{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T23:04:49Z","timestamp":1789254289392,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":74,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032375551","type":"print"},{"value":"9783032375568","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37556-8_22","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:14:29Z","timestamp":1789251269000},"page":"402-421","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Stay Unique, Stay Efficient: Preserving Model Personality in\u00a0Multi-task Merging"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7267-0428","authenticated-orcid":false,"given":"Kuangpu","family":"Guo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4782-9858","authenticated-orcid":false,"given":"Aijing","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3890-1894","authenticated-orcid":false,"given":"Jian","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7572-3049","authenticated-orcid":false,"given":"Yuhe","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1822-3731","authenticated-orcid":false,"given":"Zilei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3807-991X","authenticated-orcid":false,"given":"Ran","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1808-2169","authenticated-orcid":false,"given":"Tieniu","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"22_CR1","unstructured":"Ainsworth, S.K., Hayase, J., Srinivasa, S.: Git Re-Basin: merging models modulo permutation symmetries. In: Proceedings ICLR (2023)"},{"key":"22_CR2","unstructured":"Bai, J., et\u00a0al.: Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Caruana, R.: Multitask learning. Mach. Learn., pp. 41\u201375 (1997)","DOI":"10.1023\/A:1007379606734"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Cer, D., Diab, M., Agirre, E., Lopez-Gazpio, I., Specia, L.: SemEval-2017 task 1: semantic textual similarity multilingual and crosslingual focused evaluation. In: Proceedings of the 11th International Workshop on Semantic Evaluation (2017)","DOI":"10.18653\/v1\/S17-2001"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Chen, H.M., Hu, S.X., Luk, W., Hospedales, T., Fan, H.: FW-merging: scaling model merging with frank-wolfe optimization. In: Proceedings ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00324"},{"key":"22_CR6","unstructured":"Chen, Z., Zhang, H., Zhang, X., Zhao, L.: Quora question pairs (2018)"},{"key":"22_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, G., Han, J., Lu, X.: Remote sensing image scene classification: benchmark and state of the art. In: Proceedings of the IEEE, pp. 1865\u20131883 (2017)","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Cimpoi, M., Maji, S., Kokkinos, I., Mohamed, S., Vedaldi, A.: Describing textures in the wild. In: Proceedings CVPR (2014)","DOI":"10.1109\/CVPR.2014.461"},{"key":"22_CR9","unstructured":"Davari, M., Belilovsky, E.: Model breadcrumbs: scalable upcycling of finetuned foundation models via sparse task vectors merging. In: Proceedings ICML (2024)"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Deng, L.: The MNIST database of handwritten digit images for machine learning research. IEEE Signal Process. Mag., 141\u2013142 (2012)","DOI":"10.1109\/MSP.2012.2211477"},{"key":"22_CR11","unstructured":"Ding, Y., Liang, J., Jiang, B., Wang, Z., Zheng, A., Luo, B.: Harmonizing and merging source models for clip-based domain generalization. arXiv preprint arXiv:2506.09446 (2025)"},{"key":"22_CR12","unstructured":"Dodge, J., Ilharco, G., Schwartz, R., Farhadi, A., Hajishirzi, H., Smith, N.: Fine-tuning pretrained language models: weight initializations, data orders, and early stopping. arXiv:2002.06305 (2020)"},{"key":"22_CR13","unstructured":"Dolan, B., Brockett, C.: Automatically constructing a corpus of sentential paraphrases. In: Third International Workshop on Paraphrasing (2005)"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Eckart, C., Young, G.: The approximation of one matrix by another of lower rank. Psychometrika, 211\u2013218 (1936)","DOI":"10.1007\/BF02288367"},{"key":"22_CR15","doi-asserted-by":"crossref","unstructured":"Gargiulo, A.A., Crisostomi, D., Bucarelli, M.S., Scardapane, S., Silvestri, F., Rodola, E.: Task singular vectors: reducing task interference in model merging. In: Proceedings CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01742"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Giampiccolo, D., Magnini, B., Dagan, I., Dolan, W.B.: The third pascal recognizing textual entailment challenge. In: Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing (2007)","DOI":"10.3115\/1654536.1654538"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"He, J.: Gradient reweighting: towards imbalanced class-incremental learning. In: Proceedings CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.01577"},{"key":"22_CR18","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 Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2217\u20132226 (2019)","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"22_CR19","unstructured":"Hendrycks, D., et al.: Measuring massive multitask language understanding. In: Proceedings ICLR (2020)"},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Huang, C., Ye, P., Chen, T., He, T., Yue, X., Ouyang, W.: EMR-merging: tuning-free high-performance model merging. In: Proceedings NeurIPS (2024)","DOI":"10.52202\/079017-3900"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Hyun, J., et al.: Multi-granular spatio-temporal token merging for training-free acceleration of video LLMs. In: Proceedings ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02224"},{"key":"22_CR22","unstructured":"Ilharco, G., et al.: Editing models with task arithmetic. In: Proceedings ICLR (2023)"},{"key":"22_CR23","unstructured":"Jin, X., Ren, X., Preotiuc-Pietro, D., Cheng, P.: Dataless knowledge fusion by merging weights of language models. In: Proceedings ICLR (2023)"},{"key":"22_CR24","unstructured":"Jordan, K., Sedghi, H., Saukh, O., Entezari, R., Neyshabur, B.: Repair: Renormalizing permuted activations for interpolation repair. In: Proceedings ICLR (2023)"},{"key":"22_CR25","doi-asserted-by":"crossref","unstructured":"Kim, Y., Lee, S., Jung, A., Ryu, B., Hong, S.: Task vector quantization for memory-efficient model merging. In: Proceedings ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01870"},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3D object representations for fine-grained categorization. In: Proceedings ICCV (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"22_CR27","doi-asserted-by":"crossref","unstructured":"Lange, K., Lange, K.: Singular value decomposition. Numerical Analysis for Statisticians, pp. 129\u2013142 (2010)","DOI":"10.1007\/978-1-4419-5945-4_9"},{"key":"22_CR28","unstructured":"Lee, Y., Jung, J., Baik, S.: Mitigating parameter interference in model merging via sharpness-aware fine-tuning. In: Proceedings ICLR (2025)"},{"key":"22_CR29","unstructured":"Li, L., et al.: Map: Low-compute model merging with amortized pareto fronts via quadratic approximation. In: Proceedings ICLR (2025)"},{"key":"22_CR30","unstructured":"Li, Y., et\u00a0al.: Model merging in pre-training of large language models. In: Proceedings NeurIPS (2025)"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Lin, S., Hilton, J., Evans, O.: TruthfulQA: measuring how models mimic human falsehoods. In: Proceedings ACL (2022)","DOI":"10.18653\/v1\/2022.acl-long.229"},{"key":"22_CR32","unstructured":"Liu, S., et al.: 1bit-merging: Dynamic quantized merging for large language models. arXiv:2502.10743 (2025)"},{"key":"22_CR33","unstructured":"Liu, Y., et al.: RoBERTa: A robustly optimized BERT pretraining approach. arXiv:1907.11692 (2019)"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Lu, Z., Fan, C., Wei, W., Qu, X., Chen, D., Cheng, Y.: Twin-merging: Dynamic integration of modular expertise in model merging. In: Proceedings NeurIPS (2024)","DOI":"10.52202\/079017-2505"},{"key":"22_CR35","unstructured":"Marczak, D., Magistri, S., Cygert, S., Twardowski, B., Bagdanov, A.D., van\u00a0de Weijer, J.: No task left behind: isotropic model merging with common and task-specific subspaces. In: Proceedings ICML (2025)"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Matena, M.S., Raffel, C.A.: Merging models with fisher-weighted averaging. In: Proceedings NeurIPS (2022)","DOI":"10.52202\/068431-1287"},{"key":"22_CR37","unstructured":"Muqeeth, M., Liu, H., Raffel, C.: Soft merging of experts with adaptive routing. arXiv:2306.03745 (2023)"},{"key":"22_CR38","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y.: Reading digits in natural images with unsupervised feature learning. In: Proceedings NeurIPS (2011)"},{"key":"22_CR39","unstructured":"Oh, C., Li, Y., Song, K., Yun, S., Han, D.: DaWin: training-free dynamic weight interpolation for robust adaptation. In: Proceedings ICLR (2025)"},{"key":"22_CR40","doi-asserted-by":"crossref","unstructured":"Parrish, A., et al.: BBQ: a hand-built bias benchmark for question answering. In: Proceedings ACL (2022)","DOI":"10.18653\/v1\/2022.findings-acl.165"},{"key":"22_CR41","doi-asserted-by":"crossref","unstructured":"Qi, B., et al.: Less is more: efficient model merging with binary task switch. In: Proceedings CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01422"},{"key":"22_CR42","doi-asserted-by":"crossref","unstructured":"Qiu, Z., et al.: MINGLE: Mixtures of null-space gated low-rank experts for test-time continual model merging. In: Proceedings NeurIPS (2025)","DOI":"10.52202\/085713-4814"},{"key":"22_CR43","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings ICML (2021)"},{"key":"22_CR44","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et\u00a0al.: Language models are unsupervised multitask learners. OpenAI blog, p.\u00a09 (2019)"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Rajpurkar, P., Zhang, J., Lopyrev, K., Liang, P.: Squad: 100,000+ questions for machine comprehension of text. In: Proceedings EMNLP (2016)","DOI":"10.18653\/v1\/D16-1264"},{"key":"22_CR46","doi-asserted-by":"crossref","unstructured":"Socher, R., et al.: Recursive deep models for semantic compositionality over a sentiment treebank. In: Proceedings EMNLP (2013)","DOI":"10.18653\/v1\/D13-1170"},{"key":"22_CR47","doi-asserted-by":"crossref","unstructured":"Stallkamp, J., Schlipsing, M., Salmen, J., Igel, C.: The german traffic sign recognition benchmark: a multi-class classification competition. In: Proceedings IJCNN (2011)","DOI":"10.1109\/IJCNN.2011.6033395"},{"key":"22_CR48","unstructured":"Stoica, G., Ramesh, P., Ecsedi, B., Choshen, L., Hoffman, J.: Model merging with SVD to tie the knots. In: Proceedings ICLR (2025)"},{"key":"22_CR49","unstructured":"Sun, W., Li, Q., Geng, Y., Li, B.: Cat merging: a training-free approach for resolving conflicts in model merging. In: Proceeding ICML (2025)"},{"key":"22_CR50","unstructured":"Tang, A., Shen, L., Luo, Y., Yin, N., Zhang, L., Tao, D.: Merging multi-task models via weight-ensembling mixture of experts. In: Proceedings ICML (2024)"},{"key":"22_CR51","unstructured":"Touvron, H., et al.: Llama 2: Open foundation and fine-tuned chat models (2023). arXiv:2307.09288"},{"key":"22_CR52","doi-asserted-by":"crossref","unstructured":"Wang, A., Singh, A., Michael, J., Hill, F., Levy, O., Bowman, S.R.: Glue: A multi-task benchmark and analysis platform for natural language understanding. In: Proceedings ICLR (2018)","DOI":"10.18653\/v1\/W18-5446"},{"key":"22_CR53","unstructured":"Wang, K., Dimitriadis, N., Ortiz-Jimenez, G., Fleuret, F., Frossard, P.: Localizing task information for improved model merging and compression. In: Proceedings ICML (2024)"},{"key":"22_CR54","doi-asserted-by":"crossref","unstructured":"Warstadt, A., Singh, A., Bowman, S.R.: Neural network acceptability judgments. In: Proceedings ACL (2019)","DOI":"10.1162\/tacl_a_00290"},{"key":"22_CR55","doi-asserted-by":"crossref","unstructured":"Williams, A., Nangia, N., Bowman, S.R.: A broad-coverage challenge corpus for sentence understanding through inference. In: Proceedings ACL (2018)","DOI":"10.18653\/v1\/N18-1101"},{"key":"22_CR56","unstructured":"Wolf, T., et al.: HuggingFace\u2019s transformers: State-of-the-art natural language processing. arXiv:1910.03771 (2019)"},{"key":"22_CR57","unstructured":"Wortsman, M., et al.: Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time. In: Proceedings ICML (2022)"},{"key":"22_CR58","doi-asserted-by":"crossref","unstructured":"Wu, H., Xu, J., Le, H., Samaras, D.: Importance-based token merging for efficient image and video generation. In: Proceedings ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.00474"},{"key":"22_CR59","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: Proceedings CVPR (2010)","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"22_CR60","doi-asserted-by":"crossref","unstructured":"Yadav, P., Tam, D., Choshen, L., Raffel, C.A., Bansal, M.: Ties-merging: resolving interference when merging models. In: Proceedings NeurIPS (2023)","DOI":"10.52202\/075280-0310"},{"key":"22_CR61","unstructured":"Yan, K., et al.: CALM: consensus-aware localized merging for multi-task learning. In: Proceedings ICML (2025)"},{"key":"22_CR62","doi-asserted-by":"crossref","unstructured":"Yang, E., et al.: Continual model merging without data: Dual projections for balancing stability and plasticity. In: Proceedings NeurIPS (2025)","DOI":"10.52202\/085713-1311"},{"key":"22_CR63","unstructured":"Yang, E., et al.: AdaMerging: adaptive model merging for multi-task learning. In: Proceedings ICLR (2024)"},{"key":"22_CR64","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Mix data or merge models? balancing the helpfulness, honesty, and harmlessness of large language model via model merging. In: Proceedings NeurIPS (2025)","DOI":"10.52202\/085713-3757"},{"key":"22_CR65","unstructured":"Ye, P., et al.: Merging vision transformers from different tasks and domains. arXiv:2312.16240 (2023)"},{"key":"22_CR66","unstructured":"Yu, L., Yu, B., Yu, H., Huang, F., Li, Y.: Language models are super mario: absorbing abilities from homologous models as a free lunch. In: Proceedings ICML (2024)"},{"key":"22_CR67","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Zhao, Z., Chen, Z., Ding, Z., Yang, X., Sun, Y.: Beyond training: dynamic token merging for zero-shot video understanding. In: Proceedings ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.02047"},{"key":"22_CR68","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Yang, Q.: A survey on multi-task learning. IEEE Trans. Knowl. Data Eng., 5586\u20135609 (2021)","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"22_CR69","unstructured":"Zhao, Z., et al.: Merging loRAs like playing LEGO: pushing the modularity of lora to extremes through rank-wise clustering. In: Proceedings ICLR (2025)"},{"key":"22_CR70","doi-asserted-by":"crossref","unstructured":"Zheng, S., Wang, H.: Free-merging: Fourier transform for efficient model merging. In: Proceedings CVPR (2025)","DOI":"10.1109\/ICCV51701.2025.00368"},{"key":"22_CR71","doi-asserted-by":"crossref","unstructured":"Zhong, Y., Liu, Z., Li, Y., Wang, L.: AIM: adaptive inference of multi-modal LLMs via token merging and pruning. In: Proceedings ICCV (2025)","DOI":"10.1109\/ICCV51701.2025.01877"},{"key":"22_CR72","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Wu, X., Wu, J., Feng, L., Tan, K.C.: HM3: hierarchical multi-objective model merging for pretrained models. In: Proceedings NeurIPS (2025)","DOI":"10.52202\/085713-3830"},{"key":"22_CR73","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Song, L., Wang, B., Chen, W.: MetaGPT: merging large language models using model exclusive task arithmetic. In: Proceedings EMNLP (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.102"},{"key":"22_CR74","unstructured":"Zhu, D., et al.: REMEDY: recipe merging dynamics in large vision-language models. In: Proceedings ICLR (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37556-8_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:14:40Z","timestamp":1789251280000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37556-8_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375551","9783032375568"],"references-count":74,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37556-8_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 September 2026","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":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}