Solve puzzles. Improve your pytorch.

Bayesian active learning with EPIG data acquisition

Helps you write algorithms in PyTorch that adapt to the available (CUDA) memory

A general-purpose, deep learning-first library for constrained optimization in PyTorch

Conditional Flow Matching using JAX

Coverage tests to check the quality of your posterior estimators.

SWE-agent takes a GitHub issue and tries to automatically fix it, using GPT-4, or your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2…

💎 A curated list of awesome Competitive Programming, Algorithm and Data Structure resources

Software design principles for machine learning applications

Pytorch-like dataloaders in JAX.

Modern C++ order matching engine

Automated molecular dynamics simulations workflow for high-throughput assessment of protein-ligand dynamics

Hardware accelerated, batchable and differentiable optimizers in JAX.

Optimal transport tools implemented with the JAX framework, to get differentiable, parallel and jit-able computations.

This repository contains a collection of resources and papers on Diffusion Models for RL, accompanying the paper "Diffusion Models for Reinforcement Learning: A Survey"

TorchCFM: a Conditional Flow Matching library

Implicit Deep Adaptive Design (iDAD): Policy-Based Experimental Design without Likelihoods

Platform to experiment with the AI Software Engineer. Terminal based. NOTE: Very different from https://gptengineer.app

Small Python library to automatically set CUDA_VISIBLE_DEVICES to the least loaded device on multi-GPU systems.

Equivariant Steerable CNNs Library for Pytorch https://quva-lab.github.io/escnn/

Interact with your documents using the power of GPT, 100% privately, no data leaks

Chat with your database (SQL, CSV, pandas, polars, mongodb, noSQL, etc). PandasAI makes data analysis conversational using LLMs (GPT 3.5 / 4, Anthropic, VertexAI) and RAG.

A list of totally open alternatives to ChatGPT

Differentiable, Hardware Accelerated, Molecular Dynamics

GPT powered Zsh completion script

A playbook for systematically maximizing the performance of deep learning models.

Normalizing flows in PyTorch