English
Related papers

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

200 papers

Existing Continual Learning (CL) approaches have focused on addressing catastrophic forgetting by leveraging regularization methods, replay buffers, and task-specific components. However, realistic CL solutions must be shaped not only by…

Machine Learning · Computer Science 2023-10-11 Jinyung Hong , Theodore P. Pavlic

As humans learn new skills and apply their existing knowledge while maintaining previously learned information, "continual learning" in machine learning aims to incorporate new data while retaining and utilizing past knowledge. However,…

Robotics · Computer Science 2025-07-29 Hanne Say , Suzan Ece Ada , Emre Ugur , Minoru Asada , Erhan Oztop

Despite significant advances, continual learning models still suffer from catastrophic forgetting when exposed to incrementally available data from non-stationary distributions. Rehearsal approaches alleviate the problem by maintaining and…

Machine Learning · Statistics 2021-03-02 Binh Tang , David S. Matteson

Multitask learning assumes that models capable of learning from multiple tasks can achieve better quality and efficiency via knowledge transfer, a key feature of human learning. Though, state of the art ML models rely on high customization…

Machine Learning · Computer Science 2022-11-17 Andrea Gesmundo , Jeff Dean

This work proposes a new method to sequentially train deep neural networks on multiple tasks without suffering catastrophic forgetting, while endowing it with the capability to quickly adapt to unseen tasks. Starting from existing work on…

Computer Vision and Pattern Recognition · Computer Science 2023-02-02 Dhrupad Bhardwaj , Julia Kempe , Artem Vysogorets , Angela M. Teng , Evaristus C. Ezekwem

Accelerating model convergence in resource-constrained environments is essential for fast and efficient neural network training. This work presents learn2mix, a new training strategy that adaptively adjusts class proportions within batches,…

Machine Learning · Computer Science 2025-10-24 Shyam Venkatasubramanian , Vahid Tarokh

Approximate unlearning has gained popularity as an approach to efficiently update an LLM so that it behaves (roughly) as if it was not trained on a subset of data to begin with. However, existing methods are brittle in practice and can…

Machine Learning · Computer Science 2025-04-08 Kevin Kuo , Amrith Setlur , Kartik Srinivas , Aditi Raghunathan , Virginia Smith

Regression Mean (RegMean), an approach that formulates model merging as a linear regression problem, aims to find the optimal weights for each linear layer in the merged model by minimizing the discrepancy in predictions between the merged…

Machine Learning · Computer Science 2026-04-28 The-Hai Nguyen , Dang Huu-Tien , Takeshi Suzuki , Le-Minh Nguyen

The conventional success of textual classification relies on annotated data, and the new paradigm of pre-trained language models (PLMs) still requires a few labeled data for downstream tasks. However, in real-world applications, label noise…

Computation and Language · Computer Science 2022-10-14 Dan Qiao , Chenchen Dai , Yuyang Ding , Juntao Li , Qiang Chen , Wenliang Chen , Min Zhang

Continual learning (CL) refers to a machine learning paradigm that learns continuously without forgetting previously acquired knowledge. Thereby, major difficulty in CL is catastrophic forgetting of preceding tasks, caused by shifts in data…

Machine Learning · Computer Science 2023-03-08 Stella Ho , Ming Liu , Lan Du , Longxiang Gao , Yong Xiang

Model merging has achieved significant success, with numerous innovative methods proposed to enhance capabilities by combining multiple models. However, challenges persist due to the lack of a unified framework for classification and…

Machine Learning · Computer Science 2025-03-13 Wei Ruan , Tianze Yang , Yifan Zhou , Tianming Liu , Jin Lu

Training and deploying large-scale machine learning models is time-consuming, requires significant distributed computing infrastructures, and incurs high operational costs. Our analysis, grounded in real-world large model training on…

Distributed, Parallel, and Cluster Computing · Computer Science 2024-06-12 Samuel Hsia , Alicia Golden , Bilge Acun , Newsha Ardalani , Zachary DeVito , Gu-Yeon Wei , David Brooks , Carole-Jean Wu

This article reviews meta-learning also known as learning-to-learn which seeks rapid and accurate model adaptation to unseen tasks with applications in highly automated AI, few-shot learning, natural language processing and robotics. Unlike…

Machine Learning · Computer Science 2020-10-27 Huimin Peng

Finetuning on domain-specific data is a well-established method for enhancing LLM performance on downstream tasks. Training on each dataset produces a new set of model weights, resulting in a multitude of checkpoints saved in-house or on…

Machine Learning · Computer Science 2026-03-12 Sofia Maria Lo Cicero Vaina , Artem Chumachenko , Max Ryabinin

Artificial neural networks suffer from catastrophic forgetting when they are sequentially trained on multiple tasks. To overcome this problem, we present a novel approach based on task-conditioned hypernetworks, i.e., networks that generate…

Machine Learning · Computer Science 2022-04-12 Johannes von Oswald , Christian Henning , Benjamin F. Grewe , João Sacramento

We unveil that internal representations in large language models (LLMs) serve as reliable proxies of learned knowledge, and propose RECALL, a novel representation-aware model merging framework for continual learning without access to…

Computation and Language · Computer Science 2025-10-24 Bowen Wang , Haiyuan Wan , Liwen Shi , Chen Yang , Peng He , Yue Ma , Haochen Han , Wenhao Li , Tiao Tan , Yongjian Li , Fangming Liu , Yifan Gong , Sheng Zhang

In this paper, we introduce a discrete variant of the meta-learning framework. Meta-learning aims at exploiting prior experience and data to improve performance on future tasks. By now, there exist numerous formulations for meta-learning in…

Machine Learning · Computer Science 2021-01-12 Arman Adibi , Aryan Mokhtari , Hamed Hassani

Model merging (e.g., via interpolation or task arithmetic) fuses multiple models trained on different tasks to generate a multi-task solution. The technique has been proven successful in previous studies, where the models are trained on…

Computer Vision and Pattern Recognition · Computer Science 2023-10-12 Yi-Lin Sung , Linjie Li , Kevin Lin , Zhe Gan , Mohit Bansal , Lijuan Wang

Model merging acquires general capabilities without extra data or training by combining multiple models' parameters. Previous approaches achieve linear mode connectivity by aligning parameters into the same loss basin using permutation…

Machine Learning · Computer Science 2025-03-28 Yi-Kai Zhang , Jin Wang , Xu-Xiang Zhong , De-Chuan Zhan , Han-Jia Ye

Continual model merging integrates independently fine-tuned models sequentially without access to the original training data, offering a scalable and efficient solution for continual learning. However, existing methods face two critical…

Machine Learning · Computer Science 2025-10-23 Zihuan Qiu , Yi Xu , Chiyuan He , Fanman Meng , Linfeng Xu , Qingbo Wu , Hongliang Li