Replication code and data for the journal article titled "The Mixed Subjects Design: Treating Large Language Models as Potentially Informative Observations."

[ICLR 2025] Self-Normalized Resets for Plasticity in Continual Learning

A framework for collecting and analyzing prediction market data, including the largest publicly available dataset of Polymarket and Kalshi market and trade data.

JAxtar is a project with a JAX-native implementation of parallelizeable A* & Q* solver for neural heuristic search research.

JAX - A curated list of resources https://github.com/google/jax

🐹 Deep clean and optimize your Mac.

Implementation of Physics-Informed Diffusion Models (ICLR 2025)

Jane Street quant interview/test

A python package for causal inference in panels

System for Trading S&P 500 Daily Brackets on Kalshi Prediction Markets

Official PyTorch implementation for ICLR2025 paper "Scaling up Masked Diffusion Models on Text"

A course on aligning smol models.