Foundation Models for Time Series

An implementation of model parallel autoregressive transformers on GPUs, based on the Megatron and DeepSpeed libraries

Tile primitives for speedy kernels

PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models

Minimal, fast + educational reimplementation of the TabICLv2 architecture

Tmux Plugin Manager

Pytorch library for fast transformer implementations

DeepTab is a Python package that simplifies tabular deep learning by providing a suite of models for regression, classification, and distributional regression tasks. It includes models such as Mamb…

An open, end-to-end implementation of TabPFN-like foundation models, covering synthetic priors/data, training, and evaluation on TabArena.

PyTorch implementation of TabNet paper : https://arxiv.org/pdf/1908.07442.pdf

Following research on S4 in jax

A cheatsheet of modern C++ language and library features.

A python module implementing interfaces for various public tabular priors

A Playground for Tabular Foundation Models

Code for "TabZilla: When Do Neural Nets Outperform Boosted Trees on Tabular Data?"

Lightweight and educational reimplementation of TabPFN https://arxiv.org/pdf/2511.03634

TempoPFN: Zero-shot Time Series Forecasting (accepted at EurIPS 2025 AI for Tabular Data Workshop)

Official repository for "TimePFN: Effective Multivariate Time Series Forecasting with Synthetic Data" (AAAI 2025).

All-in-one guide to getting a tech job abroad 🌎

OpenStock is an open-source alternative to expensive market platforms. Track real-time prices, set personalized alerts, and explore detailed company insights — built openly, for everyone, forever f…