4 papers
MedDiffuseMix: Preserving Diagnostic Evidence with Saliency-Aware Diffusion Medical Image Data Augmentation
Teerath Kumar, Raja Vavekanand, Muhammad Turab
Limited data availability, class imbalance, and domain variability remain major barriers to reliable medical image classification. Conventional augmentation can improve training di…
A Comparative Analysis on Ethical Benchmarking in Large Language Models
Kira Sam, Raja Vavekanand
This work contributes to the field of Machine Ethics (ME) benchmarking, which develops tests to assess whether intelligent systems accurately represent human values and act accordi…
CELLM: An Efficient Communication in Large Language Models Training for Federated Learning
Raja Vavekanand, Kira Sam
Federated Learning (FL) is a recent model training paradigm in which client devices collaboratively train a model without ever aggregating their data. Crucially, this scheme offers…
Gravix: Active Learning for Gravitational Waves Classification Algorithms
Raja Vavekanand, Kira Sam, Vavek Bharwani
arXiv admin note: This version has been removed by arXiv administrators due to copyright infringement