TY - RPRT TI - Tracking in Dense Environments with Transformers IS - ATL-PHYS-PUB-2025-045 M1 - PUBDB-2025-04910 M1 - ATL-PHYS-PUB-2025-045 SP - 12 PY - 2025 AB - This work presents a novel application of machine learning to the pattern-recognition stage of charged-particle reconstruction, enabling learned hit-to-track association within dense environments, such as the cores of high-pTjets. Our Transformer-based architecture is based on a MaskFormer model that jointly optimises hit assignments and the estimation of the charged particles' properties. Trained and evaluated in dense environments the model delivers up to a 30 LB - PUB:(DE-HGF)29 DO - DOI:10.3204/PUBDB-2025-04910 UR - https://bib-pubdb1.desy.de/record/640807 ER -