Related papers: Improving Classifier Training Efficiency for Autom…

Detecting cyber-anomalies and attacks are becoming a rising concern these days in the domain of cybersecurity. The knowledge of artificial intelligence, particularly, the machine learning techniques can be used to tackle these issues.…

Instruction tuning is critical to improve LLMs but usually suffers from low-quality and redundant data. Data filtering for instruction tuning has proved important in improving both the efficiency and performance of the tuning process. But…

Cyberbullying has become a serious and growing concern in todays virtual world. When left unnoticed, it can have adverse consequences for social and mental health. Researchers have explored various types of cyberbullying, but most…

The performance of neural code search is significantly influenced by the quality of the training data from which the neural models are derived. A large corpus of high-quality query and code pairs is demanded to establish a precise mapping…

Subword tokenization is an essential part of modern large language models (LLMs), yet its specific contributions to training efficiency and model performance remain poorly understood. In this work, we decouple the effects of subword…

Deep learning image classifiers usually rely on huge training sets and their training process can be described as learning the similarities and differences among training images. But, images in large training sets are not usually studied…

Cyber-security garnered significant attention due to the increased dependency of individuals and organizations on the Internet and their concern about the security and privacy of their online activities. Several previous machine learning…

Large language models pretrained on extensive web corpora demonstrate remarkable performance across a wide range of downstream tasks. However, a growing concern is data contamination, where evaluation datasets may be contained in the…

There is an increase in the proliferation of online hate commensurate with the rise in the usage of social media. In response, there is also a significant advancement in the creation of automated tools aimed at identifying harmful text…

Pretraining on large-scale datasets can boost the performance of object detectors while the annotated datasets for object detection are hard to scale up due to the high labor cost. What we possess are numerous isolated filed-specific…

Benefit from large-scale training datasets, deep Convolutional Neural Networks(CNNs) have achieved impressive results in face recognition(FR). However, tremendous scale of datasets inevitably lead to noisy data, which obviously reduce the…

Image-classification datasets have been used to pretrain image recognition models. Recently, web-scale image-caption datasets have emerged as a source of powerful pretraining alternative. Image-caption datasets are more ``open-domain'',…

Recent advancements in pre-trained large foundation models (LFM) have yielded significant breakthroughs across various domains, including natural language processing and computer vision. These models have been particularly impactful in the…

Language models pre-trained on web-scale corpora demonstrate impressive capabilities on diverse downstream tasks. However, there is increasing concern whether such capabilities might arise from evaluation datasets being included in the…

Advances in Natural Language Processing (NLP) have revolutionized the way researchers and practitioners address crucial societal problems. Large language models are now the standard to develop state-of-the-art solutions for text detection…

While deep learning models are making fast progress on the task of Natural Language Inference, recent studies have also shown that these models achieve high accuracy by exploiting several dataset biases, and without deep understanding of…

Pretraining is the preliminary and fundamental step in developing capable language models (LM). Despite this, pretraining data design is critically under-documented and often guided by empirically unsupported intuitions. To address this, we…

Real-time CNN-based object detection models for applications like surveillance can achieve high accuracy but are computationally expensive. Recent works have shown 10 to 100x reduction in computation cost for inference by using…

Machine learning (ML)-accelerated discovery requires large amounts of high-fidelity data to reveal predictive structure-property relationships. For many properties of interest in materials discovery, the challenging nature and high cost of…

Testing Machine Learning (ML) models and AI-Infused Applications (AIIAs), or systems that contain ML models, is highly challenging. In addition to the challenges of testing classical software, it is acceptable and expected that statistical…