{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,6]],"date-time":"2026-10-06T19:00:41Z","timestamp":1791313241513,"version":"4.3.1"},"reference-count":168,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council of Hong Kong Special Administrative Region, China","award":["CUHK 2410072"],"award-info":[{"award-number":["CUHK 2410072"]}]},{"name":"NSF","award":["III-2106758"],"award-info":[{"award-number":["III-2106758"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1109\/tnnls.2026.3658485","type":"journal-article","created":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T19:50:43Z","timestamp":1774554643000},"page":"4014-4034","source":"Crossref","is-referenced-by-count":7,"title":["Recent Advances of Multimodal Continual Learning: A Comprehensive Survey"],"prefix":"10.1109","volume":"37","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9602-4547","authenticated-orcid":false,"given":"Dianzhi","family":"Yu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Hong Kong, China"],"department":["Department of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8841-116X","authenticated-orcid":false,"given":"Xinni","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Hong Kong, China"],"department":["Department of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5741-2047","authenticated-orcid":false,"given":"Yankai","family":"Chen","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Hong Kong, China"],"department":["Department of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4965-8263","authenticated-orcid":false,"given":"Aiwei","family":"Liu","sequence":"additional","affiliation":[{"name":"Tsinghua University","place":["Beijing, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4185-8663","authenticated-orcid":false,"given":"Yifei","family":"Zhang","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Hong Kong, China"],"department":["Department of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3491-5968","authenticated-orcid":false,"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Illinois Chicago","place":["Chicago, IL, USA"],"department":["Department of Computer Science"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8106-6447","authenticated-orcid":false,"given":"Irwin","family":"King","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong","place":["Hong Kong, China"],"department":["Department of Computer Science and Engineering"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.09.004"},{"key":"ref2","volume-title":"Lifelong Machine Learning","author":"Chen","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00452-0"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-022-00568-3"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3367329"},{"key":"ref6","doi-asserted-by":"crossref","DOI":"10.1109\/ISCC61673.2024.10733672","article-title":"Continual learning in recurrent neural networks for the Internet of Things: A stochastic approach","volume-title":"Proc. IEEE Symp. Comput. Commun. (ISCC)","author":"Filho"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-37552-9"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2855159"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/S0079-7421(08)60536-8","article-title":"Catastrophic interference in connectionist networks: The sequential learning problem","volume":"24","author":"McCloskey","year":"1989","journal-title":"Psychol. Learn. Motivat."},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1037\/\/0033-295x.97.2.285"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.06.011"},{"key":"ref12","doi-asserted-by":"crossref","DOI":"10.3389\/fpsyg.2013.00504","article-title":"The stability-plasticity dilemma: Investigating the continuum from catastrophic forgetting to age-limited learning effects","volume":"4","author":"Mermillod","year":"2013","journal-title":"Frontiers Psychol."},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3213473"},{"key":"ref14","article-title":"Recent advances of continual learning in computer vision: An overview","author":"Qu","year":"2021","journal-title":"arXiv:2109.11369"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2773081"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1611835114"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.587"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00810"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3151511"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3144183"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.715"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.37"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.398"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3246049"},{"key":"ref25","article-title":"MoRAL: MoE augmented LoRa for LLMs\u2019 lifelong learning","author":"Yang","year":"2024","journal-title":"arXiv:2402.11260"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2019.8937236"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-794"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref29","first-page":"2247","article-title":"Multimodal large language models: A survey","volume-title":"Proc. IEEE Int. Conf. Big Data (BigData)","author":"Wu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2016.01593"},{"key":"ref31","article-title":"Beyond unimodal learning: The importance of integrating multiple modalities for lifelong learning","author":"Sarfraz","year":"2024","journal-title":"arXiv:2405.02766"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612121"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01831"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.215"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00686"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2973280"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00382"},{"key":"ref38","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2135"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3371975"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1350"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3295899"},{"key":"ref43","article-title":"Continual multimodal knowledge graph construction","author":"Chen","year":"2024","journal-title":"arXiv:2305.08698"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681387"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref46","article-title":"MM-prompt: Cross-modal prompt tuning for continual visual question answering","author":"Li","year":"2025","journal-title":"arXiv:2505.19455"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446924"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3275156"},{"key":"ref49","first-page":"26129","article-title":"Continual vision-language representation learning with off-diagonal information","volume-title":"Proc. ICML","author":"Ni"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01392-1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4102"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02191"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00364"},{"key":"ref54","article-title":"Beyond anti-forgetting: Multimodal continual instruction tuning with positive forward transfer","author":"Zheng","year":"2024","journal-title":"arXiv:2401.09181"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01752"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3057446"},{"issue":"12","key":"ref57","doi-asserted-by":"crossref","first-page":"9851","DOI":"10.1109\/TPAMI.2024.3429383","article-title":"Class-incremental learning: A survey","volume":"46","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref58","article-title":"Continual learning of natural language processing tasks: A survey","author":"Ke","year":"2022","journal-title":"arXiv:2211.12701"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.emnlp-tutorials.7"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3719664"},{"key":"ref61","article-title":"Continual learning with pre-trained models: A survey","author":"Zhou","year":"2024","journal-title":"arXiv:2401.16386"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3705725"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3363240"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3476068"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00024"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002177"},{"key":"ref67","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref70","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25208"},{"key":"ref74","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019","journal-title":"arXiv:1901.06706"},{"key":"ref75","first-page":"142","article-title":"Learning word vectors for sentiment analysis","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Maas"},{"key":"ref76","first-page":"51552","article-title":"Advancing cross-domain discriminability in continual learning of vision-language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"37","author":"Xu"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_13"},{"key":"ref78","article-title":"Continual instruction tuning for large multimodal models","author":"He","year":"2023","journal-title":"arXiv:2311.16206"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-43996-4_7"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02034"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2026.3652014"},{"key":"ref82","first-page":"16736","article-title":"RATT: Recurrent attention to transient tasks for continual image captioning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chiaro"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512176"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.469"},{"key":"ref85","first-page":"346","article-title":"Mind the interference: Retaining pre-trained knowledge in parameter efficient continual learning of vision-language models","volume-title":"Proc. ECCV","author":"Tang"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.466"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612207"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02712"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_13"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_2"},{"key":"ref91","article-title":"Continual learning for multimodal data fusion of a soft gripper","author":"Kushawaha","year":"2024","journal-title":"arXiv:2409.13792"},{"key":"ref92","article-title":"Enhanced continual learning of vision-language models with model fusion","volume-title":"Proc. 1st Workshop Scalable Optim. Efficient Adapt. Found. Models","author":"Gao"},{"key":"ref93","first-page":"5682","article-title":"S-prompts learning with pre-trained transformers: An occam\u2019s Razor for domain incremental learning","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00276"},{"key":"ref95","article-title":"Boosting open-domain continual learning via leveraging intra-domain category-aware prototype","author":"Lu","year":"2024","journal-title":"arXiv:2408.09984"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3547882"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_33"},{"key":"ref98","first-page":"6467","article-title":"Gradient episodic memory for continual learning","volume-title":"Proc. NeurIPS","volume":"30","author":"L\u00f3pez-Paz"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref100","article-title":"Like what you like: Knowledge distill via neuron selectivity transfer","author":"Huang","year":"2017","journal-title":"arXiv:1707.01219"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref102","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref103","first-page":"49250","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. NeurIPS","author":"Dai"},{"key":"ref104","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref105","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"issue":"140","key":"ref109","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref110","first-page":"22379","article-title":"AFEC: Active forgetting of negative transfer in continual learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref111","first-page":"4548","article-title":"Overcoming catastrophic forgetting with hard attention to the task","volume-title":"Proc. ICML","author":"Serra"},{"key":"ref112","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. ICLR","author":"Hu"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref114","article-title":"GraphNAS: Graph neural architecture search with reinforcement learning","author":"Gao","year":"2019","journal-title":"arXiv:1904.09981"},{"key":"ref115","article-title":"On Tiny Episodic Memories in Continual Learning","author":"Chaudhry","year":"2019","journal-title":"arXiv:1902.10486"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1145\/3147.3165"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_36"},{"key":"ref118","article-title":"Minimalistic gridworld environment for gymnasium","author":"Chevalier-Boisvert"},{"key":"ref119","first-page":"726","article-title":"Transporter networks: Rearranging the visual world for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Zeng"},{"key":"ref120","first-page":"894","article-title":"CLIPort: What and where pathways for robotic manipulation","volume-title":"Proc. Conf. Robot Learn.","author":"Shridhar"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00559"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1472"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1421"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3210780"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref135","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"arXiv:1306.5151"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.383"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2211477"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2013.77"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1185"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.306"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3476968"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref145","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1021\/acssensors.0c01424"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1038\/nrg3920"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-022-01981-2"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00398"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72083-3_30"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401247"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3219551"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01524"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1145\/3605098.3635947"},{"key":"ref155","first-page":"4514","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training","volume-title":"Proc. NeurIPS","volume":"34","author":"Xue"},{"key":"ref156","doi-asserted-by":"crossref","DOI":"10.21203\/rs.3.rs-1553541\/v1","article-title":"Delta tuning: A comprehensive study of parameter efficient methods for pre-trained language models","volume-title":"arXiv:2203.06904","author":"Ding"},{"key":"ref157","article-title":"Scaling down to scale up: A guide to parameter-efficient fine-tuning","author":"Lialin","year":"2023","journal-title":"arXiv:2303.15647"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3376453"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01832"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3360454"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3417232"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3661377"},{"key":"ref165","article-title":"Investigating the catastrophic forgetting in multimodal large language models","volume-title":"Proc. NeurIPS Workshop Instruct. Tuning Instruct. Following","author":"Zhai"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.523"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1145\/3543873.3587681"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3216981"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5962385\/11676227\/11456498.pdf?arnumber=11456498","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:11:08Z","timestamp":1788808268000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11456498\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":168,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2026.3658485","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9]]}}}