Illico is a python library performing fast and lightweight wilcoxon rank-sum tests for single-cell RNASeq.

Code and manuscript for "Efficient Per-Example Gradient Computations in Convolutional Neural Networks"

Puffing up reinforcement learning

Fast and modular sklearn replacement for generalized linear models

Time-Series-Optimized Transformer for Observability

A simple and efficient Mamba implementation in pure PyTorch and MLX.

🐒 🔥 Datadog Failure Injection System for Kubernetes

Pruna is a model optimization framework built for developers, enabling you to deliver faster, more efficient models with minimal overhead.

A federated implementation of PyDESeq2, based on Substra.

Fast implementation of survival analysis models (CoxPH, WCE...) with GPU support, for R and Python.

LLM KV cache compression made easy

Moshi is a speech-text foundation model and full-duplex spoken dialogue framework. It uses Mimi, a state-of-the-art streaming neural audio codec.

Python script that downloads all pubmed abstracts corresponding to user-specified keyword searches, by performing automated NCBI E-utility queries

A collaborative learning framework for empowering biomedical research

Domain adaptation toolbox compatible with scikit-learn and pytorch

[IJCAI 2024] Redefining Contributions: Shapley-Driven Federated Learning

A library for mechanistic interpretability of GPT-style language models

Suno AI's Bark model in C/C++ for fast text-to-speech generation

Code repository associated with the FedECA article

A blazing fast inference solution for text embeddings models

Code associated to the publication: Scaling self-supervised learning for histopathology with masked image modeling, A. Filiot et al., MedRxiv (2023). We publicly release Phikon 🚀

👋 Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)

Implementation of the SRATTA paper

GrAIdient is a deep learning framework that aims at challenging the way we train and run models.

scikit-learn: machine learning in Python