28 citations · 40 across the 13 of their papers we have counts for
14 papers
LLVM Translation Validation Automated with Large Language Models and Lean
Chunhao Liao, Hongxu Xu, Xintong Zhou +2
LLVM is the cornerstone of modern compilers, but its subtle intermediate representation (IR) semantics make transformations error-prone and necessitate formal verification. Alive2,…
ShadowProbe: Language-Extensible Detection of Hidden Algorithmic Complexity Vulnerabilities
Yuanmin Xie, Xiangfan Wu, Wenhao Wu +6
Algorithmic Complexity Vulnerabilities (ACVs) arise when adversarial inputs trigger worst-case execution behavior, causing severe performance degradation or Denial-of-Service condi…
Semantic-aware and Self-improving Program Reduction via Agentic Large Language Models
Xintong Zhou, Hongxu Xu, Chunhao Liao +3
Reducing bug-triggering programs to their minimal essential form is a fundamental task in debugging language processors such as compilers and interpreters. Existing reduction techn…
Can Coding Agents Implement Missed Compiler Optimizations? Evaluating LLM Agents on LLVM Peephole Optimizations
Hongxu Xu, Chunhao Liao, Xintong Zhou +1
Coding agents built on large language models are now capable of patching sizable real-world codebases, yet whether they can develop compiler optimizations remains an open question.…
Leveraging Large Language Models for Generalizing Peephole Optimizations
Chunhao Liao, Hongxu Xu, Xintong Zhou +2
Peephole optimizations are a core component of modern optimizing compilers. It rewrites specific instruction into semantically equivalent but more efficient forms. In practice, cre…
LPO: Discovering Missed Peephole Optimizations with Large Language Models
Zhenyang Xu, Hongxu Xu, Yongqiang Tian +2
Peephole optimization is an essential class of compiler optimizations that targets small, inefficient instruction sequences within programs. By replacing such suboptimal instructio…
An Empirical Study of Bugs in Data Visualization Libraries
Weiqi Lu, Yongqiang Tian, Xiaohan Zhong +4
Data visualization (DataViz) libraries play a crucial role in presentation, data analysis, and application development, underscoring the importance of their accuracy in transformin…
On the Feasibility of Deduplicating Compiler Bugs with Bisection
Xintong Zhou, Zhenyang Xu, Yongqiang Tian +1
Random testing has proven to be an effective technique for compiler validation. However, the debugging of bugs identified through random testing presents a significant challenge du…
Unmasking the Genuine Type Inference Capabilities of LLMs for Java Code Snippets
Yiwen Dong, Zhenyang Xu, Yongqiang Tian +1
Type inference is crucial for reusing online code snippets. Although snippets are prevalently shared on platforms like StackOverflow, they often lack essential type information, su…
WDD: Weighted Delta Debugging
Xintong Zhou, Zhenyang Xu, Mengxiao Zhang +2
Delta Debugging is a widely used family of algorithms (e.g., ddmin and ProbDD) to automatically minimize bug-triggering test inputs, thus to facilitate debugging. It takes a list o…
AddressWatcher: Sanitizer-Based Localization of Memory Leak Fixes
Aniruddhan Murali, Mahmoud Alfadel, Meiyappan Nagappan +2
Memory leak bugs are a major problem in C/C++ programs. They occur when memory objects are not deallocated.Developers need to manually deallocate these objects to prevent memory le…
Toward a Better Understanding of Probabilistic Delta Debugging
Mengxiao Zhang, Zhenyang Xu, Yongqiang Tian +2
Given a list L of elements and a property that L exhibits, ddmin is a well-known test input minimization algorithm designed to automatically eliminate irrelevant elements from L. T…
Moving beyond Deletions: Program Simplification via Diverse Program Transformations
Haibo Wang, Zezhong Xing, Zheng Wang +2
To reduce the complexity of software, Developers manually simplify program (known as developer-induced program simplification in this paper) to reduce its code size yet preserving…
Harnessing the Power of LLM to Support Binary Taint Analysis
Puzhuo Liu, Chengnian Sun, Yaowen Zheng +8
This paper proposes LATTE, the first static binary taint analysis that is powered by a large language model (LLM). LATTE is superior to the state of the art (e.g., Emtaint, Arbiter…