31 August 2026 to 4 September 2026
US/Pacific timezone

HEPTv2: End-to-End Efficient Point Transformer for Charged Particle Reconstruction

2 Sept 2026, 11:12
12m
QI Auditorium

QI Auditorium

Presentation Contributed Talks

Speakers

Yuan-Tang Chou (National Tsing Hua University) Jan-Frederik Schulte (Purdue University (US))

Description

Charged-particle tracking is a core reconstruction task in high-energy physics that directly impacts all reconstruction and physics studies. At the High-Luminosity Large Hadron Collider (HL-LHC), this must be done under much higher pile-up while preserving both tracking quality and computational efficiency. While existing graph-based approaches achieve physics performance comparable to state-of-the-art traditional rule-based algorithms, their end-to-end runtime is often dominated by costly graph construction and processing. On the other hand, prior transformer-based approaches avoid explicit graph processing yet still rely on auxiliary stages such as hit filtering or clustering, making them not fully optimized end-to-end. To address these limitations, this work develops HEPTv2, a single-stage, end-to-end efficient point transformer for charged-particle tracking. HEPTv2 couples a locality-aware point encoder with a sectorized track decoder, enabling prediction of final tracks in an end-to-end trainable pipeline. On the TrackML dataset, HEPTv2 achieves 98.6\% double-majority (DM) tracking efficiency at a 0.8\% fake rate, with about 15 ms inference latency and 0.4 GB peak memory per event on a single NVIDIA A100 GPU, both of which scale near-linearly to $5\times10^5$ hits. This absolute operating cost brings learning-based tracking within reach of potential online deployment under HL-LHC-like rates. HEPTv2 also reaches the best accuracy–latency trade-off among compared methods, improving DM by more than 4.5\% over the strongest prior transformer baseline and by 1.1–2.2 % over highly optimized graph-based pipelines, while reducing latency by $7\times$ and $38–52\times$, respectively.

Do you plan to submit a 4-page extended abstract on OpenReview (only for Presentations/Posters)? Maybe

Authors

Siqi Miao Shitij Govil (Georgia Institute of Technology) Jack Patrick Rodgers (Purdue University (US)) Miaoyuan Liu (Purdue University (US)) Javier Mauricio Duarte (Univ. of California San Diego (US)) Shih-Chieh Hsu (University of Washington Seattle (US)) Yuan-Tang Chou (National Tsing Hua University) Pan Li Arnav Chandra Singh Chia-En Chang (National Yang Ming Chia Tung University) Mr Divij Agarwal (Purdue University) Bo-Cheng Lai (National Yang Ming Chiao Tung Uni. (NYCU) (TW)) Yu-Hao Hu (National Yang Ming Chia Tung University) Karma Luitel Jan-Frederik Schulte (Purdue University (US))

Presentation materials