{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,14]],"date-time":"2026-09-14T19:00:18Z","timestamp":1789412418729,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":77,"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_23","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:14:08Z","timestamp":1789251248000},"page":"422-440","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["How To Teach Large Multimodal Models New Skills?"],"prefix":"10.1007","author":[{"given":"Zhen","family":"Zhu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiming","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yao","family":"Xiao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoyao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Derek","family":"Hoiem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Aljundi, R., Chakravarty, P., Tuytelaars, T.: Expert gate: lifelong learning with a network of experts. In: CVPR, pp. 3366\u20133375 (2017)","DOI":"10.1109\/CVPR.2017.753"},{"key":"23_CR2","unstructured":"Bai, S., et al.: Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923 (2025)"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Bang, J., Kim, H., Yoo, Y., Ha, J.W., Choi, J.: Rainbow memory: continual learning with a memory of diverse samples. In: CVPR, pp. 8218\u20138227 (2021)","DOI":"10.1109\/CVPR46437.2021.00812"},{"key":"23_CR4","unstructured":"Biderman, D., et al.: LoRA learns less and forgets less, TMLR (2024)"},{"key":"23_CR5","unstructured":"Chaudhry, A., Ranzato, M., Rohrbach, M., Elhoseiny, M.: Efficient lifelong learning with A-GEM, ICLR (2019)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, C., Zhu, J., Luo, X., Shen, H., Song, J., Gao, L.: CoIN: a Benchmark of Continual Instruction Tuning for Multimodel Large Language Models, NeurIPS (2024)","DOI":"10.52202\/079017-1844"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Are we on the right way for evaluating large vision-language models? In: Globersons, A., Mackey, L., Belgrave, D., Fan, A., Paquet, U., Tomczak, J.M., Zhang, C. (eds.) NIPS (2024)","DOI":"10.52202\/079017-0850"},{"issue":"3","key":"23_CR8","first-page":"1","volume":"12","author":"Z Chen","year":"2018","unstructured":"Chen, Z., Liu, B.: Lifelong machine learning. Synth. Lect. Artif. Intell. Mach. Learn. 12(3), 1\u2013207 (2018)","journal-title":"Synth. Lect. Artif. Intell. Mach. Learn."},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Clark, K., Khandelwal, U., Levy, O., Manning, C.D.: What does BERT look at? an analysis of bert\u2019s attention. arXiv preprint arXiv:1906.04341 (2019)","DOI":"10.18653\/v1\/W19-4828"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Deitke, M., et al.: Molmo and pixMo: open weights and open data for state-of-the-art vision-language models. In: CVPR, pp. 91\u2013104 (2025)","DOI":"10.1109\/CVPR52734.2025.00018"},{"key":"23_CR11","unstructured":"Del\u00a0Chiaro, R., Twardowski, B., Bagdanov, A., Van\u00a0de Weijer, J.: RATT: recurrent attention to transient tasks for continual image captioning. In: NeurIPS, vol.\u00a033, pp. 16736\u201316748 (2020)"},{"key":"23_CR12","doi-asserted-by":"publisher","unstructured":"Douillard, A., Cord, M., Ollion, C., Robert, T., Valle, E.: PODNet: pooled outputs distillation for small-tasks incremental learning. In: ECCV. LNCS, pp. 86\u2013102. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_6","DOI":"10.1007\/978-3-030-58565-5_6"},{"issue":"1","key":"23_CR13","first-page":"12","volume":"1","author":"N Elhage","year":"2021","unstructured":"Elhage, N., Nanda, N., Olsson, C., Henighan, T., Joseph, N., Mann, B., Askell, A., Bai, Y., Chen, A., Conerly, T., et al.: A mathematical framework for transformer circuits. Transformer Circuits Thread 1(1), 12 (2021)","journal-title":"Transformer Circuits Thread"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Geva, M., Schuster, R., Berant, J., Levy, O.: Transformer feed-forward layers are key-value memories. In: Moens, M., Huang, X., Specia, L., Yih, S.W. (eds.) EMNLP, pp. 5484\u20135495 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.446"},{"key":"23_CR15","unstructured":"Gpiosenka: TIME - Image Dataset-Classification. https:\/\/www.kaggle.com\/datasets\/gpiosenka\/time-image-datasetclassification. Accessed 29 Jun 2026"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"He, X., Zhang, Y., Mou, L., Xing, E.P., Xie, P.: PathVQA: 30000+ questions for medical visual question answering. CoRR abs\/2003.10286 (2020)","DOI":"10.36227\/techrxiv.13127537"},{"key":"23_CR17","unstructured":"Hu, E.J., et al.: LoRA: low-Rank Adaptation of Large Language Models. In: ICLR (2022)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Huang, J., et al.: Mitigating catastrophic forgetting in large language models with self-synthesized rehearsal. In: Ku, L., Martins, A., Srikumar, V. (eds.) ACL, pp. 1416\u20131428 (2024)","DOI":"10.18653\/v1\/2024.acl-long.77"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Jin, W., Cheng, Y., Shen, Y., Chen, W., Ren, X.: A good prompt is worth millions of parameters: low-resource prompt-based learning for vision-language models. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) ACL, pp. 2763\u20132775 (2022)","DOI":"10.18653\/v1\/2022.acl-long.197"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Joseph, K.J., Khan, S., Khan, F.S., Anwer, R.M., Balasubramanian, V.N.: Energy-based latent aligner for incremental learning. In: CVPR, pp. 7452\u20137461 (2022)","DOI":"10.1109\/CVPR52688.2022.00730"},{"key":"23_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1007\/978-3-319-46493-0_15","volume-title":"Computer Vision \u2013 ECCV 2016","author":"A Kembhavi","year":"2016","unstructured":"Kembhavi, A., Salvato, M., Kolve, E., Seo, M., Hajishirzi, H., Farhadi, A.: A Diagram is Worth a Dozen Images. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 235\u2013251. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_15"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Rasheed, H.A., Maaz, M., Khan, S.H., Khan, F.S.: Maple: multi-modal prompt learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"23_CR23","doi-asserted-by":"crossref","unstructured":"Khattak, M.U., Wasim, S.T., Naseer, M., Khan, S., Yang, M., Khan, F.S.: Self-regulating prompts: foundational model adaptation without forgetting. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01394"},{"issue":"13","key":"23_CR24","doi-asserted-by":"publisher","first-page":"3521","DOI":"10.1073\/pnas.1611835114","volume":"114","author":"J Kirkpatrick","year":"2017","unstructured":"Kirkpatrick, J., et al.: Overcoming catastrophic forgetting in neural networks. PNAS 114(13), 3521\u20133526 (2017)","journal-title":"PNAS"},{"key":"23_CR25","unstructured":"Li, B., et al.: LLaVA-NeXT: stronger LLMs supercharge multimodal capabilities in the wild (2024). https:\/\/llava-vl.github.io\/blog\/2024-05-10-llava-next-stronger-llms\/. Accessed 29 Jun 2026"},{"key":"23_CR26","unstructured":"Li, B., et al.: LLaVA-OneVision: easy Visual Task Transfer. arXiv preprint arXiv:2408.03326 (2024)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Li, B., Wang, R., Wang, G., Ge, Y., Ge, Y., Shan, Y.: Seed-bench: benchmarking multimodal LLMs with generative comprehension. arXiv preprint arXiv:2307.16125 (2023)","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Li, X., Ren, W., Qin, W., Wang, L., Zhao, T., Hong, R.: Analyzing and reducing catastrophic forgetting in parameter efficient tuning. ICASSP, pp, 1\u20135. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10889361"},{"issue":"12","key":"23_CR29","first-page":"2935","volume":"40","author":"Z Li","year":"2018","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. PAMI 40(12), 2935\u20132947 (2018)","journal-title":"Learning without forgetting. PAMI"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Li, Z., Hoiem, D.: Learning without forgetting. TPAMI (2017)","DOI":"10.1007\/978-3-319-46493-0_37"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Lin, Y., et al.: Mitigating the Alignment Tax of RLHF. In: EMNLP (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.35"},{"key":"23_CR32","unstructured":"Lin, Y., Qi, M., Liu, L., Ma, H.: Vlm-assisted continual learning for visual question answering in self-driving. arXiv preprint arXiv:2502.00843 (2025)"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual Instruction Tuning. In: NeurIPS (2023)","DOI":"10.52202\/075280-1516"},{"key":"23_CR34","first-page":"34892","volume":"36","author":"H Liu","year":"2023","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. NeurIPS 36, 34892\u201334916 (2023)","journal-title":"Visual instruction tuning. NeurIPS"},{"key":"23_CR35","unstructured":"Liu, H., Xiao, L., Liu, J., Li, X., Feng, Z., Yang, S., Wang, J.: Revisiting MLLMs: an in-depth analysis of image classification abilities. arXiv preprint arXiv:2412.16418 (2024)"},{"key":"23_CR36","unstructured":"Liu, W., Zhu, F., Wei, L., Tian, Q.: C-clip: multimodal continual learning for vision-language model, ICLR (2025)"},{"key":"23_CR37","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, Y., Schiele, B., Sun, Q.: Online hyperparameter optimization for class-incremental learning, AAAI (2023)","DOI":"10.1609\/aaai.v37i7.26070"},{"key":"23_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Y., Li, Y., Schiele, B., Sun, Q.: Wakening past concepts without past data: class-incremental learning from online placebos, pp. 2226\u20132235. WACV (2024)","DOI":"10.1109\/WACV57701.2024.00222"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Liu, Y., Schiele, B., Sun, Q.: Adaptive aggregation networks for class-incremental learning, pp. 2544\u20132553. CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00257"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Liu, Y., Su, Y., Liu, A., Schiele, B., Sun, Q.: Mnemonics training: multi-class incremental learning without forgetting. In: CVPR, pp. 12245\u201312254 (2020)","DOI":"10.1109\/CVPR42600.2020.01226"},{"key":"23_CR41","doi-asserted-by":"crossref","unstructured":"Lu, P., et al.: Learn to explain: multimodal reasoning via thought chains for science question answering. In: Koyejo, S., Mohamed, S., Agarwal, A., Belgrave, D., Cho, K., Oh, A. (eds.) NIPS (2022)","DOI":"10.52202\/068431-0182"},{"key":"23_CR42","unstructured":"Luo, Y., Yang, Z., Meng, F., Li, Y., Zhou, J., Zhang, Y.: An empirical study of catastrophic forgetting in large language models during continual fine-tuning. arXiv preprint arXiv:2308.08747 (2023)"},{"key":"23_CR43","doi-asserted-by":"crossref","unstructured":"Luo, Z., Liu, Y., Schiele, B., Sun, Q.: Class-incremental exemplar compression for class-incremental learning. In: CVPR, pp. 11371\u201311380 (2023)","DOI":"10.1109\/CVPR52729.2023.01094"},{"key":"23_CR44","unstructured":"Marouf, I.E., Tartaglione, E., Lathuiliere, S., van\u00a0de Weijer, J.: No images, no problem: retaining knowledge in continual vqa with questions-only memory. arXiv preprint arXiv:2502.04469 (2025)"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Masry, A., Long, D.X., Tan, J.Q., Joty, S.R., Hoque, E.: Chartqa: A benchmark for question answering about charts with visual and logical reasoning. In: Muresan, S., Nakov, P., Villavicencio, A. (eds.) ACL, pp. 2263\u20132279 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"23_CR46","doi-asserted-by":"crossref","unstructured":"Mathew, M., Bagal, V., Tito, R., Karatzas, D., Valveny, E., Jawahar, C.V.: Infographicvqa. In: WACV, pp. 2582\u20132591. IEEE (2022)","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"23_CR47","doi-asserted-by":"crossref","unstructured":"Mathew, M., Karatzas, D., Jawahar, C.V.: DocVQA: a dataset for VQA on document images. In: WACV, pp. 2199\u20132208. IEEE (2021)","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"23_CR48","doi-asserted-by":"publisher","unstructured":"Meng, K., Bau, D., Andonian, A., Belinkov, Y.: Locating and editing factual associations in GPT. NeurIPS 36 (2022). https:\/\/doi.org\/10.48550\/arXiv.2202.05262. arXiv:2202.05262","DOI":"10.48550\/arXiv.2202.05262"},{"key":"23_CR49","unstructured":"Nguyen, G., Jun, T.J., Tran, T., Yalew, T., Kim, D.: ContCap: a scalable framework for continual image captioning . arXiv preprint arXiv:1909.08745 (2019)"},{"key":"23_CR50","doi-asserted-by":"crossref","unstructured":"Nikandrou, M., Pantazopoulos, G., Konstas, I., Suglia, A.: Enhancing continual learning in visual question answering with modality-aware feature distillation. arXiv preprint arXiv:2406.19297 (2024)","DOI":"10.18653\/v1\/2024.alvr-1.6"},{"key":"23_CR51","unstructured":"Olsson, C., et al.: In-context learning and induction heads. arXiv preprint arXiv:2209.11895 (2022)"},{"key":"23_CR52","unstructured":"PourKeshavarzi, M., Zhao, G., Sabokrou, M.: Looking back on learned experiences for class\/task incremental learning. In: ICLR (2022)"},{"key":"23_CR53","doi-asserted-by":"crossref","unstructured":"Prabhu, A., Torr, P.H., Dokania, P.K.: GDumb: a simple approach that questions our progress in continual learning. In: ECCV, pp. 524\u2013540 (2020)","DOI":"10.1007\/978-3-030-58536-5_31"},{"key":"23_CR54","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision, ICML (2021)"},{"key":"23_CR55","doi-asserted-by":"crossref","unstructured":"Rebuffi, S.A., Kolesnikov, A., Sperl, G., Lampert, C.H.: iCARL: incremental classifier and representation learning. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.587"},{"key":"23_CR56","unstructured":"Shenfeld, I., Pari, J., Agrawal, P.: Rl\u2019s Razor: why online reinforcement learning forgets less (2025). https:\/\/arxiv.org\/abs\/2509.04259. Accessed 29 Jun 2026"},{"key":"23_CR57","unstructured":"Shin, H., Lee, J.K., Kim, J., Kim, J.: Continual learning with deep generative replay. In: NeurIPS, pp. 2990\u20132999 (2017)"},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Simon, C., Koniusz, P., Harandi, M.: On learning the geodesic path for incremental learning, pp. 1591\u20131600. CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00164"},{"key":"23_CR59","doi-asserted-by":"crossref","unstructured":"Singh, A., et al.: Towards VQA models that can read. In: CVPR, pp. 8317\u20138326 (2019)","DOI":"10.1109\/CVPR.2019.00851"},{"key":"23_CR60","doi-asserted-by":"crossref","unstructured":"Smith, J.S., et al.: Coda-prompt: continual decomposed attention-based prompting for rehearsal-free continual learning, CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01146"},{"key":"23_CR61","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/978-3-030-58529-7_16","volume-title":"Computer Vision \u2013 ECCV 2020","author":"X Tao","year":"2020","unstructured":"Tao, X., Chang, X., Hong, X., Wei, X., Gong, Y.: Topology-Preserving Class-Incremental Learning. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12364, pp. 254\u2013270. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58529-7_16"},{"key":"23_CR62","unstructured":"visheratin: RealWorldQA: benchmark for real-world spatial understanding (2024)"},{"key":"23_CR63","doi-asserted-by":"publisher","unstructured":"Voita, E., Talbot, D., Moiseev, F., Sennrich, R., Titov, I.: Analyzing multi-head self-attention: specialized heads do the heavy lifting, the rest can be pruned. ACL, pp, 5797\u20135808 (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1580","DOI":"10.18653\/v1\/P19-1580"},{"key":"23_CR64","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-ucsd birds-200-2011 dataset, California Institute of Technology (2011). CNS-TR-2011-001 Tech. Rep"},{"key":"23_CR65","doi-asserted-by":"publisher","unstructured":"Wang, F.Y., Zhou, D.W., Ye, H.J., Zhan, D.C.: FOSTER: feature boosting and compression for class-incremental learning, ECCV. LNCS, vol. 13685. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19806-9_23","DOI":"10.1007\/978-3-031-19806-9_23"},{"key":"23_CR66","doi-asserted-by":"crossref","unstructured":"Wang, X., et al.: Orthogonal subspace learning for language model continual learning. In: Bouamor, H., Pino, J., Bali, K. (eds.) Findings of EMNLP (2023)","DOI":"10.18653\/v1\/2023.findings-emnlp.715"},{"key":"23_CR67","doi-asserted-by":"crossref","unstructured":"Wei, X., Munir, M., Marculescu, R.: Mitigating intra- and inter-modal forgetting in continual learning of unified multimodal models. NeurIPS (2025)","DOI":"10.52202\/085713-5082"},{"key":"23_CR68","doi-asserted-by":"crossref","unstructured":"Wortsman, M., Ilharco, G., Kim, J.W., Li, M., Kornblith, S., Roelofs, R., Lopes, R.G., Hajishirzi, H., Farhadi, A., Namkoong, H., Schmidt, L.: Robust fine-tuning of zero-shot models, CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00780"},{"key":"23_CR69","doi-asserted-by":"crossref","unstructured":"Xiang, J., et al.: Language models meet world models: embodied experiences enhance language models. NeurIPS 36, 75392\u201375412 (2023)","DOI":"10.52202\/075280-3295"},{"key":"23_CR70","doi-asserted-by":"crossref","unstructured":"Yu, J., et al.: Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters, CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.02191"},{"key":"23_CR71","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhang, F., Xu, C.: Vqacl: A novel visual question answering continual learning setting. In: CVPR. pp. 19102\u201319112 (2023)","DOI":"10.1109\/CVPR52729.2023.01831"},{"key":"23_CR72","doi-asserted-by":"crossref","unstructured":"Zhang, X., Zhang, F., Xu, C.: VQACL: a novel visual question answering continual learning setting. In: CVPR, pp. 19102\u201319112 (2023)","DOI":"10.1109\/CVPR52729.2023.01831"},{"key":"23_CR73","doi-asserted-by":"crossref","unstructured":"Zheng, Z., Ma, M., Wang, K., Qin, Z., Yue, X., You, Y.: Preventing zero-shot transfer degradation in continual learning of vision-language models. In: CVPR, pp. 19125\u201319136 (2023)","DOI":"10.1109\/ICCV51070.2023.01752"},{"key":"23_CR74","doi-asserted-by":"crossref","unstructured":"Zhou, D.W., et al.: Learning without forgetting for vision-language models. TPAMI (2025)","DOI":"10.1109\/TPAMI.2025.3540889"},{"key":"23_CR75","unstructured":"Zhu, D., et al.: Model tailor: mitigating catastrophic forgetting in multi-modal large language models, ICML (2024)"},{"key":"23_CR76","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Gong, Y., Hoiem, D.: Anytime Continual Learning for Open Vocabulary Classification. In: ECCV, vol 15064 (2024)","DOI":"10.1007\/978-3-031-72658-3_16"},{"key":"23_CR77","doi-asserted-by":"crossref","unstructured":"Zhu, Z., Lyu, W., Xiao, Y., Hoiem, D.: Continual learning in open-vocabulary classification with complementary memory systems. Trans. Mach. Learn. Res (2024)","DOI":"10.1007\/978-3-031-72658-3_16"}],"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_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T22:14:17Z","timestamp":1789251257000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37556-8_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032375551","9783032375568"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37556-8_23","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"}}]}}