Bio
I completed my MS and BS in Computer Science from the College of Information and Computer Sciences at the University of Massachusetts.
Interests
I am focused on developing intelligent systems that support scientific innovation by enhancing how researchers explore, reason, and generate new knowledge. My work investigates how AI can assist scientists with tasks such as knowledge retrieval, symbolic generation, and data analysis, while ensuring these systems are robust, safe, and aligned with human values. To achieve this, I'm driven towards improving algorithms for building AI tools, learning about their current limitations, and designing systems that can operate effectively under limited information or resource constraints. My aim is to create decision-making systems that empower scientists to uncover insights and drive progress in their fields. Some of my other fun interests include computer vision, game-playing AI, and robotics.
Works
MiGrATe: Mixed-Policy GRPO for Adaptation at Test-TimeResearch on doing Test-Time Training via GRPO
Personalizing RLHF with Variational Preference LearningReplication research on personalizing RLHF
Generative Models & Games for Offline IRLResearch on achieving SOTA results for Offline IRL
Staying Consistent with GradCAMResearch on improving consistency with grad-CAM
Linux Rice V2.5: ags + AICustom Linux Desktop Setup (2024 update)
Quality Diversity for Texas Hold'EmAI Poker playing agent using RL
GraphPDFElectron app for managing a PDF library
Emoji DoodlerCNC Drawing Machine w/ Facial Recognition
Linux Rice V2: HyprlandCustom Linux Desktop Setup
KanvasWireFull Stack CRUD App
Neovim ConfigPersonal Development Environment
Black Hole KicksResearch on Black Hole Mergers