Repository for TabICL: A Tabular Foundation Model for In-Context Learning on Large Data

Official PyTorch implementation of OTiS: An open model for general time series analysis.

TuneTables is a tabular classifier that implements prompt tuning for frozen prior-fitted networks.

Code for paper: Regression as Classification: Influence of Task Formulation on Neural Network Features

Zero-shot Time Series Forecasting with TabPFN (work accepted at NeurIPS 2024 TRL and TSALM workshops)

This is the official repository for "Unveiling the Potential of Text in High-Dimensional Time Series Forecasting" (Accepted by NeurIPS-24 TSALM Workshop)

A library of sklearn compatible categorical variable encoders

Hummingbird compiles trained ML models into tensor computation for faster inference.

Simba

A PyTorch library for implementing flow matching algorithms, featuring continuous and discrete flow matching implementations. It includes practical examples for both text and image modalities.

Implementation of "TS-JEPA"

This work introduces LaT-PFN, a novel time series model that combines PFN and JEPA frameworks to generate zero-shot forecasts efficiently, using a versatile latent space that enables adaptable tim…

Code for BLT research paper

Official Implementation of "Transformers Can Do Bayesian Inference", the PFN paper

Base classes for creating scikit-learn-like parametric objects, and tools for working with them.

⚡ TabPFN: Foundation Model for Tabular Data ⚡

Probabilistic time series modeling in Python

BAyesian Model-Building Interface (Bambi) in Python.

PyTorch implementation of "Rethinking the Power of Timestamps for Robust Time Series Forecasting: A Global-Local Fusion Perspective" (NeurIPS 2024)

Official implementation for "TimeXer: Empowering Transformers for Time Series Forecasting with Exogenous Variables" (NeurIPS 2024)

Neural Oblivious Decision Ensembles for Deep Learning on Tabular Data

Access to Sulie foundation models for time-series forecasting 📈

Official Implementation of "ADOPT: Modified Adam Can Converge with Any β2 with the Optimal Rate"

A unified framework for tabular probabilistic regression, time-to-event prediction, and probability distributions in python

A unified framework for machine learning with time series