Ulugbek Shernazarov

I'm a passionate computer vision and machine learning engineer with a focus on advanced models and LLMs. I'm currently studying Data Science and Artificial Intelligence at the Asian Institute of Technology.

I've contributed to various projects, such as long-range facial recognition systems, biometric tracking, and federated learning, with a strong emphasis on real-world applications and optimizing model performance.

I'm currently working on projects involving Large Language Models and advanced rain removal in image processing. You can find more about my recent projects on my GitHub and other platforms below.

Email  /  CV  /  Scholar  /  LinkedIn  /  Github

Research Interests

I'm interested in computer vision, LLMs, and machine learning. My recent projects involve tasks such as biometric recognition, federated learning, and natural language processing.

Developed an AI-powered platform that uses LLMs to generate and optimize resumes based on job descriptions. Features include ATS optimization, effectiveness metrics, and an interactive Streamlit interface.

Built a prompt-to-video generation system using Stable Diffusion with kinematic conditioning. Includes smooth interpolation, CLI and web interfaces, and export to video or GIF formats.

Exploring the use of LLMs to provide predictive recommendations for loan applications, supporting fairer decision-making.

Applying hybrid diffusion and GAN models for enhanced rain removal in image processing, improving image clarity under adverse conditions.

Developed a high-performance facial recognition system optimized for long-range security applications.

Feel free to use this website's source code.