User-friendly AI Interface (Supports Ollama, OpenAI API, ...)

Fully open reproduction of DeepSeek-R1

Deep Large-Scale Inference UsingKnockoffs

Tigramite is a python package for causal inference with a focus on time series data. The Tigramite documentation is at

Code for the paper: Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data

Instructions for setting up a SLURM cluster using Ubuntu 18.04.3 with GPUs.

A python library for user-friendly forecasting and anomaly detection on time series.

Code for the paper "Causal Transformer for Estimating Counterfactual Outcomes"

Code for a multi-agent particle environment used in the paper "Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments"

Neural Laplace: Differentiable Laplace Reconstructions for modelling any time observation with O(1) complexity.

Deep learning tool to find brand logos in everyday pictures

General purpose sound recognition demo

Self-Supervised Learning by Cross-Modal Audio-Video Clustering (NeurIPS 2020)

Reference implementation of Finite Element Networks as proposed in "Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks" at ICLR 2022

A PyTorch toolbox for domain generalization, domain adaptation and semi-supervised learning.

Code and website related to the eICU Collaborative Research Database

Official code for "Federated Multi-Task Learning under a Mixture of Distributions" (NeurIPS'21)

Jittor is a high-performance deep learning framework based on JIT compiling and meta-operators.

Python Dynamic Mode Decomposition

Flexible and powerful tensor operations for readable and reliable code (for pytorch, jax, TF and others)

This proposal has been replaced by the Topics API.

Fit interpretable models. Explain blackbox machine learning.

Official Code Repo for the Paper: "How does This Interaction Affect Me? Interpretable Attribution for Feature Interactions", In NeurIPS 2020

Multi-agent Trajectory Prediction with Fuzzy Query Attention

Count the MACs / FLOPs of your PyTorch model.

FEDML - The unified and scalable ML library for large-scale distributed training, model serving, and federated learning. FEDML Launch, a cross-cloud scheduler, further enables running any AI jobs o…

Perform data science on data that remains in someone else's server

Locally Private Graph Neural Networks (ACM CCS 2021)

Continuous builder and binary build scripts for pytorch