Stanford University
Fall 2024–June 2026M.S. in Computational & Mathematical Engineering
Former MS Student — Stanford ICME · Computational & Mathematical Engineering
I completed my ICME master's at Stanford in June 2026. At Stanford, I conducted research on world models in Professor Gordon Wetzstein's lab and served as a teaching assistant for Machine Learning (CS229).
Prior to Stanford, I spent six months at Harvard with Dr. Mengyu Wang on image segmentation and vision-language models for medical imaging fairness, and another six months with Dr. Craig Levin applying latent diffusion models to PET image reconstruction.
More recently, I have been working on CoverAgent, a targeted behavioral evaluation harness designed to red-team multi-agent systems for collusion. It has produced some results I find especially interesting—read more on my blog.
M.S. in Computational & Mathematical Engineering
National School of Statistics and Economic Administration
Undergraduate degree in Applied Mathematics
Studying whether LLM agents preserve accurate responsibility attribution when a peer agent pressures them to obscure its own role in an incident. The harness probes how human-facing reports change under multi-agent peer pressure.
Analyzed interaction between imitation learning and residual RL, showing that increased data can degrade performance.
A behavioral evaluation for whether AI assistants preserve accurate responsibility attribution when another agent pressures them to conceal fault.
Turning a single 1-bit GPIO pin into analog audio on bare metal — sigma-delta modulation, DMA, PWM, and interrupts.
Get an email when I publish something new.