3D Reconstruction of Underwater Coral Images
Implemented a deep learning-based 3D reconstruction pipeline for underwater coral imagery, processing challenging real-world visual data to recover spatial structure and geometry.
Ph.D. Student in Computer Science · University of Georgia
Mayesha Bintha Mizan
I research AI, vision, and language models.
I'm a Ph.D. student in Computer Science at the University of Georgia (GPA 4.00/4.00), researching AI, machine learning, NLP, computer vision, and LLM agents. Before starting my Ph.D., I earned a B.Sc. in Information and Communication Engineering from the Bangladesh University of Professionals, where my thesis on dimensionality reduction in handwritten digit recognition was published with Springer. I'm actively seeking Summer 2027 internship opportunities.
- Python
- C++
- Java
- JavaScript
- MySQL & Oracle
- Git
01. Projects
Image Reconstruction from fMRI Signals
Built a deep latent-space model that reconstructs natural images directly from high-dimensional fMRI brain activity, with residual encoders and U-Net refinement mapping neural signals into Stable Diffusion's latent space.
Security Testing of LLM Agents
Conducted systematic red-teaming and prompt-injection testing of tool-using LLM agents, building an automated evaluation pipeline to analyze unsafe tool execution and attack success patterns.
02. Resume
Want the full picture? Download my resume for a complete overview of my experience, education, and skills.
Download Resume (PDF)03. Get In Touch
I'm currently open to new opportunities. Whether you have a question, a project in mind, or just want to say hi — my inbox is always open.