2 citations · 3 across the 12 of their papers we have counts for
15 papers
The Parser Already Knows: Lightweight Bias Correction in Constrained Decoding
Işıl Özgü, Yaoxuan Wu, Guy Van den Broeck +1
Grammar Constrained Decoding (GCD) forces Language Models (LMs) to produce syntactically valid outputs by masking out non-conforming tokens at each step. However, because masking o…
Agentic Proof and Property-Based Testing via Property-Templates in Data-Intensive Computing
Seongmin Lee, Yaoxuan Wu, Miryung Kim
As the cost of code generation becomes cheaper with AI, the new bottleneck in software engineering has shifted to intent specification and validation. Overcoming this durability cr…
Tensor Algebraic Property Skeletons: Amplifying Property-Based Testing for AI Compilers
Yuxin Qiu, Ben Limpanukorn, Seongmin Lee +3
Deep learning (DL) compilers such as TVM and ONNX-MLIR lower tensor computation graphs into optimized executables for target backends. Testing these compilers has made substantial…
Finding Compiler-Platform Interaction Bugs in Deep Learning Pipelines via Cross-Layer Constraints
Yuxin Qiu, Jiyuan Wang, Ronak Badhe +3
The growing deployment of artificial intelligence (AI) necessitates robust deep learning (DL) compilers, such as TVM and ONNX-MLIR. These compilers take as input high-level AI mode…
Properties with Holes: Meta-Property-Based Testing of Data-Intensive Computing Frameworks
Yaoxuan Wu, Ingrid Lee, Ahmad Humayun +2
Data-intensive computing frameworks such as Apache Spark and Flink keep expanding their APIs with new data types, expressions, and operators. Their most damaging bugs return silent…
ExplainFuzz: Explainable and Constraint-Conditioned Test Generation with Probabilistic Circuits
Annaëlle Baiget, Jaron Maene, Seongmin Lee +3
Understanding and explaining the structure of generated test inputs is essential for effective software testing and debugging. Existing approaches--including grammar-based fuzzers,…
Change And Cover: Last-Mile, Pull Request-Based Regression Test Augmentation
Zitong Zhou, Matteo Paltenghi, Miryung Kim +1
Software is in constant evolution, with developers frequently submitting pull requests (PRs) to introduce new features or fix bugs. Testing PRs is critical to maintaining software…
Targeted Testing of Compiler Optimizations via Grammar-Level Composition Styles
Zitong Zhou, Ben Limpanukorn, Hong Jin Kang +5
Ensuring the correctness of compiler optimizations is critical, but existing fuzzers struggle to test optimizations effectively. First, most fuzzers use optimization pipelines (heu…
WhyFlow: Interrogative Debugger for Sensemaking Taint Analysis
Burak Yetiştiren, Hong Jin Kang, Miryung Kim
Taint analysis is a security analysis technique used to track the flow of potentially dangerous data through an application and its dependent libraries. Investigating why certain u…
Structural Code Search using Natural Language Queries
Ben Limpanukorn, Yanjun Wang, Zach Patterson +5
Searching code is a common task that developers perform to understand APIs, learn common code patterns, and navigate code. Currently, developers most commonly search using keywords…
PALM: Path-aware LLM-based Test Generation with Comprehension
Yaoxuan Wu, Xiaojie Zhou, Ahmad Humayun +2
Symbolic execution is a widely used technique for test generation, offering systematic exploration of program paths through constraint solving. However, it is fundamentally constra…
Automatically Detecting Numerical Instability in Machine Learning Applications via Soft Assertions
Shaila Sharmin, Anwar Hossain Zahid, Subhankar Bhattacharjee +3
Machine learning (ML) applications have become an integral part of our lives. ML applications extensively use floating-point computation and involve very large/small numbers; thus,…
PerfGen: Automated Performance Benchmark Generation for Big Data Analytics
Jiyuan Wang, Jason Teoh, Muhammand Ali Gulza +2
Many symptoms of poor performance in big data analytics such as computational skews, data skews, and memory skews are input dependent. However, due to the lack of inputs that can t…
Human-in-the-Loop Synthetic Text Data Inspection with Provenance Tracking
Hong Jin Kang, Fabrice Harel-Canada, Muhammad Ali Gulzar +2
Data augmentation techniques apply transformations to existing texts to generate additional data. The transformations may produce low-quality texts, where the meaning of the text i…
Fuzzing MLIR Compilers with Custom Mutation Synthesis
Ben Limpanukorn, Jiyuan Wang, Hong Jin Kang +2
Compiler technologies in deep learning and domain-specific hardware acceleration are increasingly adopting extensible compiler frameworks such as Multi-Level Intermediate Represent…