yandex-research/rtdl resource

Health v2 · maintenance only

Adoption not part of the score

1158 stars · 124 forks observed · 2026-08-28

What it is AI-extracted, prompt v1, taxonomy v1, 2026-08-30, confidence not recorded

RTDL is a curated collection of research papers and accompanying Python/PyTorch packages on deep learning for tabular data from Yandex Research. It serves as a hub linking papers (TabM, TabR, TabDDPM, etc.) to their code implementations and successor packages.

Use cases

• find state-of-the-art deep learning models for tabular data
• reproduce tabular deep learning research papers
• benchmark neural networks against gradient boosting on tabular datasets
• get PyTorch implementations of FT-Transformer and MLP models for tabular data
• learn about numerical feature embeddings in neural networks
• generate synthetic tabular data with diffusion models
• follow new research on tabular deep learning

When to choose

• you are doing research or building models on tabular data with neural networks
• you want paper-linked reference implementations of tabular DL methods
• you need benchmarks for tabular deep learning

When to avoid

• you just need a production gradient boosting library like XGBoost or LightGBM
• you expect a single maintained pip package - the original rtdl package is deprecated in favor of separate packages
• you work with images, text, or other non-tabular data

Facets

learning-resource · maturity active

machine-learning deep-learning machine-learning data-science artificial-intelligence python tabular-data pytorch research-papers neural-networks benchmarks

Member repositories

For agents

markdown · JSON · MCP: product_card(name="yandex-research/rtdl")