Research
Research Directions
An overview of my research directions at the intersection of machine learning and scientific discovery, spanning AI-driven analog and RF circuit design, lipid nanoparticle engineering, generative AI, and financial machine learning.
AI-Driven Analog and RF Circuit Design
I develop machine learning methods for automating analog and RF circuit design across the design pipeline, including topology exploration, benchmarking, inverse design, electromagnetic modeling, physical synthesis, and intelligent design automation. My research combines graph learning, physics-aware machine learning, and optimization to accelerate circuit development while improving scalability and design quality.
AI-Driven Lipid Nanoparticle Design
My research in AI-driven drug delivery focuses on predictive and generative machine learning methods for lipid nanoparticle engineering. I study interpretable modeling, biodistribution prediction, targeted delivery, and AI-guided design with the goal of building reliable computational tools that accelerate the development of next-generation therapeutic delivery systems.
Generative AI and Large Language Models
My work in generative AI focuses on improving the reliability, controllability, and efficiency of modern AI systems. I study test-time steering, uncertainty-aware decision making, adaptive inference, and scalable generation methods that help models produce more dependable outputs while balancing quality and computational cost.
AI for Financial Systems
I apply modern machine learning methods to financial forecasting and intelligent decision-making in dynamic markets. My work explores sequence modeling, state-space models, and robust time-series learning for applications such as cryptocurrency prediction, financial analysis, and algorithmic trading.