| Project | Description | |
|---|---|---|
| 📄 | Network World Models | A world model that learns how interventions spread through a network, used as a fast evaluator for a coding agent that designs network algorithms. Beats the strongest baseline in 138 of 141 settings across 8 tasks, with up to 14.5× faster rollouts than Monte Carlo. Under review at ICLR 2027 |
| 📄 | From Refusal Tokens to Refusal Control | Categorical steering vectors for fine-grained LLM refusal control. −13.7% over-refusal and +14.2% harmful-prompt refusal on Llama 3 8B with zero capability degradation. 🎉 NeurIPS 2025 MechInterp Workshop · COLM 2026 Actionable Interpretability Workshop 🎉 |
| 💠 | WaferDetect | Wafer-map defect detection platform for semiconductor fabs. A fine-tuned YOLO26x-seg model segments 21 overlapping defect classes (0.852 mask mAP@50), with Poisson/Stapper yield modeling, per-defect cost estimation, and KLARF import/export |
| 🖊️ | Sketch2Graphviz | Converts hand-drawn graph sketches into executable Graphviz DOT code using a LoRA fine-tuned Llama 3.2 11B Vision and RAG over a PostgreSQL/PGVector vector database, with a 97.96% render success rate |
| ⚙️ | AutoNeuroNet | Reverse-mode automatic differentiation engine and neural network library built from scratch in C++, published to PyPI with PyBind11 bindings and NumPy interoperability |
| 📰 | TruthGuard | AI-powered misinformation and fake news detection with a fine-tuned DistilBERT classifier, FastAPI backend, React web app, and published Chrome extension |
- 📄 First author of Network World Models as Environments for Algorithm Design on Complex Systems, under review at ICLR 2027 · arXiv:2610.01048
- 📄 First author of a paper on LLM safety and refusal steering, accepted to the NeurIPS 2025 Mechanistic Interpretability Workshop and the COLM 2026 Actionable Interpretability Workshop · arXiv:2603.13359
- 🥇 Winner of the 2023 Congressional App Challenge (Georgia's 5th District) with TruthGuard, an AI-powered fake news detector
- 🔬 ML Researcher at Emory University (Dr. Liang Zhao), working on network world models · Research Contributor at CMU LTI's WAVLab (Dr. Shinji Watanabe), working on contextual biasing for speech recognition
- 🤝 Co-founder & Executive Director of Science for Survival, a 501(c)(3) nonprofit that has impacted 700+ students across 3 continents
ML / AI
Systems & Backend
Frontend
Open to research collaborations and impactful AI projects. Reach out anytime.