International Workshop on Future Linear Colliders 2026

Session

Joint: Software and AI Applications

10 Nov 2026, 16:00

KEK

95. Development of a Graph Neural Network-Based Particle Flow Algorithm for Future Higgs Factories

Tatsuki Murata

AI Applications

Oral presentation (onsite)

Future electron-positron Higgs factories, such as the International Linear Collider (ILC) and FCC-ee, demand unprecedented precision in jet energy measurements to enable detailed studies of the Higgs boson. Highly granular calorimeters coupled with Particle Flow Algorithms (PFA) are central to achieving this performance by leveraging tracking detectors to measure charged particle energies....

40. Multi-channel phase-space integration with Feynman-diagram-gauge amplitudes for high-energy lepton colliders

junichi kanzaki (Iwate University)

Software

Oral presentation (onsite)

Accurate phase-space integration for multi-particle processes at multi-TeV lepton colliders can be challenging because of complicated resonance structures, strongly forward-peaked distributions, and large gauge cancellations among individual Feynman diagrams. We present a multi-channel phase-space method in which each integration channel is enhanced according to a single Feynman diagram...

75. Reconstructing Sparticle masses using Generative Machine Learning

Subhadeep Sarkar (Indian Institute of Technology Patna)

Oral presentation (onsite)

We explore a generative model framework to infer the masses of heavy particles from detector-level data across a broad parameter space. Our model combines a transformer-based detector encoder and a diffusion neural network. We first apply our model to a new physics scenario involving the pair production of wino-like chargino-neutralino, $pp \to \tilde\chi_1^{\pm} \tilde\chi_2^0$, in the...

117. Transformer-based jet reconstruction for Higgs factories

Taikan Suehara (ICEPP, The University of Tokyo)

AI Applications

Oral presentation

ML-based event reconstruction is widely used for various reconstruction tasks for colliders, such as particle flow and jet flavor identification. Transformer-based algorithms are especially powerful for tasks where relation between objects/particles are essentially important. We have implemented the jet flavor tagging tool based on Particle Transformer for ILD full simulation. Recent works...

60. Using FeeBL to Study Monochromatization at ILC, FCC-ee

Brendon Madison (University of Kansas)

Software

Oral presentation (onsite or remote - not decided)

We present the newly written Fast e+e- Beam and Luminosity (FeeBL), first developed as a fork of GuineaPig++ and then rewritten to use contemporary techniques, including parallelization to CPU and GPU, to speed up computation. FeeBL includes new physics options, like dedicated support for crab crossing and crab waist collisions, polarization and spin tracking and depolarization,...