Ava Kouhana
MS Student — Stanford ICME · Computational & Mathematical Engineering
I am completing my ICME master's at Stanford, graduating in June 2026. At Stanford, I research Reinforcement Learning and World Models in Professor Gordon Wetzstein's lab. 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.
Email
LinkedIn
GitHub
Scholar
Publications
Projects
CoverAgent — Multi-Agent Collision in Responsibility Attribution
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.
Residual RL with Uncertainty for Dexterous Manipulation
Analyzed interaction between imitation learning and residual RL, showing that increased data can degrade performance.
Blog
CoverAgent: Responsibility Attribution Under Pressure to Conceal
A behavioral evaluation for whether AI assistants preserve accurate responsibility attribution when another agent pressures them to conceal fault.
PiDMASound: Bare-Metal Audio on a Raspberry Pi
Turning a single 1-bit GPIO pin into analog audio on bare metal — sigma-delta modulation, DMA, PWM, and interrupts.
Grants & Awards
- Recipient of 2024 IEEE Nuclear Science, Medical Imaging Trainee Grant (NSS MIC)
- 2nd place Outstanding Poster at the 20th Anniversary of ICME Stanford Research Symposium