},{"key":"16_CR4","doi-asserted-by":"publisher","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","volume":"105","author":"G Cheng","year":"2017","unstructured":"Cheng, G., Han, J., Lu, X.: Remote sensing image scene classification: benchmark and state of the art. Proc. IEEE 105, 1865\u20131883 (2017)","journal-title":"Proc. IEEE"},{"key":"16_CR5","unstructured":"Cho, J., Lei, J., Tan, H., Bansal, M.: Unifying vision-and-language tasks via text generation. In: International Conference on Machine Learning, pp. 1931\u20131942. PMLR (2021)"},{"key":"16_CR6","unstructured":"Choshen, L., Venezian, E., Slonim, N., Katz, Y.: Fusing finetuned models for better pretraining. arXiv preprint arXiv:2204.03044 (2022)"},{"key":"16_CR7","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., , Vedaldi, A.: Describing textures in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Cossu, A., Tuytelaars, T., Carta, A., Passaro, L., Lomonaco, V., Bacciu, D.: Continual pre-training mitigates forgetting in language and vision. arXiv preprint arXiv:2205.09357 (2022)","DOI":"10.2139\/ssrn.4495233"},{"key":"16_CR9","doi-asserted-by":"crossref","unstructured":"Davari, M., Asadi, N., Mudur, S., Aljundi, R., Belilovsky, E.: Probing representation forgetting in supervised and unsupervised continual learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16712\u201316721 (2022)","DOI":"10.1109\/CVPR52688.2022.01621"},{"key":"16_CR10","unstructured":"Davari, M., Belilovsky, E.: Probing representation forgetting in continual learning. In: NeurIPS 2021 Workshop on Distribution Shifts: Connecting Methods and Applications (2021)"},{"key":"16_CR11","unstructured":"Davari, M., Belilovsky, E.: Model breadcrumbs: scalable upcycling of finetuned foundation models via sparse task vectors merging. In: ICML 2024 Workshop on Foundation Models in the Wild (2024)"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Davari, M., Kosseim, L., Bui, T.: TIMBERT: toponym identifier for the medical domain based on BERT. In: Proceedings of the 28th International Conference on Computational Linguistics, pp. 662\u2013668 (2020)","DOI":"10.18653\/v1\/2020.coling-main.58"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"16_CR14","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"16_CR15","unstructured":"Dolan, B., Brockett, C.: Automatically constructing a corpus of sentential paraphrases. In: Third International Workshop on Paraphrasing (IWP2005) (2005)"},{"key":"16_CR16","doi-asserted-by":"crossref","unstructured":"Don-Yehiya, S., Venezian, E., Raffel, C., Slonim, N., Katz, Y., Choshen, L.: Cold fusion: Collaborative descent for distributed multitask finetuning. arXiv preprint arXiv:2212.01378 (2022)","DOI":"10.18653\/v1\/2023.acl-long.46"},{"key":"16_CR17","doi-asserted-by":"crossref","unstructured":"Fabbri, A.R., Li, I., She, T., Li, S., Radev, D.R.: Multi-news: a large-scale multi-document summarization dataset and abstractive hierarchical model. arXiv preprint arXiv:1906.01749 (2019)","DOI":"10.18653\/v1\/P19-1102"},{"key":"16_CR18","doi-asserted-by":"crossref","unstructured":"Farahnak, F., Mohammadi, E., Davari, M., Kosseim, L.: Semantic similarity matching using contextualized representations. In: Canadian Conference on AI (2021)","DOI":"10.21428\/594757db.ea4e52c7"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification. IEEE J. Sel. Top. Appl. Earth Observations Remote Sens. (2019)","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Houben, S., Stallkamp, J., Salmen, J., Schlipsing, M., Igel, C.: Detection of traffic signs in real-world images: the German traffic sign detection benchmark. In: International Joint Conference on Neural Networks (2013)","DOI":"10.1109\/IJCNN.2013.6706807"},{"key":"16_CR21","unstructured":"Ilharco, G., et al.: Editing models with task arithmetic. arXiv preprint arXiv:2212.04089 (2022)"},{"key":"16_CR22","first-page":"29262","volume":"35","author":"G Ilharco","year":"2022","unstructured":"Ilharco, G., et al.: Patching open-vocabulary models by interpolating weights. Adv. Neural. Inf. Process. Syst. 35, 29262\u201329277 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR23","unstructured":"Izmailov, P., Podoprikhin, D., Garipov, T., Vetrov, D., Wilson, A.G.: Averaging weights leads to wider optima and better generalization. arXiv preprint arXiv:1803.05407 (2018)"},{"key":"16_CR24","doi-asserted-by":"crossref","unstructured":"Khot, T., Clark, P., Guerquin, M., Jansen, P., Sabharwal, A.: QASC: a dataset for question answering via sentence composition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a034, pp. 8082\u20138090 (2020)","DOI":"10.1609\/aaai.v34i05.6319"},{"key":"16_CR25","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: International Conference on Machine Learning, pp. 5583\u20135594. PMLR (2021)"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings of the IEEE International Conference on Computer Vision Workshops, pp. 554\u2013561 (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Lai, G., Xie, Q., Liu, H., Yang, Y., Hovy, E.: Race: large-scale reading comprehension dataset from examinations. arXiv preprint arXiv:1704.04683 (2017)","DOI":"10.18653\/v1\/D17-1082"},{"key":"16_CR28","unstructured":"LeCun, Y., Cortes, C., Burges, C.: MNIST handwritten digit database. ATT Labs [Online]. Available: http:\/\/yann.lecun.com\/exdb\/mnist2 (2010)"},{"key":"16_CR29","unstructured":"Legate, G., Bernier, N., Caccia, L., Oyallon, E., Belilovsky, E.: Guiding the last layer in federated learning with pre-trained models. arXiv preprint arXiv:2306.03937 (2023)"},{"key":"16_CR30","doi-asserted-by":"crossref","unstructured":"Lewis, M., et al.: BART: denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. arXiv preprint arXiv:1910.13461 (2019)","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"16_CR31","doi-asserted-by":"crossref","unstructured":"Lin, B.Y., et al.: Commongen: a constrained text generation challenge for generative commonsense reasoning. arXiv preprint arXiv:1911.03705 (2019)","DOI":"10.18653\/v1\/2020.findings-emnlp.165"},{"key":"16_CR32","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"16_CR33","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"16_CR34","unstructured":"Luo, H., et al.: UniVL: a unified video and language pre-training model for multimodal understanding and generation. arXiv preprint arXiv:2002.06353 (2020)"},{"key":"16_CR35","unstructured":"Maas, A., Daly, R.E., Pham, P.T., Huang, D., Ng, A.Y., Potts, C.: Learning word vectors for sentiment analysis. In: Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, pp. 142\u2013150 (2011)"},{"key":"16_CR36","unstructured":"Matena, M.S., Raffel, C.A.: Merging models with fisher-weighted averaging. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) Advances in Neural Information Processing Systems, vol.\u00a035, pp. 17703\u201317716. Curran Associates, Inc. (2022). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2022\/file\/70c26937fbf3d4600b69a129031b66ec-Paper-Conference.pdf"},{"issue":"1","key":"16_CR37","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/S0022-2496(02)00028-7","volume":"47","author":"IJ Myung","year":"2003","unstructured":"Myung, I.J.: Tutorial on maximum likelihood estimation. J. Math. Psychol. 47(1), 90\u2013100 (2003)","journal-title":"J. Math. Psychol."},{"key":"16_CR38","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. Adv. Neural Inf. Process. Syst. (NIPS) (2011)"},{"key":"16_CR39","first-page":"512","volume":"33","author":"B Neyshabur","year":"2020","unstructured":"Neyshabur, B., Sedghi, H., Zhang, C.: What is being transferred in transfer learning? Adv. Neural. Inf. Process. Syst. 33, 512\u2013523 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"16_CR40","unstructured":"Nguyen, J., Malik, K., Sanjabi, M., Rabbat, M.: Where to begin? Exploring the impact of pre-training and initialization in federated learning. arXiv preprint arXiv:2206.15387 (2022)"},{"key":"16_CR41","doi-asserted-by":"crossref","unstructured":"Oquab, M., Bottou, L., Laptev, I., Sivic, J.: Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1717\u20131724 (2014)","DOI":"10.1109\/CVPR.2014.222"},{"key":"16_CR42","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"16_CR43","unstructured":"Radford, A., Narasimhan, K., Salimans, T., Sutskever, I.: Improving language understanding with unsupervised learning. OpenAI blog (2018)"},{"issue":"8","key":"16_CR44","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"issue":"1","key":"16_CR45","first-page":"5485","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(1), 5485\u20135551 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: SQuAD: 100,000+ questions for machine comprehension of text. arXiv preprint arXiv:1606.05250 (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"16_CR47","unstructured":"Ram\u00e9, A., Ahuja, K., Zhang, J., Cord, M., Bottou, L., Lopez-Paz, D.: Model ratatouille: recycling diverse models for out-of-distribution generalization. arXiv preprint arXiv:2212.10445 (2022)"},{"key":"16_CR48","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"issue":"15","key":"16_CR49","doi-asserted-by":"publisher","first-page":"e2016239118","DOI":"10.1073\/pnas.2016239118","volume":"118","author":"A Rives","year":"2021","unstructured":"Rives, A., et al.: Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proc. Natl. Acad. Sci. 118(15), e2016239118 (2021)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"16_CR50","unstructured":"Rothchild, D., Tamkin, A., Yu, J., Misra, U., Gonzalez, J.: C5T5: controllable generation of organic molecules with transformers. arXiv preprint arXiv:2108.10307 (2021)"},{"key":"16_CR51","doi-asserted-by":"crossref","unstructured":"Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pp. 1631\u20131642 (2013)","DOI":"10.18653\/v1\/D13-1170"},{"key":"16_CR52","unstructured":"Stoica, G., Bolya, D., Bjorner, J., Hearn, T., Hoffman, J.: Zipit! merging models from different tasks without training. arXiv preprint arXiv:2305.03053 (2023)"},{"key":"16_CR53","doi-asserted-by":"publisher","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.: GLUE: a multi-task benchmark and analysis platform for natural language understanding. In: Linzen, T., Chrupa\u0142a, G., Alishahi, A. (eds.) Proceedings of the 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP, pp. 353\u2013355. Association for Computational Linguistics, Brussels, Belgium (Nov 2018). https:\/\/doi.org\/10.18653\/v1\/W18-5446, https:\/\/aclanthology.org\/W18-5446","DOI":"10.18653\/v1\/W18-5446"},{"key":"16_CR54","doi-asserted-by":"publisher","first-page":"625","DOI":"10.1162\/tacl_a_00290","volume":"7","author":"A Warstadt","year":"2019","unstructured":"Warstadt, A., Singh, A., Bowman, S.R.: Neural network acceptability judgments. Trans. Assoc. Comput. Linguist. 7, 625\u2013641 (2019)","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"16_CR55","unstructured":"Wolf, T., et\u00a0al.: Transformers: state-of-the-art natural language processing. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp. 38\u201345 (2020)"},{"key":"16_CR56","unstructured":"Wortsman, M., et\u00a0al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In: International Conference on Machine Learning, pp. 23965\u201323998. PMLR (2022)"},{"key":"16_CR57","doi-asserted-by":"crossref","unstructured":"Wortsman, M., et\u00a0al.: Robust fine-tuning of zero-shot models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7959\u20137971 (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"16_CR58","doi-asserted-by":"crossref","unstructured":"Xiao, J., Hays, J., Ehinger, K.A., Oliva, A., Torralba, A.: Sun database: large-scale scene recognition from abbey to zoo. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 3485\u20133492 (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"16_CR59","unstructured":"Yadav, P., Tam, D., Choshen, L., Raffel, C., Bansal, M.: Ties-merging: resolving interference when merging models. In: Thirty-seventh Conference on Neural Information Processing Systems (2023)"},{"key":"16_CR60","unstructured":"Yang, Z., Maricar, Y., Davari, M., Grenon-Godbout, N., Rabbany, R.: Toxbuster: In-game chat toxicity buster with BERT. arXiv preprint arXiv:2305.12542 (2023)"},{"key":"16_CR61","doi-asserted-by":"crossref","unstructured":"Yin, P., Neubig, G., Yih, W.t., Riedel, S.: TaBERT: pretraining for joint understanding of textual and tabular data. arXiv preprint arXiv:2005.08314 (2020)","DOI":"10.18653\/v1\/2020.acl-main.745"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73226-3_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T16:01:48Z","timestamp":1732982508000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73226-3_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9783031732256","9783031732263"],"references-count":61,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73226-3_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}