MLCB 2024
Santa Clara, CA
Santa Clara, CA
A scrubbable political map of the world from 3000 BCE to today, with thousands of dated events pinned to it, from ancient battles to the Second World War and the Gulf War. Drag the timeline, zoom into a single day, and click a region or a marker for the story. Borders are approximate and the event data is still being checked.
A solar system simulator. Initially you can see the planets where they are right now in real time, and you can change the date and speed to see orbits and positions. As you explore and zoom around, you can find details about the different planets, switch into True Scale mode to see real physical sizes and distances, and then zoom all the way out to the nearest star systems such as Alpha Centauri, Barnard's Star, and TRAPPIST-1 to see some known exoplanets.
Which open-weight model is the best on an RTX 3060 (12GB)? An ongoing hunt across models and settings: official vs. abliterated weights, thinking mode on vs. off. As small models keep closing the gap on bigger ones, we'll chart that here too.
A financial calculator for renting or buying a property. Click any property in the US for estimated rent and buying costs, and see which is the better financial choice over time. Mortgage rates, appreciation, market returns, saving discipline, and more are all factored in.
I completed my Ph.D. in Computer Science at Oregon State University in 2022.
I was advised by David Hendrix and Liang Huang. We studied how algorithms paired with deep learning models (such as RNNs and Transformers) can predict structures from RNA and Protein sequences, as well as how they can encode syntax in human languages.
For my masters at CMU, I worked with Jaime Carbonell and Anatole Gershman to build a virtual assistant for self-driving cars, and I worked with Roni Rosenfeld on the Polly Telephone system, where I built and deployed telephone applications that spread messages about Ebola to people in affected West African countries.
I worked with my undergrad advisor Jason Eisner on Transition-Based Dependency Parsing, trying to introduce backtracking to an Arc-Eager Transition-Based Dependency Parser.
I am generally interested in developing algorithms for Structured Prediction tasks in sequences.
MLCB 2024
ACL 2018
SLaTE 2015
TLT 2014