Publications (41)
Mut4All: Fuzzing Compilers via LLM-Synthesized Mutators Learned from Bug Reports
Bo Wang, Pengyang Wang, Chong Chen +9
Mutation-based fuzzing is effective for uncovering compiler bugs, but designing high-quality mutators for modern languages with complex constructs (e.g., templates, macros) remains…
Dimension reduction in quantum sampling of stochastic processes
Chengran Yang, Marta Florido-Llin`as, Mile Gu +1
Quantum technologies offer a promising route to the efficient sampling and analysis of stochastic processes, with potential applications across the sciences. Such quantum advantage…
Benchmarking Large Language Models for Multi-Language Software Vulnerability Detection
Ting Zhang, Chengran Yang, Yindu Su +8
Recent advancements in generative AI have led to the widespread adoption of large language models (LLMs) in software engineering, addressing numerous long-standing challenges. Howe…
SecureVibeBench: Benchmarking Secure Vibe Coding of AI Agents via Reconstructing Vulnerability-Introducing Scenarios
Junkai Chen, Huihui Huang, Yunbo Lyu +10
Large language model-powered code agents are rapidly transforming software engineering, yet the security risks of their generated code have become a critical concern. Existing benc…
TestDecision: Sequential Test Suite Generation via Greedy Optimization and Reinforcement Learning
Guoqing Wang, Chengran Yang, Xiaoxuan Zhou +4
With the rapid evolution of LLMs, automated software testing is witnessing a paradigm shift. While proprietary models like GPT-4o demonstrate impressive capabilities, their high de…
Curiosity-Driven Testing for Sequential Decision-Making Process
Junda He, Zhou Yang, Jieke Shi +5
Sequential decision-making processes (SDPs) are fundamental for complex real-world challenges, such as autonomous driving, robotic control, and traffic management. While recent adv…
AgentSZZ: Teaching the LLM Agent to Play Detective with Bug-Inducing Commits
Yunbo Lyu, Jieke Shi, Hong Jin Kang +8
The SZZ algorithm is the dominant technique for identifying bug-inducing commits and underpins many software engineering tasks, such as defect prediction and vulnerability analysis…
PTM4Tag+: Tag Recommendation of Stack Overflow Posts with Pre-trained Models
Junda He, Bowen Xu, Zhou Yang +5
Stack Overflow is one of the most influential Software Question & Answer (SQA) websites, hosting millions of programming-related questions and answers. Tags play a critical role in…
PenForge: On-the-Fly Expert Agent Construction for Automated Penetration Testing
Huihui Huang, Jieke Shi, Junkai Chen +6
Penetration testing is essential for identifying vulnerabilities in web applications before real adversaries can exploit them. Recent work has explored automating this process with…
ACECode: A Reinforcement Learning Framework for Aligning Code Efficiency and Correctness in Code Language Models
Chengran Yang, Hong Jin Kang, Jieke Shi +1
CodeLLMs have demonstrated remarkable advancements in software engineering tasks. However, while these models can generate functionally correct code, they often produce code that i…
Token Sugar: Making Source Code Sweeter for LLMs through Token-Efficient Shorthand
Zhensu Sun, Chengran Yang, Xiaoning Du +3
Large language models (LLMs) have shown exceptional performance in code generation and understanding tasks, yet their high computational costs hinder broader adoption. One importan…
Variational learning of integrated quantum photonic circuits
Hui Zhang, Chengran Yang, Wai-Keong Mok +11
Integrated photonic circuits play a crucial role in implementing quantum information processing in the noisy intermediate-scale quantum (NISQ) era. Variational learning is a promis…
R2Vul: Learning to Reason about Software Vulnerabilities with Reinforcement Learning and Structured Reasoning Distillation
Martin Weyssow, Chengran Yang, Junkai Chen +12
Large language models (LLMs) have shown promising performance in software vulnerability detection, yet their reasoning capabilities remain unreliable. We propose R2Vul, a method th…
AgentExecutor: Partial Code Execution via Agentic Context Generation
Junkai Chen, Chengran Yang, Xing Hu +3
Executing code snippets is essential for dynamic program analysis, but it remains challenging to execute an arbitrary code snippet due to issues like missing context and incomplete…
Multi-Granularity Detector for Vulnerability Fixes
Truong Giang Nguyen, Thanh Le-Cong, Hong Jin Kang +9
With the increasing reliance on Open Source Software, users are exposed to third-party library vulnerabilities. Software Composition Analysis (SCA) tools have been created to alert…
Boosting LLMs for Mutation Generation
Bo Wang, Ming Deng, Mingda Chen +5
LLM-based mutation testing is a promising testing technology, but existing approaches typically rely on a fixed set of mutations as few-shot examples or none at all. This can resul…
Variational Quantum Dimension Reduction for Recurrent Quantum Models
Chufan Lyu, Ximing Wang, Mile Gu +2
Recurrent quantum models (RQMs) realize sequential quantum processes through repeated application of a unitary operation on a memory system coupled with a series of output register…
Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation
Chengran Yang, Zichao Wei, Heminghao Deng +6
Large Language Model (LLM) based code generation is predominantly formulated as a strictly monotonic process, appending tokens linearly to an immutable prefix. This formulation con…
PTM4Tag: Sharpening Tag Recommendation of Stack Overflow Posts with Pre-trained Models
Junda He, Bowen Xu, Zhou Yang +3
Stack Overflow is often viewed as the most influential Software Question Answer (SQA) website with millions of programming-related questions and answers. Tags play a critical role…
Matrix Product States for Quantum Stochastic Modelling
Chengran Yang, Felix C. Binder, Varun Narasimhachar +1
In stochastic modeling, there has been a significant effort towards finding predictive models that predict a stochastic process' future using minimal information from its past. Mea…
Extreme dimensionality reduction with quantum modelling
Thomas J. Elliott, Chengran Yang, Felix C. Binder +3
Effective and efficient forecasting relies on identification of the relevant information contained in past observations -- the predictive features -- and isolating it from the rest…
Semantics-Aligned, Curriculum-Driven, and Reasoning-Enhanced Vulnerability Repair Framework
Chengran Yang, Ting Zhang, Jinfeng Jiang +9
Current learning-based Automated Vulnerability Repair (AVR) approaches, while promising, often fail to generalize effectively in real-world scenarios. Our diagnostic analysis revea…
Quantum enhanced rare event discovery and sampling
Naixu Guo, Po-Wei Huang, Qisheng Wang +4
Financial crashes, cascading failures in infrastructure, and critical errors in AI systems are frequently triggered by events that occur with extremely small probability. Efficient…
Out of Distribution, Out of Luck: How Well Can LLMs Trained on Vulnerability Datasets Detect Top 25 CWE Weaknesses?
Yikun Li, Ngoc Tan Bui, Ting Zhang +16
Automated vulnerability detection research has made substantial progress, yet its real-world impact remains limited. Prior work found that current vulnerability datasets suffer fro…
Efficient Search of Live-Coding Screencasts from Online Videos
Chengran Yang, Ferdian Thung, David Lo
Programming videos on the Internet are valuable resources for learning programming skills. To find relevant videos, developers typically search online video platforms (e.g., YouTub…
Measures of distinguishability between stochastic processes
Chengran Yang, Felix C. Binder, Mile Gu +1
Quantifying how distinguishable two stochastic processes are lies at the heart of many fields, such as machine learning and quantitative finance. While several measures have been p…
TitanCA: Lessons from Orchestrating LLM Agents to Discover 100+ CVEs
Ting Zhang, Yikun Li, Chengran Yang +15
Software vulnerabilities remain one of the most persistent threats to modern digital infrastructure. While static application security testing (SAST) tools have long served as the…
Variational Quantum Circuit Decoupling
Ximing Wang, Chengran Yang, Mile Gu
Decoupling systems into independently evolving components has a long history of simplifying seemingly complex systems. They enable a better understanding of the underlying dynamics…
APIDocBooster: An Extract-Then-Abstract Framework Leveraging Large Language Models for Augmenting API Documentation
Chengran Yang, Jiakun Liu, Bowen Xu +5
API documentation is often the most trusted resource for programming. Many approaches have been proposed to augment API documentation by summarizing complementary information from…
An Execution-Verified Multi-Language Benchmark for Code Semantic Reasoning
Yikun Li, Jinfeng Jiang, Ting Zhang +7
Evaluating whether large language models (LLMs) can recover execution-relevant program structure, rather than only produce code that passes tests, remains an open problem. Existing…
Bridging Developer Instructions and Code Completion Through Instruction-Aware Fill-in-the-Middle Paradigm
Zhensu Sun, Chengran Yang, Chao Peng +4
Large Language Models (LLMs) have significantly advanced code completion, yet they often fail when the developer's intent is underspecified in the code context. To address this, de…
Compiling Code LLMs into Lightweight Executables
Jieke Shi, Junda He, Zhou Yang +6
The demand for better prediction accuracy and higher execution performance in neural networks continues to grow. The emergence and success of Large Language Models (LLMs) have prod…
Think Like Human Developers: Harnessing Community Knowledge for Structured Code Reasoning
Chengran Yang, Zhensu Sun, Hong Jin Kang +2
Large Language Models (LLMs) have significantly advanced automated code generation, yet they struggle with complex coding tasks requiring multi-step logical reasoning. High-quality…
Implementing quantum dimensionality reduction for non-Markovian stochastic simulation
Kang-Da Wu, Chengran Yang, Ren-Dong He +5
Complex systems are embedded in our everyday experience. Stochastic modelling enables us to understand and predict the behaviour of such systems, cementing its utility across the q…
Executing as You Generate: Hiding Execution Latency in LLM Code Interpreters
Zhensu Sun, Zhihao Lin, Zhi Chen +4
Current LLM systems are increasingly equipped with a code interpreter that executes generated code to obtain results. This works serially: the model first generates the complete co…
Learning Quantum-Samplers for Stochastic Processes with Quantum Sequence Models
Ximing Wang, Chengran Yang, Chidambaram Aditya Somasundaram +2
Quantum circuits that generate coherent superpositions of stochastic processes are key to many downstream quantum-accelerated tasks, such as risk analysis, importance sampling, and…
Provable superior accuracy in machine learned quantum models
Chengran Yang, Andrew Garner, Feiyang Liu +5
In modelling complex processes, the potential past data that influence future expectations are immense. Models that track all this data are not only computationally wasteful but al…
Secure Code Generation via Online Reinforcement Learning with Vulnerability Reward Model
Tianyi Wu, Mingzhe Du, Yue Liu +4
Large language models (LLMs) are increasingly used in software development, yet their tendency to generate insecure code remains a major barrier to real-world deployment. Existing…
Lossless Tensor Compression as Program Synthesis
Jieke Shi, Junda He, Wenjia Jiang +11
Model checkpoints are growing in both number and size, which makes archival, transfer, and deployment increasingly costly. General-purpose compressors can reduce storage requiremen…
Beyond Function-Level Analysis: Context-Aware Reasoning for Inter-Procedural Vulnerability Detection
Yikun Li, Ting Zhang, Jieke Shi +10
Recent progress in ML and LLMs has improved vulnerability detection, and recent datasets have reduced label noise and unrelated code changes. However, most existing approaches stil…
Understanding and Improving Model Editing for Secure Code Generation
Weifeng Sun, Quanjun Zhang, Yuchen Chen +3
Large language models (LLMs) are widely used for code generation, yet they can reproduce vulnerable implementations learned from insecure training patterns. Prior work has mainly e…