English
Related papers

Related papers: Self-Updating Models with Error Remediation

200 papers

Iterative self-training (self-distillation) repeatedly refits a model on pseudo-labels generated by its own predictions. We study this procedure in overparameterized linear regression: an initial estimator is trained on noisy labels, and…

Machine Learning · Statistics 2026-02-17 Mingqi Wu , Archer Y. Yang , Qiang Sun

Comment updating is an emerging task in software evolution that aims to automatically revise source code comments in accordance with code changes. This task plays a vital role in maintaining code-comment consistency throughout software…

Software Engineering · Computer Science 2025-12-11 Qingyuan Liang , Zeyu Sun , Qihao Zhu , Junhao Hu , Yifan Zhao , Yakun Zhang , Lu Zhang

Can a model learn to escape its own learning plateau? Reinforcement learning methods for finetuning large reasoning models stall on datasets with low initial success rates, and thus little training signal. We investigate a fundamental…

Machine Learning · Computer Science 2026-02-09 Shobhita Sundaram , John Quan , Ariel Kwiatkowski , Kartik Ahuja , Yann Ollivier , Julia Kempe

Continual instruction tuning enables large language models (LLMs) to learn incrementally while retaining past knowledge, whereas existing methods primarily focus on how to retain old knowledge rather than on selecting which new knowledge to…

Computation and Language · Computer Science 2025-03-21 Peiyi Lin , Fukai Zhang , Kai Niu , Hao Fu

Deep learning-based solutions for semantic segmentation suffer from significant performance degradation when tested on data with different characteristics than what was used during the training. Adapting the models using annotated data from…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Xingchen Zhao , Niluthpol Chowdhury Mithun , Abhinav Rajvanshi , Han-Pang Chiu , Supun Samarasekera

Reward models (RM) capture the values and preferences of humans and play a central role in Reinforcement Learning with Human Feedback (RLHF) to align pretrained large language models (LLMs). Traditionally, training these models relies on…

Machine Learning · Computer Science 2024-09-12 Yifei He , Haoxiang Wang , Ziyan Jiang , Alexandros Papangelis , Han Zhao

Practical recommender systems need be periodically retrained to refresh the model with new interaction data. To pursue high model fidelity, it is usually desirable to retrain the model on both historical and new data, since it can account…

Information Retrieval · Computer Science 2021-01-15 Yang Zhang , Fuli Feng , Chenxu Wang , Xiangnan He , Meng Wang , Yan Li , Yongdong Zhang

Adapting models deployed to test distributions can mitigate the performance degradation caused by distribution shifts. However, privacy concerns may render model parameters inaccessible. One promising approach involves utilizing…

Machine Learning · Computer Science 2023-10-18 Zige Wang , Yonggang Zhang , Zhen Fang , Long Lan , Wenjing Yang , Bo Han

This work proposes a self-supervised training strategy designed for combinatorial problems. An obstacle in applying supervised paradigms to such problems is the need for costly target solutions often produced with exact solvers. Inspired by…

Machine Learning · Computer Science 2024-11-01 Andrea Corsini , Angelo Porrello , Simone Calderara , Mauro Dell'Amico

Unpaired Multi-Modal Learning (UMML) which leverages unpaired multi-modal data to boost model performance on each individual modality has attracted a lot of research interests in medical image analysis. However, existing UMML methods…

Computer Vision and Pattern Recognition · Computer Science 2025-03-10 Lei Zhu , Yanyu Xu , Huazhu Fu , Xinxing Xu , Rick Siow Mong Goh , Yong Liu

Data augmentation, a cornerstone technique in deep learning, is crucial in enhancing model performance, especially with scarce labeled data. While traditional techniques are effective, their reliance on hand-crafted methods limits their…

Machine Learning · Computer Science 2024-10-04 Mucong Ding , Bang An , Yuancheng Xu , Anirudh Satheesh , Furong Huang

Time series imputation models have traditionally been developed using complete datasets with artificial masking patterns to simulate missing values. However, in real-world infrastructure monitoring, practitioners often encounter datasets…

Machine Learning · Computer Science 2025-06-26 Ryan Hildebrant , Rahul Bhope , Sharad Mehrotra , Christopher Tull , Nalini Venkatasubramanian

The recent success of large pre-trained language models (PLMs) heavily hinges on massive labeled data, which typically produces inferior performance in low-resource scenarios. To remedy this dilemma, we study self-training as one of the…

Machine Learning · Computer Science 2023-10-23 Jianing Wang , Qiushi Sun , Nuo Chen , Chengyu Wang , Jun Huang , Ming Gao , Xiang Li

Event cameras asynchronously capture brightness changes with low latency, high temporal resolution, and high dynamic range. However, annotation of event data is a costly and laborious process, which limits the use of deep learning methods…

Computer Vision and Pattern Recognition · Computer Science 2023-12-27 Simon Klenk , David Bonello , Lukas Koestler , Nikita Araslanov , Daniel Cremers

Language models have demonstrated remarkable performance in solving reasoning tasks; however, even the strongest models still occasionally make reasoning mistakes. Recently, there has been active research aimed at improving reasoning…

Computation and Language · Computer Science 2024-08-30 Tian Ye , Zicheng Xu , Yuanzhi Li , Zeyuan Allen-Zhu

Semi-supervised learning (SSL) can reduce the need for large labelled datasets by incorporating unlabelled data into the training. This is particularly interesting for semantic segmentation, where labelling data is very costly and…

Computer Vision and Pattern Recognition · Computer Science 2022-10-20 Sebastian Scherer , Robin Schön , Rainer Lienhart

Deep learning models rely heavily on large volumes of labeled data to achieve high performance. However, real-world datasets often contain noisy labels due to human error, ambiguity, or resource constraints during the annotation process.…

Computer Vision and Pattern Recognition · Computer Science 2024-12-09 Gouranga Bala , Anuj Gupta , Subrat Kumar Behera , Amit Sethi

Recent deep neural networks (DNNs) can easily overfit to biased training data with noisy labels. Label correction strategy is commonly used to alleviate this issue by designing a method to identity suspected noisy labels and then correct…

Computer Vision and Pattern Recognition · Computer Science 2021-09-03 Yichen Wu , Jun Shu , Qi Xie , Qian Zhao , Deyu Meng

Because of the ambiguous and subjective property of the facial expression recognition (FER) task, the label noise is widely existing in the FER dataset. For this problem, in the training phase, current FER methods often directly predict…

Computer Vision and Pattern Recognition · Computer Science 2023-05-30 Xiang Zhang , Yan Lu , Huan Yan , Jingyang Huang , Yusheng Ji , Yu Gu

The goal of test-time adaptation is to adapt a source-pretrained model to a continuously changing target domain without relying on any source data. Typically, this is either done by updating the parameters of the model (model adaptation)…

Computer Vision and Pattern Recognition · Computer Science 2023-12-01 Mrigank Raman , Rohan Shah , Akash Kannan , Pranit Chawla
‹ Prev 1 4 5 6 7 8 10 Next ›