I'm Yanlai. I'm doing a master's in ECE at Rowan, working with Dr. Ying Tang. My day mostly sits between computer vision, multi-modal LLMs, and the front-end work that turns a research idea into a page someone can open in a browser.
The main thing right now is cockpit visual understanding: reading HUD gauges, sectional charts, weather radar, and traffic scenes the way a pilot would. Alongside that I work on PING, putting LLM peer agents inside learning games, and I keep a handful of small web tools online because people still use them.
Before Rowan I did a BS in AI at Chongqing Jiaotong University and spent most of a year at Lenovo writing OCR and handwriting-recognition pipelines. I write things up when I've figured something out worth writing down, and I put code online when someone else might use it.
