arXiv subjects

Chong Wang

Publications and source records attributed to Chong Wang.

At least 91 records · Page 5Linked to original sources

arXiv2025

Evaluating Large Language Models for Line-Level Vulnerability Localization

Recently, Automated Vulnerability Localization (AVL) has attracted growing attention, aiming to facilitate diagnosis by pinpointing the specific lines of code responsible for vulnerabilities. Large Language Models (LLMs) have shown potential in various domains, yet their effectiveness in line-level vulnerability localization remains underexplored. In this work, we present the first comprehensive empirical evaluation of LLMs for AVL. Our study examines 19 leading LLMs suitable for code analysis, including ChatGPT and multiple open-source models, spanning encoder-only, encoder-decoder, and decoder-only architectures, with model sizes from 60M to 70B parameters. We evaluate three paradigms including few-shot prompting, discriminative fine-tuning, and generative fine-tuning with and without Low-Rank Adaptation (LoRA), on both a BigVul-derived dataset for C/C++ and a smart contract vulnerability dataset.} Our results show that discriminative fine-tuning achieves substantial performance gains over existing learning-based AVL methods when sufficient training data is available. In low-data settings, prompting advanced LLMs such as ChatGPT proves more effective. We also identify challenges related to input length and unidirectional context during fine-tuning, and propose two remedial strategies: a sliding window approach and right-forward embedding, both of which yield significant improvements. Moreover, we provide the first assessment of LLM generalizability in AVL, showing that certain models can transfer effectively across Common Weakness Enumerations (CWEs) and projects. However, performance degrades notably for newly discovered vulnerabilities containing unfamiliar lexical or structural patterns, underscoring the need for continual adaptation.

cs.SE↗

arXiv2025

Casting a SPELL: Sentence Pairing Exploration for LLM Limitation-breaking

Large language models (LLMs) have revolutionized software development through AI-assisted coding tools, enabling developers with limited programming expertise to create sophisticated applications. However, this accessibility extends to malicious actors who may exploit these powerful tools to generate harmful software. Existing jailbreaking research primarily focuses on general attack scenarios against LLMs, with limited exploration of malicious code generation as a jailbreak target. To address this gap, we propose SPELL, a comprehensive testing framework specifically designed to evaluate the weakness of security alignment in malicious code generation. Our framework employs a time-division selection strategy that systematically constructs jailbreaking prompts by intelligently combining sentences from a prior knowledge dataset, balancing exploration of novel attack patterns with exploitation of successful techniques. Extensive evaluation across three advanced code models (GPT-4.1, Claude-3.5, and Qwen2.5-Coder) demonstrates SPELL's effectiveness, achieving attack success rates of 83.75%, 19.38%, and 68.12% respectively across eight malicious code categories. The generated prompts successfully produce malicious code in real-world AI development tools such as Cursor, with outputs confirmed as malicious by state-of-the-art detection systems at rates exceeding 73%. These findings reveal significant security gaps in current LLM implementations and provide valuable insights for improving AI safety alignment in code generation applications.

cs.CR↗

arXiv2025

Moiré-modulated $Γ$ valley in twisted bilayer and twisted double-bilayer MoTe$_2$

Twisted MoTe$_2$ hosts intriguing correlated quantum phenomena including the fractional quantum anomalous Hall effect in twisted bilayer (t-BL) MoTe$_2$ near 3.7$^\circ$, which is sensitive to the twist angle and moiré superlattices. Here, we directly visualize the twist-angle-modulated electronic structure of t-BL and twisted double-bilayer (t-DBL) near this critical angle. We find that the moiré superlattice not only modifies the relative energy between $Γ$ and K valleys in t-BL MoTe$_2$, but also strongly reconstructs the $Γ$ valley for both t-BL and t-DBL. Specifically, the deep $p_z$-derived band at $Γ$ exhibits a distinct splitting that systematically varies with increasing twist angle. Theoretical analysis suggests that this modulation arises from the twist-angle-dependent lattice relaxation, especially interfacial corrugations. Our work directly visualizes the moiré-modulated electronic structure and provides key spectroscopic information of lattice relaxation and interlayer interactions underlying the physics of twisted MoTe$_2$.

cond-mat.str-el↗

arXiv2025

MFGDiffusion: Mask-Guided Smoke Synthesis for Enhanced Forest Fire Detection

Smoke is the first visible indicator of a wildfire.With the advancement of deep learning, image-based smoke detection has become a crucial method for detecting and preventing forest fires. However, the scarcity of smoke image data from forest fires is one of the significant factors hindering the detection of forest fire smoke. Image generation models offer a promising solution for synthesizing realistic smoke images. However, current inpainting models exhibit limitations in generating high-quality smoke representations, particularly manifesting as inconsistencies between synthesized smoke and background contexts. To solve these problems, we proposed a comprehensive framework for generating forest fire smoke images. Firstly, we employed the pre-trained segmentation model and the multimodal model to obtain smoke masks and image captions.Then, to address the insufficient utilization of masks and masked images by inpainting models, we introduced a network architecture guided by mask and masked image features. We also proposed a new loss function, the mask random difference loss, which enhances the consistency of the generated effects around the mask by randomly expanding and eroding the mask edges.Finally, to generate a smoke image dataset using random masks for subsequent detection tasks, we incorporated smoke characteristics and use a multimodal large language model as a filtering tool to select diverse and reasonable smoke images, thereby improving the quality of the synthetic dataset. Experiments showed that our generated smoke images are realistic and diverse, and effectively enhance the performance of forest fire smoke detection models. Code is available at https://github.com/wghr123/MFGDiffusion.

cs.CV↗

arXiv2025

Synthetic bootstrapped pretraining

We introduce Synthetic Bootstrapped Pretraining (SBP), a language model (LM) pretraining procedure that first learns a model of relations between documents from the pretraining dataset and then leverages it to synthesize a vast new corpus for joint training. While the standard pretraining teaches LMs to learn causal correlations among tokens within a single document, it is not designed to efficiently model the rich, learnable inter-document correlations that can potentially lead to better performance. We validate SBP by designing a compute-matched pretraining setup and pretrain a 3B-parameter and a 6B-parameter model on up to 1T tokens from scratch. We find SBP consistently improves upon a strong repetition baseline and delivers up to 60% of performance improvement attainable by an oracle upper bound with access to 20x more unique data. Qualitative analysis reveals that the synthesized documents go beyond mere paraphrases -- SBP first abstracts a core concept from the seed material and then crafts a new narration on top of it. Besides strong empirical performance, SBP admits a natural Bayesian interpretation: the synthesizer implicitly learns to abstract the latent concepts shared between related documents.

cs.CL↗

arXiv2025

RLAX: Large-Scale, Distributed Reinforcement Learning for Large Language Models on TPUs

Reinforcement learning (RL) has emerged as the de-facto paradigm for improving the reasoning capabilities of large language models (LLMs). We have developed RLAX, a scalable RL framework on TPUs. RLAX employs a parameter-server architecture. A master trainer periodically pushes updated model weights to the parameter server while a fleet of inference workers pull the latest weights and generates new rollouts. We introduce a suite of system techniques to enable scalable and preemptible RL for a diverse set of state-of-art RL algorithms. To accelerate convergence and improve model quality, we have devised new dataset curation and alignment techniques. Large-scale evaluations show that RLAX improves QwQ-32B's pass@8 accuracy by 12.8% in just 12 hours 48 minutes on 1024 v5p TPUs, while remaining robust to preemptions during training.

cs.LG↗

arXiv2025

Time-step Mixup for Efficient Spiking Knowledge Transfer from Appearance to Event Domain

The integration of event cameras and spiking neural networks holds great promise for energy-efficient visual processing. However, the limited availability of event data and the sparse nature of DVS outputs pose challenges for effective training. Although some prior work has attempted to transfer semantic knowledge from RGB datasets to DVS, they often overlook the significant distribution gap between the two modalities. In this paper, we propose Time-step Mixup knowledge transfer (TMKT), a novel fine-grained mixing strategy that exploits the asynchronous nature of SNNs by interpolating RGB and DVS inputs at various time-steps. To enable label mixing in cross-modal scenarios, we further introduce modality-aware auxiliary learning objectives. These objectives support the time-step mixup process and enhance the model's ability to discriminate effectively across different modalities. Our approach enables smoother knowledge transfer, alleviates modality shift during training, and achieves superior performance in spiking image classification tasks. Extensive experiments demonstrate the effectiveness of our method across multiple datasets. The code will be released after the double-blind review process.

cs.CV↗

arXiv2025

Layerwise Stratification and Band Reordering in Twisted Multilayer MoTe$_2$

We introduce a generalizable, physics informed strategy for generating training data that enables a machine learning force field accurate over a broad range of twist angles and stacking layer numbers in moire systems. Applying this to multilayer twisted MoTe2 (tMoTe2), we identify a structural and electronic stratification: the two moire interface (MI) layers retain substantial lattice reconstruction even in thick multilayers, while outer bulk like layers show rapidly attenuated distortions.Surprisingly, this stratification becomes strongest not in the ultra-small twist angle regime (<~1°), where in plane domain formation is well known, but rather at intermediate angles (2-5°). Simultaneously, interlayer hybridization across the MI-bulk boundary is strongly suppressed, leading to electronic isolation. In twisted double bilayer MoTe2, this stratification gives rise to coexisting honeycomb and triangular lattice motifs in the frontier valence bands. We further demonstrate that twist angle and weak gating can create energy shift of bands belonging to the two motifs, producing Chern band reordering and nonlinear electric polarization with modest hole doping. Our approach allows efficient simulation of multilayer moire systems and reveals structural-electronic separation phenomena absent in bilayer systems.

cond-mat.mtrl-sci↗

arXiv2025

MoFa: A Unified Performance Modeling Framework for LLM Pretraining

The exponential growth in LLM scales, with parameters soaring from billions to trillions, has necessitated distributed pretraining across large clusters comprising thousands to tens of thousands of devices. While hybrid parallelization strategies enable such pretraining, the vast combinatorial strategy space introduces significant optimization challenges. Traditional manual tuning methods incur prohibitive trial-and-error costs, and existing performance modeling approaches exhibit critical limitations: they fail to comprehensively account for prevalent optimization features and ignore the substantial overhead imposed by essential fault tolerance mechanisms like checkpoint recovery in long-duration pretraining. To address these gaps, we propose MoFa, a novel pretraining performance modeling framework that unifies multi-dimensional optimization features and fault tolerance. MoFa incorporates an enhanced cost model to accurately capture the effects of key optimizations and integrates a fault tolerance model based on historical cluster reliability data. Besides, a MoFa-based tuning system is developed to explore optimal pretraining performance and potential bottlenecks in various scenarios. Extensive modeling evaluations demonstrate that MoFa can achieve high prediction accuracy across various scenarios. In addition, through comprehensive tuning experiments, our framework systematically reveals the key factors influencing pretraining performance under different configurations, which provides solid a priori guidance for LLM pretraining system design and deployment.

cs.DC↗

arXiv2025

Assessing UML Diagrams by GPT: Implications for Education

In software engineering (SE) research and practice, UML is well known as an essential modeling methodology for requirements analysis and software modeling in both academia and industry. In particular, fundamental knowledge of UML modeling and practice in creating high-quality UML diagrams are included in SE-relevant courses in the undergraduate programs of many universities. This leads to a time-consuming and labor-intensive task for educators to review and grade a large number of UML diagrams created by the students. Recent advances in generative AI techniques, such as GPT, have paved new ways to automate many SE tasks. However, current research or tools seldom explore the capabilities of GPT in evaluating the quality of UML diagrams. This paper aims to investigate the feasibility and performance of GPT in assessing the quality of UML use case diagrams, class diagrams, and sequence diagrams. First, 11 evaluation criteria with grading details were proposed for these UML diagrams. Next, a series of experiments was designed and conducted on 40 students' UML modeling reports to explore the performance of GPT in evaluating and grading these UML diagrams. The research findings reveal that GPT can complete this assessment task, but it cannot replace human experts yet. Meanwhile, there are five evaluation discrepancies between GPT and human experts. These discrepancies vary in the use of different evaluation criteria in different types of UML diagrams, presenting GPT's strengths and weaknesses in this automatic evaluation task.

cs.SE↗

arXiv2025

RATTENTION: Towards the Minimal Sliding Window Size in Local-Global Attention Models

Local-global attention models have recently emerged as compelling alternatives to standard Transformers, promising improvements in both training and inference efficiency. However, the crucial choice of window size presents a Pareto tradeoff: larger windows maintain performance akin to full attention but offer minimal efficiency gains in short-context scenarios, while smaller windows can lead to performance degradation. Current models, such as Gemma2 and Mistral, adopt conservative window sizes (e.g., 4096 out of an 8192 pretraining length) to preserve performance. This work investigates strategies to shift this Pareto frontier, enabling local-global models to achieve efficiency gains even in short-context regimes. Our core motivation is to address the intrinsic limitation of local attention -- its complete disregard for tokens outside the defined window. We explore RATTENTION, a variant of local attention integrated with a specialized linear attention mechanism designed to capture information from these out-of-window tokens. Pretraining experiments at the 3B and 12B scales demonstrate that RATTENTION achieves a superior Pareto tradeoff between performance and efficiency. As a sweet spot, RATTENTION with a window size of just 512 consistently matches the performance of full-attention models across diverse settings. Furthermore, the recurrent nature inherent in the linear attention component of RATTENTION contributes to enhanced long-context performance, as validated on the RULER benchmark. Crucially, these improvements do not compromise training efficiency; thanks to a specialized kernel implementation and the reduced window size, RATTENTION maintains training speeds comparable to existing state-of-the-art approaches. We open-sourced our Pallas kernels along with model codes to facilitate further research effort.

cs.CL↗

arXiv2025

Breaking the Modality Wall: Time-step Mixup for Efficient Spiking Knowledge Transfer from Static to Event Domain

The integration of event cameras and spiking neural networks (SNNs) promises energy-efficient visual intelligence, yet scarce event data and the sparsity of DVS outputs hinder effective training. Prior knowledge transfers from RGB to DVS often underperform because the distribution gap between modalities is substantial. In this work, we present Time-step Mixup Knowledge Transfer (TMKT), a cross-modal training framework with a probabilistic Time-step Mixup (TSM) strategy. TSM exploits the asynchronous nature of SNNs by interpolating RGB and DVS inputs at various time steps to produce a smooth curriculum within each sequence, which reduces gradient variance and stabilizes optimization with theoretical analysis. To employ auxiliary supervision from TSM, TMKT introduces two lightweight modality-aware objectives, Modality Aware Guidance (MAG) for per-frame source supervision and Mixup Ratio Perception (MRP) for sequence-level mix ratio estimation, which explicitly align temporal features with the mixing schedule. TMKT enables smoother knowledge transfer, helps mitigate modality mismatch during training, and achieves superior performance in spiking image classification tasks. Extensive experiments across diverse benchmarks and multiple SNN backbones, together with ablations, demonstrate the effectiveness of our method.

cs.CV↗

arXiv2025

Exploringand Unleashing the Power of Large Language Models in CI/CD Configuration Translation

Continuous Integration (CI) is a cornerstone of modern collaborative software development, and numerous CI platforms are available. Differences in maintenance overhead, reliability, and integration depth with code-hosting platforms make migration between CI platforms a common practice. A central step in migration is translating CI configurations, which is challenging due to the intrinsic complexity of CI configurations and the need to understand semantic differences and relationships across CI platforms. With the advent of large language models (LLMs), recent advances in software engineering highlight their potential for CI configuration translation. In this paper, we present a study on LLM-based CI configuration translation, focusing on the migration from Travis CI to GitHub Actions. First, using 811 migration records, we quantify the effort involved and find that developers read an average of 38 lines of Travis configuration and write 58 lines of GitHub Actions configuration, with nearly half of the migrations requiring multiple commits. We further analyze translations produced by each of the four LLMs and identify 1,121 issues grouped into four categories: logic inconsistencies (38%), platform discrepancies (32%), environment errors (25%), and syntax errors (5%). Finally, we evaluate three enhancement strategies and show that combining guideline-based prompting with iterative refinement achieves the best performance, reaching a Build Success Rate of 75.5%-nearly a threefold improvement over GPT-4o with a basic prompt.

cs.SE↗

arXiv2025

Code Digital Twin: Empowering LLMs with Tacit Knowledge for Complex Software Development

Recent advances in large language models (LLMs) have demonstrated strong capabilities in software engineering tasks, raising expectations of revolutionary productivity gains. However, enterprise software development is largely driven by incremental evolution, where challenges extend far beyond routine coding and depend critically on tacit knowledge, including design decisions at different levels and historical trade-offs. To achieve effective AI-powered support for complex software development, we should align emerging AI capabilities with the practical realities of enterprise development. To this end, we systematically identify challenges from both software and LLM perspectives. Alongside these challenges, we outline opportunities where AI and structured knowledge frameworks can enhance decision-making in tasks such as issue localization and impact analysis. To address these needs, we propose the Code Digital Twin, a living framework that models both the physical and conceptual layers of software, preserves tacit knowledge, and co-evolves with the codebase. By integrating hybrid knowledge representations, multi-stage extraction pipelines, incremental updates, LLM-empowered applications, and human-in-the-loop feedback, the Code Digital Twin transforms fragmented knowledge into explicit and actionable representations. Our vision positions it as a bridge between AI advancements and enterprise software realities, providing a concrete roadmap toward sustainable, intelligent, and resilient development and evolution of ultra-complex systems.

cs.SE↗

arXiv2025

Extracting Conceptual Knowledge to Locate Software Issues

Issue localization, which identifies faulty code elements such as files or functions, is critical for effective bug fixing. While recent LLM-based and LLM-agent-based approaches improve accuracy, they struggle in large-scale repositories due to concern tangling, where relevant logic is buried in large functions, and concern scattering, where related logic is dispersed across files. To address these challenges, we propose RepoLens, a novel approach that abstracts and leverages conceptual knowledge from code repositories. RepoLens decomposes fine-grained functionalities and recomposes them into high-level concerns, semantically coherent clusters of functionalities that guide LLMs. It operates in two stages: an offline stage that extracts and enriches conceptual knowledge into a repository-wide knowledge base, and an online stage that retrieves issue-specific terms, clusters and ranks concerns by relevance, and integrates them into localization workflows via minimally intrusive prompt enhancements. We evaluate RepoLens on SWE-Lancer-Loc, a benchmark of 216 tasks derived from SWE-Lancer. RepoLens consistently improves three state-of-the-art tools, namely AgentLess, OpenHands, and mini-SWE-agent, achieving average gains of over 22% in Hit@k and 46% in Recall@k for file- and function-level localization. It generalizes across models (GPT-4o, GPT-4o-mini, GPT-4.1) with Hit@1 and Recall@10 gains up to 504% and 376%, respectively. Ablation studies and manual evaluation confirm the effectiveness and reliability of the constructed concerns.

cs.SE↗

arXiv2025

Contextualized Representation Learning for Effective Human-Object Interaction Detection

Human-Object Interaction (HOI) detection aims to simultaneously localize human-object pairs and recognize their interactions. While recent two-stage approaches have made significant progress, they still face challenges due to incomplete context modeling. In this work, we introduce a Contextualized Representation Learning that integrates both affordance-guided reasoning and contextual prompts with visual cues to better capture complex interactions. We enhance the conventional HOI detection framework by expanding it beyond simple human-object pairs to include multivariate relationships involving auxiliary entities like tools. Specifically, we explicitly model the functional role (affordance) of these auxiliary objects through triplet structures . This enables our model to identify tool-dependent interactions such as 'filling'. Furthermore, the learnable prompt is enriched with instance categories and subsequently integrated with contextual visual features using an attention mechanism. This process aligns language with image content at both global and regional levels. These contextualized representations equip the model with enriched relational cues for more reliable reasoning over complex, context-dependent interactions. Our proposed method demonstrates superior performance on both the HICO-Det and V-COCO datasets in most scenarios. The source code is available at https://github.com/lzzhhh1019/CRL.

cs.CV↗

arXiv2025

A Study on Thinking Patterns of Large Reasoning Models in Code Generation

Currently, many large language models (LLMs) are utilized for software engineering tasks such as code generation. The emergence of more advanced models known as large reasoning models (LRMs), such as OpenAI's o3, DeepSeek R1, and Qwen3. They have demonstrated the capability of performing multi-step reasoning. Despite the advancement in LRMs, little attention has been paid to systematically analyzing the reasoning patterns these models exhibit and how such patterns influence the generated code. This paper presents a comprehensive study aimed at investigating and uncovering the reasoning behavior of LRMs during code generation. We prompted several state-of-the-art LRMs of varying sizes with code generation tasks and applied open coding to manually annotate the reasoning traces. From this analysis, we derive a taxonomy of LRM reasoning behaviors, encompassing 15 reasoning actions across four phases. Our empirical study based on the taxonomy reveals a series of findings. First, we identify common reasoning patterns, showing that LRMs generally follow a human-like coding workflow, with more complex tasks eliciting additional actions such as scaffolding, flaw detection, and style checks. Second, we compare reasoning across models, finding that Qwen3 exhibits iterative reasoning while DeepSeek-R1-7B follows a more linear, waterfall-like approach. Third, we analyze the relationship between reasoning and code correctness, showing that actions such as unit test creation and scaffold generation strongly support functional outcomes, with LRMs adapting strategies based on task context. Finally, we evaluate lightweight prompting strategies informed by these findings, demonstrating the potential of context- and reasoning-oriented prompts to improve LRM-generated code. Our results offer insights and practical implications for advancing automatic code generation.

cs.SE↗

arXiv2025

A Taxonomy of Prompt Defects in LLM Systems

Large Language Models (LLMs) have become key components of modern software, with prompts acting as their de-facto programming interface. However, prompt design remains largely empirical and small mistakes can cascade into unreliable, insecure, or inefficient behavior. This paper presents the first systematic survey and taxonomy of prompt defects, recurring ways that prompts fail to elicit their intended behavior from LLMs. We organize defects along six dimensions: (1) Specification and Intent, (2) Input and Content, (3) Structure and Formatting, (4) Context and Memory, (5) Performance and Efficiency, and (6) Maintainability and Engineering. Each dimension is refined into fine-grained subtypes, illustrated with concrete examples and root cause analysis. Grounded in software engineering principles, we show how these defects surface in real development workflows and examine their downstream effects. For every subtype, we distill mitigation strategies that span emerging prompt engineering patterns, automated guardrails, testing harnesses, and evaluation frameworks. We then summarize these strategies in a master taxonomy that links defect, impact, and remedy. We conclude with open research challenges and a call for rigorous engineering-oriented methodologies to ensure that LLM-driven systems are dependable by design.

cs.SE↗