Research interests: AI/ML methods for everything, numerical modeling of physical processes. @ MSU
Stars
Minimal reproduction of DeepSeek R1-Zero
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Code for our paper "Hamiltonian Neural Networks"
ML for finance and forecasting (LSTM, RL and BIMT)
NNQS for the Klein--Gordon--Fock equation
Fork of codebase from Miles Cranmer's GitHub
Brain-Inspired Modular Training (BIMT), a method for making neural networks more modular and interpretable.