Marco

andrej-karpathy-skills. A single CLAUDE.md file to improve Claude Code behavior, derived from Andrej Karpathy's observations on LLM coding pitfalls.

SymbolicRegressionToolkit. Toolkit for symbolic regression/equation discovery

ICLR26-GenSR. [ICLR26]GenSR: Symbolic regression based on equation generative space

ds4. DeepSeek 4 Flash and PRO local inference engine for Metal, CUDA and ROCm

integrated-qsp-vpop-onco-efficacy-CPT-PSP. Code for the manuscript "An integrated quantitative systems pharmacology virtual population approach for calibration with oncology efficacy endpoints."

SMAC3. Python

IPBT. A Population Based Training variant for hyperparameter optimization that efficiently adjusts its step size via task-agnostic restarts

tolaria. Desktop app to manage markdown knowledge bases

ml-intern. 🤗 ml-intern: an open-source ML engineer that reads papers, trains models, and ships ML models

symbolic_regression.rs. Rust + WebAssembly port of SymbolicRegression.jl

Python-M3GP. An easy-to-use scikit-learn inspired implementation of the Multidimensional Multiclass Genetic Programming with Multidimensional Populations (M3GP) algorithm

PSE. Official PyTorch implementation of PSE/PSRN: Fast and efficient symbolic expression discovery through parallelized symbolic enumeration. Evaluates millions of expressions simultaneously on GPU with automated subtree reuse.

symregg. Python bindings for SymRegg

SciExplorer. Repository for the SciExplorer framework. SciExplorer builds on LLM APIs to create artificial scientist agents that can explore unknown systems by controlling experiments and running analysis code.

meal-lab. Create delicious meal plans using Linear Optimization

ShinkaEvolve. ShinkaEvolve: Towards Open-Ended and Sample-Efficient Program Evolution 🧬

llm-srbench. [ICML2025 Oral] LLM-SRBench: A New Benchmark for Scientific Equation Discovery with Large Language Models

awesome-genetic-programming. Curated list of resources about Genetic Programming

particles.js. A lightweight JavaScript library for creating particles

PBT-Zoo. Population Based Training variants - Comparison and analysis | TMLR

AIX360. Interpretability and explainability of data and machine learning models

taipy. Turns Data and AI algorithms into production-ready web applications in no time.

giskard-oss. 🐢 Open-Source Evaluation & Testing library for LLM Agents

dragonfly_gen. De novo drug design with deep interactome learning

pykan. Kolmogorov Arnold Networks

LLM-SR. [ICLR 2025 Oral] This is the official repo for the paper "LLM-SR" on Scientific Equation Discovery and Symbolic Regression with Large Language Models

plip. Pathology Language and Image Pre-Training (PLIP) is the first vision and language foundation model for Pathology AI (Nature Medicine). PLIP is a large-scale pre-trained model that can be used to extract visual and language features from pathology images and text description. The model is a fine-tuned version of the original CLIP model.

Trial2Vec. Findings of EMNLP'22 | Trial2Vec: Zero-Shot Clinical Trial Document Similarity Search using Self-Supervision

PyTrial. PyTrial: A Comprehensive Platform for Artificial Intelligence for Drug Development

lifted. Python

clinical-trial-outcome-prediction. benchmark dataset and Deep learning method (Hierarchical Interaction Network, HINT) for clinical trial approval probability prediction, published in Cell Patterns 2022.

guidance. A guidance language for controlling large language models.

TableDiffusion. The first differentially-private diffusion model for tabular data

litellm. Python SDK, Proxy Server (AI Gateway) to call 100+ LLM APIs in OpenAI (or native) format, with cost tracking, guardrails, loadbalancing and logging. [Bedrock, Azure, OpenAI, VertexAI, Cohere, Anthropic, Sagemaker, HuggingFace, VLLM, NVIDIA NIM]

gradio. Build and share delightful machine learning apps, all in Python. 🌟 Star to support our work!

TinyLlama. The TinyLlama project is an open endeavor to pretrain a 1.1B Llama model on 3 trillion tokens.

azure-open-ai-embeddings-qna. A simple web application for a OpenAI-enabled document search. This repo uses Azure OpenAI Service for creating embeddings vectors from documents. For answering the question of a user, it retrieves the most relevant document and then uses GPT-3, GPT-3.5 or GPT-4 to extract the matching answer for the question.

Llama-2-Onnx. Python

unstructured. Convert documents to structured data effortlessly. Unstructured is open-source ETL solution for transforming complex documents into clean, structured formats for language models. Visit our website to learn more about our enterprise grade Platform product for production grade workflows, partitioning, enrichments, chunking and embedding.

SpanMarkerNER. SpanMarker for Named Entity Recognition

interpretable-ml-book. Book about interpretable machine learning

open_llama. OpenLLaMA, a permissively licensed open source reproduction of Meta AI’s LLaMA 7B trained on the RedPajama dataset

ResponsibleAIAccelerator. Repo to hold examples of responsible model assessment for a variety of different verticals such as healthcare and financial services

LLM-Adapters. Code for our EMNLP 2023 Paper: "LLM-Adapters: An Adapter Family for Parameter-Efficient Fine-Tuning of Large Language Models"

GOMEA. Library for optimization with the model-based evolutionary algorithm GOMEA (Gene-pool Optimal Mixing Evolutionary Algorithm)

gpt-engineer. CLI platform to experiment with codegen. Precursor to: https://lovable.dev

llm-foundry. LLM training code for Databricks foundation models

llama.cpp. Port of Facebook's LLaMA model in C/C++

MO-PBT. An algorithm for multi-objective hyperparameter optimization: Multi-Objective Population Based Training (MO-PBT), ICML 2023

falcon.cpp. (not yet working) ggml implementation for falcon

simple-chatgpt-chat-streaming-demo. A Node.JS chat demo where the chat streams to the browser.

auto-evaluator. TypeScript

composer. Supercharge Your Model Training

pandas-ai. Chat with your database or your datalake (SQL, CSV, parquet). PandasAI makes data analysis conversational using LLMs and RAG.

pysr_paper. A paper describing the implementation of PySR and SymbolicRegression.jl

SF-GOMENAS. Python

langchain. The agent engineering platform.

The-HustleGPT-Challenge. Building Startups with an AI Co-Founder

AutoGPT. AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

codealpaca. Python

multi_objective_learning. Python

annotated_deep_learning_paper_implementations. 🧑‍🏫 60+ Implementations/tutorials of deep learning papers with side-by-side notes 📝; including transformers (original, xl, switch, feedback, vit, ...), optimizers (adam, adabelief, sophia, ...), gans(cyclegan, stylegan2, ...), 🎮 reinforcement learning (ppo, dqn), capsnet, distillation, ... 🧠

trl. Train transformer language models with reinforcement learning.

PhySO. Physical Symbolic Optimization

ITEA. Interaction-Transformation Evolutionary Algorithm

robust-CE. Generate robust counterfactual explanations for machine learning models

chatgpt-failures. Failure archive for ChatGPT and similar models

Open-Assistant. OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.

TabularBenchmarks. Jupyter Notebook

SciMED. A computational framework for finding symbolic expressions from physical datasets.

Crash_course_on_RL. This is a self-contained repository to explain two basic Reinforcement (RL) algorithms.

Awesome-explainable-AI. A collection of research materials on explainable AI/ML

CFAI. A collection of algorithms of counterfactual explanations.

rils-rols. RILS-ROLS: Robust Symbolic Regression via Iterated Local Search and Ordinary Least Squares

Dreambooth-Stable-Diffusion. Implementation of Dreambooth (https://arxiv.org/abs/2208.12242) with Stable Diffusion

rome. Locating and editing factual associations in GPT (NeurIPS 2022)

memit. Mass-editing thousands of facts into a transformer memory (ICLR 2023)

stable-diffusion-videos. Create 🔥 videos with Stable Diffusion by exploring the latent space and morphing between text prompts

symbolicregression. SR based on LLMs.

stable-diffusion. Jupyter Notebook

git-gud. Wanna git gud? Then get git-gud, and git gud at git!

auto-sklearn. Automated Machine Learning with scikit-learn

OptiCL. An end-to-end framework for mixed-integer optimization with data-driven learned constraints.

AITemplate. AITemplate is a Python framework which renders neural network into high performance CUDA/HIP C++ code. Specialized for FP16 TensorCore (NVIDIA GPU) and MatrixCore (AMD GPU) inference.

pybind11. Seamless operability between C++11 and Python

CmdParser. A simple and lightweight command line parser using C++11.

pyoperon. Python bindings and scikit-learn interface for the Operon library for symbolic regression.

swig. SWIG is a software development tool that connects programs written in C and C++ with a variety of high-level programming languages.

nodevo. An implementation of Genetic Programming in Rust.

pyo3. Rust bindings for the Python interpreter

CGP-GOMEA. C++

evotorch. Advanced evolutionary computation library built directly on top of PyTorch, created at NNAISENSE.

fast_map-elites. The fastest MAP-Elites implementation?

SymbolicGWPopulation_paper. TeX

LovelyPlots. Matplotlib style sheets to nicely format figures for scientific papers, thesis and presentations while keeping them fully editable in Adobe Illustrator.

mimic3-benchmarks. Python suite to construct benchmark machine learning datasets from the MIMIC-III 💊 clinical database.

GeneticEngine. Program Synthesis framework that features heuristics methods (e.g., Genetic Programming) and grammars are defined in Python dataclasses

2dmrsim. 2-D Multi Robot Simulator

gpzgd. C

CMA-ES_with_Margin. (GECCO 2022) CMA-ES with Margin: Lower-Bounding Marginal Probability for Mixed-Integer Black-Box Optimization

srsd-benchmark. [DMLR] Rethinking Symbolic Regression Datasets and Benchmarks for Scientific Discovery

SAGE. [TDSC 2021] IntruSion alert-driven Attack Graph Extractor. https://ieeexplore.ieee.org/document/9557854

awesome-actions. A curated list of awesome actions to use on GitHub

feat. A feature engineering automation tool for learning data representations

CARLA. CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithms

ML-Notebooks. :fire: Machine Learning Notebooks

sentence-transformers. State-of-the-Art Embeddings, Retrieval, and Reranking

CoronaVirusModel. Python

ENCAS. Neural Architecture Search + Cascades | Best Paper @ GECCO 2022

gplearn. Genetic Programming in Python, with a scikit-learn inspired API

fanova. Functional ANOVA

racer. Black-box, gradient-free optimization of car-racing policies.

gp-benchmarks. Genetic Programming benchmarks analysis

genetic-drawing. A genetic algorithm toy project for drawing

Procedural-painting. Procedural painting algorithms in Unity 3d with compute shaders based on genetic evolution algorithms

chriscummins.github.io. Data for my personal website

srbench. A living benchmark framework for symbolic regression

dolos. :detective: Source code plagiarism detection

pycma. Python implementation of CMA-ES

PySR. High-Performance Symbolic Regression in Python and Julia

GerryFair. library for fair auditing and learning of classifiers with respect to rich subgroup fairness.

alibi. Algorithms for explaining machine learning models

truce. Python

interpret. Fit interpretable models. Explain blackbox machine learning.

LORE. LOcal Rule-based Exlanations

Laplace. Laplace approximations for Deep Learning.

genetic-programming. Symbolic regression solver, based on genetic programming methodology.

L0_regularization. Learning Sparse Neural Networks through L0 regularization

PaCMAP. PaCMAP: Large-scale Dimension Reduction Technique Preserving Both Global and Local Structure

BinaryGOMEA. The most recent and best-performing version of the Gene-pool Optimal Mixing Eovlutionary Algorithm

featureform. The Virtual Feature Store. Turn your existing data infrastructure into a feature store.

language-models-are-knowledge-graphs-pytorch. Language models are open knowledge graphs ( non official implementation )

gpmallt. Code for GP-MaL-LT, IEEE Transactions on Evolutionary Computation 2021.

Mem2Seq. Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems

NeuralSymbolicRegressionThatScales. Source code and Dataset creation for the paper "Neural Symbolic Regression That Scales"

covid-chestxray-dataset. We are building an open database of COVID-19 cases with chest X-ray or CT images.

vstat. SIMD-enabled descriptive statistics (mean, variance, covariance, correlation)

dcgp. Implementation of a differentiable CGP (Cartesian Genetic Programming)

imodels. Interpretable ML package 🔍 for concise, transparent, and accurate predictive modeling (sklearn-compatible).

SAGOMEA. SAGOMEA is an efficient surrogate-assisted Evolutionary Algorithm for combinatorial (discrete) optimization problems with expensive fitness functions.

git-blame-someone-else. Blame someone else for your bad code.

TensorGP. A vectorized approach to Genetic Programming

SymbolicRegression.jl. Distributed High-Performance Symbolic Regression in Julia

dataset-sts. Semantic Text Similarity Dataset Hub

symbolic_deep_learning. Code for "Discovering Symbolic Models from Deep Learning with Inductive Biases"

SentEval. A python tool for evaluating the quality of sentence embeddings.

Information-Retrieval. Information Retrieval algorithms developed in python. To follow the blog posts, click on the link:

slides. Slides of my talks and lectures

operon. C++ Large Scale Genetic Programming

2dhmsr. Java framework for experimenting with a 2-D version of the voxel-based soft robots.

COVID19_metadata. Interoperable secondary data for research on the new COVID-19 coronavirus sars-cov-2

GazeTracking. 👀 Eye Tracking library easily implementable to your projects

evolved-ge. Java

jgea. Java General Evolutionary Algorithm (jgea) is a modular Java framework for experimenting with Evolutionary Computation.

SupContrast. PyTorch implementation of "Supervised Contrastive Learning" (and SimCLR incidentally)

lipizzaner-gan. [AAAI 2018] "Towards distributed coevolutionary GANs" by Abdullah Al-Dujaili, Tom Schmiedlechner, Erik Hemberg, Una-May O'Reilly

dlib. A toolkit for making real world machine learning and data analysis applications in C++

CS-GOMEA. Source code for the paper "Convolutional neural network surrogate-assisted GOMEA"

moc. Multi-Objective Counterfactuals

AI-Feynman. Python

Torch.NET. .NET bindings for PyTorch. Machine Learning with C# / F# with Multi-GPU/CPU support

fair_gp. Genetic programming approaches to learning fair classifiers

AIF360. A comprehensive set of fairness metrics for datasets and machine learning models, explanations for these metrics, and algorithms to mitigate bias in datasets and models.

naszilla. Naszilla is a Python library for neural architecture search (NAS)

autokeras. AutoML library for deep learning

nascell-automl. Python

nasbench. NASBench: A Neural Architecture Search Dataset and Benchmark

MacroNAS. Source code for reproducing experiments in "Local Search is a Remarkably Strong Baseline for Neural Architecture Search" (2020)

MacroNASBenchmark. Benchmarks for Macro Neural Architecture Search; used and described in the paper "Local Search is a Remarkably Strong Baseline for Neural Architecture Search", https://arxiv.org/abs/2004.08996

GPFormulasInterpretability. Meta-learning approach for human-interpretable formulas generation

nsga-net. NSGA-Net, a Neural Architecture Search Algorithm

brain-tokyo-workshop. 🧠🗼

ML-From-Scratch. Machine Learning From Scratch. Bare bones NumPy implementations of machine learning models and algorithms with a focus on accessibility. Aims to cover everything from linear regression to deep learning.

Face-and-Emotion-Recognition. Realtime person's face recognize and can classify emotion using webcam, video or images.

face_recognition. The world's simplest facial recognition api for Python and the command line

PyTorch-GAN. PyTorch implementations of Generative Adversarial Networks.

mlpack. mlpack: a fast, header-only C++ machine learning library

HillVallEA. Hill-Valley Evolutionary Algorithm (GECCO2018)

pmlb. PMLB: A large, curated repository of benchmark datasets for evaluating supervised machine learning algorithms.

mimic-code. MIMIC Code Repository: Code shared by the research community for the MIMIC family of databases

LSHBOX. A c++ toolbox of locality-sensitive hashing (LSH), provides several popular LSH algorithms, also support python and matlab.

RegexGenerator. This project contains the source code of a tool for generating regular expressions for text extraction: 1. automatically, 2. based only on examples of the desired behavior, 3. without any external hint about how the target regex should look like