English
Related papers

Related papers: Fisher Mask Nodes for Language Model Merging

200 papers

Code-switching, or alternating between languages within a single conversation, presents challenges for multilingual language models on NLP tasks. This research investigates if pre-training Multilingual BERT (mBERT) on code-switched datasets…

Computation and Language · Computer Science 2025-03-12 Katherine Xie , Nitya Babbar , Vicky Chen , Yoanna Turura

Recently, leveraging BERT pre-training to improve the phoneme encoder in text to speech (TTS) has drawn increasing attention. However, the works apply pre-training with character-based units to enhance the TTS phoneme encoder, which is…

Audio and Speech Processing · Electrical Eng. & Systems 2022-07-21 Guangyan Zhang , Kaitao Song , Xu Tan , Daxin Tan , Yuzi Yan , Yanqing Liu , Gang Wang , Wei Zhou , Tao Qin , Tan Lee , Sheng Zhao

The performance of Neural Network (NN)-based language models is steadily improving due to the emergence of new architectures, which are able to learn different natural language characteristics. This paper presents a novel framework, which…

Computation and Language · Computer Science 2017-08-24 Youssef Oualil , Dietrich Klakow

Every data selection method inherently has a target. In practice, these targets often emerge implicitly through benchmark-driven iteration: researchers develop selection strategies, train models, measure benchmark performance, then refine…

Transformer language models (TLMs) are critical for most NLP tasks, but they are difficult to create for low-resource languages because of how much pretraining data they require. In this work, we investigate two techniques for training…

Computation and Language · Computer Science 2023-01-06 Luke Gessler , Amir Zeldes

A big convergence of model architectures across language, vision, speech, and multimodal is emerging. However, under the same name "Transformers", the above areas use different implementations for better performance, e.g., Post-LayerNorm…

Applying deep learning and computational intelligence to finance has been a popular area of applied research, both within academia and industry, and continues to attract active attention. The inherently high volatility and non-stationary of…

Machine Learning · Computer Science 2025-03-17 Michael Charles Albada , Mojolaoluwa Joshua Sonola

Model merging constructs versatile models by integrating task-specific models without requiring labeled data or expensive joint retraining. Although recent methods improve adaptability to heterogeneous tasks by generating customized merged…

Machine Learning · Computer Science 2026-02-09 Haiyun Qiu , Xingyu Wu , Liang Feng , Kay Chen Tan

Large, self-supervised transformer-based language representation models have recently received significant amounts of attention, and have produced state-of-the-art results across a variety of tasks simply by scaling up pre-training on…

Computation and Language · Computer Science 2019-10-25 Alexandre Matton , Luke de Oliveira

This paper addresses an important problem of ranking the pre-trained deep neural networks and screening the most transferable ones for downstream tasks. It is challenging because the ground-truth model ranking for each task can only be…

Machine Learning · Computer Science 2022-07-20 Wenqi Shao , Xun Zhao , Yixiao Ge , Zhaoyang Zhang , Lei Yang , Xiaogang Wang , Ying Shan , Ping Luo

Model merging has emerged as a cost-efficient approximation to multitask learning. Among merging strategies, task arithmetic is notable for its simplicity and effectiveness. In this work, we provide a theoretical motivation for task vectors…

Model merging has emerged as an efficient method to combine multiple single-task fine-tuned models. The merged model can enjoy multi-task capabilities without expensive training. While promising, merging into a single model often suffers…

Computer Vision and Pattern Recognition · Computer Science 2026-04-15 Akash Dhasade , Divyansh Jhunjhunwala , Milos Vujasinovic , Gauri Joshi , Anne-Marie Kermarrec

In this paper, we explore the possibility of building a unified foundation model that can be adapted to both vision-only and text-only tasks. Starting from BERT and ViT, we design a unified transformer consisting of modality-specific…

Computer Vision and Pattern Recognition · Computer Science 2021-12-15 Qing Li , Boqing Gong , Yin Cui , Dan Kondratyuk , Xianzhi Du , Ming-Hsuan Yang , Matthew Brown

The rapid growth in the parameter size of Large Language Models (LLMs) has spurred the development of Parameter-Efficient Fine-Tuning (PEFT) methods to mitigate the substantial computational costs of fine-tuning. Among these, Fisher Induced…

Computation and Language · Computer Science 2025-05-27 Kang Xue , Ming Dong , Xinhui Tu , Tingting He

Recent progress in neural machine translation is directed towards larger neural networks trained on an increasing amount of hardware resources. As a result, NMT models are costly to train, both financially, due to the electricity and…

Computation and Language · Computer Science 2020-05-19 Tom Kocmi , Ondřej Bojar

Model merging has emerged as a practical approach to combine capabilities of specialized large language models (LLMs) without additional training. In the Long-to-Short (L2S) scenario, merging a base model with a long-chain-of-thought…

Machine Learning · Computer Science 2026-03-24 Tian Xia

Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current…

Machine Learning · Computer Science 2020-10-27 Minjia Zhang , Yuxiong He

Natural Language Processing (NLP) has witnessed a transformative leap with the advent of transformer-based architectures, which have significantly enhanced the ability of machines to understand and generate human-like text. This paper…

Computation and Language · Computer Science 2025-03-27 Tianhao Wu , Yu Wang , Ngoc Quach

Tremendous amounts of multimedia associated with speech information are driving an urgent need to develop efficient and effective automatic summarization methods. To this end, we have seen rapid progress in applying supervised deep neural…

Computation and Language · Computer Science 2020-06-03 Shi-Yan Weng , Tien-Hong Lo , Berlin Chen

Recent advancements in language representation models such as BERT have led to a rapid improvement in numerous natural language processing tasks. However, language models usually consist of a few hundred million trainable parameters with…

Machine Learning · Computer Science 2019-12-12 Mehrdad Valipour , En-Shiun Annie Lee , Jaime R. Jamacaro , Carolina Bessega