Tural Mammadov

International Workshop on Reliable and trustworthy Automated Software Engineering(RASE) How Grammar-Based Synthetic Data Shapes Behavior Learning: An Empirical Study of Input Generation Strategies

International Workshop on Trustworthy and Responsible aUtonomous SysTems(TRUST) Can Open-Weight LLMs Predict Test Outcomes from Traces? A Cross-Subject Boundary Study on Tests4Py

ACM Transactions on Software Engineering and Methodology Neural Program Modeling Learning Program-Specific Models that Predict Execution Features from Input Features and vice versa

ACM International Conference on AI-Powered Software (AIware) Can LLMs Really Reason about Code? Studying How Well LLMs Understand the Relation between Input, Code, and Output

Automated Software Engineering Conference (ASE) BASHIRI: Learning Failure Oracles from Execution Features

ACM Transactions on Software Engineering and Methodology Learning Program Behavioral Models from Synthesized Input-Output Pairs

International Conference on Software Engineering - Companion (ICSE-Companion)