arXiv subjects

Jiyang Zhang

Publications and source records attributed to Jiyang Zhang.

16 recordsLinked to original sources

arXiv2026

Retrofitting Code Using LLMs to Support Exceptional Behavior

Exception Related Code (ERC), which includes throw statements, conditions (if statements) that guard those throw statements, and try/catch blocks, is an essential component of software systems, allowing developers to detect and handle exceptional states that deviate from the expected program behavior. However, manually writing ERC across large codebases is tedious. We propose a novel task: retrofitting existing code with ERC. Namely, given code (without ERC) and Exceptional Behavior Tests (EBTs) (e.g., check if method throws InvalidArgumentException if null is given as the value to the argument) we aim to automatically generate missing ERC, such that the given tests pass. We design and implement Exception Coder (EXCODER) that performs context engineering to help Large Language Models (LLMs) tackle this task. EXCODER integrates static and dynamic program analysis with LLMs by providing the extracted contextual information to the LLMs. To evaluate EXCODER, we build a benchmark constructed from GitHub Java repositories, where we systematically remove ERC in 304 methods from 75 projects. Our results demonstrate that EXCODER provides an effective, though imperfect, solution to this problem in automated code generation, offering developers the first way to implement ERC following test-driven development. When combined with Qwen 2.5 Coder 32b, EXCODER achieves pass@1, 5, and 10 rates of 85.92% (12.56 percentage points over baseline), 86.18% (12.82 p.p. over baseline), and 86.51% (13.15 p.p. over baseline), respectively, on developer-written test suites. Our manual inspection of the generated code further reveals limitations of EXCODER, pointing to directions for future work.

cs.SE↗

arXiv2026

Optimal slit width for high-precision orbital angular momentum measurement using angular double-slit interferometry

We demonstrate an optimization of angular double-slit interferometry for accurate measurement of orbital angular momentum (OAM) of vortex beams. By scanning the dynamic double slits, the topological charge (TC) magnitude is directly determined from the oscillation frequency of the on-axis intensity. Based on repeated experimental investigations, we establish a critical criterion for slit width selection: to avoid phase truncation or period overlap, the angular width of each slit must exactly match the spiral phase period 2π/|l|. Under this optimal condition, the interference pattern exhibits the highest visibility and the measurement error is minimized. Experiments for l = 5, 10, and 15 are performed as representative examples, and the universality of this criterion is confirmed. Furthermore, by introducing an additional phase shift, the sign of the TC is unambiguously determined, as demonstrated for l = 10 and l = -15. This simple, robust method provides a high-precision pathway for OAM metrology.

physics.optics↗

arXiv2026

LLMs Lean on Priors, Not Programming Language Semantics

Recent work asks whether large language models (LLMs) condition their reasoning on explicit rules rather than statistical regularities from pretraining. Program execution provides a canonical instance: formal semantics define behavior through symbolic transition rules that can be systematically altered under distribution shift. We investigate whether LLMs can condition their reasoning on formal semantics through program execution and introduce PLSemanticsBench, pairing featherweight C programs with two semantic systems -- small-step operational semantics and K semantics -- and probing four capabilities: composing rules for final states, selecting rules when state is unmutated, sustaining such conditioning over long traces, and following supplied rules under novel semantics. To decouple semantic reasoning from syntactic familiarity, we redefine familiar operators to induce symbol-meaning conflict and introduce novel symbols defined only through the supplied rules, and stress-test models on Human-Written, LLM-Translated, and Fuzzer-Generated splits with increasing structural complexity. Across 11 frontier LLMs, strong final-state accuracy under standard semantics (up to 90%) drops sharply -- by as much as 40--60% points -- under semantic mutations and increasing structural complexity. Only a handful of models achieve non-zero long-horizon conditioning accuracy, and even the best systems reach just 35%. Together, these results suggest that contemporary LLMs often rely on pretrained lexical associations rather than systematically conditioning on supplied formal rules. PLSemanticsBench is publicly available at https://EngineeringSoftware.github.io/PLSemanticsBench.

cs.PL↗

arXiv2026

AutoMerge: Search-Based Model Merging Framework for Effective Model Reuse

Software reuse has long been recognized as a critical and widely studied topic in software engineering, offering substantial benefits in reducing development costs, improving software quality, and enhancing operational efficiency. This paradigm extends into deep learning through model reuse. Recently, model merging has emerged in the domain of large language models (LLMs) as a training-free approach that takes multiple task-specific models with the same architecture as source models and merges them without retraining, enhancing model reuse within LLMs. However, no prior work has systematically investigated whether such an approach can be effectively applied to other deep learning models with different architectures across domains. To bridge this gap, we present the first systematic study that evaluates five model merging techniques on three distinct model architectures across three domains: LLMs, image classification, and autonomous driving. Our findings reveal that directly applying existing model merging techniques leads to highly inconsistent results and falls notably short of their success within LLMs. Moreover, a single model merging technique often fails to handle the heterogeneous structural properties within a model, limiting its applicability to different model architectures across domains. Furthermore, the effectiveness of model merging techniques is highly sensitive to hyperparameter configurations, thereby constraining their potential for broader adoption. Inspired by these insights, we propose AutoMerge, a novel search-based model merging framework that first segments complex models into multiple heterogeneous blocks and then systematically explores the merging space to identify the merging technique and its hyperparameter configuration.

cs.SE↗

arXiv2025

Assessing Coronary Microvascular Dysfunction using Angiography-based Data-driven Methods

Coronary microvascular dysfunction (CMD), characterized by impaired regulation of blood flow in the coronary microcirculation, plays a key role in the pathogenesis of ischemic heart disease and is increasingly recognized as a contributor to adverse cardiovascular outcomes. Despite its clinical importance, CMD remains underdiagnosed due to the reliance on invasive procedures such as pressure wire-based measurements of the index of microcirculatory resistance (IMR) and coronary flow reserve (CFR), which are costly, time-consuming, and carry procedural risks. To date, no study has sought to quantify CMD indices using data-driven approaches while leveraging the rich information contained in coronary angiograms. To address these limitations, this study proposes a novel data-driven framework for inference of CMD indices based on coronary angiography. A physiologically validated multi-physics model was used to generate synthetic datasets for data-driven model training, consisting of CMD indices and computational angiograms with corresponding contrast intensity profiles (CIPs). Two neural network architectures were developed: a single-input-channel encoder-MLP model for IMR prediction and a dual-input-channel encoder-MLP model for CFR prediction, both incorporating epistemic uncertainty estimation to quantify prediction confidence. Results demonstrate that the data-driven models achieve high predictive accuracy when evaluated against physics-based synthetic datasets, and that the uncertainty estimates are positively correlated with prediction errors. Furthermore, the utility of CIPs as informative surrogates for coronary physiology is demonstrated, underscoring the potential of the proposed framework to enable accurate, real-time, image-based CMD assessment using routine angiography without the need for more invasive approaches.

cs.CE↗

arXiv2025

A Multi-physics Model of Flow from Coronary Angiography: Insights to Microvascular Function

Coronary Microvascular Dysfunction (CMD) is characterized by impaired vasodilation and can lead to insufficient blood flow to the myocardium during stress or exertion, affecting millions of people globally. Despite their diagnostic value, invasive, wire-based diagnosis techniques of CMD, such as index of microcirculatory resistance (IMR) and coronary flow reserve (CFR), are underutilized due to their complexity and inconsistency. Coronary angiography, one of the most commonly used imaging modalities, offers valuable flow information that assists in diagnosing CMD. However, this information is not fully understood or utilized in current clinical practice. In this study, a 3D-0D coupled multi-physics computational fluid dynamics (CFD) model was developed and calibrated to simulate and study the process of contrast injection and washout during clinical angiography. A contrast intensity profile (CIP) was introduced to describe the dynamics of coronary angiography data. Additionally, sensitivity studies were conducted to evaluate the influence of various coronary lumped parameter model (LPM) parameters on the shapes of CIPs. The results demonstrate that the multi-physics model can be effectively calibrated to produce physiologically meaningful hemodynamic results. Sensitivity studies reveal that resistance has a greater impact on the rising and falling slopes of CIP than capacitance, with higher resistance amplifying this effect. The model and results are presented here. These results are potentially transformative, as they provide a tool for interpreting angiographic data and ultimately extracting information concerning coronary microcirculation.

cs.CE↗

arXiv2025

A Tool for Generating Exceptional Behavior Tests With Large Language Models

Exceptional behavior tests (EBTs) are crucial in software development for verifying that code correctly handles unwanted events and throws appropriate exceptions. However, prior research has shown that developers often prioritize testing "happy paths", e.g., paths without unwanted events over exceptional scenarios. We present exLong, a framework that automatically generates EBTs to address this gap. exLong leverages a large language model (LLM) fine-tuned from CodeLlama and incorporates reasoning about exception-throwing traces, conditional expressions that guard throw statements, and non-exceptional behavior tests that execute similar traces. Our demonstration video illustrates how exLong can effectively assist developers in creating comprehensive EBTs for their project (available at https://youtu.be/Jro8kMgplZk).

cs.SE↗

arXiv2024

exLong: Generating Exceptional Behavior Tests with Large Language Models

Many popular programming languages, including C#, Java, and Python, support exceptions. Exceptions are thrown during program execution if an unwanted event happens, e.g., a method is invoked with an illegal argument value. Software developers write exceptional behavior tests (EBTs) to check that their code detects unwanted events and throws appropriate exceptions. Prior research studies have shown the importance of EBTs, but those studies also highlighted that developers put most of their efforts on "happy paths", e.g., paths without unwanted events. To help developers fill the gap, we present the first framework, dubbed exLong, that automatically generates EBTs. exLong is a large language model instruction fine-tuned from CodeLlama and embeds reasoning about traces that lead to throw statements, conditional expressions that guard throw statements, and non-exceptional behavior tests that execute similar traces. We compare exLong with the state-of-the-art models for test generation (CAT-LM) and one of the strongest foundation models (GPT-4o), as well as with analysis-based tools for test generation (Randoop and EvoSuite). Our results show that exLong outperforms existing models and tools. Furthermore, we contributed several pull requests to open-source projects and 23 EBTs generated by exLong were already accepted.

cs.SE↗

arXiv2024

Few-shot fault diagnosis based on multi-scale graph convolution filtering for industry

Industrial equipment fault diagnosis often encounter challenges such as the scarcity of fault data, complex operating conditions, and varied types of failures. Signal analysis, data statistical learning, and conventional deep learning techniques face constraints under these conditions due to their substantial data requirements and the necessity for transfer learning to accommodate new failure modes. To effectively leverage information and extract the intrinsic characteristics of faults across different domains under limited sample conditions, this paper introduces a fault diagnosis approach employing Multi-Scale Graph Convolution Filtering (MSGCF). MSGCF enhances the traditional Graph Neural Network (GNN) framework by integrating both local and global information fusion modules within the graph convolution filter block. This advancement effectively mitigates the over-smoothing issue associated with excessive layering of graph convolutional layers while preserving a broad receptive field. It also reduces the risk of overfitting in few-shot diagnosis, thereby augmenting the model's representational capacity. Experiments on the University of Paderborn bearing dataset (PU) demonstrate that the MSGCF method proposed herein surpasses alternative approaches in accuracy, thereby offering valuable insights for industrial fault diagnosis in few-shot learning scenarios.

cs.AI↗

arXiv2023

Multilingual Code Co-Evolution Using Large Language Models

Many software projects implement APIs and algorithms in multiple programming languages. Maintaining such projects is tiresome, as developers have to ensure that any change (e.g., a bug fix or a new feature) is being propagated, timely and without errors, to implementations in other programming languages. In the world of ever-changing software, using rule-based translation tools (i.e., transpilers) or machine learning models for translating code from one language to another provides limited value. Translating each time the entire codebase from one language to another is not the way developers work. In this paper, we target a novel task: translating code changes from one programming language to another using large language models (LLMs). We design and implement the first LLM, dubbed Codeditor, to tackle this task. Codeditor explicitly models code changes as edit sequences and learns to correlate changes across programming languages. To evaluate Codeditor, we collect a corpus of 6,613 aligned code changes from 8 pairs of open-source software projects implementing similar functionalities in two programming languages (Java and C#). Results show that Codeditor outperforms the state-of-the-art approaches by a large margin on all commonly used automatic metrics. Our work also reveals that Codeditor is complementary to the existing generation-based models, and their combination ensures even greater performance.

cs.SE↗

arXiv2023

Using Large-scale Heterogeneous Graph Representation Learning for Code Review Recommendations at Microsoft

Code review is an integral part of any mature software development process, and identifying the best reviewer for a code change is a well-accepted problem within the software engineering community. Selecting a reviewer who lacks expertise and understanding can slow development or result in more defects. To date, most reviewer recommendation systems rely primarily on historical file change and review information; those who changed or reviewed a file in the past are the best positioned to review in the future. We posit that while these approaches are able to identify and suggest qualified reviewers, they may be blind to reviewers who have the needed expertise and have simply never interacted with the changed files before. Fortunately, at Microsoft, we have a wealth of work artifacts across many repositories that can yield valuable information about our developers. To address the aforementioned problem, we present CORAL, a novel approach to reviewer recommendation that leverages a socio-technical graph built from the rich set of entities (developers, repositories, files, pull requests (PRs), work items, etc.) and their relationships in modern source code management systems. We employ a graph convolutional neural network on this graph and train it on two and a half years of history on 332 repositories within Microsoft. We show that CORAL is able to model the manual history of reviewer selection remarkably well. Further, based on an extensive user study, we demonstrate that this approach identifies relevant and qualified reviewers who traditional reviewer recommenders miss, and that these developers desire to be included in the review process. Finally, we find that "classical" reviewer recommendation systems perform better on smaller (in terms of developers) software projects while CORAL excels on larger projects, suggesting that there is "no one model to rule them all."

cs.SE↗

arXiv2022

CoditT5: Pretraining for Source Code and Natural Language Editing

Pretrained language models have been shown to be effective in many software-related generation tasks; however, they are not well-suited for editing tasks as they are not designed to reason about edits. To address this, we propose a novel pretraining objective which explicitly models edits and use it to build CoditT5, a large language model for software-related editing tasks that is pretrained on large amounts of source code and natural language comments. We fine-tune it on various downstream editing tasks, including comment updating, bug fixing, and automated code review. By outperforming standard generation-based models, we demonstrate the generalizability of our approach and its suitability for editing tasks. We also show how a standard generation model and our edit-based model can complement one another through simple reranking strategies, with which we achieve state-of-the-art performance for the three downstream editing tasks.

cs.SE↗

arXiv2022

Impact of Evaluation Methodologies on Code Summarization

There has been a growing interest in developing machine learning (ML) models for code summarization tasks, e.g., comment generation and method naming. Despite substantial increase in the effectiveness of ML models, the evaluation methodologies, i.e., the way people split datasets into training, validation, and test sets, were not well studied. Specifically, no prior work on code summarization considered the timestamps of code and comments during evaluation. This may lead to evaluations that are inconsistent with the intended use cases. In this paper, we introduce the time-segmented evaluation methodology, which is novel to the code summarization research community, and compare it with the mixed-project and cross-project methodologies that have been commonly used. Each methodology can be mapped to some use cases, and the time-segmented methodology should be adopted in the evaluation of ML models for code summarization. To assess the impact of methodologies, we collect a dataset of (code, comment) pairs with timestamps to train and evaluate several recent ML models for code summarization. Our experiments show that different methodologies lead to conflicting evaluation results. We invite the community to expand the set of methodologies used in evaluations.

cs.SE↗

arXiv2021

Deep Metric Learning Model for Imbalanced Fault Diagnosis

Intelligent diagnosis method based on data-driven and deep learning is an attractive and meaningful field in recent years. However, in practical application scenarios, the imbalance of time-series fault is an urgent problem to be solved. This paper proposes a novel deep metric learning model, where imbalanced fault data and a quadruplet data pair design manner are considered. Based on such data pair, a quadruplet loss function which takes into account the inter-class distance and the intra-class data distribution are proposed. This quadruplet loss pays special attention to imbalanced sample pair. The reasonable combination of quadruplet loss and softmax loss function can reduce the impact of imbalance. Experiment results on two open-source datasets show that the proposed method can effectively and robustly improve the performance of imbalanced fault diagnosis.

cs.LG↗

arXiv2021

Learning to Generate Code Comments from Class Hierarchies

Descriptive code comments are essential for supporting code comprehension and maintenance. We propose the task of automatically generating comments for overriding methods. We formulate a novel framework which accommodates the unique contextual and linguistic reasoning that is required for performing this task. Our approach features: (1) incorporating context from the class hierarchy; (2) conditioning on learned, latent representations of specificity to generate comments that capture the more specialized behavior of the overriding method; and (3) unlikelihood training to discourage predictions which do not conform to invariant characteristics of the comment corresponding to the overridden method. Our experiments show that the proposed approach is able to generate comments for overriding methods of higher quality compared to prevailing comment generation techniques.

cs.CL↗

arXiv2019

orthoDr: Semiparametric Dimension Reduction via Orthogonality Constrained Optimization

orthoDr is a package in R that solves dimension reduction problems using orthogonality constrained optimization approach. The package serves as a unified framework for many regression and survival analysis dimension reduction models that utilize semiparametric estimating equations. The main computational machinery of orthoDr is a first-order algorithm developed by \cite{wen2013feasible} for optimization within the Stiefel manifold. We implement the algorithm through Rcpp and OpenMP for fast computation. In addition, we developed a general-purpose solver for such constrained problems with user-specified objective functions, which works as a drop-in version of optim(). The package also serves as a platform for future methodology developments along this line of work.

stat.CO↗