Model-Based Co-Training for Multi-Agent RL
Opponent-aware, model-based co-training for multi-agent reinforcement learning — a learned model of how the other agents behave, planned against as they adapt. Co-authored manuscript in preparation.
Research
Bayes-HDC: Probabilistic Vector Symbolic Architectures
A probabilistic library that makes every hypervector a posterior distribution — an algebra of uncertainty for hyperdimensional computing, with closed-form moment propagation, calibrated predictions, and coverage-guaranteed prediction sets.
Safety for Autonomous UAV Swarms
A survey of safety and verification methods for AI-driven UAV swarms — reliability, anomaly detection, formation control, and test strategies. NSF-funded; accepted at the IEEE S&P SecureTrans Workshop.
Projects
USC Formula SAE Telemetry Platform
Real-time telemetry for USC's Formula SAE racecar — live sensor data off the car's MoTeC data-acquisition hardware, over its telemetry radio, to a live dashboard; plus role-scoped config and an LDX watcher that re-injects values MoTeC strips from its .ldx files. Hardware to software: DAQ, telemetry, Next.js/FastAPI/WebSockets.
Error-Related Potentials for Brain-Computer Interfaces
A BCI that decodes error-related potentials (ErrP) from EEG and turns them into a reinforcement signal — so an agent can learn to map neural activity to actions. EEG detection at ~76% within-subject; built with NeuroTech@USC, runner-up at the 2026 intercollegiate BCI Competition at UC Berkeley.
Experience
SRSE
Incoming Research Intern · SRSE, UIUC
Summer 2026Incoming summer research with Prof. Saikat Dutta (Cornell).
Graduate Research Assistant · USC RESL
Spring 2026 – PresentRobotic Embedded Systems Lab — multi-agent reinforcement learning: opponent-aware, model-based co-training (a latent model of other agents' strategies, planned against as they adapt). Also robustness/safety testing for autonomous-driving perception (anomaly detection on Waymo/KITTI/nuScenes, LiDAR–camera fusion).
Founding Engineer (Intern) · Forge (YC W24)
2024, 2025FastAPI backend and Next.js frontend serving 100+ restaurant chains; built the automated testing and CI/CD pipeline.
Undergraduate Research Assistant · AIEA Lab, UC Santa Cruz
2022 – 2024AI Explainability & Accountability Lab — interpretability and accountability methods for machine-learning systems.
NSF Research Intern · Embry-Riddle Aeronautical University
Summer 2023Algorithmic safety for autonomous drone swarms with Prof. Yongxin Liu — the work behind the UAV-swarm safety survey above.
DRS
Hardware Engineering Co-op · DRS Daylight Solutions
2021–2022Led a 6-person team building a cable impedance tester; optimized quantum-cascade-laser controller SDKs.
Writing
Notes on Physics-Informed Neural Networks
Living doc
Why PDE constraints work as inductive bias, and where the framing strains.
Black Swan
Essay
On rare events, fragility, and what models miss.
The Unaccounted Variable
Essay
Systems thinking through the lens of what the model leaves out.
Honors
2023
D.E. Shaw Fellow
2023
NSF REU — Selected (Embry-Riddle)