English
Related papers

Related papers: Emerging Property of Masked Token for Effective Pr…

200 papers

Masked Image Modeling (MIM) achieves outstanding success in self-supervised representation learning. Unfortunately, MIM models typically have huge computational burden and slow learning process, which is an inevitable obstacle for their…

Computer Vision and Pattern Recognition · Computer Science 2023-03-10 Haoqing Wang , Yehui Tang , Yunhe Wang , Jianyuan Guo , Zhi-Hong Deng , Kai Han

Mask-based pretraining has become a cornerstone of modern large-scale models across language, vision, and recently biology. Despite its empirical success, its role and limits in learning data representations have been unclear. In this work,…

Machine Learning · Computer Science 2025-09-29 Mingze Dong , Leda Wang , Yuval Kluger

In this paper, we introduce Saliency-Based Adaptive Masking (SBAM), a novel and cost-effective approach that significantly enhances the pre-training performance of Masked Image Modeling (MIM) approaches by prioritizing token salience. Our…

Computer Vision and Pattern Recognition · Computer Science 2024-04-15 Hyesong Choi , Hyejin Park , Kwang Moo Yi , Sungmin Cha , Dongbo Min

Code completion is one of the most useful features in the Integrated Development Environments (IDEs), which can accelerate software development by suggesting the next probable token based on the contextual code in real-time. Recent studies…

Software Engineering · Computer Science 2021-01-01 Fang Liu , Ge Li , Yunfei Zhao , Zhi Jin

Large Language Models (LLMs) are discovered to suffer from accurately retrieving key information. To address this, we propose Mask-Enhanced Autoregressive Prediction (MEAP), a simple yet effective training paradigm that seamlessly…

Computation and Language · Computer Science 2026-03-16 Xialie Zhuang , Zhikai Jia , Jianjin Li , Zhenyu Zhang , Li Shen , Zheng Cao , Shiwei Liu

Time series analysis is widely used in extensive areas. Recently, to reduce labeling expenses and benefit various tasks, self-supervised pre-training has attracted immense interest. One mainstream paradigm is masked modeling, which…

Machine Learning · Computer Science 2023-10-24 Jiaxiang Dong , Haixu Wu , Haoran Zhang , Li Zhang , Jianmin Wang , Mingsheng Long

Vision representation learning, especially self-supervised learning, is pivotal for various vision applications. Ensemble learning has also succeeded in enhancing the performance and robustness of the vision models. However, traditional…

Computer Vision and Pattern Recognition · Computer Science 2024-11-26 Zhong-Yu Li , Yu-Song Hu , Bo-Wen Yin , Ming-Ming Cheng

In this paper, we study how to use masked signal modeling in vision and language (V+L) representation learning. Instead of developing masked language modeling (MLM) and masked image modeling (MIM) independently, we propose to build joint…

Computer Vision and Pattern Recognition · Computer Science 2023-03-16 Gukyeong Kwon , Zhaowei Cai , Avinash Ravichandran , Erhan Bas , Rahul Bhotika , Stefano Soatto

Gene transformer models such as Nucleotide Transformer, DNABert, and LOGO are trained to learn optimal gene sequence representations by using the Masked Language Modeling (MLM) training objective over the complete Human Reference Genome.…

Computation and Language · Computer Science 2024-10-23 Soumyadeep Roy , Shamik Sural , Niloy Ganguly

Masked language models (MLMs) conventionally mask 15% of tokens due to the belief that more masking would leave insufficient context to learn good representations; this masking rate has been widely used, regardless of model sizes or masking…

Computation and Language · Computer Science 2023-02-13 Alexander Wettig , Tianyu Gao , Zexuan Zhong , Danqi Chen

Masked Image Modeling (MIM) has recently been established as a potent pre-training paradigm. A pretext task is constructed by masking patches in an input image, and this masked content is then predicted by a neural network using visible…

Computer Vision and Pattern Recognition · Computer Science 2023-01-16 Philippe Weinzaepfel , Vincent Leroy , Thomas Lucas , Romain Brégier , Yohann Cabon , Vaibhav Arora , Leonid Antsfeld , Boris Chidlovskii , Gabriela Csurka , Jérôme Revaud

Masked language modeling (MLM) has become one of the most successful self-supervised pre-training task. Inspired by its success, Point-BERT, as a pioneer work in point cloud, proposed masked point modeling (MPM) to pre-train point…

Computer Vision and Pattern Recognition · Computer Science 2022-08-16 Kexue Fu , Mingzhi Yuan , Manning Wang

While modern Transformer-based language models (LMs) have achieved major success in multi-task generalization, they often struggle to capture long-range dependencies within their context window. This work introduces a novel approach using…

Computation and Language · Computer Science 2025-09-23 Alok N. Shah , Khush Gupta , Keshav Ramji , Pratik Chaudhari

Molecular property prediction is an increasingly critical task within drug discovery and development. Typically, neural networks can learn molecular properties using graph-based, language-based or feature-based methods. Recent advances in…

Machine Learning · Computer Science 2025-07-31 Philip Spence , Brooks Paige , Anne Osbourn

Masked Image Modeling (MIM) is a powerful self-supervised strategy for visual pre-training without the use of labels. MIM applies random crops to input images, processes them with an encoder, and then recovers the masked inputs with a…

Computer Vision and Pattern Recognition · Computer Science 2024-04-23 Maryam Haghighat , Peyman Moghadam , Shaheer Mohamed , Piotr Koniusz

Multi-token prediction has emerged as a promising objective for improving language model pretraining, but its benefits have not consistently generalized to other settings such as fine-tuning. In this paper, we propose MuToR, a simple and…

Computation and Language · Computer Science 2025-05-16 Anastasios Gerontopoulos , Spyros Gidaris , Nikos Komodakis

Historically, LLMs have been trained using either autoregressive (AR) or masked language modeling (MLM) objectives, with AR models gaining dominance in recent years. However, AR models are inherently incapable of masked infilling, which is…

Machine Learning · Computer Science 2025-02-12 Daniel Israel , Aditya Grover , Guy Van den Broeck

In this paper, we introduce Masked Feature Modelling (MFM), a novel approach for the unsupervised pre-training of a Graph Attention Network (GAT) block. MFM utilizes a pretrained Visual Tokenizer to reconstruct masked features of objects…

Computer Vision and Pattern Recognition · Computer Science 2023-08-28 Dimitrios Daskalakis , Nikolaos Gkalelis , Vasileios Mezaris

Recently, pre-trained language models mostly follow the pre-train-then-fine-tuning paradigm and have achieved great performance on various downstream tasks. However, since the pre-training stage is typically task-agnostic and the…

Computation and Language · Computer Science 2020-10-08 Yuxian Gu , Zhengyan Zhang , Xiaozhi Wang , Zhiyuan Liu , Maosong Sun

Predicting attributes in the landmark free facial images is itself a challenging task which gets further complicated when the face gets occluded due to the usage of masks. Smart access control gates which utilize identity verification or…

Computer Vision and Pattern Recognition · Computer Science 2022-01-12 Prerana Mukherjee , Vinay Kaushik , Ronak Gupta , Ritika Jha , Daneshwari Kankanwadi , Brejesh Lall