Moonshine: Industry-leading speech recognition models for edge devices
I'm a core contributor to these speech-to-text models released by Moonshine AI. They're 5x faster than Whisper with higher accuracy!
Teaching things to think: Bootstrapping on-device reasoning for smart devices
How can you train smart devices to reason about their actions and state? That's what I investigated in this IEEE PerCom '25 paper.
Sasha: Introducing LLMs for reasoning in smart homes
I built the first LLM-powered smart home, then published the results in this ACM IMWUT paper. I was honored to receive an ACM Distinguished Paper Award for this work.
Using LLMs to control a smart home
Experimenting with GPT models to build a smarter smart home assistant.
Leveraging data to conserve water resources
A report on my summer project with NMED and the City of Rio Rancho's water utility, where I repurposed billing data for conducting geospatial water use analysis.
