English
Related papers

Related papers: StatsMerging: Statistics-Guided Model Merging via …

200 papers

Transfer learning has become a powerful tool to initialize deep learning models to achieve faster convergence and higher performance. This is especially useful in the medical imaging analysis domain, where data scarcity limits possible…

Computer Vision and Pattern Recognition · Computer Science 2025-04-16 Ibrahim Almakky , Santosh Sanjeev , Anees Ur Rehman Hashmi , Mohammad Areeb Qazi , Hu Wang , Mohammad Yaqub

As deep learning models grow in complexity and the volume of training data increases, reducing storage and computational costs becomes increasingly important. Dataset distillation addresses this challenge by synthesizing a compact set of…

Computer Vision and Pattern Recognition · Computer Science 2025-05-20 Zhe Li , Sarah Cechnicka , Cheng Ouyang , Katharina Breininger , Peter Schüffler , Bernhard Kainz

In this paper, we investigate a novel deep-model reusing task. Our goal is to train a lightweight and versatile student model, without human-labelled annotations, that amalgamates the knowledge and masters the expertise of two pretrained…

Computer Vision and Pattern Recognition · Computer Science 2019-04-24 Jingwen Ye , Yixin Ji , Xinchao Wang , Kairi Ou , Dapeng Tao , Mingli Song

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

This paper introduces a continual learning approach named MagMax, which utilizes model merging to enable large pre-trained models to continuously learn from new data without forgetting previously acquired knowledge. Distinct from…

Machine Learning · Computer Science 2024-07-31 Daniel Marczak , Bartłomiej Twardowski , Tomasz Trzciński , Sebastian Cygert

Automatic scoring of student responses enhances efficiency in education, but deploying a separate neural network for each task increases storage demands, maintenance efforts, and redundant computations. To address these challenges, this…

Computation and Language · Computer Science 2025-03-14 Luyang Fang , Ehsan Latif , Haoran Lu , Yifan Zhou , Ping Ma , Xiaoming Zhai

Knowledge distillation aims to train a compact student network using soft supervision from a larger teacher network and hard supervision from ground truths. However, determining an optimal knowledge fusion ratio that balances these…

Machine Learning · Computer Science 2024-02-20 Chengming Hu , Haolun Wu , Xuan Li , Chen Ma , Xi Chen , Jun Yan , Boyu Wang , Xue Liu

Knowledge distillation, transferring knowledge from a teacher model to a student model, has emerged as a powerful technique in neural machine translation for compressing models or simplifying training targets. Knowledge distillation…

Computation and Language · Computer Science 2024-04-24 Jingxuan Wei , Linzhuang Sun , Yichong Leng , Xu Tan , Bihui Yu , Ruifeng Guo

Multi-task model merging aims to consolidate knowledge from multiple fine-tuned task-specific experts into a unified model while minimizing performance degradation. Existing methods primarily approach this by minimizing differences between…

Machine Learning · Computer Science 2025-10-28 Wenju Sun , Qingyong Li , Wen Wang , Yang Liu , Yangli-ao Geng , Boyang Li

We propose the task of knowledge distillation detection, which aims to determine whether a student model has been distilled from a given teacher, under a practical setting where only the student's weights and the teacher's API are…

Machine Learning · Computer Science 2025-10-03 Qin Shi , Amber Yijia Zheng , Qifan Song , Raymond A. Yeh

What does a neural network learn when training from a task-specific dataset? Synthesizing this knowledge is the central idea behind Dataset Distillation, which recent work has shown can be used to compress large datasets into a small set of…

Machine Learning · Computer Science 2024-03-05 Tian Qin , Zhiwei Deng , David Alvarez-Melis

Model merging has attracted significant attention as a powerful paradigm for model reuse, facilitating the integration of task-specific models into a singular, versatile framework endowed with multifarious capabilities. Previous studies,…

Machine Learning · Computer Science 2025-01-03 Zhengqi Xu , Han Zheng , Jie Song , Li Sun , Mingli Song

Large pretrained visual models exhibit remarkable generalization across diverse recognition tasks. Yet, real-world applications often demand compact models tailored to specific problems. Variants of knowledge distillation have been devised…

Computer Vision and Pattern Recognition · Computer Science 2024-05-08 Juliette Marrie , Michael Arbel , Julien Mairal , Diane Larlus

Classification tasks require a balanced distribution of data to ensure the learner to be trained to generalize over all classes. In real-world datasets, however, the number of instances vary substantially among classes. This typically leads…

Machine Learning · Computer Science 2020-11-24 Joel Jang , Yoonjeon Kim , Kyoungho Choi , Sungho Suh

Model merging aims to cheaply combine individual task-specific models into a single multitask model. In this work, we view past merging methods as leveraging different notions of a ''task parameter subspace'' in which models are matched…

Machine Learning · Computer Science 2024-04-16 Derek Tam , Mohit Bansal , Colin Raffel

In this paper, we propose Stochastic Knowledge Distillation (SKD) to obtain compact BERT-style language model dubbed SKDBERT. In each iteration, SKD samples a teacher model from a pre-defined teacher ensemble, which consists of multiple…

Computation and Language · Computer Science 2022-11-30 Zixiang Ding , Guoqing Jiang , Shuai Zhang , Lin Guo , Wei Lin

Model merging has attracted attention as an effective path toward multi-task adaptation by integrating knowledge from multiple task-specific models. Among existing approaches, dynamic merging mitigates performance degradation caused by…

Machine Learning · Computer Science 2026-05-01 Junqi Gao , Dazhi Zhang , Zhichang Guo , Biqing Qi , Yi Ran , Wangmeng Zuo

Optimization-based meta-learning typically assumes tasks are sampled from a single distribution - an assumption oversimplifies and limits the diversity of tasks that meta-learning can model. Handling tasks from multiple different…

Machine Learning · Computer Science 2021-09-29 Zhe Wang , Jake Grigsby , Arshdeep Sekhon , Yanjun Qi

Unified models capable of solving a wide variety of tasks have gained traction in vision and NLP due to their ability to share regularities and structures across tasks, which improves individual task performance and reduces computational…

Robotics · Computer Science 2023-10-13 Siddhant Haldar , Lerrel Pinto

Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…

Computation and Language · Computer Science 2020-05-04 Linqing Liu , Huan Wang , Jimmy Lin , Richard Socher , Caiming Xiong