# Fine-tuned Normalizing Flows for ALICE Zero Degree Calorimeter Fast Simulation

arXiv: https://arxiv.org/abs/2608.12795 · HTML: https://mlsanity.com/paper/2608.12795/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 13 Aug 2026.

## Builds on (most cited first, 13 of 13)

- [Distilling the Knowledge in a Neural Network](https://mlsanity.com/paper/1503.02531/) (2015)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Neural Spline Flows](https://mlsanity.com/paper/1906.04032/) (2019)
- [MADE: Masked Autoencoder for Distribution Estimation](https://mlsanity.com/paper/1502.03509/) (2015)
- [CaloChallenge 2022: A Community Challenge for Fast Calorimeter Simulation](https://mlsanity.com/paper/2410.21611/) (2024)
- [End-to-end Sinkhorn Autoencoder with Noise Generator](https://mlsanity.com/paper/2006.06704/) (2020)
- [Faster Uncertainty Quantification for Inverse Problems with Conditional Normalizing Flows](https://mlsanity.com/paper/2007.07985/) (2020)
- [Selectively increasing the diversity of GAN-generated samples](https://mlsanity.com/paper/2207.01561/) (2022)
- [Generative Diffusion Models for Fast Simulations of Particle Collisions at CERN](https://mlsanity.com/paper/2406.03233/) (2024)
- [Transflow Learning: Repurposing Flow Models Without Retraining](https://mlsanity.com/paper/1911.13270/) (2019)
- [Taming Normalizing Flows](https://mlsanity.com/paper/2211.16488/) (2022)
- [Inverse Autoregressive Flows for Zero Degree Calorimeter fast simulation](https://mlsanity.com/paper/2512.20346/) (2025)
- [Even Faster Simulations with Flow Matching: A Study of Zero Degree Calorimeter Responses](https://mlsanity.com/paper/2507.18811/) (2025)

## Abstract (arXiv)

Simulating the ALICE Zero Degree Calorimeter (ZDC) neutron detector responses at the LHC is computationally expensive, requiring complex Monte Carlo chains. We develop a generative surrogate, focusing on Normalizing Flows (NFs). Through transfer learning, we pre-train on the full imbalanced dataset and fine-tune specialized models for different particle types (γ, n, Lambda, KS0, Sigma^+) using two gradual-unfreezing schemes. As standard ZDC metrics like Wasserstein distance overlook conditional structure, we introduce refined metrics: conditional weighted MAE, dispersion ratio, and Jaccard co-activation error, that better capture physics-relevant input-output dependencies and response variability. Our ensemble of fine-tuned models achieves a Wasserstein distance of 1.61 ± 0.02, outperforming baselines across all metrics. This work provides a generalizable NF-based framework for LHC detector simulation, combining NFs, conditional fine-tuning, and physics-motivated evaluation.