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.

The easiest way to do motion tracking!

PyTorch implementation of differentiable Sphere Tracing / Ray Marching with SDFs (Signed Distance Function) and CSG (Constructive Solid Geometry).

Training a SpaceX-style rocket to land autonomously using reinforcement learning. Powered by Unity MLAgents.

Learning Continuous Signed Distance Functions for Shape Representation

Open3D: A Modern Library for 3D Data Processing

Machine learning framework for predicting the responses of drug combinations in pre-clinical studies, such as those based on cell lines or patient-derived cells.

TensorFlow implementation of an arbitrary order Factorization Machine

PyTorch implementation of the Covariate-GPLVM

A highly efficient implementation of Gaussian Processes in PyTorch

Gaussian Process Prior Variational Autoencoder

TCRGP, a novel Gaussian process method that can predict if TCRs recognize certain epitopes. This method can utilize different CDR sequences from both TCRα and TCRβ chains from single-cell data and …

Bayesian Convolutional Neural Network with Variational Inference based on Bayes by Backprop in PyTorch.