YJYanyan Jiang

Yanyan Jiang

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yanyan Jiang has a total of 81 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Visualinux: Visual Debugging for the Linux Kernel

    by Hanzhi Liu, Yanyan Jiang, Chang Xu

    Debugging the Linux kernel is challenging because script-based debuggers present overwhelming, unstructured textual information. To address this, we present Visualinux, a system designed to make the kernel state visually tractable. Visualinux introduces two domain-specific languages: ViewCL, for constructing reduced object graphs at controllable abstraction levels, and ViewQL, for customizing these graphs to meet specific debugging objectives. Furthermore, Visualinux can visualize differences between kernel state snapshots, helping developers track changes in data structures over time. Our evaluation shows that Visualinux can effectively visualize complex kernel components and assist in diagnosing sophisticated kernel bugs.

  • Open Access

    Streamlining Repository Tasks with Effective Snippet Retrieval

    by Tangzhi Xu, Cong Li, Zhaogui Xu, Yanyan Jiang, Yuan Yao, Xiaorui Zhu, Feng Xu, Peng Di, Chang Xu, Zhendong Su

    Repository-level software engineering tasks are increasingly automated using repo-level retrieval-augmented generation (RLRAG), where a retriever selects relevant snippets from a repository to assist a language model (LM) in completing tasks. However, existing retrievers often lack effective designs to support LMs of varying capacities. To bridge this gap, we introduce RepoET, a novel retriever for RLRAG. RepoET organizes LMs and tools into an agentic workflow that closely mimics human search logic: “ search-files \(\to\) filter-files \(\to\) search-snippets \(\to\) filter-snippets ”. In our evaluation, RepoET outperformed state-of-the-art retrievers by accurately retrieving more relevant snippets in a better order across two widely used datasets, SWE-bench Lite and RepoQA, utilizing four LMs of different capabilities and sizes (as small as 3B). RepoET improved recall by over 12% and precision by over 20%, yielding a 21% improvement in Acc@k, along with superior snippet ordering. These retrieval improvements led to significant gains in downstream tasks: (1) we resolved 136 issues (45.33%) in SWE-bench Lite with GPT-4o without any additional information, and further improved the success rate by \(\sim\) 12% with multiple attempts; (2) we improved the accuracy of searching for designated functions by over 23% in RepoQA.

  • Open Access

    Data Knows What the App Needs: An Intelligent Resource Watermark for Mobile Systems

    by Zesen Liu, Zicheng Wang, Yinggang Guo, Lizhi Sun, Ligeng Chen, Yixin Guo, Claire Gu, Jun Xiao, Tao Wang, Lu Liu, et al.

  • Open Access

    Evolving Beyond Pressure: RL-Enhanced Camera Launch for Resource-Critical Scenarios

    by Zicheng Wang, Zesen Liu, Yinggang Guo, Lizhi Sun, Ligeng Chen, Yixin Guo, Claire Gu, Jun Xiao, Tao Wang, Lu Liu, et al.

  • Open Access

    Validating JIT Compilers via Compilation Space Exploration

    by Cong Li, Yanyan Jiang, Chang Xu, Zhendong Su

    We introduce the concept of compilation space as a new pivot for the comprehensive validation of just-in-time (JIT) compilers in modern language virtual machines (LVMs). The compilation space of a program encompasses a wide range of equivalent JIT-compilation choices, which can be cross-validated to ensure the correctness of the program’s JIT compilations. To thoroughly explore the compilation space in a lightweight and LVM-agnostic manner, we strategically mutate test programs with JIT-relevant but semantics-preserving code constructs, aiming to provoke diverse JIT compilation optimizations. We primarily implement this approach in Artemis , a tool for validating Java Virtual Machines (JVMs). Within three months, Artemis successfully discovered 85 bugs in three widely used production JVMs—HotSpot, OpenJ9, and the Android Runtime—where 53 were already confirmed or fixed and many of which were classified as critical. It is noteworthy that all reported bugs concern JIT compilers, highlighting the effectiveness and practicality of our technique. Building on the promising results with JVMs, we experimentally applied our technique to a state-of-the-art JavaScript Engine (JSE) fuzzer called Fuzzilli, aiming to augment it to find mis-compilation bugs without significantly sacrificing its ability to detect crashes. Our experiments demonstrate that our enhanced version of Fuzzilli namely Apollo could achieve comparable code coverage with a considerably smaller number of generated programs with a similar number of crashes. Additionally, Apollo successfully uncovered four mis-compilations in JavaScriptCore and SpiderMonkey within seven days. Following Artemis ’ and Apollo ’s success, we are expecting that the generality and practicability of our approach will make it broadly applicable for understanding and validating the JIT compilers of other LVMs.


  • NexuSym: Marrying symbolic path finders with large language models

    by Jiayi Wang, Ping Yu, Yi Qin, Yanyan Jiang, Yuan Yao, Xiaoxing Ma


  • Question Selection for Multimodal Code Search Synthesis Using Probabilistic Version Spaces

    by Jiarong Wu, Yanyan Jiang, Lili Wei, Congying Xu, Shing-Chi Cheung, Chang Xu

    Searching the occurrences of specific code patterns (code search) is a common task in software engineering, and programming by example (PBE) techniques have been applied to ease customizing code patterns. However, previous PBE tools only synthesize programs meeting the input-output examples, which may not always align with the user intent. To bridge this gap, this paper proposes Excalibur, a multi-modal (example and natural language description) and interactive synthesizer for code search. Excalibur ensures that the generated programs are correct for the provided examples (soundness) and include the user-intended program (bounded completeness). Furthermore, Excalibur helps the user identify the user-intended program through question-answer interaction. To minimize the required interaction efforts, question selection is crucial. To improve question selection for code search, we propose probabilistic version spaces (ProbVS), in which the user-intended program’s probability is high and others are low. ProbVS combines traditional version spaces for compactly representing extensive programs and large language models (on the user-provided natural language description) for adjusting programs’ probabilities to align with users’ intents. Extensive experiments on a benchmark of 44 tasks demonstrated the effectiveness of Excalibur and ProbVS and demystified how ProbVS affects probability distributions and how the configurable parameters affect ProbVS.


  • Open Access

    Understanding the Linux Kernel, Visually

    by Hanzhi Liu, Yanyan Jiang, Chang Xu


  • Open Access

    System support for ubiquitous human-cyber-physical fusion applications

    by Yunfan Cao, Chaoyi Zhao, Hanzhi Liu, Jiayi Wang, Huiyan Wang, Ping Yu, Chun Cao, Chang Xu, Xiaoxing Ma, Yanyan Jiang

    泛在计算为人机物融合应用带来了新的可能性, 但也面临着异构资源管理、需求多样性和计算资源受限等问题; 同时, 人工智能模型的快速发展也为智能应用的开发带来了机遇与挑战. 为此, 本文提出了元级化软件定义的泛在操作系统设计理念, 通过引入``软件孪生''技术实现对异构资源的抽象管理, 采用``上传下达''的层级结构应对复杂需求的分解, 并通过智能原生设计实现对人工智能模型的支持. 本文进一步以操作系统智能助手、``天网''监控系统和疾病防控系统三个典型泛在计算应用场景为例, 阐述了本文所提出的泛在操作系统设计理念在实践中的优势和潜在价值, 预示着智能时代下人机物融合的广泛应用前景.


  • Open Access

    Validity-Preserving Delta Debugging via Generator Trace Reduction

    by Luyao Ren, Xing Zhang, Ziyue Hua, Yanyan Jiang, Xiao He, Yingfei Xiong, Tao Xie

    Reducing test inputs that trigger bugs is crucial for efficient debugging. Delta debugging is the most popular approach for this purpose. When test inputs need to conform to certain specifications, existing delta debugging practice encounters a validity problem: it blindly applies reduction rules, producing a large number of invalid test inputs that do not satisfy the required specifications. This overall diminishing effectiveness and efficiency becomes even more pronounced when the specifications extend beyond syntactical structures. Our key insight is that we should leverage input generators, which are aware of these specifications, to generate valid reduced inputs, rather than straightforwardly performing reduction on test inputs. In this article, we propose a generator-based delta debugging method, namely GReduce, which derives validity-preserving reducers. Specifically, given a generator and its execution, demonstrating how the bug-inducing test input is generated, GReduce searches for other executions on the generator that yield reduced, valid test inputs. The evaluation results on five benchmarks (i.e., graphs, DL models, JavaScript programs, SymPy, and algebraic data types) show that GReduce substantially outperforms state-of-the-art syntax-based reducers including Perses and T-PDD, and also outperforms QuickCheck, SmartCheck, as well as the state-of-the-art choice-sequence-based reducer Hypothesis, demonstrating the effectiveness, efficiency, and versatility of GReduce.