English
Related papers

Related papers: Fisher Mask Nodes for Language Model Merging

200 papers

We study the problem of incorporating prior knowledge into a deep Transformer-based model,i.e.,Bidirectional Encoder Representations from Transformers (BERT), to enhance its performance on semantic textual matching tasks. By probing and…

Computation and Language · Computer Science 2021-02-23 Tingyu Xia , Yue Wang , Yuan Tian , Yi Chang

In this paper, we introduce a new vision-language pre-trained model -- ImageBERT -- for image-text joint embedding. Our model is a Transformer-based model, which takes different modalities as input and models the relationship between them.…

Computer Vision and Pattern Recognition · Computer Science 2020-01-24 Di Qi , Lin Su , Jia Song , Edward Cui , Taroon Bharti , Arun Sacheti

This paper investigates model merging, a technique for deriving Markov models from text or speech corpora. Models are derived by starting with a large and specific model and by successively combining states to build smaller and more general…

cmp-lg · Computer Science 2008-02-03 Thorsten Brants

Over the past few decades, Artificial Intelligence(AI) has progressed from the initial machine learning stage to the deep learning stage, and now to the stage of foundational models. Foundational models have the characteristics of…

Computation and Language · Computer Science 2024-11-28 Lewen Yang , Xuanyu Zhou , Juao Fan , Xinyi Xie , Shengxin Zhu

Transfer learning - i.e., further fine-tuning a pre-trained model on a downstream task - can confer significant advantages, including improved downstream performance, faster convergence, and better sample efficiency. These advantages have…

Machine Learning · Computer Science 2023-10-30 Prateek Yadav , Derek Tam , Leshem Choshen , Colin Raffel , Mohit Bansal

Standard fine-tuning of language models typically performs well on in-distribution data, but suffers with generalization to distribution shifts. In this work, we aim to improve the generalization of adapter-based cross-lingual task transfer…

Computation and Language · Computer Science 2024-04-05 Chen Cecilia Liu , Jonas Pfeiffer , Ivan Vulić , Iryna Gurevych

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

Model merging, such as model souping, is the practice of combining different models with the same architecture together without further training. In this work, we present a model merging methodology that addresses the difficulty of…

Computation and Language · Computer Science 2025-05-27 Lucas Bandarkar , Benjamin Muller , Pritish Yuvraj , Rui Hou , Nayan Singhal , Hongjiang Lv , Bing Liu

Parameter-efficient fine-tuning approaches have recently garnered a lot of attention. Having considerably lower number of trainable weights, these methods can bring about scalability and computational effectiveness. In this paper, we look…

Computation and Language · Computer Science 2023-02-23 Mohammad Akbar-Tajari , Sara Rajaee , Mohammad Taher Pilehvar

Multimodal learning pipelines have benefited from the success of pretrained language models. However, this comes at the cost of increased model parameters. In this work, we propose Adapted Multimodal BERT (AMB), a BERT-based architecture…

Computation and Language · Computer Science 2022-12-02 Odysseas S. Chlapanis , Georgios Paraskevopoulos , Alexandros Potamianos

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

Recent advances, such as GPT and BERT, have shown success in incorporating a pre-trained transformer language model and fine-tuning operation to improve downstream NLP systems. However, this framework still has some fundamental problems in…

Computation and Language · Computer Science 2019-05-22 Zhongyang Li , Xiao Ding , Ting Liu

Large-scale cross-lingual language models (LM), such as mBERT, Unicoder and XLM, have achieved great success in cross-lingual representation learning. However, when applied to zero-shot cross-lingual transfer tasks, most existing methods…

Computation and Language · Computer Science 2020-12-16 Yuwei Fang , Shuohang Wang , Zhe Gan , Siqi Sun , Jingjing Liu

Massively multilingual language models such as multilingual BERT offer state-of-the-art cross-lingual transfer performance on a range of NLP tasks. However, due to limited capacity and large differences in pretraining data sizes, there is a…

Computation and Language · Computer Science 2021-09-13 Jonas Pfeiffer , Ivan Vulić , Iryna Gurevych , Sebastian Ruder

The introduction of the Transformer neural network, along with techniques like self-supervised pre-training and transfer learning, has paved the way for advanced models like BERT. Despite BERT's impressive performance, opportunities for…

Computation and Language · Computer Science 2024-07-02 Farnaz Zeidi , Mehmet Fatih Amasyali , Çiğdem Erol

Combining multiple machine learning models has long been a technique for enhancing performance, particularly in distributed settings. Traditional approaches, such as model ensembles, work well, but are expensive in terms of memory and…

Machine Learning · Computer Science 2024-12-23 Albert Manuel Orozco Camacho , Stefan Horoi , Guy Wolf , Eugene Belilovsky

The recently proposed BERT has shown great power on a variety of natural language understanding tasks, such as text classification, reading comprehension, etc. However, how to effectively apply BERT to neural machine translation (NMT) lacks…

Computation and Language · Computer Science 2020-02-18 Jinhua Zhu , Yingce Xia , Lijun Wu , Di He , Tao Qin , Wengang Zhou , Houqiang Li , Tie-Yan Liu

Model merging is attracting attention as a novel method for creating a new model by combining the weights of different trained models. While previous studies reported that model merging works well for models trained on a single dataset with…

Machine Learning · Computer Science 2024-09-23 Masanori Yamada , Tomoya Yamashita , Shin'ya Yamaguchi , Daiki Chijiwa

Language model pre-training has proven to be useful in learning universal language representations. As a state-of-the-art language model pre-training model, BERT (Bidirectional Encoder Representations from Transformers) has achieved amazing…

Computation and Language · Computer Science 2020-02-06 Chi Sun , Xipeng Qiu , Yige Xu , Xuanjing Huang

Model merging, particularly through weight averaging, has shown surprising effectiveness in saving computations and improving model performance without any additional training. However, the interpretability of why and how this technique…

Machine Learning · Computer Science 2025-08-20 Hu Wang , Congbo Ma , Ibrahim Almakky , Ian Reid , Gustavo Carneiro , Mohammad Yaqub