home.social

#iaifi — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #iaifi, aggregated by home.social.

fetched live
  1. New #openaccess publication #SciPost #Physics

    A Lorentz-equivariant transformer for all of the LHC

    Johann Brehmer, Víctor Bresó, Pim de Haan, Tilman Plehn, Huilin Qu, Jonas Spinner, Jesse Thaler
    SciPost Phys. 19, 108 (2025)
    scipost.org/SciPostPhys.19.4.1

    #CuspAI @uniheidelberg #CERN #MIT #IAIFI
    #NextGenerationEU

  2. New #openaccess publication #SciPost #Physics Core

    Towards universal unfolding of detector effects in high-energy physics using denoising diffusion probabilistic models

    Camila Pazos, Shuchin Aeron, Pierre-Hugues Beauchemin, Vincent Croft, Zhengyan Huan, Martin Klassen, Taritree Wongjirad
    SciPost Phys. Core 8, 064 (2025)
    scipost.org/SciPostPhysCore.8.

    #TuftsUniversity #IAIFI #UL

  3. New #openaccess publication #SciPost #Physics

    Learning the simplicity of scattering amplitudes

    Clifford Cheung, Aurélien Dersy, Matthew D. Schwartz
    SciPost Phys. 18, 040 (2025)
    scipost.org/SciPostPhys.18.2.0

    #Walter_Burke #Harvard #IAIFI

  4. New #openaccess publication #SciPost #Physics

    Goodness of fit by Neyman-Pearson testing

    Gaia Grosso, Marco Letizia, Maurizio Pierini, Andrea Wulzer
    SciPost Phys. 16, 123 (2024)
    scipost.org/SciPostPhys.16.5.1

    #IAIFI #INFN Padova #CERN #Harvard #UNIPD #MIT #UniGe #IFAE

  5. New #openaccess publication #SciPost #Physics

    EPiC-GAN: Equivariant point cloud generation for particle jets

    Erik Buhmann, Gregor Kasieczka, Jesse Thaler
    SciPost Phys. 15, 130 (2023)
    scipost.org/SciPostPhys.15.4.1

    #UH
    #CDCS
    #MIT
    #IAIFI
    #BMBF
    #DFG
    #FriedrichNaumannStiftung
    #NSF
    #DOE

  6. Next was a great talk by @jascha on learned optimizers at #IAIFI. This work is going after the important problem of moving away from hand-designed optimizers in deep learning, and Sohl-Dickstein shows some promising results here youtube.com/watch?v=FrqLLRpAdL (4/11)

  7. 📢New paper (finally...) out today📢 'EPiC-GAN: Equivariant Point Cloud Generation for Particle Jets' with Erik (#UniHamburg too) and Jesse (#IAIFI)

    A short summary below, full paper at arxiv.org/abs/2301.08128

    One useful way to represent data from particle physics collisions is a point cloud: each collision event is a cloud of points & each point has a position in space (the position of the specific sensor or particle) and some additional features attached (for example the energy)