arXiv subjects

Hongtian Yu

Publications and source records attributed to Hongtian Yu.

5 recordsLinked to original sources

arXiv2026

Antineutron reconstruction in electromagnetic calorimeters with mixed-representation learning

A long-standing bottleneck in GeV-scale accelerator experiments lies in reconstructing long-lived neutral hadrons in conventional electromagnetic calorimeters (ECALs), where hadron--nucleus interactions fall outside the detector's native response regime. In this paper, we develop a physics-inspired representation approach for antineutron reconstruction using a large corpus of real collision data. Motivated by two distinct energy deposition patterns from the penetrating high energy antineutrons in ECALs, we propose a Mixed-representation Calorimetric Network (MrCAL) that integrates complementary visual and sequential representation branches within a unified object-detection architecture. This architecture jointly predicts particle identity, momentum direction, and momentum magnitude. Our approach improves the precision of antineutron momentum-direction reconstruction by up to 96% and, for the first time, enables direct measurement of momentum magnitude solely from ECAL readouts, achieving a momentum resolution of approximately 17% at 1 GeV/c. The model maintains robust performance through comprehensive generalization tests spanning a wide variety of physics processes and background environments. This work unlocks a novel measurement capability for legacy ECAL systems at large experimental facilities, broadening their scientific scope via innovative final-state neutral-hadron detection.

hep-ex↗

arXiv2026

Vision Calorimeter for High-Energy Particle Detection

In high-energy physics, estimating anti-neutron parameters (position and momentum) using the electromagnetic calorimeter (EMC) is crucial but challenging. To conquer this challenge, we propose Vision Calorimeter (ViC), a framework that migrates visual object detectors to analyze particle images. The motivation lies in introducing a physics-inspired heat-conduction operator (HCO) into the detector's backbone and head to handle the discrete and sparse patterns of these images. Implemented via the Discrete Cosine Transform, HCO extracts frequency-domain features, bridging the distribution gap between natural and particle images. Experiments demonstrate that ViC significantly outperforms conventional methods, reducing the incident position prediction error by 46.16% (from 17.31{\deg} to 9.32{\deg}) and providing the first baseline result with an incident momentum regression error of 21.48%. This study underscores ViC's great potential as a reliable particle detector for high-energy physics. Code is available at https://github.com/yuhongtian17/ViC.

hep-ex↗

arXiv2024

Vision Calorimeter for Anti-neutron Reconstruction: A Baseline

In high-energy physics, anti-neutrons ($\bar{n}$) are fundamental particles that frequently appear as final-state particles, and the reconstruction of their kinematic properties provides an important probe for understanding the governing principles. However, this confronts significant challenges instrumentally with the electromagnetic calorimeter (EMC), a typical experimental sensor but recovering the information of incident $\bar{n}$ insufficiently. In this study, we introduce Vision Calorimeter (ViC), a baseline method for anti-neutron reconstruction that leverages deep learning detectors to analyze the implicit relationships between EMC responses and incident $\bar{n}$ characteristics. Our motivation lies in that energy distributions of $\bar{n}$ samples deposited in the EMC cell arrays embody rich contextual information. Converted to 2-D images, such contextual energy distributions can be used to predict the status of $\bar{n}$ ($i.e.$, incident position and momentum) through a deep learning detector along with pseudo bounding boxes and a specified training objective. Experimental results demonstrate that ViC substantially outperforms the conventional reconstruction approach, reducing the prediction error of incident position by 42.81% (from 17.31$^{\circ}$ to 9.90$^{\circ}$). More importantly, this study for the first time realizes the measurement of incident $\bar{n}$ momentum, underscoring the potential of deep learning detectors for particle reconstruction. Code is available at https://github.com/yuhongtian17/ViC.

hep-ex↗

arXiv2024

VMamba: Visual State Space Model

Designing computationally efficient network architectures remains an ongoing necessity in computer vision. In this paper, we adapt Mamba, a state-space language model, into VMamba, a vision backbone with linear time complexity. At the core of VMamba is a stack of Visual State-Space (VSS) blocks with the 2D Selective Scan (SS2D) module. By traversing along four scanning routes, SS2D bridges the gap between the ordered nature of 1D selective scan and the non-sequential structure of 2D vision data, which facilitates the collection of contextual information from various sources and perspectives. Based on the VSS blocks, we develop a family of VMamba architectures and accelerate them through a succession of architectural and implementation enhancements. Extensive experiments demonstrate VMamba's promising performance across diverse visual perception tasks, highlighting its superior input scaling efficiency compared to existing benchmark models. Source code is available at https://github.com/MzeroMiko/VMamba.

cs.CV↗

arXiv2023

Spatial Transform Decoupling for Oriented Object Detection

Vision Transformers (ViTs) have achieved remarkable success in computer vision tasks. However, their potential in rotation-sensitive scenarios has not been fully explored, and this limitation may be inherently attributed to the lack of spatial invariance in the data-forwarding process. In this study, we present a novel approach, termed Spatial Transform Decoupling (STD), providing a simple-yet-effective solution for oriented object detection with ViTs. Built upon stacked ViT blocks, STD utilizes separate network branches to predict the position, size, and angle of bounding boxes, effectively harnessing the spatial transform potential of ViTs in a divide-and-conquer fashion. Moreover, by aggregating cascaded activation masks (CAMs) computed upon the regressed parameters, STD gradually enhances features within regions of interest (RoIs), which complements the self-attention mechanism. Without bells and whistles, STD achieves state-of-the-art performance on the benchmark datasets including DOTA-v1.0 (82.24% mAP) and HRSC2016 (98.55% mAP), which demonstrates the effectiveness of the proposed method. Source code is available at https://github.com/yuhongtian17/Spatial-Transform-Decoupling.

cs.CV↗