Publications (86)
Data-Driven Search-based Software Engineering
Vivek Nair, Amritanshu Agrawal, Jianfeng Chen +6
This paper introduces Data-Driven Search-based Software Engineering (DSE), which combines insights from Mining Software Repositories (MSR) and Search-based Software Engineering (SB…
FAST: an Intelligent Assistant for Finding Relevant Papers
Zhe Yu, Tim Menzies
Literature reviews are essential for any researcher trying to keep up to date with the burgeoning software engineering literature. FAST is a novel tool for reducing the effort…
FIDES: Faithful Inference via Deep Evidence Signals for Retrieval-Memory Conflict in RAG
Zhe Yu, Wenpeng Xing, Tiancheng Zhao +3
When retrieved evidence contradicts parametric memory, language models frequently ignore context and default to memorized priors -- a failure that undermines the core purpose of re…
Learning to Recognize Actionable Static Code Warnings (is Intrinsically Easy)
Xueqi Yang, Jianfeng Chen, Rahul Yedida +2
Static code warning tools often generate warnings that programmers ignore. Such tools can be made more useful via data mining algorithms that select the "actionable" warnings; i.e.…
Total transmission modes in draining bathtub model with vorticity
Zhe Yu, Liang-Bi Wu
We investigate the total transmission modes (TTMs) in the draining bathtub model (DBM) with vorticity using the Chebyshev-Lobatto pseudospectral method, where the boundary conditio…
Story Point Estimation Using Large Language Models
Pranam Prakash Shetty, Adarsh Balakrishnan, Mengqiao Xu +2
This study investigates the use of large language models (LLMs) for story point estimation. Story points are unitless, project-specific effort estimates that help developers on the…
Modeling Image-Caption Rating from Comparative Judgments
Kezia Minni, Qiang Zhang, Monoshiz Mahbub Khan +1
Image caption rating is becoming increasingly important because computer-generated captions are used extensively for descriptive annotation. However, rating the accuracy of caption…
A Distributed Cooperative Control Framework for Synchronized Reconnection of a Multi-Bus Microgrid
Di Shi, Xi Chen, Zhiwei Wang +4
One critical value microgrids bring to power systems is resilience, the capability of being able to island from the main grid under certain conditions and connect back when necessa…
UniCA: Unified Covariate Adaptation for Time Series Foundation Model
Lu Han, Yu Liu, Lan Li +9
Time Series Foundation Models (TSFMs) have achieved remarkable success through large-scale pretraining. However, their design primarily targets real-valued series, limiting their a…
Evidence for Two Distinct Broad-Line Regions from Reverberation Mapping of PG 0026+129
Chen Hu, Sha-Sha Li, Wei-Jian Guo +17
We report on the results of a new spectroscopic monitoring campaign of the quasar PG 0026+129 at the Calar Alto Observatory 2.2m telescope from July 2017 to February 2020. Signific…
Extended Prony Analysis on Power System Oscillation Under a Near-Resonance Condition
Tianwei Xia, Zhe Yu, Kai Sun +2
Power system oscillations under a large disturbance often exhibit distorted waveforms as captured by increasingly deployed phasor measurement units. One cause is the occurrence of…
The parameterized quasinormal modes for modified Teukolsky equations
Zhe Yu, Liang-Bi Wu
We introduce the modified Teukolsky equation within a parameterized framework, analogous to the case of small deviations of potential in spherical symmetry. Both the radial and ang…
Finding Better Active Learners for Faster Literature Reviews
Zhe Yu, Nicholas A. Kraft, Tim Menzies
Literature reviews can be time-consuming and tedious to complete. By cataloging and refactoring three state-of-the-art active learning techniques from evidence-based medicine and l…
Explaining Non-monotonic Normative Reasoning using Argumentation Theory with Deontic Logic
Zhe Yu, Yiwei Lu
In our previous research, we provided a reasoning system (called LeSAC) based on argumentation theory to provide legal support to designers during the design process. Building on t…
Bayesian Estimation Based Load Modeling Report
Chang Fu, Zhe Yu, Di Shi
This report presents the detailed steps of establishing the composite load model in the power system. The derivations of estimation the ZIP model and IM model parameters are propos…
A General-Purpose Dehazing Algorithm based on Local Contrast Enhancement Approaches
Bangyong Sun, Vincent Whannou de Dravo, Zhe Yu
Dehazing is in the image processing and computer vision communities, the task of enhancing the image taken in foggy conditions. To better understand this type of algorithm, we pres…
WebRetriever: A Large-Scale Comprehensive Benchmark for Efficient Web Agent Evaluation
Wei Dong, Tianyu Fu, Zhe Yu +9
As web agents increasingly demonstrate capabilities in automated task execution, the development of robust evaluation frameworks for assessing their navigation and task completion…
Particle production during Inflation with a non-minimally coupled spectator scalar field
Zhe Yu, Chengjie Fu, Zong-Kuan Guo
We study the inflationary model with a spectator scalar field coupled to both the inflaton and Ricci scalar. The interaction between the field and the gravity, denoted by…
Forced Oscillation Source Location via Multivariate Time Series Classification
Yao Meng, Zhe Yu, Di Shi +2
Precisely locating low-frequency oscillation sources is the prerequisite of suppressing sustained oscillation, which is an essential guarantee for the secure and stable operation o…
Supermassive Black Holes with High Accretion Rates in Active Galactic Nuclei. XII. Reverberation Mapping Results for 15 PG Quasars from a Long-Duration High-Cadence Campaign
Chen Hu, Sha-Sha Li, Sen Yang +15
We present the first results from long-term high-cadence spectroscopic monitoring of 15 PG quasars with relatively strong Fe II emission as a part of a broader reverberation mappin…
The impact of large-scale EV charging on the real-time operation of distribution systems: A comprehensive review
Zhe Yu, Chuang Yang, Qin Wang
With the large-scale integration of electric vehicles (EVs) in the distribution grid, the unpredictable nature of EV charging introduces considerable uncertainties to the grid's re…
TERMINATOR: Better Automated UI Test Case Prioritization
Zhe Yu, Fahmid M. Fahid, Tim Menzies +3
Automated UI testing is an important component of the continuous integration process of software development. A modern web-based UI is an amalgam of reports from dozens of microser…
NTIRE 2020 Challenge on NonHomogeneous Dehazing
Codruta O. Ancuti, Cosmin Ancuti, Florin-Alexandru Vasluianu +49
This paper reviews the NTIRE 2020 Challenge on NonHomogeneous Dehazing of images (restoration of rich details in hazy image). We focus on the proposed solutions and their results e…
A Generalized-Jacobi-Function Spectral Method for Space-Time Fractional Reaction-Diffusion Equations with Viscosity Terms
Zhe Yu, Boying Wu, Jiebao Sun +1
In this work, we study a new spectral Petrov-Galerkin approximation of space-time fractional reaction-diffusion equations with viscosity terms built by Riemann-Liouville fractional…
Revisiting Emission-Line Measurement Methods for Narrow-Line Active Galactic Nuclei
Viraja C. Khatu, Sarah C. Gallagher, Keith Horne +16
Measuring broad emission-line widths in active galactic nuclei (AGN) is not straightforward owing to the complex nature of flux variability in these systems. Line-width measurement…
Understanding Static Code Warnings: an Incremental AI Approach
Xueqi Yang, Zhe Yu, Junjie Wang +1
Knowledge-based systems reason over some knowledge base. Hence, an important issue for such systems is how to acquire the knowledge needed for their inference. This paper assesses…
Cross-Border Legal Adaptation of Autonomous Vehicle Design based on Logic and Non-monotonic Reasoning
Zhe Yu, Yiwei Lu, Burkhard Schafer +1
This paper focuses on the legal compliance challenges of autonomous vehicles in a transnational context. We choose the perspective of designers and try to provide supporting legal…
An Argumentation-Based Legal Reasoning Approach for DL-Ontology
Zhe Yu, Yiwei Lu
Ontology is a popular method for knowledge representation in different domains, including the legal domain, and description logics (DL) is commonly used as its description language…
From Retinal Evidence to Safe Decisions: RETINA-SAFE and ECRT for Hallucination Risk Triage in Medical LLMs
Zhe Yu, Wenpeng Xing, Meng Han
Hallucinations in medical large language models (LLMs) remain a safety-critical issue, particularly when available evidence is insufficient or conflicting. We study this problem in…
Rescattering of non-minimal coupling scalar particles during inflation
Zhe Yu, Xunliang Yang, Yungui Gong
We investigate the rescattering effects arising from non-minimally coupled scalar particles that are suddenly produced during inflation. The coupling term significa…
Finding Faster Configurations using FLASH
Vivek Nair, Zhe Yu, Tim Menzies +2
Finding good configurations for a software system is often challenging since the number of configuration options can be large. Software engineers often make poor choices about conf…
Better Software Analytics via "DUO": Data Mining Algorithms Using/Used-by Optimizers
Amritanshu Agrawal, Tim Menzies, Leandro L. Minku +2
This paper claims that a new field of empirical software engineering research and practice is emerging: data mining using/used-by optimizers for empirical studies or DUO. For examp…
Recover the lost Phasor Measurement Unit Data Using Alternating Direction Multipliers Method
Mang Liao, Di Shi, Zhe Yu +3
This paper presents a novel algorithm for recovering missing data of phasor measurement units (PMUs). Due to the low-rank property of PMU data, missing measurement recovery can be…
Holographic thermal correlators from recursions
Jie Ren, Zhe Yu
We express holographic thermal correlators using a recurrence relation of at , building on recent advances in the connection formula for the Heun equation. We…
Higher-order exponential Runge-Kutta Galerkin finite element method for semilinear parabolic problems with nonsmooth data
Shuo Yang, Runjie Zhang, Zhe Yu +1
We develop a rigorous numerical analysis framework for a class of semilinear parabolic problems with nonsmooth initial data. We employ a linear Galerkin finite element method for s…
FLASH: A Faster Optimizer for SBSE Tasks
Vivek Nair, Zhe Yu, Tim Menzies
Most problems in search-based software engineering involve balancing conflicting objectives. Prior approaches to this task have required a large number of evaluations- making them…
Online Coherence Identification Using Dynamic Time Warping for Controlled Islanding
Hasan Ul Banna, Zhe Yu, Di Shi +5
Controlled islanding is considered to be the last countermeasure to prevent system-wide blackouts in case of cascading failures. It splits the system into self-sustained islands to…
A Multi-class Ride-hailing Service Subsidy System Utilizing Deep Causal Networks
Zhe Yu, Chi Xia, Shaosheng Cao +1
In the ride-hailing industry, subsidies are predominantly employed to incentivize consumers to place more orders, thereby fostering market growth. Causal inference techniques are e…
Market Dynamics and Indirect Network Effects in Electric Vehicle Diffusion
Zhe Yu, Shanjun Li, Lang Tong
The diffusion of electric vehicles (EVs) is studied in a two-sided market framework consisting of EVs on the one side and EV charging stations (EVCSs) on the other. A sequential ga…
Better Technical Debt Detection via SURVEYing
Fahmid M. Fahid, Zhe Yu, Tim Menzies
Software analytics can be improved by surveying; i.e. rechecking and (possibly) revising the labels offered by prior analysis. Surveying is a time-consuming task and effective surv…
Non-homogeneous fourth order elliptic inequalities with the convolution term
Zhe Yu
We are concerned with the study of the twin non-local inequalities featuring non-homogeneous differential operators $$\displaystyle -Î^2 u + λÎu \geq (K_{α, β} * u^p)u^q \quad…
Elliptic inequalities with nonlinear convolution and Hardy terms in cone-like domains
Marius Ghergu, Zhe Yu
We study the inequality in an unbounded cone () generated by a subdomain …
Large-scale Charging of Electric Vehicles: A Multi-Armed Bandit Approach
Zhe Yu, Yunjian Xu, Lang Tong
The successful launch of electric vehicles (EVs) depends critically on the availability of convenient and economic charging facilities. The problem of scheduling of large-scale cha…
Optimal Distributed Energy Resources Sizing for Commercial Building Hybrid Microgrids
Yishen Wang, Zhehan Yi, Di Shi +3
As microgrids have advanced from early prototypes to relatively mature technologies, converting data center integrated commercial buildings to microgrids provides economic, reliabi…
Diagnosing Tsallis Holographic Dark Energy models with interactions
Nan Zhang, Ya-Bo Wu, Jia-Nan Chi +2
It has been found that the geometrical diagnostic methods can break the degeneracy for dark energy models. In this paper, we investigate the diagnostic, the statefinder hierar…
Composition Collapse: Stable Factual Knowledge Does Not Imply Compositional Reasoning
Zhe Yu, Wenpeng Xing, Yunzhao Wei +4
Post-training is routinely evaluated through aggregate benchmark scores that treat multi-hop reasoning as a single capability -- as if a model that answers more questions correctly…
Reverberation Mapping of Two Luminous Quasars: the Broad-line Region Structure and Black Hole Mass
Sha-Sha Li, Sen Yang, Zi-Xu Yang +21
We report the results of a multi-year spectroscopic and photometric monitoring campaign of two luminous quasars, PG~0923+201 and PG~1001+291, both located at the high-luminosity en…
Distributed Frequency Emergency Control with Coordinated Edge Intelligence
Yingmeng Xiang, Zhehan Yi, Xiao Lu +5
Developing effective strategies to rapidly support grid frequency while minimizing loss in case of severe contingencies is an important requirement in power systems. While distribu…
Fairway: A Way to Build Fair ML Software
Joymallya Chakraborty, Suvodeep Majumder, Zhe Yu +1
Machine learning software is increasingly being used to make decisions that affect people's lives. But sometimes, the core part of this software (the learned model), behaves in a b…
LatentAudit: Real-Time White-Box Faithfulness Monitoring for Retrieval-Augmented Generation with Verifiable Deployment
Zhe Yu, Wenpeng Xing, Meng Han
Retrieval-augmented generation (RAG) mitigates hallucination but does not eliminate it: a deployed system must still decide, at inference time, whether its answer is actually suppo…
Comparative Separation: Evaluating Separation on Comparative Judgment Test Data
Xiaoyin Xi, Neeku Capak, Kate Stockwell +1
This research seeks to benefit the software engineering society by proposing comparative separation, a novel group fairness notion to evaluate the fairness of machine learning soft…
An Extended Kalman Filter Enhanced Hilbert-Huang Transform in Oscillation Detection
Zhe Yu, Di Shi, Haifeng Li +3
Hilbert-Huang transform (HHT) has drawn great attention in power system analysis due to its capability to deal with dynamic signal and provide instantaneous characteristics such as…
Differential Parity: Relative Fairness Between Two Sets of Decisions
Zhe Yu, Xiaoyin Xi, Pranam Prakash Shetty
With AI systems widely applied to assist humans in decision-making processes such as talent hiring, school admission, and loan approval; there is an increasing need to ensure that…
Cordon-MAS: Defending RAG against Knowledge Poisoning via Information-Flow Control
Zhe Yu, Wenpeng Xing, Gaolei Li +4
Retrieval-augmented generation (RAG) increasingly underpins high-stakes applications, yet remains vulnerable to Confundo-style poisoning where adversarially optimized documents man…
Isolated singularities for elliptic equations with convolution terms in a punctured ball
Marius Ghergu, Zhe Yu
The purpose of this article is two-fold. First, we investigate the inequality $$ -Îu+V(x) u\geq f\quad\mbox{ in } B_1\setminus\{0\}\subset \mathbb{R}^N , N \geq 2, $$ where $f\in…
FairReweighing: Density Estimation-Based Reweighing Framework for Improving Separation in Fair Regression
Xiaoyin Xi, Zhe Yu
There has been a prevalence of applying AI software in both high-stakes public-sector and industrial contexts. However, the lack of transparency has raised concerns about whether t…
Modeling Art Evaluations from Comparative Judgments: A Deep Learning Approach to Predicting Aesthetic Preferences
Manoj Reddy Bethi, Sai Rupa Jhade, Pravallika Yaganti +2
Modeling human aesthetic judgments in visual art presents significant challenges due to individual preference variability and the high cost of obtaining labeled data. To reduce cos…
Aggregation-Based Datacenter Energy Management in Wholesale Electricity Markets
Zhe Yu, Yuanxiong Guo, Miao Pan +1
In this paper, we study how datacenter energy cost can be effectively reduced in the wholesale electricity market via cooperative power procurement. Intuitively, by aggregating wor…
Crowdtesting : When is The Party Over?
Junjie Wang, Ye Yang, Zhe Yu +2
Trade-offs such as "how much testing is enough" are critical yet challenging project decisions in software engineering. Most existing approaches adopt risk-driven or value-based an…
Deadline Scheduling as Restless Bandits
Zhe Yu, Yunjian Xu, Lang Tong
The problem of stochastic deadline scheduling is considered. A constrained Markov decision process model is introduced in which jobs arrive randomly at a service center with stocha…
Total Recall, Language Processing, and Software Engineering
Zhe Yu, Tim Menzies
A broad class of software engineering problems can be generalized as the "total recall problem". This short paper claims that identifying and exploring total recall language proces…
Comprehensive Evaluation of ChatGPT Reliability Through Multilingual Inquiries
Poorna Chander Reddy Puttaparthi, Soham Sanjay Deo, Hakan Gul +3
ChatGPT is currently the most popular large language model (LLM), with over 100 million users, making a significant impact on people's lives. However, due to the presence of jailbr…
On the Documentation of Refactoring Types
Eman Abdullah AlOmar, Jiaqian Liu, Kenneth Addo +4
Commit messages are the atomic level of software documentation. They provide a natural language description of the code change and its purpose. Messages are critical for software m…
Time Series Classification for Locating Forced Oscillation Sources
Yao Meng, Zhe Yu, Ning Lu +1
Forced oscillations are caused by sustained cyclic disturbances. This paper presents a machine learning (ML) based time-series classification method that uses the synchrophasor mea…
Detecting Is Not Resolving: The Monitoring Control Gap in Retrieval Augmented LLMs
Zhe Yu, Wenpeng Xing, Chen Ye +4
Retrieval-augmented LLMs are deployed for tasks where evidence quality determines action safety, yet evaluation protocols assume that single-turn robustness predicts robustness whe…
Impact of particle production during inflation on the CMB detection
Xunliang Yang, Zhe Yu, Zhoujian Cao
This work focuses on particle production described by a nonminimally coupled model during inflation. In this model, three parameters determine the characteristic frequency and stre…
Bayesian Estimation Based Parameter Estimation for Composite Load
Chang Fu, Zhe Yu, Di Shi +4
Accurate identification of parameters of load models is essential in power system computations, including simulation, prediction, and stability and reliability analysis. Convention…
Distributed Estimation of Oscillations in Power Systems: an Extended Kalman Filtering Approach
Zhe Yu, Di Shi, Zhiwei Wang +3
Online estimation of electromechanical oscillation parameters provides essential information to prevent system instability and blackout and helps to identify event categories and l…
One Leak Away: How Pretrained Model Exposure Amplifies Jailbreak Risks in Finetuned LLMs
Yixin Tan, Zhe Yu, Jun Sakuma +1
Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, parti…
Virtual absorption modes of Schwarzschild-de Sitter spacetimes in semi-open systems
Liang-Bi Wu, Yu-Sen Zhou, Zhe Yu +2
We present a study of virtual absorption modes (VAMs) in Schwarzschild-de Sitter (SdS) spacetime under semi-open boundary conditions, where the VAMs correspond to total transmissio…
Approaching Code Search for Python as a Translation Retrieval Problem with Dual Encoders
Monoshiz Mahbub Khan, Zhe Yu
Code search is vital in the maintenance and extension of software systems. Past works have used separate language models for the natural language and programming language artifacts…
Identifying Self-Admitted Technical Debts with Jitterbug: A Two-step Approach
Zhe Yu, Fahmid Morshed Fahid, Huy Tu +1
Keeping track of and managing Self-Admitted Technical Debts (SATDs) are important to maintaining a healthy software project. This requires much time and effort from human experts t…
Online Low Frequency Oscillation Detection and Analysis System with an Ensemble Filter
Desong Bian, Zhe Yu, Di Shi +2
The widespread deployment of phasor measurement unit (PMU) overpower systems makes it possible to monitor and analyze grid dynamics in real-time. Low-frequency oscillation is harmf…
Mano Technical Report
Tianyu Fu, Anyang Su, Chenxu Zhao +20
Graphical user interfaces (GUIs) are the primary medium for human-computer interaction, yet automating GUI interactions remains challenging due to the complexity of visual elements…
Assessing Expert System-Assisted Literature Reviews With a Case Study
Zhe Yu, Jeffrey C. Carver, Gregg Rothermel +1
Given the large number of publications in software engineering, frequent literature reviews are required to keep current on work in specific areas. One tedious work in literature r…
A Joint Planning Model for Fixed and Mobile Electric Vehicle Charging Stations Considering Flexible Capacity Strategy
Zhe Yu, Xue Hu, Qin Wang
The widespread adoption of electric vehicles (EVs) has significantly increased demand on both transportation and power systems, posing challenges to their stable operation. To supp…
Online Calibration of Phasor Measurement Unit Using Density-Based Spatial Clustering
Xinan Wang, Di Shi, Zhiwei Wang +4
Data quality of Phasor Measurement Unit (PMU) is receiving increasing attention as it has been identified as one of the limiting factors that affect many wide-area measurement syst…
A Data-driven Region Generation Framework for Spatiotemporal Transportation Service Management
Liyue Chen, Jiangyi Fang, Zhe Yu +3
MAUP (modifiable areal unit problem) is a fundamental problem for spatial data management and analysis. As an instantiation of MAUP in online transportation platforms, region gener…
Wide Area Measurement System-based Low Frequency Oscillation Damping Control through Reinforcement Learning
Yousaf Hashmy, Zhe Yu, Di Shi +1
Ensuring the stability of power systems is gaining more attraction today than ever before, due to the rapid growth of uncertainties in load and renewable energy penetration. Lately…
Improving Vulnerability Inspection Efficiency Using Active Learning
Zhe Yu, Christopher Theisen, Laurie Williams +1
Software engineers can find vulnerabilities with less effort if they are directed towards code that might contain more vulnerabilities. HARMLESS is an incremental support vector ma…
Efficient Story Point Estimation With Comparative Learning
Monoshiz Mahbub Khan, Xiaoyin Xi, Andrew Meneely +2
Story points are unitless, project-specific effort estimates that help developers plan their sprints. Traditionally, developers have collaboratively estimated story points using pl…
Bilevel Optimization Based Transmission Expansion Planning Considering Phase Shifting Transformer
Xiaohu Zhang, Di Shi, Zhiwei Wang +4
In this paper, the phase shifting transformer (PST) is introduced in the Transmission Expansion Planning (TEP) problem considering significant wind power integration. The proposed…
The Attribution Blind Spot: Detecting When Language Models Rely on Memory Rather Than Retrieved Context
Zhe Yu, Wenpeng Xing, Yunzhao Wei +4
Retrieval-augmented generation promises to ground language model outputs in external evidence, yet the field has no reliable way to verify whether retrieved context actually govern…
FairBalance: How to Achieve Equalized Odds With Data Pre-processing
Zhe Yu, Joymallya Chakraborty, Tim Menzies
This research seeks to benefit the software engineering society by providing a simple yet effective pre-processing approach to achieve equalized odds fairness in machine learning s…
Better Data Labelling with EMBLEM (and how that Impacts Defect Prediction)
Huy Tu, Zhe Yu, Tim Menzies
Standard automatic methods for recognizing problematic development commits can be greatly improved via the incremental application of human+artificial expertise. In this approach,…
Estimation of Participation Factors for Power System Oscillation from Measurements
Tianwei Xia, Zhe Yu, Kai Sun +2
In a power system, when the participation factors of generators are computed to rank their participations into an oscillatory mode, a model-based approach is conventionally used on…