mlsanityData to 14 Oct 2026

Uncovering Hidden Leptonic Correlations with Flow Matching and Autoencoders

arXiv 2608.15042 ↗First posted 15 Aug 2026hep-ph cs.LG hep-thcited by 0

Not on the map. Why?

Abstract (arXiv)

We perform a global search for values of the Yukawa matrices and Majorana masses in the Type-I seesaw mechanism. Using flow matching, which is a generative artificial intelligence (generative AI) method, we generate a broad set of solutions reproducing the experimentally measured values of the neutrino mass-squared differences and the mixing angles. Then, a machine learning method known as an autoencoder is applied to uncover non-trivial correlations among physical quantities in the lepton sector. Our analysis reveals new non-linear relations involving neutrino masses and CP phases. These findings may contribute to elucidating the origins of the mass hierarchies and mixing patterns among generation structure.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 14 of its 35 references that are in the map. First posted on arXiv 15 Aug 2026.

Builds on

14 of 35 references.

References · 14

  1. 2022Scalable Diffusion Models with Transformerscited by 6,054
  2. 2024Flow map matching with stochastic interpolants: A mathematical framework for consistency modelscited by 109
  3. 2023Flow Matching for Scalable Simulation-Based Inferencecited by 101
  4. 2025A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Modelscited by 76
  5. 2025An Introduction to Flow Matching and Diffusion Modelscited by 35
  6. 2024sbi reloaded: a toolkit for simulation-based inference workflowscited by 23
  7. 2023Exploring the flavor structure of quarks and leptons with reinforcement learningcited by 12
  8. 2024Reinforcement learning-based statistical search strategy for an axion model from flavorcited by 8
  9. 2024Truth, beauty, and goodness in grand unification: a machine learning approachcited by 5
  10. 2024Exploring the Truth and Beauty of Theory Landscapes with Machine Learningcited by 4
  11. 2025Exploring the flavor structure of leptons via diffusion modelscited by 3
  12. 2025Good flavor search in SU(5): a machine learning approachcited by 3
2 more
  1. 2025Discovering Symmetry Groups with Flow Matchingcited by 3
  2. 2026Revisiting One-Zero and Two-Zero Neutrino Mass Textures in Light of Recent Oscillation and Cosmological Datacited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders
  2. 2025Towards AI-assisted Neutrino Flavor Theory Design
  3. 2026Learning Standard Model structure from LHC data with Riemannian flow matching
  4. 2025Even Faster Simulations with Flow Matching: A Study of Zero Degree Calorimeter Responses
  5. 2026CDRL: Certification-Driven Reinforcement Learning for Neutrino Flavor Model Discovery
  6. 2025Diffusion-model approach to flavor models: A case study for S4^prime modular flavor model
  7. 2025Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics
  8. 2024Applying generative neural networks for fast simulations of the ALICE (CERN) experiment