SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It solves 12.47% of bugs in the SWE-bench evaluation set and takes just 1 minute to run.

A library of Reversible Data Transforms

Synthetic data generation for tabular data

A machine learning library for detecting anomalies in signals.

State space and deep generative models for time series.

Data Lineage Tracing Library

Graph Algorithms

Synthetic Data Generation for mixed-type, multivariate time series.

Explain, analyze, and visualize NLP language models. Ecco creates interactive visualizations directly in Jupyter notebooks explaining the behavior of Transformer-based language models (like GPT2, B…

Benchmarking synthetic data generation methods.

Implementation of Transformer model (originally from Attention is All You Need) applied to Time Series.

An open source automl library for using machine learning in healthcare.