An End-to-End Generative Diffusion Model for Heavy-Ion Collisions

TL;DR

This paper introduces DiffHIC, a generative diffusion model that efficiently simulates heavy-ion collisions, achieving significant speedups while accurately reproducing key physical observables for high-precision physics research.

Contribution

The paper presents DiffHIC, an end-to-end generative diffusion model that emulates heavy-ion collisions with high accuracy and computational efficiency, surpassing traditional hybrid models.

Findings

Achieves ~10^5 times speedup over traditional simulations.

Accurately reproduces anisotropic flow and multi-particle correlations.

Provides a scalable tool for high-precision heavy-ion physics studies.

Abstract

Heavy-ion collision physics has entered the high precision era, demanding theoretical models capable of generating huge statistics to compare with experimental data. However, traditional hybrid models, which combine hydrodynamics and hadronic transport, are computationally intensive, creating a significant bottleneck. In this work, we introduce DiffHIC, an end-to-end generative diffusion model, to emulate ultra-relativistic heavy-ion collisions. The model takes initial entropy density profiles and transport coefficients as input and directly generates two-dimensional final-state particle spectra. Our results demonstrate that DiffHIC achieves a computational speedup of approximately $10^5$ against traditional simulations, while accurately reproducing a wide range of physical observables, including integrated and differential anisotropic flow, multi-particle correlations, and momentum fluctuations. This framework provides a powerful and efficient tool for phenomenological studies in the high-precision era of heavy-ion physics.