Current projects

Abstract diagram of an agent loop connecting code, measurement, and a microcontroller
P.02 Ongoing

Agentic MCU Kernel Optimization

Investigating whether language-model agents can help write, test, and refine the low-level kernels that make inference practical on microcontrollers.

  • Agentic systems
  • Code generation
  • Kernels
  • Edge AI
A note on results. These pages describe ongoing explorations. Performance numbers, dates, and outcomes are added only after they have been measured and can be reproduced. See the publication record for finished work.

Research directions

The projects are specific, but the questions overlap. These are the directions that connect them.

R.01

Efficient AI

Models and training methods that deliver useful capability within real compute, memory, and energy budgets.

R.02

Agentic systems

Language-model agents that can inspect a problem, use tools, test ideas, and improve software systems.

R.03

TinyML & edge AI

Always-on sensing and inference on microcontrollers and other devices at the far edge of the network.

R.04

Inference optimization

Kernels, memory layout, quantization, and deployment choices that make inference faster and more predictable.

Publications

Publication record

No peer-reviewed publications are listed yet.

The project pages are the most current record of the work. Published papers and preprints will be listed on the publications page when they exist.