English
Related papers

Related papers: The Finetuner's Fallacy: When to Pretrain with You…

200 papers

Data teams at frontier AI companies routinely train small proxy models to make critical decisions about pretraining data recipes for full-scale training runs. However, the community has a limited understanding of whether and when…

Machine Learning · Computer Science 2026-04-14 Jiachen T. Wang , Tong Wu , Kaifeng Lyu , James Zou , Dawn Song , Ruoxi Jia , Prateek Mittal

Automated program repair (APR) aims to fix software bugs automatically without human debugging efforts and plays a crucial role in software development and maintenance. Despite promising, APR is still challenged by a long-standing…

Software Engineering · Computer Science 2024-01-17 Quanjun Zhang , Chunrong Fang , Weisong Sun , Yan Liu , Tieke He , Xiaodong Hao , Zhenyu Chen

The development of deep learning techniques has allowed Neural Machine Translation (NMT) models to become extremely powerful, given sufficient training data and training time. However, systems struggle when translating text from a new…

Computation and Language · Computer Science 2022-03-23 Danielle Saunders

Parameter-efficient fine-tuning (PEFT) techniques have emerged to address overfitting and high computational costs associated with fully fine-tuning in self-supervised learning. Mainstream PEFT methods add a few trainable parameters while…

Computer Vision and Pattern Recognition · Computer Science 2025-06-06 Xingliang Lei , Yiwen Ye , Zhisong Wang , Ziyang Chen , Minglei Shu , Weidong Cai , Yanning Zhang , Yong Xia

Transfer learning is beneficial by allowing the expressive features of models pretrained on large-scale datasets to be finetuned for the target task of smaller, more domain-specific datasets. However, there is a concern that these…

Computer Vision and Pattern Recognition · Computer Science 2023-08-21 Angelina Wang , Olga Russakovsky

Fine-grained object retrieval aims to learn discriminative representation to retrieve visually similar objects. However, existing top-performing works usually impose pairwise similarities on the semantic embedding spaces or design a…

Computer Vision and Pattern Recognition · Computer Science 2023-03-07 Shijie Wang , Jianlong Chang , Zhihui Wang , Haojie Li , Wanli Ouyang , Qi Tian

With the great success of pre-trained models, the pretrain-then-finetune paradigm has been widely adopted on downstream tasks for source code understanding. However, compared to costly training a large-scale model from scratch, how to…

Software Engineering · Computer Science 2022-03-16 Deze Wang , Zhouyang Jia , Shanshan Li , Yue Yu , Yun Xiong , Wei Dong , Xiangke Liao

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

Models trained on a labeled source domain (e.g., labeled images from wildlife camera traps) often generalize poorly when deployed on an out-of-distribution (OOD) target domain (e.g., images from new camera trap locations). In the domain…

Computer Vision and Pattern Recognition · Computer Science 2024-06-24 Helen Qu , Sang Michael Xie

Domain adaptation (DA) mitigates the domain shift problem when transferring knowledge from one annotated domain to another similar but different unlabeled domain. However, existing models often utilize one of the ImageNet models as the…

Computer Vision and Pattern Recognition · Computer Science 2021-05-04 Youshan Zhang , Brian D. Davison

Domain adaptive pretraining, i.e. the continued unsupervised pretraining of a language model on domain-specific text, improves the modelling of text for downstream tasks within the domain. Numerous real-world applications are based on…

Computation and Language · Computer Science 2021-09-15 Rasmus Kær Jørgensen , Mareike Hartmann , Xiang Dai , Desmond Elliott

Adapting pre-trained models to specialized tasks often leads to catastrophic forgetting, where new knowledge overwrites foundational capabilities. Existing methods either compromise performance on the new task or struggle to balance…

Machine Learning · Computer Science 2026-03-10 Dyah Adila , Hanna Mazzawi , Benoit Dherin , Xavier Gonzalvo

Large Language Models (LLMs) often require domain-specific fine-tuning to address targeted tasks, which risks degrading their general capabilities. Maintaining a balance between domain-specific enhancements and general model utility is a…

Computation and Language · Computer Science 2025-06-05 Jun Rao , Zepeng Lin , Xuebo Liu , Xiaopeng Ke , Lian Lian , Dong Jin , Shengjun Cheng , Jun Yu , Min Zhang

Language models are pre-trained using large corpora of generic data like book corpus, common crawl and Wikipedia, which is essential for the model to understand the linguistic characteristics of the language. New studies suggest using…

Computation and Language · Computer Science 2022-09-28 Arnav Ladkat , Aamir Miyajiwala , Samiksha Jagadale , Rekha Kulkarni , Raviraj Joshi

Conventional continual pretraining (CPT) for large language model (LLM) domain adaptation often suffers from catastrophic forgetting and limited domain capacity. Existing strategies adopt layer expansion, introducing additional trainable…

Machine Learning · Computer Science 2025-10-14 Jinyang Zhang , Yue Fang , Hongxin Ding , Weibin Liao , Muyang Ye , Xu Chu , Junfeng Zhao , Yasha Wang

Finetuning pretrained models occurs in a low-dimensional subspace of the full parameter space. Prior work has focused on characterizing this optimization subspace, but largely ignored the complementary question: why do certain directions…

Machine Learning · Computer Science 2026-05-11 Junjie Yu , Yue Wang , Zihan Deng , Yan Zhu , Wenxiao Ma , Quanying Liu

Training foundation models on extensive datasets and then finetuning them on specific tasks has emerged as the mainstream approach in artificial intelligence. However, the model robustness, which is a critical aspect for safety, is often…

Computer Vision and Pattern Recognition · Computer Science 2023-12-15 Kai Qiu , Huishuai Zhang , Zhirong Wu , Stephen Lin

Efficient finetuning of pretrained language transformers is becoming increasingly prevalent for solving natural language processing tasks. While effective, it can still require a large number of tunable parameters. This can be a drawback…

Computation and Language · Computer Science 2023-05-31 Umang Gupta , Aram Galstyan , Greg Ver Steeg

State-of-the-art performance on language understanding tasks is now achieved with increasingly large networks; the current record holder has billions of parameters. Given a language model pre-trained on massive unlabeled text corpora, only…

Computation and Language · Computer Science 2020-04-30 Evani Radiya-Dixit , Xin Wang

Transfer learning has fundamentally changed the landscape of natural language processing (NLP) research. Many existing state-of-the-art models are first pre-trained on a large text corpus and then fine-tuned on downstream tasks. However,…

Computation and Language · Computer Science 2021-09-10 Haoming Jiang , Pengcheng He , Weizhu Chen , Xiaodong Liu , Jianfeng Gao , Tuo Zhao
‹ Prev 1 4 5 6 7 8 10 Next ›