About Me
My name is Jesse (Vanderbilt PhD ‘24). I am an assistant professor at Tennessee Tech University where I lead the language and artificial intelligence research (LAIR) group.
I study how neural networks, and language models in particular, learn and reason. I also put that understanding to work on real problems, from helping keep endangered languages alive to detecting tornadoes.
- Deep learning fundamentals
- Large language models
- Cherokee language revitalization
- Spiking neural networks Emerging
- Tornado detection Emerging
More on each area, with papers and press, is on the Research page.
I am currently accepting applications for master’s and Ph.D. students. If you are a curious person with an interest in solving real problems and exploring untrodden paths through AI then feel free to reach out via email!
Introduction to LLMs
For those interested in learning more about LLMs, I have put together a reading list here! It’s the backbone of my graduate seminar on LLMs, CSC 7970, where you can see the papers week by week.
Interactive Tools
I build browser-based tools for teaching machine learning. The main one is Torch Canvas, where you draw a neural network as a diagram and get the PyTorch code (and can go the other way, from code to diagram). For example, here is a full LLM:
Open Llama 2 7B in Torch Canvas
See everything it can open, from a 10-layer MLP to Qwen2.5-VL, or browse more tools and demos on the Learn page.
Goals
Here you’ll find papers, work in progress, and whatever I’m up to (usually running/climbing, reading, and writing).
I think of goals like completing a thru hike. To reach an objective, you need to minimize zero days. To do that I track progress publicly and below there a set of widgets that show my progress.
