Showing hep-exShow all
3 papers · 1 filter
hep-ex2026
Reconstruct everything everywhere all at once: An end-to-end model for future colliders
Max Hart, Kwok Yiu Wong, Samuel Van Stroud +3
We present the Reconstruct Everything Model (REM), an end-to-end multitask model for sparse, multimodal sensor data, demonstrated in high-energy physics. To our knowledge, REM is t…
hep-ex2026
Better Queries, Cheaper Attention: Adapting Transformers for Efficient Sparse Reconstruction
Philippa Duckett, Samuel Van Stroud, Max Hart +2
Query-based transformer decoders are effective for object reconstruction from sparse scientific sensor measurements, but their scalability to high-multiplicity data is limited by f…
hep-ex2025
GLOW: A Unified Particle Flow Transformer
Dmitrii Kobylianskii, Samuel Van Stroud, Kwok Yiu Wong +5
We present GLOW, a transformer-based particle flow model that combines incidence matrix supervision from HGPflow with a MaskFormer architecture. Evaluated on CLIC detector simulati…