Skip to content

HEP–ML Community

HEP–ML Living Guide

A community-curated field guide to machine learning for particle physics — opinionated entry points, annotated reading lists, and a structured way into a fast-moving literature.

This resource replaces the HEP–ML Living Review

The original Living Review of Machine Learning for Particle Physics is frozen as an archival reference covering the literature until 1 June 2026. The Living Guide is its successor: a curated, annotated entry point into a now mature and diversifying field. Read more on the About page.

What this guide is

Machine learning in particle physics has grown to over 4 000 papers and several hundred new ones each year. A comprehensive list is no longer the most useful resource a researcher needs — INSPIRE-HEP and arXiv already do that job well. This guide answers a different question:

Where should I start, what matters, and why?

Each section is written by a researcher active in the area. Every recommendation comes with a sentence of context. The guide is opinionated by design — it is not a search index, it is a map.

How to navigate

You can enter the literature along two independent axes — pick whichever matches how you're thinking about a problem.

  • By HEP application

    Start here if you have a physics problem in mind — fast simulation, anomaly detection in collider data, unfolding, triggering, etc.

    → Browse applications

  • By ML method

    Start here if you're curious about a methodology — diffusion models, equivariant networks, simulation-based inference, foundation models.

    → Browse methods

Citing the Guide

If you find the guide useful in your work, please cite it. See Cite us for the recommended BibTeX entry.