mlsanityData to 14 Oct 2026

PC-Droid: Faster diffusion and improved quality for particle cloud generation

arXiv 2307.06836 ↗First posted 13 Jul 2023hep-ex cs.LG hep-phcited by 8

On the map: Diffusion models → Flow matching, time series and science

Abstract (arXiv)

Building on the success of PC-JeDi we introduce PC-Droid, a substantially improved diffusion model for the generation of jet particle clouds. By leveraging a new diffusion formulation, studying more recent integration solvers, and training on all jet types simultaneously, we are able to achieve state-of-the-art performance for all types of jets across all evaluation metrics. We study the trade-off between generation speed and quality by comparing two attention based architectures, as well as the potential of consistency distillation to reduce the number of diffusion steps. Both the faster architecture and consistency models demonstrate performance surpassing many competing models, with generation time up to two orders of magnitude faster than PC-JeDi and three orders of magnitude faster than Delphes.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Placed in Flow matching, time series and science, one of 14 directions in Diffusion models. Builds on 37 of its 62 references that are in the map. First posted on arXiv 13 Jul 2023.

Builds on

37 of 62 references.

Closest ancestors · 3

Same direction, newest first

  1. 2023Comparison of Point Cloud and Image-based Models for Calorimeter Fast Simulation10 Jul
  2. 2023End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics17 May
  3. 2022Score-based Generative Models for Calorimeter Shower Simulation17 Jun

Other references · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  2. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  3. 2020Denoising Diffusion Implicit Modelscited by 9,781
  4. 2020Score-Based Generative Modeling through Stochastic Differential Equationscited by 9,122
  5. 2022Hierarchical Text-Conditional Image Generation with CLIP Latentscited by 6,585
  6. 2022Classifier-Free Diffusion Guidancecited by 5,847
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,761
  8. 2015Continuous control with deep reinforcement learningcited by 3,407
  9. 2013Playing Atari with Deep Reinforcement Learningcited by 3,274
  10. 2022Elucidating the Design Space of Diffusion-Based Generative Modelscited by 3,045
  11. 2015Variational Inference with Normalizing Flowscited by 2,170
  12. 2022DPM-Solver: A Fast ODE Solver for Diffusion Probabilistic Model Sampling in Around 10 Stepscited by 1,979
22 more
  1. 2023Consistency Modelscited by 1,822
  2. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,114
  3. 2022DPM-Solver++: Fast Solver for Guided Sampling of Diffusion Probabilistic Modelscited by 938
  4. 2019Neural Spline Flowscited by 596
  5. 2020A Review on Generative Adversarial Networks: Algorithms, Theory, and Applicationscited by 209
  6. 2017CaloGAN: Simulating 3D High Energy Particle Showers in Multi-Layer Electromagnetic Calorimeters with Generative Adversarial Networkscited by 78
  7. 2017Accelerating Science with Generative Adversarial Networks: An Application to 3D Particle Showers in Multi-Layer Calorimeterscited by 55
  8. 2021CaloFlow: Fast and Accurate Generation of Calorimeter Showers with Normalizing Flowscited by 46
  9. 2021Particle Cloud Generation with Message Passing Generative Adversarial Networkscited by 46
  10. 2019Calorimetry with Deep Learning: Particle Simulation and Reconstruction for Collider Physicscited by 42
  11. 2021CaloFlow II: Even Faster and Still Accurate Generation of Calorimeter Showers with Normalizing Flowscited by 34
  12. 2023CaloClouds: Fast Geometry-Independent Highly-Granular Calorimeter Simulationcited by 33
  13. 2023PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physicscited by 27
  14. 2019LHC analysis-specific datasets with Generative Adversarial Networkscited by 26
  15. 2017Controlling Physical Attributes in GAN-Accelerated Simulation of Electromagnetic Calorimeterscited by 23
  16. 2023EPiC-GAN: Equivariant Point Cloud Generation for Particle Jetscited by 23
  17. 2020Simulation of electron-proton scattering events by a Feature-Augmented and Transformed Generative Adversarial Network (FAT-GAN)cited by 20
  18. 2022New directions for surrogate models and differentiable programming for High Energy Physics detector simulationcited by 16
  19. 2022CaloFlow for CaloChallenge Dataset 1cited by 14
  20. 2023Attention to Mean-Fields for Particle Cloud Generationcited by 12
  21. 2023High-dimensional and Permutation Invariant Anomaly Detectioncited by 12
  22. 2021Turbo-Sim: a generalised generative model with a physical latent spacecited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 4; 2024: 1; 2025: 0; 2026: 3.

8 papers.

  1. 2023CaloClouds II: Ultra-Fast Geometry-Independent Highly-Granular Calorimeter Simulationcited by 20
  2. 2023Deep Generative Models for Detector Signature Simulation: A Taxonomic Reviewcited by 18
  3. 2023EPiC-ly Fast Particle Cloud Generation with Flow-Matching and Diffusioncited by 17
  4. 2023Flow Matching Beyond Kinematics: Generating Jets with Particle-ID and Trajectory Displacement Informationcited by 7
  5. 2024Extrapolating Jet Radiation with Autoregressive Transformerscited by 2
  6. 2026Generative models on phase spacecited by 0
  7. 2026Learning Standard Model structure from LHC data with Riemannian flow matchingcited by 0
  8. 2026Lantern: Conflict-Aware Gradient Blending for Physics-Guided Diffusion Models in Calorimeter Simulationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024Efficient Diffusion Models: A Comprehensive Survey from Principles to Practices
  2. 2025NnD: Diffusion-based Generation of Physically-Nonnegative Objects
  3. 2023Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
  4. 2025Jet Image Generation in High Energy Physics Using Diffusion Models
  5. 2025Generative Monte Carlo Sampling for Constant-Cost Particle Transport
  6. 2026LegoDiffusion: Micro-Serving Text-to-Image Diffusion Workflows
  7. 2026Particle-Guided Diffusion Models for Partial Differential Equations
  8. 2024SwiftDiffusion: Efficient Diffusion Model Serving with Add-on Modules