arXiv subjects

Zhuoyi Wang

Publications and source records attributed to Zhuoyi Wang.

7 recordsLinked to original sources

arXiv2026

Prospects for Deep-Learning-Based Mass Reconstruction of Ultra-High-Energy Cosmic Rays using Simulated Air-Shower Profiles

Knowledge of the mass composition of ultra-high-energy cosmic rays is crucial to understanding their origins; however, current approaches have limited event-by-event resolution. With fluorescence telescope measurements of the longitudinal shower profile, there are opportunities to improve this situation by applying Machine Learning (ML) to leverage more information beyond $X_{max}$ alone. To our knowledge, we present the first study of a deep-learning neural-network approach to predict a primary's mass ($\ln{A}$) directly from the longitudinal energy-deposit profile of simulated extensive air showers. We train and validate our model on simulated showers, generated with CONEX and EPOS-LHC, covering nuclei from $A = 1$ to 61, sampled uniformly in $\ln{A}$. After rescaling, our network achieves a maximum bias better than 0.4 in $\ln{A}$ with a resolution between 1.5 for protons and 1 for iron, corresponding to a proton-iron Merit Factor of 2.19 (AUC = 0.976). We benchmark this against simpler ML models trained on profile-shape parameters ($X_{ max}$, $E_{cal}$, $R$, and $L$) extracted from the same data. We find that even simple models can substantially exceed published benchmarks for combinations of these observables, demonstrating that ML methods applied even to standard profile-shape parameters can significantly improve available mass sensitivity. The CNN outperforms this strong baseline, and this performance is only mildly degraded when cross-predicting on simulations made with the Sibyll-2.3d hadronic interaction model, showing robustness against model choice. The network also maintains its performance across a wide range of noise conditions. An ablation study further demonstrates that the full profile contains composition-sensitive structure not captured by the GH parameterization, while the strong performance of the CNN suggests this information should be resolvable in real events.

astro-ph.HE↗

arXiv2025

Topological links and knots of speckled light mediated by coherence singularities

Links and knots are exotic topological structures that have garnered significant interest across multiple branches of natural sciences. Coherent links and knots, such as those constructed by phase or polarization singularities of coherent light, have been observed in various three-dimensional optical settings. However, incoherent links and knots - knotted or connected lines of coherence singularities - arise from a fundamentally different concept. They are hidden in the statistic properties of a randomly fluctuating field, making their presence often elusive or undetectable. Here, we theoretically construct and experimentally demonstrate such topological entities of incoherent light. By leveraging a state-of-the-art incoherent modal-decomposition scheme, we unveil incoherent topological structures from fluctuating light speckles, including Hopf links and Trefoil knots of coherence singularities that are robust against coherence and intensity fluctuations. Our work is applicable to diverse wave systems where incoherence or practical coherence is prevalent, and may pave the way for design and implementation of statistically-shaped topological structures for various applications such as high-dimensional optical information encoding and optical communications.

physics.optics↗

arXiv2023

Genuine full characterization of partially coherence beam

For partially coherent light fields with random fluctuations, the intensity distributions and statistics have been proven to be more propagation robust compared with coherent light. However, its full potential in practical applications has not been realized due to the lack of four-dimensional optical field measurement. Here, a general modal decomposition method of partially coherent light field is proposed and demonstrated. The decomposed random modes can be used to, but not limited to, reconstruct average intensity, cross spectral density and orthogonal decomposition properties of the partially coherent light fields. Due to its versatility and flexibility, this method provides a powerful tool to further reveal light field invariant or retrieve embedded information after propagation through complex media. The Gaussian-shell-model beam and partially coherent Gaussian array are used as examples to demonstrate the reconstruction and even prediction of second-order statistical characteristics. This method is expected to pave the way for applications of partially coherent light in optical imaging, optical encryption and anti-turblence optical communication.

physics.optics↗

arXiv2023

An Automated Vulnerability Detection Framework for Smart Contracts

With the increase of the adoption of blockchain technology in providing decentralized solutions to various problems, smart contracts have become more popular to the point that billions of US Dollars are currently exchanged every day through such technology. Meanwhile, various vulnerabilities in smart contracts have been exploited by attackers to steal cryptocurrencies worth millions of dollars. The automatic detection of smart contract vulnerabilities therefore is an essential research problem. Existing solutions to this problem particularly rely on human experts to define features or different rules to detect vulnerabilities. However, this often causes many vulnerabilities to be ignored, and they are inefficient in detecting new vulnerabilities. In this study, to overcome such challenges, we propose a framework to automatically detect vulnerabilities in smart contracts on the blockchain. More specifically, first, we utilize novel feature vector generation techniques from bytecode of smart contract since the source code of smart contracts are rarely available in public. Next, the collected vectors are fed into our novel metric learning-based deep neural network(DNN) to get the detection result. We conduct comprehensive experiments on large-scale benchmarks, and the quantitative results demonstrate the effectiveness and efficiency of our approach.

cs.CR↗

arXiv2021

A Primal-Dual Subgradient Approachfor Fair Meta Learning

The problem of learning to generalize to unseen classes during training, known as few-shot classification, has attracted considerable attention. Initialization based methods, such as the gradient-based model agnostic meta-learning (MAML), tackle the few-shot learning problem by "learning to fine-tune". The goal of these approaches is to learn proper model initialization, so that the classifiers for new classes can be learned from a few labeled examples with a small number of gradient update steps. Few shot meta-learning is well-known with its fast-adapted capability and accuracy generalization onto unseen tasks. Learning fairly with unbiased outcomes is another significant hallmark of human intelligence, which is rarely touched in few-shot meta-learning. In this work, we propose a Primal-Dual Fair Meta-learning framework, namely PDFM, which learns to train fair machine learning models using only a few examples based on data from related tasks. The key idea is to learn a good initialization of a fair model's primal and dual parameters so that it can adapt to a new fair learning task via a few gradient update steps. Instead of manually tuning the dual parameters as hyperparameters via a grid search, PDFM optimizes the initialization of the primal and dual parameters jointly for fair meta-learning via a subgradient primal-dual approach. We further instantiate examples of bias controlling using mean difference and decision boundary covariance as fairness constraints to each task for supervised regression and classification, respectively. We demonstrate the versatility of our proposed approach by applying our approach to various real-world datasets. Our experiments show substantial improvements over the best prior work for this setting.

cs.LG↗

arXiv2019

Co-Representation Learning For Classification and Novel Class Detection via Deep Networks

One of the key challenges of performing label prediction over a data stream concerns with the emergence of instances belonging to unobserved class labels over time. Previously, this problem has been addressed by detecting such instances and using them for appropriate classifier adaptation. The fundamental aspect of a novel-class detection strategy relies on the ability of comparison among observed instances to discriminate them into known and unknown classes. Therefore, studies in the past have proposed various metrics suitable for comparison over the observed feature space. Unfortunately, these similarity measures fail to reliably identify distinct regions in observed feature spaces useful for class discrimination and novel-class detection, especially in streams containing high-dimensional data instances such as images and texts. In this paper, we address this key challenge by proposing a semi-supervised multi-task learning framework called \sysname{} which aims to intrinsically search for a latent space suitable for detecting labels of instances from both known and unknown classes. We empirically measure the performance of \sysname{} over multiple real-world image and text datasets and demonstrate its superiority by comparing its performance with existing semi-supervised methods.

cs.LG↗

arXiv2018

Adaptive Image Stream Classification via Convolutional Neural Network with Intrinsic Similarity Metrics

When performing data classification over a stream of continuously occurring instances, a key challenge is to develop an open-world classifier that anticipates instances from an unknown class. Studies addressing this problem, typically called novel class detection, have considered classification methods that reactively adapt to such changes along the stream. Importantly, they rely on the property of cohesion and separation among instances in feature space. Instances belonging to the same class are assumed to be closer to each other (cohesion) than those belonging to different classes (separation). Unfortunately, this assumption may not have large support when dealing with high dimensional data such as images. In this paper, we address this key challenge by proposing a semisupervised multi-task learning framework called CSIM which aims to intrinsically search for a latent space suitable for detecting labels of instances from both known and unknown classes. Particularly, we utilize a convolution neural network layer that aids in the learning of a latent feature space suitable for novel class detection. We empirically measure the performance of CSIM over multiple realworld image datasets and demonstrate its superiority by comparing its performance with existing semi-supervised methods.

cs.CV↗