{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T09:19:17Z","timestamp":1789118357345,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":85,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371669","type":"print"},{"value":"9783032371676","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\/978-3-032-37167-6_1","type":"book-chapter","created":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T08:51:58Z","timestamp":1789116718000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["RUTaL: Residual Upcycling with\u00a0Task Ladder for\u00a0Efficient Multi-task Learning"],"prefix":"10.1007","author":[{"given":"Haiming","family":"Yao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianxing","family":"Liao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"You","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,12]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Agiza, A., Neseem, M., Reda, S.: Mtlora: low-rank adaptation approach for efficient multi-task learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16196\u201316205 (2024)","DOI":"10.1109\/CVPR52733.2024.01533"},{"issue":"4","key":"1_CR2","doi-asserted-by":"publisher","first-page":"2396","DOI":"10.1109\/TPAMI.2023.3330944","volume":"46","author":"V Arampatzakis","year":"2023","unstructured":"Arampatzakis, V., Pavlidis, G., Mitianoudis, N., Papamarkos, N.: Monocular depth estimation: a thorough review. IEEE Trans. Pattern Anal. Mach. Intell. 46(4), 2396\u20132414 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Baek, S., Lee, S., Jo, H., Choi, H., Min, D.: Tadformer: task-adaptive dynamic transformer for efficient multi-task learning. arXiv preprint arXiv:2501.04293 (2025)","DOI":"10.1109\/CVPR52734.2025.01384"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Br\u00fcggemann, D., Kanakis, M., Obukhov, A., Georgoulis, S., Van Gool, L.: Exploring relational context for multi-task dense prediction. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01557"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Chen, S., Geet al.: Adaptformer: adapting vision transformers for scalable visual recognition. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) (2022)","DOI":"10.52202\/068431-1212"},{"key":"1_CR6","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. arXiv preprint arXiv:2205.08534 (2022)"},{"key":"1_CR7","unstructured":"Chen, Z., et al.: Vision transformer adapter for dense predictions. In: Proceedings of the International Conference on Learning Representations (ICLR) (2023)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Dai, X., et al.: Dynamic detr: end-to-end object detection with dynamic attention. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2988\u20132997 (2021)","DOI":"10.1109\/ICCV48922.2021.00298"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Diao, H., et al.: Unipt: universal parallel tuning for transfer learning with efficient parameter and memory. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28729\u201328740 (2024)","DOI":"10.1109\/CVPR52733.2024.02714"},{"issue":"3","key":"1_CR10","doi-asserted-by":"publisher","first-page":"220","DOI":"10.1038\/s42256-023-00626-4","volume":"5","author":"N Ding","year":"2023","unstructured":"Ding, N., et al.: Parameter-efficient fine-tuning of large-scale pre-trained language models. Nat. Mach. Intell. 5(3), 220\u2013235 (2023)","journal-title":"Nat. Mach. Intell."},{"key":"1_CR11","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. In: Proceedings of the International Conference on Learning Representations (ICLR) (2020)"},{"issue":"120","key":"1_CR12","first-page":"1","volume":"23","author":"W Fedus","year":"2022","unstructured":"Fedus, W., Zoph, B., Shazeer, N.: Switch transformers: scaling to trillion parameter models with simple and efficient sparsity. J. Mach. Learn. Res. 23(120), 1\u201339 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Feng, Y., et al.: Dive into Moe: diversity-enhanced reconstruction of large language models from dense into mixture-of-experts. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 19375\u201319394 (2025)","DOI":"10.18653\/v1\/2025.acl-long.951"},{"key":"1_CR14","doi-asserted-by":"crossref","unstructured":"Fu, M., Zhu, K., Ding, Z., Wu, J.: DTL: parameter-and memory-efficient disentangled vision learning. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3616318"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Fu, Z., et al.: On the effectiveness of parameter-efficient fine-tuning. In: Proceedings of the AAAI conference on artificial intelligence, vol. 37, pp. 12799\u201312807 (2023)","DOI":"10.1609\/aaai.v37i11.26505"},{"key":"1_CR16","unstructured":"Han, C., Wang, Q., Cui, Y., Cao, Z., Wang, W., Qi, S., Liu, D.: E$$^{2}$$vpt: an effective and efficient approach for visual prompt tuning. arXiv preprint arXiv:2307.13770 (2023)"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Han, G., Lim, S.N.: Few-shot object detection with foundation models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28608\u201328618 (2024)","DOI":"10.1109\/CVPR52733.2024.02703"},{"key":"1_CR18","unstructured":"He, E., et al.: Upcycling large language models into mixture of experts. arXiv preprint arXiv:2410.07524 (2024)"},{"key":"1_CR19","unstructured":"He, J., Zhou, C., Ma, X., Berg-Kirkpatrick, T., Neubig, G.: Towards a unified view of parameter-efficient transfer learning. In: Proceedings of the International Conference on Learning Representations (ICLR) (2022)"},{"key":"1_CR20","unstructured":"He, J., Zhou, C., Ma, X., Berg-Kirkpatrick, T., Neubig, G.: Towards a unified view of parameter-efficient transfer learning. In: Proceedings of the International Conference on Learning Representations (2022). https:\/\/openreview.net\/forum?id=0RDcd5Axok"},{"key":"1_CR21","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: Proceedings of the International Conference on Machine Learning (ICML), pp. 2790\u20132799. PMLR (2019)"},{"key":"1_CR22","unstructured":"Hu, E., et al.: Lora: low-rank adaptation of large language models. In: Proceedings of the International Conference on Learning Representations (ICLR) (2022)"},{"issue":"2","key":"1_CR23","first-page":"3","volume":"1","author":"EJ Hu","year":"2022","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models. ICLR 1(2), 3 (2022)","journal-title":"ICLR"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Het al.: Going beyond multi-task dense prediction with synergy embedding models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 28181\u201328190 (2024)","DOI":"10.1109\/CVPR52733.2024.02662"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Ders: towards extremely efficient upcycled mixture-of-experts models. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 10056\u201310066 (2025)","DOI":"10.1109\/CVPR52734.2025.00940"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Jia, M., et al.: Visual prompt tuning. In: Proceedings of the European conference on computer vision, pp. 709\u2013727. Springer (2022)","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Jiang, F., Wang, S., Gong, X.: Task-conditional adapter for multi-task dense prediction. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 2059\u20132068 (2024)","DOI":"10.1145\/3664647.3681581"},{"key":"1_CR28","unstructured":"Jie, S., Deng, Z.H.: Convolutional bypasses are better vision transformer adapters. arXiv preprint arXiv:2207.07039 (2022)"},{"key":"1_CR29","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"1_CR30","unstructured":"Karimi Mahabadi, R., Henderson, J., Ruder, S.: Compacter: efficient low-rank hypercomplex adapter layers. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), vol. 34, pp. 1022\u20131035 (2021)"},{"key":"1_CR31","doi-asserted-by":"crossref","unstructured":"Karimi Mahabadi, R., Ruder, S., Dehghani, M., Henderson, J.: Parameter-efficient multi-task fine-tuning for transformers via shared hypernetworks. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) (2021)","DOI":"10.18653\/v1\/2021.acl-long.47"},{"key":"1_CR32","doi-asserted-by":"crossref","unstructured":"Kerssies, T., et al.: Your vit is secretly an image segmentation model. In: Proceedings of the computer vision and pattern recognition conference, pp. 25303\u201325313 (2025)","DOI":"10.1109\/CVPR52734.2025.02356"},{"key":"1_CR33","unstructured":"Komatsuzaki, A., et al.: Sparse upcycling: training mixture-of-experts from dense checkpoints. arXiv preprint arXiv:2212.05055 (2022)"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Lester, B., Al-Rfou, R., Constant, N.: The power of scale for parameter-efficient prompt tuning. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 3045\u20133059 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"1_CR35","doi-asserted-by":"publisher","first-page":"131224","DOI":"10.52202\/079017-4170","volume":"37","author":"J Li","year":"2024","unstructured":"Li, J., et al.: Cumo: scaling multimodal LLM with co-upcycled mixture-of-experts. Adv. Neural. Inf. Process. Syst. 37, 131224\u2013131246 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR36","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models. In: Proceedings of the International conference on machine learning, pp. 19730\u201319742. PMLR (2023)"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Li, X.L., Liang, P.: Prefix-tuning: Optimizing continuous prompts for generation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) (2021)","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"1_CR38","unstructured":"Liu, A., et al.: Deepseek-v3 technical report. arXiv preprint arXiv:2412.19437 (2024)"},{"key":"1_CR39","first-page":"18878","volume":"34","author":"B Liu","year":"2021","unstructured":"Liu, B., Liu, X., Jin, X., Stone, P., Liu, Q.: Conflict-averse gradient descent for multi-task learning. Adv. Neural. Inf. Process. Syst. 34, 18878\u201318890 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Y.C., Ma, C.Y., Tian, J., He, Z., Kira, Z.: Polyhistor: parameter-efficient multi-task adaptation for dense vision tasks. In: Proceedings of the Advances in Neural Information Processing Systems (NeurIPS) (2022)","DOI":"10.52202\/068431-2673"},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Z., Let al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR42","doi-asserted-by":"crossref","unstructured":"Lu, Y., Kumar, A., Zhai, S., Cheng, Y., Javidi, T., Feris, R.: Fully-adaptive feature sharing in multi-task networks with applications in person attribute classification. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5334\u20135343 (2017)","DOI":"10.1109\/CVPR.2017.126"},{"key":"1_CR43","unstructured":"Lu, Y., Cao, S., Wang, Y.X.: Swiss army knife: synergizing biases in knowledge from vision foundation models for multi-task learning. In: Proceedings of the Thirteenth International Conference on Learning Representations (2025). https:\/\/openreview.net\/forum?id=eePww5u7J3"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Luo, W., et al.: Exploring intrinsic normal prototypes within a single image for universal anomaly detection. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 9974\u20139983 (2025)","DOI":"10.1109\/CVPR52734.2025.00932"},{"key":"1_CR45","doi-asserted-by":"crossref","unstructured":"Maninis, K.K., Radosavovic, I., Kokkinos, I.: Attentive single-tasking of multiple tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1851\u20131860 (2019)","DOI":"10.1109\/CVPR.2019.00195"},{"key":"1_CR46","doi-asserted-by":"crossref","unstructured":"Mantri, K.S.I., Sch\u00f6nlieb, C.B., Ribeiro, B., Baskin, C., Eliasof, M.: Ditask: Multi-task fine-tuning with diffeomorphic transformations. In: Proceedings of the Computer Vision and Pattern Recognition Conference, pp. 25218\u201325229 (2025)","DOI":"10.1109\/CVPR52734.2025.02348"},{"key":"1_CR47","doi-asserted-by":"crossref","unstructured":"Mercea, O.B., Gritsenko, A., Schmid, C., Arnab, A.: Time-memory-and parameter-efficient visual adaptation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5536\u20135545 (2024)","DOI":"10.1109\/CVPR52733.2024.00529"},{"key":"1_CR48","doi-asserted-by":"crossref","unstructured":"Misra, I., Shrivastava, A., Gupta, A., Hebert, M.: Cross-stitch networks for multi-task learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.433"},{"key":"1_CR49","doi-asserted-by":"crossref","unstructured":"Mottaghi, R., et al.: The role of context for object detection and semantic segmentation in the wild. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 891\u2013898 (2014)","DOI":"10.1109\/CVPR.2014.119"},{"key":"1_CR50","unstructured":"Oquab, M., et al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Peebles, W., Xie, S.: Scalable diffusion models with transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4195\u20134205 (2023)","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"Pfeiffer, J., R\u00fcckl\u00e9, A., Poth, C., Kamath, A., Vuli\u0107, I., Ruder, S., Cho, K., Gurevych, I.: Adapterhub: A framework for adapting transformers. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing EMNLP (2020)","DOI":"10.18653\/v1\/2020.emnlp-demos.7"},{"key":"1_CR53","doi-asserted-by":"crossref","unstructured":"Ruder, S., Bingel, J., Augenstein, I., S\u00f8gaard, A.: Latent multi-task architecture learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 4822\u20134829 (2019)","DOI":"10.1609\/aaai.v33i01.33014822"},{"key":"1_CR54","unstructured":"Shazeer, N., Mirhoseini, A., Maziarz, K., Davis, A., Le, Q., Hinton, G., Dean, J.: Outrageously large neural networks: the sparsely-gated mixture-of-experts layer. arXiv preprint arXiv:1701.06538 (2017)"},{"key":"1_CR55","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1007\/978-3-642-33715-4_54","volume-title":"Computer Vision \u2013 ECCV 2012","author":"N Silberman","year":"2012","unstructured":"Silberman, N., Hoiem, D., Kohli, P., Fergus, R.: Indoor Segmentation and Support Inference from RGBD Images. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7576, pp. 746\u2013760. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33715-4_54"},{"key":"1_CR56","doi-asserted-by":"publisher","first-page":"12991","DOI":"10.52202\/068431-0944","volume":"35","author":"YL Sung","year":"2022","unstructured":"Sung, Y.L., Cho, J., Bansal, M.: LST: ladder side-tuning for parameter and memory efficient transfer learning. Adv. Neural. Inf. Process. Syst. 35, 12991\u201313005 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"1_CR57","unstructured":"Tang, A., Shen, L., Luo, Y., Yin, N., Zhang, L., Tao, D.: Merging multi-task models via weight-ensembling mixture of experts. In: Salakhutdinov, R., et al., (eds.) Proceedings of the 41st International Conference on Machine Learning. Proceedings of Machine Learning Research, vol.\u00a0235, pp. 47778\u201347799. PMLR (2024). https:\/\/proceedings.mlr.press\/v235\/tang24e.html"},{"key":"1_CR58","unstructured":"Tang, A., et al.: Parameter efficient multi-task model fusion with partial linearization. arXiv preprint arXiv:2310.04742 (2023)"},{"key":"1_CR59","doi-asserted-by":"crossref","unstructured":"Vandenhende, S., Georgoulis, S., Van\u00a0Gool, L.: MTI-net: multi-scale task interaction networks for multi-task learning. In: Proceedings of the Computer vision\u2013ECCV 2020: 16th European conference, Glasgow, UK, August 23\u201328, 2020, proceedings, part IV 16. pp. 527\u2013543. Springer (2020)","DOI":"10.1007\/978-3-030-58548-8_31"},{"key":"1_CR60","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Deep high-resolution representation learning for visual recognition. IEEE Trans. Pattern Anal. Mach. Intell. 43(10), 3349\u20133364 (2020)","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"1_CR61","unstructured":"Xie, E., et al.: Segformer: simple and efficient design for semantic segmentation with transformers. In: PRoceedings of the Advances in Neural Information Processing Systems (NeurIPS) (2021)"},{"key":"1_CR62","doi-asserted-by":"crossref","unstructured":"Xin, Y., Du, J., Wang, Q., Lin, Z., Yan, K.: VMT-adapter: parameter-efficient transfer learning for multi-task dense scene understanding. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), vol. 38, pp. 16085\u201316093 (2024)","DOI":"10.1609\/aaai.v38i14.29541"},{"key":"1_CR63","unstructured":"Xin, Y., et\u00a0al.: Parameter-efficient fine-tuning for pre-trained vision models: a survey and benchmark. arXiv preprint arXiv:2402.02242 (2024)"},{"key":"1_CR64","doi-asserted-by":"crossref","unstructured":"Xu, M., Zhang, Z., Wei, F., Hu, H., Bai, X.: Side adapter network for open-vocabulary semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2945\u20132954 (2023)","DOI":"10.1109\/CVPR52729.2023.00288"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Xu, Y., Li, X., Yuan, H., Yang, Y., Zhang, L.: Multi-task learning with multi-query transformer for dense prediction. IEEE Trans. Circuits Syst. Video Technol. (2023)","DOI":"10.1109\/TCSVT.2023.3292995"},{"key":"1_CR66","unstructured":"Yang, E., et al.: Adamerging: adaptive model merging for multi-task learning. arXiv preprint arXiv:2310.02575 (2023)"},{"key":"1_CR67","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Multi-task dense prediction via mixture of low-rank experts. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 27927\u201327937 (2024)","DOI":"10.1109\/CVPR52733.2024.02638"},{"key":"1_CR68","unstructured":"Yang, Y., et al.: Multi-task dense predictions via unleashing the power of diffusion. In: Yue, Y., Garg, A., Peng, N., Sha, F., Yu, R. (eds.) International Conference on Learning Representations, vol.\u00a02025, pp. 18813\u201318830 (2025). https:\/\/proceedings.iclr.cc\/paper_files\/paper\/2025\/file\/2f2b1d6bbd50865eca40e2774a057eef-Paper-Conference.pdf"},{"key":"1_CR69","doi-asserted-by":"crossref","unstructured":"Ye, H., Xu, D.: Invpt++: Inverted pyramid multi-task transformer for visual scene understanding. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3397031"},{"key":"1_CR70","doi-asserted-by":"crossref","unstructured":"Sung, Y.-L., Cho, J., M.B.: Vl-adapter: parameter-efficient transfer learning for vision-and-language tasks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.00516"},{"key":"1_CR71","doi-asserted-by":"crossref","unstructured":"Yin, D., Han, X., Li, B., Feng, H., Bai, J.: Parameter-efficient is not sufficient: exploring parameter, memory, and time efficient adapter tuning for dense predictions. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 1398\u20131406 (2024)","DOI":"10.1145\/3664647.3680940"},{"key":"1_CR72","unstructured":"Yu, B.X., Chang, J., Liu, L., Tian, Q., Chen, C.W.: Towards a unified view on visual parameter-efficient transfer learning. In: Proceedings of the International Conference on Learning Representations (ICLR) (2022)"},{"key":"1_CR73","unstructured":"Yu, J., et\u00a0al.: Unleashing the power of multi-task learning: a comprehensive survey spanning traditional, deep, and pretrained foundation model eras. arXiv preprint arXiv:2404.18961 (2024)"},{"key":"1_CR74","unstructured":"Yu, T., et al.: Gradient surgery for multi-task learning. In: Proceedings of the Advances in Neural Information Processing Systems, vol. 33, pp. 5824\u20135836 (2020)"},{"key":"1_CR75","doi-asserted-by":"crossref","unstructured":"Zaken, E.B., Goldberg, Y., Ravfogel, S.: Bitfit: simple parameter-efficient fine-tuning for transformer-based masked language-models. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), pp.\u00a01\u20139 (2022)","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"1_CR76","unstructured":"Zaken, E.B., Goldberg, Y., Ravfogel, S.: Bitfit: simple parameter-efficient fine-tuning for transformer-based masked language-models. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL) (2022)"},{"key":"1_CR77","doi-asserted-by":"crossref","unstructured":"Zhang, J.O., Sax, A., Zamir, A., Guibas, L., Malik, J.: Side-tuning: a baseline for network adaptation via additive side networks. In: Proceedings of the European conference on computer vision, pp. 698\u2013714. Springer (2020)","DOI":"10.1007\/978-3-030-58580-8_41"},{"key":"1_CR78","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Bridgenet: comprehensive and effective feature interactions via bridge feature for multi-task dense predictions. IEEE Trans. Pattern Anal. Mach. Intell. (2025)","DOI":"10.1109\/TPAMI.2025.3535875"},{"key":"1_CR79","doi-asserted-by":"crossref","unstructured":"Zhang, K., et al.: A generalist vision-language foundation model for diverse biomedical tasks. Nat. Med. 30(11), 3129\u20133141 (2024)","DOI":"10.1038\/s41591-024-03185-2"},{"issue":"12","key":"1_CR80","doi-asserted-by":"publisher","first-page":"5586","DOI":"10.1109\/TKDE.2021.3070203","volume":"34","author":"Y Zhang","year":"2021","unstructured":"Zhang, Y., Yang, Q.: A survey on multi-task learning. IEEE Trans. Knowl. Data Eng. 34(12), 5586\u20135609 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"1_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Cui, Z., Xu, C., Yan, Y., Sebe, N., Yang, J.: Pattern-affinitive propagation across depth, surface normal and semantic segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4106\u20134115 (2019)","DOI":"10.1109\/CVPR.2019.00423"},{"key":"1_CR82","doi-asserted-by":"crossref","unstructured":"Zhou, X., et al.: Dynamic adapter meets prompt tuning: Parameter-efficient transfer learning for point cloud analysis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14707\u201314717 (2024)","DOI":"10.1109\/CVPR52733.2024.01393"},{"key":"1_CR83","doi-asserted-by":"crossref","unstructured":"Zhu, T., et al.: Llama-Moe: building mixture-of-experts from llama with continual pre-training. In: Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pp. 15913\u201315923 (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.890"},{"key":"1_CR84","doi-asserted-by":"crossref","unstructured":"Zhu, X., et al.: Moe jetpack: from dense checkpoints to adaptive mixture of experts for vision tasks. In: Proceedings of the Advances in Neural Information Processing Systems, vol. 37, pp. 12094\u201312118 (2024)","DOI":"10.52202\/079017-0386"},{"key":"1_CR85","unstructured":"Zhu, X., et al.: Deformable DETR: deformable transformers for end-to-end object detection. In: Proceedings of the International Conference on Learning Representations (ICLR) (2021)"}],"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\/978-3-032-37167-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,11]],"date-time":"2026-09-11T08:52:33Z","timestamp":1789116753000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37167-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371669","9783032371676"],"references-count":85,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37167-6_1","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":"12 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"}}]}}