A survey on generative AI for detector effects unfolding in particle and nuclear physics

Abstract

In particle and nuclear physics, “detector effects unfolding” can be viewed as a high-dimensional inverse problem whose goal is to recover the true event distributions from observed experimental data corrupted by detector-induced distortions. Recent advances in generative AI have positioned data-driven and machine learning-based approaches as powerful alternatives to traditional unfolding techniques, offering superior scalability to high-dimensional data, capability of learning complex detector responses, and the ability to operate directly at the event level. We survey state-of-the-art generative AI-based models for detector folding and unfolding. We review existing architectures and training strategies, and highlight recent methodological advances and open challenges. Through a detailed discussion of latent space representations, uncertainty quantification, physics insights, and background removals, we demonstrate the potential to significantly advance the field.

Keywords

generative AI / detector effects / unfolding / particle physics / nuclear physics / uncertainty quantification / inverse problems

References

[1] G. Aarts, K. Fukushima, T. Hatsuda, A. Ipp, S. Shi, L. Wang, et al., Physics-driven learning for inverse problems in quantum chromodynamics, Nat. Rev. Phys., 7(2025), 154-163. https://doi.org/10.1038/s42254-024-00798-x

[2] A. Abhishek, E. Drechsler, W. Fedorko, B. Stelzer, CaloDVAE: discrete variational autoencoders for fast calorimeter shower simulation, Proceedings of the Fourth Workshop on Machine Learning and the Physical Sciences, 2021, 1-11.

[3] Y. Alanazi, N. Sato, P. Ambrozewicz, A. Hiller Blin, W. Melnitchouk, M. Battaglieri, et al., A survey of machine learning-based physics event generation, Proceedings of the 30th International Joint Conference on Artificial Intelligence (IJCAI-21), 2021, 4286-4293. https://doi.org/10.24963/ijcai.2021/588

[4] Y. Alanazi, P. Ambrozewicz, M. Battaglieri, A. Hiller Blin, M. Kuchera, Y. Li et al., Machine learning-based event generator for electron-proton scattering, Phys. Rev. D, 106(2022), 096002. https://doi.org/10.1103/PhysRevD.106.096002

[5] Y. Alanazi, N. Sato, T. Liu, W. Melnitchouk, P. Ambrozewicz, F. Hauenstein, et al., Simulation of electron-proton scattering events by a feature-augmented and transformed generative adversarial network (FAT-GAN), Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence (IJCAI-21), 2021, 2126-2132. https://doi.org/10.24963/ijcai.2021/293

[6] T. Alghamdi, J. Xu, N. Ramachandra, N. Sato, Y. Li, Towards an event-level analysis in hadronic physics using generative ai-based surrogates, Proceedings of IEEE 37th International Conference on Tools with Artificial Intelligence (ICTAI), 2025, 445-452. https://doi.org/10.1109/ICTAI66417.2025.00067

[7] T. Alghamdi, Y. Alanazi, M. Battaglieri, Ł. Bibrzycki, A. V. Golda, A. N. Hiller Blin, et al., Toward a generative modeling analysis of CLAS exclusive 2π photoproduction, Phys. Rev. D, 108(2023), 094030. https://doi.org/10.1103/PhysRevD.108.094030

[8] T. Alghamdi, T. Vittorini, M. Spreafico, M. Battaglieri, N. Sato, Y. Li, Unfolding particle detector acceptance in high energy physics with generative AI, Proceedings of IEEE 36th International Conference on Tools with Artificial Intelligence (ICTAI), 2024, 962-968. https://doi.org/10.1109/ICTAI62512.2024.00138

[9] O. Amram, K. Pedro, Denoising diffusion models with geometry adaptation for high fidelity calorimeter simulation, Phys. Rev. D, 108(2023), 072014. https://doi.org/10.1103/PhysRevD.108.072014

[10] L. Anderlini, C. Chimpoesh, N. Kazeev, A. Shishigina, Generative models uncertainty estimation, J. Phys.: Conf. Ser., 2438(2023). 012088. https://doi.org/10.1088/1742-6596/2438/1/012088

[11] A. Andreassen, P. Komiske, E. Metodiev, B. Nachman, J. Thaler, Omnifold: a method to simultaneously unfold all observables, Phys. Rev. Lett., 124(2020), 182001. https://doi.org/10.1103/PhysRevLett.124.182001

[12] J. Araz, V. Mikuni, F. Ringer, N. Sato, F. Acosta, R. Whitehill, Point cloud-based diffusion models for the Electron-Ion Collider, Phys. Lett. B, 868(2025), 139694. https://doi.org/10.1016/j.physletb.2025.139694

[13] M. Backes, A. Butter, M. Dunford, B. Malaescu, Event-by-event comparison between machine-learning- and transfer-matrix-based unfolding methods, Eur. Phys. J. C, 84(2024), 770. https://doi.org/10.1140/epjc/s10052-024-13136-3

[14] H. Baran, Deep generative models for ultra-high granularity particle physics detector simulation: a voyage from emulation to extrapolation, Ph. D Thesis, Ludwig-Maximilians-Universität München, 2023. https://doi.org/10.5282/edoc.34137

[15] M. Bellagente, A. Butter, G. Kasieczka, T. Plehn, R. Winterhalder, How to GAN away detector effects, SciPost Phys., 8(2020), 070. https://doi.org/10.21468/SciPostPhys.8.4.070

[16] S. Biedron, L. Brouwer, D. L. Bruhwiler, N. M. Cook, A. L. Edelen, D. Filippetto, et al., Snowmass21 accelerator modeling community white paper, arXiv: 2203.08335. https://doi.org/10.48550/arXiv.2203.08335

[17] V. Blobel, An unfolding method for high-energy physics experiments, Proceedings of the Conference on Advanced Statistical Techniques in Particle Physics, 2002, 258-267.

[18] A. Boehnlein, M. Diefenthaler, N. Sato, M. Schram, V. Ziegler, C. Fanelli, et al., Colloquium: machine learning in nuclear physics, Rev. Mod. Phys., 94(2022), 031003. https://doi.org/10.1103/revmodphys.94.031003

[19] J. Brehmer, G. Louppe, J. Pavez, K. Cranmer, Mining gold from implicit models to improve likelihood-free inference, Proc. Natl. Acad. Sci. U.S.A., 117(2020) 5242-5249. https://doi.org/10.1073/pnas.1915980117

[20] E. Buhmann, S. Diefenbacher, E. Eren, F. Gaede, G. Kasicezka, A. Korol, et al., Caloclouds: fast geometry-independent highly-granular calorimeter simulation, JINST, 18(2023), P11025. https://doi.org/10.1088/1748-0221/18/11/P11025

[21] E. Buhmann, S. Diefenbacher, E. Eren, F. Gaede, G. Kasieczka, A. Korol, et al., Decoding photons: physics in the latent space of a BIB-AE generative network, EPJ Web Conf., 251(2021), 03003. https://doi.org/10.1051/epjconf/202125103003

[22] E. Buhmann, F. Gaede, G. Kasieczka, A. Korol, W. Korcari, K. Krüger, et al., CaloClouds II: ultra-fast geometry-independent highly-granular calorimeter simulation, JINST, 19(2024), P04020. https://doi.org/10.1088/1748-0221/19/04/P04020

[23] A. Butter, T. Plehn, Generative networks for LHC events, In: Artificial intelligence for high energy physics, Singapore: World Scientific Publishing, 2020, 191-240. https://doi.org/10.1142/97898112340330007

[24] G. Carleo, I. Cirac, K. Cranmer, L. Daudet, M. Schuld, N. Tishby, et al., Machine learning and the physical sciences, Rev. Mod. Phys., 91(2019), 045002. https://doi.org/10.1103/RevModPhys.91.045002

[25] J. Chan, B. Nachman, Unbinned profiled unfolding, Phys. Rev. D, 108(2023), 016002. https://doi.org/10.1103/PhysRevD.108.016002

[26] S. V. Chekanov, HepSim: a repository with predictions for high-energy physics experiments, Adv. High Energy Phys., 2015 (2015), 136093. https://doi.org/10.1155/2015/136093

[27] G. Cowan, Statistical data analysis, Oxford: Oxford Academic, 1998. https://doi.org/10.1093/oso/9780198501565.001.0001

[28] J. Cresswell, B. Ross, G. Loaiza-Ganem, H. Reyes-Gonzalez, M. Letizia, A. Caterini, Caloman: fast generation of calorimeter showers with density estimation on learned manifolds, Proceedings of the Machine Learning and the Physical Sciences Workshop, 2022, 1-8.

[29] K. Datta, D. Kar, D. Roy, Unfolding with generative adversarial networks, arXiv: 1806.00433. https://doi.org/10.48550/arXiv.1806.00433

[30] L. de Oliveira, M. Paganini, B. Nachman, Learning particle physics by example: location-aware generative adversarial networks for physics synthesis, Comput. Softw. Big Sci., 1(2017), 4. https://doi.org/10.1007/s41781-017-0004-6

[31] M. Debbagh, Learning structured output representations from attributes using deep conditional generative models, arXiv: 2305.00980. https://doi.org/10.48550/arXiv.2305.00980

[32] K. Deja, J. Dubiński, P. Nowak, S. Wenzel, P. Spurek, T. Trzcinski, End-to-end sinkhorn autoencoder with noise generator, IEEE Access, 9(2020), 7211-7219. https://doi.org/10.1109/ACCESS.2020.3048622

[33] K. Desai, B. Nachman, J. Thaler, Moment extraction using an unfolding protocol without binning, Phys. Rev. D, 110(2024), 116013. https://doi.org/10.1103/PhysRevD.110.116013

[34] P. Devlin, J. W. Qiu, F. Ringer, N. Sato, Diffusion model approach to simulating electron-proton scattering events, Phys. Rev. D, 110(2024), 016030. https://doi.org/10.1103/PhysRevD.110.016030

[35] S. Diefenbacher, G. Liu, V. Mikuni, B. Nachman, W. Nie, Improving generative model-based unfolding with schrödinger bridges, Phys. Rev. D, 109(2024), 076011, https://doi.org/10.1103/PhysRevD.109.076011

[36] C. Fanelli, J. Giroux, ELUQuant: event-level uncertainty quantification in deep inelastic scattering, Mach. Learn.: Sci. Technol., 5(2024), 015017. https://doi.org/10.1088/2632-2153/ad2098

[37] M. F. Giannelli, R. Zhang, CaloShowerGAN, a generative adversarial network model for fast calorimeter shower simulation, Eur. Phys. J. Plus, 139(2024), 597. https://doi.org/10.1140/epjp/s13360-024-05397-4

[38] D. Glazier, R. Tyson, Converting sweights to probabilities with density ratios, Comput. Phys. Commun., 318(2026), 109890. https://doi.org/10.1016/j.cpc.2025.109890

[39] I. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley, S. Ozair, et al., Generative adversarial nets, Proceedings of the 28th International Conference on Neural Information Processing Systems, 2014, 2672-2680.

[40] A. Hariri, D. Dyachkova, S. Gleyzer, Graph generative models for fast detector simulations in high energy physics, Proceedings of the Third Workshop on Machine Learning and the Physical Sciences, 2021, 1-6.

[41] J. Ho, A. Jain, P. Abbeel, Denoising diffusion probabilistic models, Proceedings of the 34th Conference on Neural Information Processing Systems, 2020, 1-12.

[42] Y. Huang, Y. Ren, S. Yoo, J. Huang, Fast 2D bicephalous convolutional autoencoder for compressing 3D time projection chamber data, Proceedings of the SC ’23 Workshops of the International Conference on High Performance Computing, Network, Storage, and Analysis, 2023, 298-305. https://doi.org/10.1145/3624062.3625127

[43] K. Jaruskova, S. Vallecorsa, Ensemble models for calorimeter simulations, J. Phys.: Conf. Ser., 2438(2023), 012080. https://doi.org/10.1088/1742-6596/2438/1/012080

[44] R. Kansal, J. Duarte, B. Orzari, T. Tomei, M. Pierini, M. Touranakou, et al., Graph generative adversarial networks for sparse data generation in high energy physics, Proceedings of the Third Workshop on Machine Learning and the Physical Sciences, 2021, 1-9.

[45] D. P. Kingma, M. Welling, Auto-encoding variational bayes, Proceedings of the International Conference on Learning Representations, 2014, 1-14.

[46] D. Kobylianskii, N. Soybelman, N. Kakati, E. Dreyer, B. Nachman, E. Gross, Advancing set-conditional set generation: diffusion models for fast simulation of reconstructed particles, Phys. Rev. D, 110(2024), 092013. https://doi.org/10.1103/PhysRevD.110.092013

[47] D. Koh, A. Mishra, K. Terao, Deep neural network uncertainty quantification for LArTPC reconstruction, JINST, 18(2023), P12013. https://doi.org/10.1088/1748-0221/18/12/P12013

[48] C. Krause, D. Shih, CaloFlow II: even faster and still accurate generation of calorimeter showers with normalizing flows, arXiv: 2110.11377. https://doi.org/10.48550/arXiv.2110.11377

[49] C. Krause, D. Shih, Fast and accurate simulations of calorimeter showers with normalizing flows, Phys. Rev. D, 107(2023), 113003. https://doi.org/10.1103/PhysRevD.107.113003

[50] V. Mikuni, B. Nachman, M. Pettee, Fast point cloud generation with diffusion models in high energy physics, Phys. Rev. D, 108(2023), 036025. https://doi.org/10.1103/PhysRevD.108.036025

[51] B. Nachman, J. Thaler, Neural resampler for Monte Carlo reweighting with preserved uncertainties, Phys. Rev. D, 102(2020), 076004. https://doi.org/10.1103/PhysRevD.102.076004

[52] L. Ng, Ł. Bibrzycki, J. Nys, C. Fernández-Ramírez, A. Pilloni, V. Mathieu, et al., Deep learning exotic hadrons, Phys. Rev. D, 105(2022), L091501. https://doi.org/10.1103/PhysRevD.105.L091501

[53] M. Paganini, L. de Oliveira, B. Nachman, CaloGAN: simulating 3D high energy particle showers in multilayer electromagnetic calorimeters with generative adversarial networks, Phys. Rev. D, 97(2018), 014021. https://doi.org/10.1103/PhysRevD.97.014021

[54] I. Pang, D. Shih, J. A. Raine, Calorimeter shower superresolution, Phys. Rev. D, 109(2024), 092009. https://doi.org/10.1103/PhysRevD.109.092009

[55] C. Pazos, S. Aeron, P. Beauchemin, V. Croft, Z. Huan, M. Klassen, et al., Towards universal unfolding of detector effects in high-energy physics using denoising diffusion probabilistic models, arXiv: 2406.01507. https://doi.org/10.48550/arXiv.2406.01507

[56] A. Peisert, F. Sauli, Drift and diffusion of electrons in gases: a compilation (with an introduction to the use of computing programs), Geneva: CERN, 1984. https://doi.org/10.5170/CERN-1984-008

[57] M. Pivk, F. R. Le Diberder, SPlot: a statistical tool to unfold data distributions, Nucl. Instrum. Meth. A, 555(2005), 356-369. https://doi.org/10.1016/j.nima.2005.08.106

[58] M. Raissi, P. Perdikaris, G. Em Karniadakis, Physics informed deep learning (part I): data-driven solutions of nonlinear partial differential equations, arXiv: 1711.10561. https://doi.org/10.48550/arXiv.1711.10561

[59] D. J. Rezende, S. Mohamed, Variational inference with normalizing flows, Proceedings of the 32nd International Conference on Machine Learning, 2015, 1530-1538.

[60] T. Salimans, J. Ho, Progressive distillation for fast sampling of diffusion models, arXiv: 2202.00512. https://doi.org/10.48550/arXiv.2202.00512

[61] D. L. B. Sombillo, Y. Ikeda, T. Sato, A. Hosaka, Classifying the pole of an amplitude using a deep neural network, Phys. Rev. D, 102(2020), 016024. https://doi.org/10.1103/PhysRevD.102.016024

[62] L. Van der Maaten, G. Hinton, Visualizing data using t-SNE, J. Mach. Learn. Res., 9(2008), 2579-2605.

[63] V. Vatellis, Advancing physics data analysis through machine learning and physics-informed neural networks, arXiv: 2410.14760. https://doi.org/10.48550/arXiv.2410.14760

[64] S. Zhao, J. Song, S. Ermon, InfoVAE: balancing learning and inference in variational autoencoders, Proceedings of the AAAI Conference on Artificial Intelligence, 33(2019), 5885-5892. https://doi.org/10.1609/aaai.v33i01.33015885