English
Related papers

Related papers: MagMax: Leveraging Model Merging for Seamless Cont…

200 papers

Continually learning new skills is important for intelligent systems, yet standard deep learning methods suffer from catastrophic forgetting of the past. Recent works address this with weight regularisation. Functional regularisation,…

We present a novel training approach, named Merge-and-Bound (M&B) for Class Incremental Learning (CIL), which directly manipulates model weights in the parameter space for optimization. Our algorithm involves two types of weight merging:…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Taehoon Kim , Donghwan Jang , Bohyung Han

Future deep learning models will be distinguished by systems that perpetually learn through interaction, imagination, and cooperation, blurring the line between training and inference. This makes continual learning a critical challenge, as…

Machine Learning · Computer Science 2025-05-20 Truman Hickok

Connectionist models such as neural networks suffer from catastrophic forgetting. In this work, we study this problem from the perspective of information theory and define forgetting as the increase of description lengths of previous data…

Machine Learning · Computer Science 2020-06-29 Xu He , Min Lin

Model merging and task arithmetic have emerged as promising scalable approaches to merge multiple single-task checkpoints to one multi-task model, but their applicability is reduced by significant performance loss. Previous works have…

Machine Learning · Computer Science 2024-05-14 Ke Wang , Nikolaos Dimitriadis , Guillermo Ortiz-Jimenez , François Fleuret , Pascal Frossard

Previous studies on continual knowledge learning (CKL) in large language models (LLMs) have predominantly focused on approaches such as regularization, architectural modifications, and rehearsal techniques to mitigate catastrophic…

Computation and Language · Computer Science 2025-02-06 Yeongbin Seo , Dongha Lee , Jinyoung Yeo

Model merging enables the reuse of fine-tuned models without joint training or access to original data. Dynamic merging further improves flexibility by selectively activating task-relevant parameters and efficiently composing experts across…

Machine Learning · Computer Science 2026-05-20 Guodong Du , Wanyu Lin

We present a novel Balanced Incremental Model Agnostic Meta Learning system (BI-MAML) for learning multiple tasks. Our method implements a meta-update rule to incrementally adapt its model to new tasks without forgetting old tasks. Such a…

Machine Learning · Computer Science 2020-06-16 Yang Zheng , Jinlin Xiang , Kun Su , Eli Shlizerman

While most continual learning methods focus on mitigating forgetting and improving accuracy, they often overlook the critical aspect of network calibration, despite its importance. Neural collapse, a phenomenon where last-layer features…

Machine Learning · Computer Science 2026-04-23 Trung-Anh Dang , Vincent Nguyen , Ngoc-Son Vu , Christel Vrain

Continual learning is an emerging paradigm in machine learning, wherein a model is exposed in an online fashion to data from multiple different distributions (i.e. environments), and is expected to adapt to the distribution change.…

Machine Learning · Computer Science 2022-03-29 Binghui Peng , Andrej Risteski

Continual learning (CL) refers to the ability to continually learn over time by accommodating new knowledge while retaining previously learned experience. While this concept is inherent in human learning, current machine learning methods…

Machine Learning · Computer Science 2024-08-15 Anna Vettoruzzo , Joaquin Vanschoren , Mohamed-Rafik Bouguelia , Thorsteinn Rögnvaldsson

In recent years, deep neural networks have found success in replicating human-level cognitive skills, yet they suffer from several major obstacles. One significant limitation is the inability to learn new tasks without forgetting previously…

Machine Learning · Computer Science 2019-08-20 Gabrielle K. Liu

Continual Learning is considered a key step toward next-generation Artificial Intelligence. Among various methods, replay-based approaches that maintain and replay a small episodic memory of previous samples are one of the most successful…

Machine Learning · Computer Science 2022-12-27 Guangji Bai , Chen Ling , Yuyang Gao , Liang Zhao

Continual learning models for stationary data focus on learning and retaining concepts coming to them in a sequential manner. In the most generic class-incremental environment, we have to be ready to deal with classes coming one by one,…

Machine Learning · Computer Science 2023-07-11 Lukasz Korycki , Bartosz Krawczyk

The ability of artificial agents to increment their capabilities when confronted with new data is an open challenge in artificial intelligence. The main challenge faced in such cases is catastrophic forgetting, i.e., the tendency of neural…

Machine Learning · Computer Science 2020-12-16 Eden Belouadah , Adrian Popescu , Ioannis Kanellos

Dual-to-Dual MLLMs refer to Multimodal Large Language Models, which can enable unified multimodal comprehension and generation through text and image modalities. Although exhibiting strong instantaneous learning and generalization…

Machine Learning · Computer Science 2026-02-23 Jingyang Qiao , Zhizhong Zhang , Xin Tan , Jingyu Gong , Yanyun Qu , Yuan Xie

Large Language Models (LLMs) require instruction fine-tuning to perform different downstream tasks. However, the instruction fine-tuning phase still demands significant computational resources and labeled data, lacking a paradigm that can…

Computation and Language · Computer Science 2025-03-10 Yiguan Lin , Bin Xu , Yinghao Li , Yang Gao

Instruction tuning is now a widely adopted approach to aligning large multimodal models (LMMs) to follow human intent. It unifies the data format of vision-language tasks, enabling multi-task joint training. However, vision-language tasks…

Machine Learning · Computer Science 2023-11-29 Jinghan He , Haiyun Guo , Ming Tang , Jinqiao Wang

Model merging provides a scalable alternative to multi-task training by combining specialized finetuned models through parameter arithmetic, enabling efficient deployment without the need for joint training or access to all task data. While…

Machine Learning · Computer Science 2025-10-21 Yifei He , Siqi Zeng , Yuzheng Hu , Rui Yang , Tong Zhang , Han Zhao

Continual learning allows the system to learn and adapt to new tasks while retaining the knowledge acquired from previous tasks. However, deep learning models suffer from catastrophic forgetting of knowledge learned from earlier tasks while…

Machine Learning · Computer Science 2024-12-17 Dupati Srikar Chandra , P. K. Srijith , Dana Rezazadegan , Chris McCarthy
‹ Prev 1 3 4 5 6 7 10 Next ›