Theo Teske
Generative AI Engineer
Building scalable solutions at the cutting-edge of machine learning research.
Recent Blog Posts
How Fine-Tuning Warps the Hidden Geometry of Transformers
A transformer is trained to predict tokens, but in the process it learns something richer than a next-token probability distribution. It learns a geometry over tokens and contexts. Hidden states be...
Read more →
Fast Exponentiation and Modular Exponentiation
I give an exposition of both the fast exponentiation and modular exponentiation algorithms, then we apply the latter to the LeetCode problem 2438. Range Product Queries of Powers. The solution to t...
Read more →
Sample Technical Post Demonstrating Math and Code
This is a sample post demonstrating the technical capabilities of my Jekyll blog, including LaTeX math rendering and syntax-highlighted code blocks.
Read more →
Featured Projects
Neural Network Implementation from Scratch
A pure NumPy implementation of a deep neural network with backpropagation
FlowTaxi: Conditional Flow Matching for NYC Taxi Demand
A conditional continuous-time flow matching model that transports Gaussian noise into realistic NYC taxi drop-off hotspots via neural ODEs.