TabICLv2: A state-of-the-art tabular foundation model

PluRel: Synthetic Data unlocks Scaling Laws for Relational Foundation Models

MLE-bench is a benchmark for measuring how well AI agents perform at machine learning engineering

The Declarative Data Generator

A holistic framework for advancing LLMs as data science agents

Comprehensive open-source library of AI research and engineering skills for any AI model. Package the skills and your claude code/codex/gemini agent will be an AI research agent with full horsepowe…

LimiX: Unleashing Structured-Data Modeling Capability for Generalist Intelligence https://arxiv.org/abs/2509.03505

A practical guide to diffusion models, implemented from scratch.

[NeurIPS 2025] Tracking and Understanding Object Transformations

A largely incomplete but hopefully useful list of links to datasets for relational learning and inductive logic programming. No guarantees on availability.

Relational Transformer: Toward Zero-Shot Foundation Models for Relational Data

GraphPFN: A Prior-Data Fitted Graph Foundation Model

A model zoo for Grounding-DINO-based open-world detection models.

This repository is for tracking issues, feature requests, and feedback for KumoRFM.

🔬 MCP server to query KumoRFM in your agentic flows

Tabular Deep Learning Library for PyTorch

This is a curated list of research on diffusion models for tabular data, and serves as the official repository for the survey paper "Diffusion Models for Tabular Data: Challenges, Current Progress,…

[WIP] Resources for AI engineers. Also contains supporting materials for the book AI Engineering (Chip Huyen, 2025)

🌐 Make websites accessible for AI agents. Automate tasks online with ease.

[ICCV 25] The official repository of paper 'Detection, Pose Estimation and Segmentation for Multiple Bodies: Closing the Virtuous Circle'

ReDeLEx is a Python framework for developing and evaluating RDL models on relational databases via RelBench and CTU datasets.

personal website

RelBench: Relational Deep Learning Benchmark

🦀 Small exercises to get you used to reading and writing Rust code!

[Pytorch] Generative retrieval model using semantic IDs from "Recommender Systems with Generative Retrieval"

A comprehensive toolkit and benchmark for tabular data learning, featuring 35+ deep methods, more than 10 classical methods, and 300 diverse tabular datasets.

(ICLR 2025 Spotlight) TabReD: Analyzing Pitfalls and Filling the Gaps in Tabular Deep Learning Benchmarks

Minimal sequential neural network written in Rust.

Jan is an open source alternative to ChatGPT that runs 100% offline on your computer.