Portfolio

Computational Projects

Exploring Deep Segmentation Models for Brain Tumors: CNNs, Transformers, and Promptable Architectures

Final project for Stanford's CS 231N: Deep Learning for Computer Vision (Spring 2025). Developed deep learning models for automated brain tumor segmentation using the BraTS 2021 dataset, comparing CNNs, transformers, and promptable architectures for pixel-level tumor detection.

Medical AI · Computer Vision · Deep Learning · Semantic Segmentation · Healthcare Technology

Computational Projects

Robust Brand Logo Detection Under Adversarial Conditions

Final report for Stanford's CS 131: Computer Vision (Winter 2025). Built a custom CNN with adversarial training to detect Coca-Cola logos under blur, noise, and occlusion. Achieved +13% accuracy over YOLOv8 with extensive data augmentation.

Computer Vision · Adversarial Robustness · Object Detection · Data Augmentation

Computational Projects

Heap Allocator

Final project for Stanford's CS 107 (Winter 2025). Implemented a full implicit + explicit free list allocator in C, including malloc, free, and realloc. Built debugging utilities (validate_heap, dump_heap) and stress-tested on real allocation traces.

Systems Programming · Memory Management · C · Performance Optimization

Computational Projects

What's in the noise? Musical Genre Classification using Neural Networks

Final project for Stanford's CS 129 (Winter 2024). Trained VGG-style CNNs, GRUs, and LSTMs on mel spectrograms from GTZAN, incorporating noise, pitch-shift, and time-stretch augmentations for robustness.

Audio Classification · Deep Learning · CNNs · Music Information Retrieval

Computational Projects

Protecting Against Propaganda: AI for Misinformation Detection & Critical Thinking

Final project for Stanford's CS 197 (Winter 2024). Built a GPT-4–powered browser extension that detects persuasive fallacies in political news, provides real-time annotations, and generates "extremeness" scores. Ran a pilot RCT to evaluate behavioral impacts.

Human-AI Interaction · Politics & Psychology · Media Literacy · Language Models

AI Policy/Ethics

Seeing is Believing? A Sociotechnical Evaluation of Saliency Maps for Brain Tumor Segmentation

Final poster for Stanford's CS 281: Ethics of Artificial Intelligence (Spring 2025). Benchmarking Grad-CAM, Integrated Gradients, and GradientSHAP across segmentation models, combining quantitative evaluation with clinician + researcher feedback to assess clinical usability.

Explainable AI · Medical Imaging · Model Interpretability · Human-AI Interaction

AI Policy/Ethics

Governance of Frontier AI: Monitoring, Institutions, and Policy Transitions

Final research paper for the Stanford Existential Risks Initiative (SERI) Summer 2025. Examines how to govern frontier AI before catastrophic risks materialize, proposing risk-monitoring taxonomies, cross-lab oversight architectures, and pathways from voluntary commitments to binding regulation.

AI Governance · AI Safety · Policy · Institutional Design · Existential Risk

SERI