# End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics Source: [End-To-End Latent Variational Diffusion Models for Inverse Problems in High Energy Physics]() Collection index: [llms.txt]() Data updated: 2026-01-01T12:31:15.814Z Authors: Alexander Shmakov, Kevin Greif, Michael Fenton, Aishik Ghosh, Pierre Baldi, Daniel Whiteson Published: 2023-05-17T17:43:10.000Z ## Abstract High-energy collisions at the Large Hadron Collider (LHC) provide valuable insights into open questions in particle physics. However, detector effects must be corrected before measurements can be compared to certain theoretical predictions or measurements from other detectors. Methods to solve this \\textit{inverse problem} of mapping detector observations to theoretical quantities of the underlying collision are essential parts of many physics analyses at the LHC. We investigate and compare various generative deep learning methods to approximate this inverse mapping. We introduce a novel unified architecture, termed latent variation diffusion models, which combines the latent learning of cutting-edge generative art approaches with an end-to-end variational framework. We demonstrate the effectiveness of this approach for reconstructing global distributions of theoretical kinematic quantities, as well as for ensuring the adherence of the learned posterior distributions to known physics constraints. Our unified approach achieves a distribution-free distance to the truth of over 20 times less than non-latent state-of-the-art baseline and 3 times less than traditional latent diffusion models. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Kinematic Unfolding on Simulated semi-leptonic tt production v2.7.2 (MADGRAPH\_AMC@NLO) (test)](): Kinematic Unfolding; Simulated semi-leptonic tt production v2.7.2 (MADGRAPH\_AMC@NLO) (test); Wasserstein Distance: 73.56. ## Original sources and implementation [Original paper]() [PDF]()