English
Related papers

Related papers: Multi-Level Collaboration in Model Merging

200 papers

Embedding layers in transformer-based NLP models typically account for the largest share of model parameters, scaling with vocabulary size but not yielding performance gains proportional to scale. We propose an alternative approach in which…

Computation and Language · Computer Science 2025-05-06 Henry Ndubuaku , Mouad Talhi

State-of-the-art studies have demonstrated the superiority of joint modelling over pipeline implementation for medical named entity recognition and normalization due to the mutual benefits between the two processes. To exploit these…

Computation and Language · Computer Science 2018-12-17 Sendong Zhao , Ting Liu , Sicheng Zhao , Fei Wang

Large Language Models (LLMs) have demonstrated exceptional capabilities across diverse natural language processing (NLP) tasks. The release of open-source LLMs like LLaMA and Qwen has triggered the development of numerous fine-tuned models…

Computation and Language · Computer Science 2025-06-17 Zichuan Fu , Xian Wu , Yejing Wang , Wanyu Wang , Shanshan Ye , Hongzhi Yin , Yi Chang , Yefeng Zheng , Xiangyu Zhao

Large language models (LLMs) exhibit varying strengths and weaknesses across different tasks, prompting recent studies to explore the benefits of ensembling models to leverage their complementary advantages. However, existing LLM ensembling…

Computation and Language · Computer Science 2025-02-26 Yuxuan Yao , Han Wu , Mingyang Liu , Sichun Luo , Xiongwei Han , Jie Liu , Zhijiang Guo , Linqi Song

In the paradigm of multi-task learning, mul- tiple related prediction tasks are learned jointly, sharing information across the tasks. We propose a framework for multi-task learn- ing that enables one to selectively share the information…

Machine Learning · Computer Science 2012-07-03 Abhishek Kumar , Hal Daume

Large reasoning models (LRMs) excel at a long chain of reasoning but often fail to faithfully follow instructions regarding output format, constraints, or specific requirements. We investigate whether this gap can be closed by integrating…

Machine Learning · Computer Science 2026-02-27 Zhehao Huang , Yuhang Liu , Baijiong Lin , Yixin Lou , Zhengbao He , Hanling Tian , Tao Li , Xiaolin Huang

Model merging aims to integrate multiple expert models into a single model that inherits their complementary strengths without incurring the inference-time cost of ensembling. Recent progress has shown that merging can be highly effective…

Artificial Intelligence · Computer Science 2026-05-19 Shilian Chen , Jie Zhou , Qin Chen , Wen Wu , Xin Li , Qi Feng , Liang He

Adapting to diverse user needs at test time is a key challenge in controllable multi-objective generation. Existing methods are insufficient: merging-based approaches provide indirect, suboptimal control at the parameter level, often…

Machine Learning · Computer Science 2025-10-17 Guofu Xie , Chen Zhang , Xiao Zhang , Yunsheng Shi , Ting Yao , Jun Xu

Machine unlearning aims to selectively remove specific knowledge from a trained model. Existing approaches, such as Task Arithmetic, fine-tune the model on the forget set to create a task vector (i.e., a direction in weight space) for…

Machine Learning · Computer Science 2025-07-03 Hyo Seo Kim , Dongyoon Han , Junsuk Choe

Transfer and multi-task learning have traditionally focused on either a single source-target pair or very few, similar tasks. Ideally, the linguistic levels of morphology, syntax and semantics would benefit each other by being trained in a…

Computation and Language · Computer Science 2017-07-25 Kazuma Hashimoto , Caiming Xiong , Yoshimasa Tsuruoka , Richard Socher

Multimodal Continual Instruction Tuning (MCIT) is essential for sequential task adaptation of Multimodal Large Language Models (MLLMs) but is severely restricted by catastrophic forgetting. While existing literature focuses on the reasoning…

Machine Learning · Computer Science 2026-04-16 Zijian Gao , Wangwang Jia , Xingxing Zhang , Pengfei Qian , Tao Sun , Bo Ding , Yong Dou , Huaimin Wang , Kele Xu

Weight-space model merging combines independently fine-tuned models without accessing original training data, offering a practical alternative to joint training. While merging succeeds in multitask settings, its behavior in multilingual…

Computation and Language · Computer Science 2026-04-06 Baban Gain , Asif Ekbal , Trilok Nath Singh

Achieving high-performing language models which include medium- and lower-resource languages remains a challenge. Massively multilingual models still underperform compared to language-specific adaptations, especially at smaller model…

Computation and Language · Computer Science 2025-12-12 Kevin Glocker , Kätriin Kukk , Romina Oji , Marcel Bollmann , Marco Kuhlmann , Jenny Kunz

Model merging is a scalable alternative to multi-task training that combines the capabilities of multiple specialised models into a single model. This is particularly attractive for large speech foundation models, which are typically…

Computation and Language · Computer Science 2026-03-06 Carlos Carvalho , Francisco Teixeira , Thomas Rolland , Alberto Abad

Model Merging (MM) has emerged as a scalable paradigm for multi-task learning (MTL), enabling multiple task-specific models to be integrated without revisiting the original training data. Despite recent progress, the reliability of MM under…

Machine Learning · Computer Science 2026-03-12 Yuhan Xie , Chen Lyu

We survey the model merging literature through the lens of loss landscape geometry to connect observations from empirical studies on model merging and loss landscape analysis to phenomena that govern neural network training and the…

We propose a novel method to merge convolutional neural-nets for the inference stage. Given two well-trained networks that may have different architectures that handle different tasks, our method aligns the layers of the original networks…

Computer Vision and Pattern Recognition · Computer Science 2018-05-15 Yi-Min Chou , Yi-Ming Chan , Jia-Hong Lee , Chih-Yi Chiu , Chu-Song Chen

Averaging neural network parameters is an intuitive method for fusing the knowledge of two independent models. It is most prominently used in federated learning. If models are averaged at the end of training, this can only lead to a good…

Machine Learning · Computer Science 2024-03-20 Linara Adilova , Maksym Andriushchenko , Michael Kamp , Asja Fischer , Martin Jaggi

Adapting large language models (LLMs) to new languages typically involves continual pre-training (CT) followed by supervised fine-tuning (SFT). However, this CT-then-SFT approach struggles with limited data in the context of low-resource…

Computation and Language · Computer Science 2025-02-10 Mingxu Tao , Chen Zhang , Quzhe Huang , Tianyao Ma , Songfang Huang , Dongyan Zhao , Yansong Feng

Model merging has shown great promise at combining expert models, but the benefit of merging is unclear when merging "generalist" models trained on many tasks. We explore merging in the context of large (~100B) models, by recycling…

Computation and Language · Computer Science 2025-02-05 Muhammad Khalifa , Yi-Chern Tan , Arash Ahmadian , Tom Hosking , Honglak Lee , Lu Wang , Ahmet Üstün , Tom Sherborne , Matthias Gallé