English
Related papers

Related papers: Merge and Bound: Direct Manipulations on Weights f…

200 papers

Fine-tuning a task-specific multilingual large language model (LLM) involves training the model on a multilingual dataset with examples in all the required languages. Updating one or more supported languages with additional data or adding…

Computation and Language · Computer Science 2026-01-26 Alphaeus Dmonte , Vidhi Gupta , Daniel J Perry , Mark Arehart

Model merging combines the parameters of multiple neural networks into a single model without additional training. As fine-tuned large language models (LLMs) proliferate, merging offers a computationally efficient alternative to ensembles…

Computation and Language · Computer Science 2026-03-31 Mingyang Song , Mao Zheng

In this paper, we introduce a novel method for merging the weights of multiple pre-trained neural networks using a genetic algorithm called MeGA. Traditional techniques, such as weight averaging and ensemble methods, often fail to fully…

Neural and Evolutionary Computing · Computer Science 2024-07-01 Daniel Yun

Mixed Integer Linear Programming (MILP) is a pillar of mathematical optimization that offers a powerful modeling language for a wide range of applications. During the past decades, enormous algorithmic progress has been made in solving…

Optimization and Control · Mathematics 2024-02-09 Lara Scavuzzo , Karen Aardal , Andrea Lodi , Neil Yorke-Smith

Class-Incremental Learning (CIL) requires models to continually acquire knowledge of new classes without forgetting old ones. Despite Pre-trained Models (PTMs) have shown excellent performance in CIL, catastrophic forgetting still occurs as…

Machine Learning · Computer Science 2025-06-19 Hai-Long Sun , Da-Wei Zhou , Hanbin Zhao , Le Gan , De-Chuan Zhan , Han-Jia Ye

Class-incremental learning (CIL) aims to adapt to emerging new classes without forgetting old ones. Traditional CIL models are trained from scratch to continually acquire knowledge as data evolves. Recently, pre-training has achieved…

Machine Learning · Computer Science 2024-08-06 Da-Wei Zhou , Zi-Wen Cai , Han-Jia Ye , De-Chuan Zhan , Ziwei Liu

Multi-task learning (MTL) trains deep neural networks to optimize several objectives simultaneously using a shared backbone, which leads to reduced computational costs, improved data efficiency, and enhanced performance through cross-task…

Machine Learning · Computer Science 2025-09-30 Hoang Phan , Lam Tran , Quyen Tran , Ngoc N. Tran , Tuan Truong , Qi Lei , Nhat Ho , Dinh Phung , Trung Le

Model merging has recently emerged as a lightweight alternative to ensembling, combining multiple fine-tuned models into a single set of parameters with no additional training overhead. Yet, existing merging methods fall short of matching…

Multi-task learning (MTL) is often achieved by merging datasets before fine-tuning, but the growing availability of fine-tuned models has led to new approaches such as model merging via task arithmetic. A major challenge in this setting is…

Machine Learning · Computer Science 2025-09-15 Brahim Touayouch , Loïc Fosse , Géraldine Damnati , Gwénolé Lecorvé

In this paper, we surveyed the existing literature studying different approaches and algorithms for the four critical components in the general branch and bound (B&B) algorithm, namely, branching variable selection, node selection, node…

Machine Learning · Computer Science 2021-11-12 Lingying Huang , Xiaomeng Chen , Wei Huo , Jiazheng Wang , Fan Zhang , Bo Bai , Ling Shi

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

Class Incremental Learning (CIL) requires models to continuously learn new classes without forgetting previously learned ones, while maintaining stable performance across all possible class sequences. In real-world settings, the order in…

Machine Learning · Computer Science 2026-03-05 Guannan Lai , Da-Wei Zhou , Xin Yang , Han-Jia Ye

Training large neural networks and merging task-specific models both exploit low-rank structure and require parameter importance estimation, yet these challenges have been pursued in isolation. Current workflows compute curvature…

Machine Learning · Computer Science 2026-03-30 Alireza Moayedikia , Alicia Troncoso

Model merging provides a compelling paradigm for integrating specialized expertise into a unified multi-task model, a goal that aligns naturally with the sequential knowledge acquisition in continual learning (CL). However, the requirement…

Machine Learning · Computer Science 2026-05-12 Xi Wang , Cheng Deng

Incremental Learning (IL) is useful when artificial systems need to deal with streams of data and do not have access to all data at all times. The most challenging setting requires a constant complexity of the deep model and an incremental…

Computer Vision and Pattern Recognition · Computer Science 2020-09-01 Eden Belouadah , Adrian Popescu , Ioannis Kanellos

We propose a novel multi-dimensional integration algorithm using a machine learning (ML) technique. After training a ML regression model to mimic a target integrand, the regression model is used to evaluate an approximation of the integral.…

Computational Physics · Physics 2021-10-14 Boram Yoon

Class-incremental learning (CIL) with pre-trained models (PTMs) faces a critical trade-off between efficient adaptation and long-term stability. While analytic learning enables rapid, recursive closed-form updates, its efficacy is often…

Machine Learning · Computer Science 2026-05-08 Binyu Zhao , Wei Zhang , Xingrui Yu , Zhaonian Zou , Ivor Tsang

Task arithmetic is a straightforward yet highly effective strategy for model merging, enabling the resultant model to exhibit multi-task capabilities. Recent research indicates that models demonstrating linearity enhance the performance of…

Machine Learning · Computer Science 2025-04-16 Rui Dai , Sile Hu , Xu Shen , Yonggang Zhang , Xinmei Tian , Jieping Ye

In the scenario of class-incremental learning (CIL), deep neural networks have to adapt their model parameters to non-stationary data distributions, e.g., the emergence of new classes over time. However, CIL models are challenged by the…

Machine Learning · Computer Science 2023-06-22 Depeng Li , Zhigang Zeng

Current research on class-incremental learning primarily focuses on single-label classification tasks. However, real-world applications often involve multi-label scenarios, such as image retrieval and medical imaging. Therefore, this paper…

Computer Vision and Pattern Recognition · Computer Science 2025-11-27 Chenhao Ding , Songlin Dong , Zhengdong Zhou , Jizhou Han , Qiang Wang , Yuhang He , Yihong Gong
‹ Prev 1 3 4 5 6 7 10 Next ›