Efficient Parameter-Efficient Fine-Tuning for Large Language Models

PDF

Aditya Mehrotra, John Smith, Jane Doe

NeurIPS 20242024

We propose a novel method for parameter-efficient fine-tuning of large language models that reduces memory requirements by 70% while maintaining comparable performance to full fine-tuning.

Scaling Distributed Machine Learning Systems: A Survey

PDF

Aditya Mehrotra, Alice Johnson

arXiv preprint2024

A comprehensive survey of techniques for scaling machine learning systems across distributed computing environments, covering both data and model parallelism approaches.

Adversarial Robustness in Computer Vision Models

PDF

Bob Williams, Aditya Mehrotra, Carol Davis

CVPR 20232023

We investigate adversarial attack vectors in state-of-the-art computer vision models and propose a new defense mechanism that improves robustness by 35%.