Hasnain Ali Arain

🏠 Karachi, Pakistan 75460

Hello, I'm Hasnain 👋

I hold a Bachelor's degree in Computer and Information Systems Engineering from NED University. Currently, I work as a Machine Learning Engineer, specializing in Generative AI and Large Language Models (LLMs).

Research Interests

Computer Vision
Multimodal AI
Natural Language Processing
Robotics

Research and Professional Involvements

Outside of my job as a Machine Learning Engineer, I love diving into international hackathons and tech competitions where I get to work with talented people from around the world on exciting problems. I also spend time on personal projects that let me experiment with new technologies and collaborate with others.

I’m really passionate about giving back through teaching, so I volunteer with non-profits to help underprivileged students in Pakistan learn tech skills in their local language, Urdu. To keep learning and stay inspired, I regularly take online courses and tackle new, challenging projects.

Future Aspirations

I am excited to advance my academic journey through a graduate program in the United States, focusing on artificial intelligence. My aim is to contribute to transformative research and influence the future of technology.

News

Oct 06, 2024	Delivered a workshop on Generative AI at Pak Angels: Essential Generative AI Training Program. View
Jul 14, 2024	Scored 145/160 in Duolingo English Test
Mar 07, 2024	Achieved a GRE score of 318: Quant 164, Verbal 154, AWA 4.0.
Aug 28, 2023	Joined Arbisoft as a Machine Learning Engineer
Aug 21, 2023	Graduated from NED University of Engineering and Technology with Distinction - CGPA: 3.95 (Top 4%)

Latest Blog Posts

Aug 03, 2024	Building a Data Science Assistant with Llama 3 and Streamlit
Jun 28, 2024	Traditional Machine Learning Approaches: Machine Learning apart from Deep Learning
May 12, 2024	AI/ML Everywhere: A Beginner’s Guide

Checkout More

Selected Publications

PROMETHEUS-VTON: Precise Rendering Of Mixed Environments and Textiles for High-fidelity Ensemble Unification System in Virtual Try-On

Hasnain Ali Arain, and Ateeb Taseer

Oct 2024

Abs HTML PDF

Virtual try-on (VTON) technology has the potential to revolutionize online shopping experiences, but existing approaches face challenges in achieving photorealism and adapting to diverse clothing styles. This paper introduces PROMETHEUS-VTON, an enhanced virtual try-on system that builds upon the IDM-VTON framework to address these limitations. Our key contribution is the fine-tuning of the UNet2DConditionModel architecture to improve performance on complex garments and poses. We curated a dataset of 60,000 high-resolution images, including traditional Pakistani clothing, to address the lack of diversity in existing datasets. Through comprehensive experiments, we demonstrate significant improvements over state-of-the-art methods, achieving a 15.7% reduction in LPIPS score, a 2.5% in-crease in SSIM, and a 4.4% improvement in CLIP Image Similarity score compared to our baseline model. PROMETHEUS-VTON shows particular strength in handling non-Western garments and complex poses, representing a significant step towards making virtual try-on technology more robust and versatile.

Engaged in exciting research projects with upcoming publications in the pipeline.