My academic research across network measurement, agentic network experimentation, and computer vision.
I am currently researching WebRTC, L4S, and DualPI2 implementations. I will also be at the IETF to learn more about how these systems are being implemented and used.
The lab published a user-space DualPI2 module for Mahimahi in ACM SIGCOMM CCR.
I second-authored the DualPI2 paper, validated Mahimahi's fidelity against the Linux kernel with time-series and nonparametric analysis, and built concurrent network experiments with Linux namespaces and traffic control.
The lab studies computer vision and 3D reconstruction.
I built a 3D Gaussian Splatting cleanup pipeline using geometric constraints and lineage pruning. I am now studying how agents interact with 3D Gaussians, including how memory, tools, and the action space affect scene cleanup.
The project uses agents to run browser and desktop tasks under controlled home-network conditions.
I separated orchestration, sandboxed network environments, agent services, and tool execution, then built Kubernetes orchestration for agents running on dedicated VMs with configured bottleneck queues.