English
Related papers

Related papers: Where to start? Analyzing the potential value of i…

200 papers

Pretrained language models are promising particularly for low-resource languages as they only require unlabelled data. However, training existing models requires huge amounts of compute, while pretrained cross-lingual models often…

Computation and Language · Computer Science 2020-06-05 Julian Martin Eisenschlos , Sebastian Ruder , Piotr Czapla , Marcin Kardas , Sylvain Gugger , Jeremy Howard

Midtraining, the practice of mixing specialized data with more general pretraining data in an intermediate training phase, has become widespread in language model development, yet there is little understanding of what makes it effective. We…

Computation and Language · Computer Science 2026-02-03 Emmy Liu , Graham Neubig , Chenyan Xiong

Machine unlearning, a process enabling pre-trained models to remove the influence of specific training samples, has attracted significant attention in recent years. Although extensive research has focused on developing efficient machine…

Machine Learning · Computer Science 2026-01-13 Heng Xu , Tianqing Zhu , Dayong Ye , Lefeng Zhang , Le Wang , Wanlei Zhou

Foundation Models (FMs) have demonstrated remarkable insights into the relational dynamics of the world, leading to the crucial question: how do these models acquire an understanding of world hybrid relations? Traditional statistical…

Artificial Intelligence · Computer Science 2024-06-18 Yang Chen , Cong Fang , Zhouchen Lin , Bing Liu

Obtaining labeled data to train a model for a task of interest is often expensive. Prior work shows training models on multitask data augmented with task descriptions (prompts) effectively transfers knowledge to new tasks. Towards…

Computation and Language · Computer Science 2023-05-26 Hamish Ivison , Noah A. Smith , Hannaneh Hajishirzi , Pradeep Dasigi

The weights of neural networks have emerged as a novel data modality, giving rise to the field of weight space learning. A central challenge in this area is that learning meaningful representations of weights typically requires large,…

Machine Learning · Computer Science 2025-10-03 Damian Falk , Konstantin Schürholt , Konstantinos Tzevelekakis , Léo Meynent , Damian Borth

The pretraining-finetuning paradigm has become the prevailing trend in modern deep learning. In this work, we discover an intriguing linear phenomenon in models that are initialized from a common pretrained checkpoint and finetuned on…

Machine Learning · Computer Science 2024-05-29 Zhanpeng Zhou , Zijun Chen , Yilan Chen , Bo Zhang , Junchi Yan

Although the pre-training followed by fine-tuning paradigm is used extensively in many fields, there is still some controversy surrounding the impact of pre-training on the fine-tuning process. Currently, experimental findings based on text…

Machine Learning · Computer Science 2023-09-12 Jiashu Pu , Shiwei Zhao , Ling Cheng , Yongzhu Chang , Runze Wu , Tangjie Lv , Rongsheng Zhang

Large pre-trained models, or foundation models, have shown impressive performance when adapted to a variety of downstream tasks, often out-performing specialized models. Hypernetworks, neural networks that generate some or all of the…

Machine Learning · Computer Science 2025-03-04 Jeffrey Gu , Serena Yeung-Levy

The rapidly evolving fields of Machine Learning (ML) and Artificial Intelligence have witnessed the emergence of platforms like Hugging Face (HF) as central hubs for model development and sharing. This experience report synthesizes insights…

Software Engineering · Computer Science 2024-02-13 Joel Castaño , Silverio Martínez-Fernández , Xavier Franch

Tabular data is prevalent in real-world machine learning applications, and new models for supervised learning of tabular data are frequently proposed. Comparative studies assessing the performance of models typically consist of…

Machine Learning · Computer Science 2024-12-19 Andrej Tschalzev , Sascha Marton , Stefan Lüdtke , Christian Bartelt , Heiner Stuckenschmidt

Neural network-based function approximation plays a pivotal role in the advancement of scientific computing and machine learning. Yet, training such models faces several challenges: (i) each target function often requires training a new…

Machine Learning · Computer Science 2025-10-13 Xinwen Hu , Yunqing Huang , Nianyu Yi , Peimeng Yin

In this paper we explore few-shot imitation learning for control problems, which involves learning to imitate a target policy by accessing a limited set of offline rollouts. This setting has been relatively under-explored despite its…

Machine Learning · Computer Science 2023-06-26 Massimiliano Patacchiola , Mingfei Sun , Katja Hofmann , Richard E. Turner

Using deep learning models on small scale datasets would result in overfitting. To overcome this problem, the process of pre-training a model and fine-tuning it to the small scale dataset has been used extensively in domains such as image…

Computation and Language · Computer Science 2019-11-05 Sanjay Kamath , Brigitte Grau , Yue Ma

Pre-trained models have become indispensable for efficiently building models across a broad spectrum of downstream tasks. The advantages of pre-trained models have been highlighted by empirical studies on scaling laws, which demonstrate…

Machine Learning · Statistics 2026-02-05 Kazuto Fukuchi , Ryuichiro Hataya , Kota Matsui

A promising paradigm for adapting instruction-tuned language models is to learn task-specific updates on a pretrained base model and subsequently merge them into the instruction-tuned model. However, existing approaches typically treat the…

Computation and Language · Computer Science 2026-05-05 Zhiwen Ruan , Yichao Du , Jianjie Zheng , Longyue Wang , Yun Chen , Peng Li , Jinsong Su , Yang Liu , Guanhua Chen

Transformers that are pre-trained on multilingual corpora, such as, mBERT and XLM-RoBERTa, have achieved impressive cross-lingual transfer capabilities. In the zero-shot transfer setting, only English training data is used, and the…

Computation and Language · Computer Science 2021-09-13 Yang Chen , Alan Ritter

Commonsense reasoning benchmarks have been largely solved by fine-tuning language models. The downside is that fine-tuning may cause models to overfit to task-specific data and thereby forget their knowledge gained during pre-training.…

Computation and Language · Computer Science 2021-09-08 Kaixin Ma , Filip Ilievski , Jonathan Francis , Satoru Ozaki , Eric Nyberg , Alessandro Oltramari

Pre-training has exhibited notable benefits to downstream tasks by boosting accuracy and speeding up convergence, but the exact reasons for these benefits still remain unclear. To this end, we propose to quantitatively and explicitly…

Machine Learning · Computer Science 2024-10-14 Xin Jiang , Xu Cheng , Zechao Li

Parameter fine tuning is a transfer learning approach whereby learned parameters from pre-trained source network are transferred to the target network followed by fine-tuning. Prior research has shown that this approach is capable of…

Computer Vision and Pattern Recognition · Computer Science 2019-09-20 Tasfia Shermin , Shyh Wei Teng , Manzur Murshed , Guojun Lu , Ferdous Sohel , Manoranjan Paul