XGXinyu Gao

Xinyu Gao

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Xinyu Gao has a total of 53 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    TrackTest: Trajectory Generation and Prioritization for Testing Multiple Object Tracking System

    by Xinyu Gao, Haoxin Chen, Shuoxiao Zhang, Enyi Tang, Hengrui Xu, Haoxiang Tian, Minghui Wei, An Guo

  • Open Access

    Fuzzing the Boundary between Models and Code in Hybrid AI-Enabled Systems

    by Xinyu Gao, Yang Feng, Yuchen Lu, Zhenqian Liu, Zhenyu Chen, Baowen Xu

    Deep learning (DL) techniques are increasingly integrated into traditional software systems, giving rise to hybrid AI-enabled systems that combine neural models with program logic. While these systems exhibit remarkable capabilities, their complex and heterogeneous architectures pose significant challenges for reliability and testing, particularly in safety-critical domains such as autonomous driving. Existing testing approaches either target traditional code or isolate neural networks, overlooking failures arising from their interactions. In this paper, we present Neude, a lightweight and extensible coverage-guided fuzzing framework specifically designed for hybrid AI-enabled systems. Unlike existing tools, Neude combines observations of program execution and neural model coverage to guide input mutations toward unexplored state spaces, enabling systematic testing of the entire hybrid system. Moreover, Neude employs domain-aware mutation operators coupled with metamorphic relations, allowing automated bug detection without manual assertions. We evaluate Neude on Pylot, a complex autonomous driving system with tightly coupled neural and program components. Experimental results show that Neude uncovers diverse errors, and further analysis reveals how model uncertainty propagates through deterministic program logic to trigger downstream module failures. Our findings highlight the fragility of current hybrid architectures, calling for a paradigm shift from model-centric testing to system-centric quality assurance that accounts for the intricate interplay between neural and procedural components.

  • Open Access

    Steering Tree-of-Thought Reasoning via Deductive Verification

    by Haoliang Cheng, Enyi Tang, Shuoxiao Zhang, Jiahe Mao, Yanling Fu, Jason Ma, Keyu Cui, Yuchuan Liu, Yu Tian, Xinyu Gao, et al.

    Large language models (LLMs) have demonstrated great potential in code reasoning tasks, but their reasoning processes lack reliable verification mechanisms, making it difficult to ensure logical correctness. The Tree of Thoughts (ToT) framework improves reasoning by exploring multiple paths and employing backtracking, yet its path selection relies entirely on LLM-based self-evaluation—a heuristic and error-prone mechanism—leading to frequent erroneous pruning and unproductive exploration. We identify a key insight: LLMs’ encoding capability is stronger than their reasoning capability—translating code semantics into formal constraints is a pattern-matching task that LLMs can perform reliably, while verification should be delegated to SMT(Satisfiability Modulo Theories) solvers. Based on this insight, we propose Deductive Steering, a mechanism that integrates SMT solver verification into Tree of Thoughts exploration. It consists of four core components: (1) Candidate Generator produces candidate reasoning steps, each comprising a natural language thought t and its SMT constraint encoding ϕ; (2) Deductive Evaluator verifies whether a candidate constraint ϕ is a logical consequence of the accumulated constraint Φ by checking the unsatisfiability of Φ ∧ ¬ ϕ; (3) Counterexample Refinement uses counterexample to guide the LLM in correcting its reasoning when verification fails; (4) Exploration and Backtracking Strategy manages path exploration and backtracks to alternative candidates when verification fails. Experiments on five benchmarks covering fault localization, program synthesis, and loop invariant generation show that, compared with ToT, Deductive Steering improves task-level effectiveness by 9.2–32.6 percentage points while reducing token consumption by 35.7–52.4%. The method generalizes across different LLMs and extends to mathematical reasoning, demonstrating broad applicability to domains where reasoning can be encoded as formal constraints.

  • Open Access

    StateTree: A Tree-Based Modeling Approach for Fault Detection in Recurrent Neural Networks

    by Xinyu Gao, Shuoxiao Zhang, Minghui Wei, Xiao Zhang, An Guo, Enyi Tang

    Recurrent Neural Networks (RNNs) have become a core component of modern intelligent software due to their strong ability to model temporal dependencies. As RNNs are increasingly deployed in safety-critical domains, ensuring their reliability is crucial. However, most existing testing techniques are designed for feedforward networks and struggle with RNNs. The stateful nature, recurrent feedback, and long-term dependencies of RNNs make it difficult for existing testing methods to capture decision logic and temporal behaviors, which in turn makes detecting fault-inducing behaviors that emerge through temporal decision evolution challenging. To address these challenges, we propose StateTree, a tree-based abstract modeling approach for systematic testing of RNN-based systems. StateTree constructs an Abstract State Tree (AST) that captures major RNN decision behaviors, where each root-to-leaf path represents an abstract decision for intuitive interpretation and structured exploration. Using the AST, StateTree guides the testing process toward both major and previously unseen paths to reveal erroneous behaviors. Experiments show that StateTree accurately abstracts RNN decisions, detects hundreds of faults, and retraining with its identified test cases improves robustness beyond existing RNN coverage methods, demonstrating its effectiveness in both fault detection and model performance enhancement.

  • Drivence: Realistic Driving Sequence Synthesis for Testing Multi-Sensor Fusion Perception Systems

    by Xinyu Gao, Zhijie Wang, Yang Feng, Chaolan Wang, Zhehua Zhou, Yuheng Huang, Lei Ma, Zhenyu Chen, Baowen Xu

    Multi-Sensor Fusion (MSF) based perception systems have become the foundation supporting many industrial applications and domains, such as self-driving cars, robotic arms, and unmanned aerial vehicles. With the rapid development of data-driven artificial intelligence (AI), the perception capabilities of MSF have been comprehensively enhanced, especially in understanding complex, dynamic external environments. Similar to traditional software, AI-enabled MSF systems also require rigorous testing. However, existing testing methods are still limited to evaluating the frame-level perception capabilities (e.g., object detection in static scenes) of singlesensor systems (e.g., image-based and point cloud-based systems). Given that many safety-critical intelligent systems, such as selfdriving cars, are operated in dynamic environments where perception systems play an important role, there comes an urgent need to assess their dynamic perception capabilities in understanding and responding to external environmental variations in real-time. To bridge this gap, we design and implement DRIVENCE, an automated metamorphic testing tool for testing the dynamic perception capabilities of MSF-based systems. DRIVENCE accounts for various real-world physical constraints to generate realistic multi-modal test sequences by inserting multiple dynamic traffic participants into the background image and point cloud driving sequences. To diversify testing sequences, we incorporate six driving patterns derived from real-world common driving behaviors into the testing process. We conduct experiments with five SOTA MSF-based tracking systems to evaluate DRIVENCE from the perspectives of (1) generated test cases’ realism, (2) fault detection capabilities, and (3) test efficiency. The results show that DRIVENCE can generate realistic and modality-consistent test driving sequences and effectively detect various dynamic perception errors within MSF systems.


  • Spatial Semantic Fuzzing for LiDAR-Based Autonomous Driving Perception Systems

    by An Guo, Zhiwei Su, Xinyu Gao, Chunrong Fang, Senrong Wang, Haoxiang Tian, Wu Wen, Lei Ma, Zhenyu Chen

    Autonomous driving systems (ADSs) have the potential to enhance safety through advanced perception and reaction capabilities, reduce emissions by alleviating congestion, and contribute to various improvements in quality of life. Despite significant advancements in ADSs, several real-world accidents resulting in fatalities have occurred due to failures in the autonomous driving perception modules. As a critical component of autonomous vehicles, LiDAR-based perception systems are marked by high complexity and low interpretability, necessitating the development of effective testing methods for these systems. Current testing methods largely depend on manual data collection and labeling, which restricts their ability to detect a diverse range of erroneous behaviors. This process is not only time-consuming and labor-intensive, but it may also result in the recurrent discovery of similar erroneous behaviors during testing, hindering a comprehensive assessment of the systems. In this paper, we propose and implement a fuzzing framework for LiDAR-based autonomous driving perception systems, named LDFuzz, grounded in metamorphic testing theory. This framework offers the first uniform solution for the automated generation of tests with oracle information. To enhance testing efficiency and increase the number of tests that identify erroneous behaviors, we incorporate spatial and semantic coverage based on the characteristics of point cloud data to guide the generation process. We evaluate the performance of LDFuzz through experiments conducted on four LiDAR-based autonomous driving perception systems designed for the 3D object detection task. The experimental results demonstrate that the tests produced by LDFuzz can effectively detect an average of 7.5% more erroneous behaviors within LiDAR-based perception systems than the optimal baseline. Furthermore, the findings indicate that LDFuzz significantly enhances the diversity of failed tests.


  • Open Access

    When Autonomous Vehicle Meets V2X Cooperative Perception: How Far Are We?

    by An Guo, Shuoxiao Zhang, Enyi Tang, Xinyu Gao, Haomin Pang, Haoxiang Tian, Yanzhou Mu, Wu Wen, Chunrong Fang, Zhenyu Chen

    With the tremendous advancement of deep learning and communication technology, Vehicle-to-Everything (V2X) cooperative perception has the potential to address limitations in sensing distant objects and occlusion for a single-agent perception system. V2X cooperative perception systems are software systems characterized by diverse sensor types and cooperative agents, varying fusion schemes, and operation under different communication conditions. Therefore, their complex composition gives rise to numerous operational challenges. Furthermore, when cooperative perception systems produce erroneous predictions, the types of errors and their underlying causes remain insufficiently explored. To bridge this gap, we take an initial step by conducting an empirical study of V2X cooperative perception. To systematically evaluate the impact of cooperative perception on the ego vehicle's perception performance, we identify and analyze six prevalent error patterns in cooperative perception systems. We further conduct a systematic evaluation of the critical components of these systems through our large-scale study and identify the following key findings: (1) The LiDAR-based cooperation configuration exhibits the highest perception performance; (2) Vehicle-to-infrastructure (V2I) and vehicle-to-vehicle (V2V) communication exhibit distinct cooperative perception performance under different fusion schemes; (3) Increased cooperative perception errors may result in a higher frequency of driving violations; (4) Cooperative perception systems are not robust against communication interference when running online. Our results reveal potential risks and vulnerabilities in critical components of cooperative perception systems. We hope that our findings can better promote the design and repair of cooperative perception systems.


  • Open Access

    Generate Realistic Test Scenes for V2X Communication Systems

    by An Guo, Xinyu Gao, Chunrong Fang, Haoxiang Tian, Weisong Sun, Yanzhou Mu, Shuncheng Tang, Lei Ma, Zhenyu Chen

    Accurately perceiving complex driving environments is essential for ensuring the safe operation of autonomous vehicles. With the tremendous progress in deep learning and communication technologies, cooperative perception with Vehicle-to-Everything (V2X) technologies has emerged as a solution to overcome the limitations of single-agent perception systems in perceiving distant objects and occlusions. Despite the considerable advancements, V2X cooperative perception systems require thorough testing and continuous enhancement of system performance. Given that V2X driving scenes entail intricate communications with multiple vehicles across various geographic locations, creating V2X test scenes for these systems poses a significant challenge. Moreover, current testing methodologies rely on manual data collection and labeling, which are both time-consuming and costly. In this paper, we design and implement V2XGen, an automated testing generation tool for V2X cooperative perception systems. V2XGen utilizes a high-fidelity approach to generate realistic cooperative object instances and strategically place them within the background data in crucial positions. Furthermore, V2XGen adopts a fitness-guided V2X scene generation strategy for the transformed scene generation process and improves testing efficiency. We conduct experiments on V2XGen using multiple cooperative perception systems with different fusion schemes to assess its performance on various tasks. The experimental results demonstrate that V2XGen is capable of generating realistic test scenes and effectively detecting erroneous behaviors in different V2X-oriented driving conditions. Furthermore, the results validate that retraining systems under test with the generated scenes can enhance average detection precision while reducing occlusion and long-range perception errors.


  • Open Access

    SoVAR: Build Generalizable Scenarios from Accident Reports for Autonomous Driving Testing

    by An Guo, Yuan Zhou, Haoxiang Tian, Chunrong Fang, Yunjian Sun, Weisong Sun, Xinyu Gao, Anh Tuan Luu, Yang Liu, Zhenyu Chen

    Autonomous driving systems (ADSs) have undergone remarkable development and are increasingly employed in safety-critical applications. However, recently reported data on fatal accidents involving ADSs suggests that the desired level of safety has not yet been fully achieved. Consequently, there is a growing need for more comprehensive and targeted testing approaches to ensure safe driving. Scenarios from real-world accident reports provide valuable resources for ADS testing, including critical scenarios and high-quality seeds. However, existing scenario reconstruction methods from accident reports often exhibit limited accuracy in information extraction. Moreover, due to the diversity and complexity of road environments, matching current accident information with the simulation map data for reconstruction poses significant challenges. In this paper, we design and implement SoVAR, a tool for automatically generating road-generalizable scenarios from accident reports. SoVAR utilizes well-designed prompts with linguistic patterns to guide the large language model (LLM) in extracting accident information from textual data. Subsequently, it formulates and solves accident-related constraints in conjunction with the extracted accident information to generate accident trajectories. Finally, SoVAR reconstructs accident scenarios on various map structures and converts them into test scenarios to evaluate its capability to detect defects in industrial ADSs. We experiment with SoVAR, using the accident reports from the National Highway Traffic Safety Administration's (NHTSA) database to generate test scenarios for the industrial-grade ADS Apollo. The experimental findings demonstrate that SoVAR can effectively generate generalized accident scenarios across different road structures. Furthermore, the results confirm that SoVAR identified 5 distinct safety violation types that contributed to the crash of Baidu Apollo.