14.2.7.1.3 Continual Learning for Large Language Models, Vision Language Models

Chapter Contents (Back)
Continual Learning. 2607

Hu, H.X.[He-Xiang], Sener, O.[Ozan], Sha, F.[Fei], Koltun, V.[Vladlen],
Drinking From a Firehose: Continual Learning With Web-Scale Natural Language,
PAMI(45), No. 5, May 2023, pp. 5684-5696.
IEEE DOI 2304
Task analysis, Benchmark testing, Learning systems, Multitasking, Social networking (online), Neural networks, Data models, web-scale datasets BibRef

Zhang, W.T.[Wen-Tao], Huang, Y.J.[Yu-Jun], Zhang, W.Z.[Wei-Zhuo], Zhang, T.[Tong], Lao, Q.[Qicheng], Yu, Y.[Yue], Zheng, W.S.[Wei-Shi], Wang, R.X.[Rui-Xuan],
Continual Learning of Image Classes With Language Guidance From a Vision-Language Model,
CirSysVideo(34), No. 12, December 2024, pp. 13152-13163.
IEEE DOI Code:
WWW Link. 2501
Visualization, Adaptation models, Data models, Task analysis, Knowledge engineering, Semantics, language guidance BibRef

Yu, J.[Jiazuo], Huang, Z.C.[Zi-Chen], Zhuge, Y.Z.[Yun-Zhi], Zhang, L.[Lu], Hu, P.[Ping], Wang, D.[Dong], Lu, H.C.[Hu-Chuan], He, Y.[You],
MoE-Adapters++: Toward More Efficient Continual Learning of Vision-Language Models Via Dynamic Mixture-of-Experts Adapters,
PAMI(47), No. 12, December 2025, pp. 11912-11928.
IEEE DOI 2511
Training, Adaptation models, Computational modeling, Collaboration, Accuracy, Incremental learning, Magnetic heads, vision-language models BibRef

Chen, Y.Z.[Yi-Zhou], Huang, X.[Xihao], Zhang, W.[Wei],
Large Visual Language Models Continual Learning With Dynamic Mixture of Experts,
IP(34), 2025, pp. 8301-8316.
IEEE DOI 2512
Adaptation models, Computational modeling, Training, Foundation models, Data models, Visualization, Tuning, catastrophic forgetting BibRef

Fu, H.[Hao], Zhao, H.[Hanbin], Dong, J.H.[Jia-Hua], Ding, H.H.[Heng-Hui], Zhang, C.[Chao], Qian, H.[Hui],
IAP: Improving Continual Learning of Vision-Language Models via Instance-Aware Prompting,
IP(35), 2026, pp. 717-731.
IEEE DOI Code:
WWW Link. 2602
Incremental learning, Data models, Logic gates, Computational modeling, Adaptation models, Visualization, multi-modal learning BibRef

Zhang, H.S.[Hong-Sheng], Ji, Z.[Zhong], Liu, J.R.[Jing-Ren], Pang, Y.W.[Yan-Wei], Han, J.G.[Jun-Gong],
Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning,
IP(35), 2026, pp. 615-628.
IEEE DOI 2602
Adaptation models, Training, Prototypes, Data models, Stability analysis, Vision language model, Knowledge engineering, dual-teacher knowledge distillation BibRef

Liu, Y.Y.[Yu-Yang], Po, L.M.[Lai-Man], Hung, F.[Farrell], Wang, Z.[Zhuohan], Wu, H.X.[Hao-Xuan], Jiang, Z.[Zeyu], Li, K.[Kun], Xu, X.[Xuyuan], Cheung, K.W.[Kwok-Wai],
CSBoRA: A continual learning method for large language models with true orthogonality and reduced forgetting,
PR(179), 2026, pp. 113782.
Elsevier DOI 2606
Continual Standard-Basis Low-Rank Adaptation, Supervised continual learning, Large language model, True orthogonality BibRef

He, C.Y.[Chi-Yuan], Qiu, Z.[Zihuan], Meng, F.M.[Fan-Man], Xu, L.F.[Lin-Feng], Wu, Q.B.[Qing-Bo], Li, H.L.[Hong-Liang],
DesCLIP: Robust Continual Learning via General Attribute Descriptions for VLM-Based Visual Recognition,
MultMed(28), 2026, pp. 5021-5035.
IEEE DOI 2607
Visualization, Adaptation models, Training, Overfitting, Data models, Computational modeling, Buildings, Tuning, Optimization, vision-language model BibRef

Li, X.G.[Xue-Guang], Guo, C.[Cheng], Tang, X.[Xinyu], Jie, Y.[Yingmo],
RectLoRA: Subspace parameter-efficient fine-tuning for continual adaptation of LLMs and LVMs,
PR(179), 2026, pp. 113887.
Elsevier DOI 2606
Large language models, Large vision models, Parameter-efficient fine-tuning, Continual learning, Catastrophic forgetting BibRef


Ma, Y.[Yue], Ren, H.T.[Huan-Tao], Wang, B.[Boyu], Jin, J.G.[Jin-Gang], Velipasalar, S.[Senem], Qiu, Q.[Qinru],
LVP-CLIP: Revisiting CLIP for Continual Learning with Label Vector Pool,
MULA25(231-240)
IEEE DOI 2512
Training, Incremental learning, Scalability, Vectors, Encoding, clip, vision-language model, continual learning, classification BibRef

Yu, L.[Lu], Han, H.Y.[Hao-Yu], Tao, Z.[Zhe], Yao, H.T.[Han-Tao], Xu, C.S.[Chang-Sheng],
Language Guided Concept Bottleneck Models for Interpretable Continual Learning,
CVPR25(14976-14986)
IEEE DOI Code:
WWW Link. 2508
Training, Learning systems, Visualization, Decision making, Semantics, Prototypes, Predictive models, vision-language models BibRef

Yu, Y.C.[Yu-Chu], Huang, C.P.[Chi-Pin], Chen, J.J.[Jr-Jen], Chang, K.P.[Kai-Po], Lai, Y.H.[Yung-Hsuan], Yang, F.E.[Fu-En], Wang, Y.C.A.F.[Yu-Chi-Ang Frank],
Select and Distill: Selective Dual-teacher Knowledge Transfer for Continual Learning on Vision-language Models,
ECCV24(XXVI: 219-236).
Springer DOI 2412
BibRef

Tang, L.X.[Long-Xiang], Tian, Z.[Zhuotao], Li, K.[Kai], He, C.M.[Chun-Ming], Zhou, H.T.[Han-Tao], Zhao, H.S.[Heng-Shuang], Li, X.[Xiu], Jia, J.Y.[Jia-Ya],
Mind the Interference: Retaining Pre-trained Knowledge in Parameter Efficient Continual Learning of Vision-language Models,
ECCV24(XXXVI: 346-365).
Springer DOI 2412
BibRef

Yu, J.[Jiazuo], Zhuge, Y.Z.[Yun-Zhi], Zhang, L.[Lu], Hu, P.[Ping], Wang, D.[Dong], Lu, H.C.[Hu-Chuan], He, Y.[You],
Boosting Continual Learning of Vision-Language Models via Mixture-of-Experts Adapters,
CVPR24(23219-23230)
IEEE DOI Code:
WWW Link. 2410
Training, Degradation, Adaptation models, Incremental learning, Codes, continual learning, task incremental learning BibRef

Roy, A.[Anurag], Moulick, R.[Riddhiman], Verma, V.K.[Vinay K.], Ghosh, S.[Saptarshi], Das, A.[Abir],
Convolutional Prompting meets Language Models for Continual Learning,
CVPR24(23616-23626)
IEEE DOI Code:
WWW Link. 2410
Convolution, Large language models, Training data, Machine learning, Transformers, Continual Learning, Vision Transformer BibRef

Ni, B.L.[Bo-Lin], Zhao, H.B.[Hong-Bo], Zhang, C.H.[Cheng-Hao], Hu, K.[Ke], Meng, G.F.[Gao-Feng], Zhang, Z.X.[Zhao-Xiang], Xiang, S.M.[Shi-Ming],
Enhancing Visual Continual Learning with Language-Guided Supervision,
CVPR24(24068-24077)
IEEE DOI 2410
Training, Visualization, Head, Protocols, Correlation, Continual learning BibRef

Qi, B.Q.[Bi-Qing], Chen, X.[Xinquan], Gao, J.Q.[Jun-Qi], Li, D.[Dong], Liu, J.X.[Jian-Xing], Wu, L.G.[Li-Gang], Zhou, B.[Bowen],
Interactive Continual Learning: Fast and Slow Thinking,
CVPR24(12882-12892)
IEEE DOI 2410
Learning systems, Resistance, Large language models, Collaboration, Memory modules BibRef

Verma, V.[Vinay], Mehta, N.[Nikhil], Liang, K.J.[Kevin J], Mishra, A.[Aakansha], Carin, L.[Lawrence],
Meta-Learned Attribute Self-Interaction Network for Continual and Generalized Zero-Shot Learning,
WACV24(2709-2719)
IEEE DOI 2404
Training, Adaptation models, Protocols, Zero-shot learning, Computational modeling, Reservoirs, Data models, Algorithms, Vision + language and/or other modalities BibRef

Khan, M.G.Z.A.[Muhammad Gul Zain Ali], Naeem, M.F.[Muhammad Ferjad], Van Gool, L.J.[Luc J.], Stricker, D.[Didier], Tombari, F.[Federico], Afzal, M.Z.[Muhammad Zeshan],
Introducing Language Guidance in Prompt-based Continual Learning,
ICCV23(11429-11439)
IEEE DOI 2401
BibRef

Zheng, Z.W.[Zang-Wei], Ma, M.Y.[Ming-Yuan], Wang, K.[Kai], Qin, Z.H.[Zi-Heng], Yue, X.Y.[Xiang-Yu], You, Y.[Yang],
Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models,
ICCV23(19068-19079)
IEEE DOI Code:
WWW Link. 2401
BibRef

Chapter on Pattern Recognition, Clustering, Statistics, Grammars, Learning, Neural Nets, Genetic Algorithms continues in
Lifelong Learning .


Last update:Jul 18, 2026 at 15:29:28