English
Related papers

Related papers: ColBERT-Zero: To Pre-train Or Not To Pre-train Col…

200 papers

Pre-trained models of code built on the transformer architecture have performed well on software engineering (SE) tasks such as predictive code generation, code summarization, among others. However, whether the vector representations from…

Software Engineering · Computer Science 2021-08-26 Anjan Karmakar , Romain Robbes

Condensed datasets offer a compact representation of larger datasets, but training models directly on them or using them to enhance model performance through knowledge distillation (KD) can result in suboptimal outcomes due to limited…

Machine Learning · Computer Science 2025-11-11 Kuluhan Binici , Shivam Aggarwal , Cihan Acar , Nam Trung Pham , Karianto Leman , Gim Hee Lee , Tulika Mitra

Contemporary question answering (QA) systems, including transformer-based architectures, suffer from increasing computational and model complexity which render them inefficient for real-world applications with limited resources. Further,…

Transformer-based models generally allocate the same amount of computation for each token in a given sequence. We develop a simple but effective "token dropping" method to accelerate the pretraining of transformer models, such as BERT,…

Computation and Language · Computer Science 2022-03-25 Le Hou , Richard Yuanzhe Pang , Tianyi Zhou , Yuexin Wu , Xinying Song , Xiaodan Song , Denny Zhou

Diversity has been gaining interest in the NLP community in recent years. At the same time, state-of-the-art transformer models such as ModernBERT use very large pre-training datasets, which are driven by size rather than by diversity. This…

Computation and Language · Computer Science 2026-02-26 Louis Estève , Christophe Servan , Thomas Lavergne , Agata Savary

Optical Coherence Tomography (OCT) provides high-resolution cross-sectional images useful for diagnosing various diseases, but their distinct characteristics from natural images raise questions about whether large-scale pre-training on…

Computer Vision and Pattern Recognition · Computer Science 2025-02-19 Zihao Han , Philippe De Wilde

Model depth is a double-edged sword in deep learning: deeper models achieve higher accuracy but require higher computational cost. To efficiently train models at scale, an effective strategy is the progressive training, which scales up…

Machine Learning · Computer Science 2025-11-10 Zhiqi Bu

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

Knowledge distillation (KD) is widely used for training a compact model with the supervision of another large model, which could effectively improve the performance. Previous methods mainly focus on two aspects: 1) training the student to…

Computer Vision and Pattern Recognition · Computer Science 2020-07-27 Tiancheng Wen , Shenqi Lai , Xueming Qian

Knowledge Distillation (KD) compresses computationally expensive pre-trained language models (PLMs) by transferring their knowledge to smaller models, allowing their use in resource-constrained or real-time settings. However, most smaller…

Computation and Language · Computer Science 2023-11-08 Hayeon Lee , Rui Hou , Jongpil Kim , Davis Liang , Hongbo Zhang , Sung Ju Hwang , Alexander Min

In text classification tasks, fine tuning pretrained language models like BERT and GPT-3 yields competitive accuracy; however, both methods require pretraining on large text datasets. In contrast, general topic modeling methods possess the…

Computation and Language · Computer Science 2024-02-13 Weijie Xu , Xiaoyu Jiang , Jay Desai , Bin Han , Fuqin Yan , Francis Iannacci

This paper investigates the effectiveness of pre-training for few-shot intent classification. While existing paradigms commonly further pre-train language models such as BERT on a vast amount of unlabeled corpus, we find it highly effective…

Computation and Language · Computer Science 2024-09-17 Haode Zhang , Yuwei Zhang , Li-Ming Zhan , Jiaxin Chen , Guangyuan Shi , Albert Y. S. Lam , Xiao-Ming Wu

Knowledge distillation is one of the most popular and effective techniques for knowledge transfer, model compression and semi-supervised learning. Most existing distillation approaches require the access to original or augmented training…

Machine Learning · Computer Science 2020-12-11 Liangchen Luo , Mark Sandler , Zi Lin , Andrey Zhmoginov , Andrew Howard

Knowledge distillation is the process of transferring the knowledge from a large model to a small model. In this process, the small model learns the generalization ability of the large model and retains the performance close to that of the…

Machine Learning · Computer Science 2021-03-26 Zhenyan Hou , Wenxuan Fan

Almost all the state-of-the-art neural networks for computer vision tasks are trained by (1) pre-training on a large-scale dataset and (2) finetuning on the target dataset. This strategy helps reduce dependence on the target dataset and…

Computer Vision and Pattern Recognition · Computer Science 2021-11-22 Shuvam Chakraborty , Burak Uzkent , Kumar Ayush , Kumar Tanmay , Evan Sheehan , Stefano Ermon

In recent years, BERT has made significant breakthroughs on many natural language processing tasks and attracted great attentions. Despite its accuracy gains, the BERT model generally involves a huge number of parameters and needs to be…

Computation and Language · Computer Science 2021-02-19 Cheng Yang , Shengnan Wang , Yuechuan Li , Chao Yang , Ming Yan , Jingqiao Zhang , Fangquan Lin

Pre-trained language models such as BERT have proven to be highly effective for natural language processing (NLP) tasks. However, the high demand for computing resources in training such models hinders their application in practice. In…

Computation and Language · Computer Science 2019-08-27 Siqi Sun , Yu Cheng , Zhe Gan , Jingjing Liu

With the urgent demand for generalized deep models, many pre-trained big models are proposed, such as BERT, ViT, GPT, etc. Inspired by the success of these models in single domains (like computer vision and natural language processing), the…

Computer Vision and Pattern Recognition · Computer Science 2024-04-11 Xiao Wang , Guangyao Chen , Guangwu Qian , Pengcheng Gao , Xiao-Yong Wei , Yaowei Wang , Yonghong Tian , Wen Gao

In recent years, researchers tend to pre-train ever-larger language models to explore the upper limit of deep models. However, large language model pre-training costs intensive computational resources and most of the models are trained from…

Computation and Language · Computer Science 2021-10-15 Cheng Chen , Yichun Yin , Lifeng Shang , Xin Jiang , Yujia Qin , Fengyu Wang , Zhi Wang , Xiao Chen , Zhiyuan Liu , Qun Liu

Pretrained language models have led to significant performance gains in many NLP tasks. However, the intensive computing resources to train such models remain an issue. Knowledge distillation alleviates this problem by learning a…

Computation and Language · Computer Science 2020-05-04 Linqing Liu , Huan Wang , Jimmy Lin , Richard Socher , Caiming Xiong