Milan Čugurović, Milena Vujošević Janičić, Aleksandar Prokopec, Boris Spasojević, Vojin Jovanović: Tunable Machine Learning for Size-Aware Optimizing Compilation. US Letter Patent Application (filed).
Milan Čugurović, Stefan Milenković, Lazar Milikić, Milena Vujošević Janičić, Aleksandar Prokopec, Boris Spasojević, Vojin Jovanović: Static Profiling Using Signature Embeddings. US Letter Patent Application (filed).
Vojin Jovanović, Milan Čugurović, Lazar Milikić: Static Profiling with Graph Neural Networks. US Letter Patent Application (published), US20260126977A1. URL
Milan Čugurović, Aleksandar Prokopec, Boris Spasojević, Vojin Jovanović, Milena Vujošević Janičić: GraalMHC++: A Tunable ML Framework for Size-Aware Optimizing Compilation. Journal of Systems and Software. URL
Milan Čugurović, Aleksandar Prokopec, Boris Spasojević, Vojin Jovanović, Milena Vujošević Janičić: The Promise of Static Profiling: Exploring the Limits. Companion Proceedings of the 10th International Conference on the Art, Science, and Engineering of Programming, 4–8. DOI
Milan Čugurović, Aleksandar Prokopec, Boris Spasojević, Vojin Jovanović, Milena Vujošević Janičić: GraalMHC: ML-Based Method-Hotness Classification for Binary-Size Reduction in Optimizing Compilers. Proceedings of the 35th ACM SIGPLAN International Conference on Compiler Construction, 1–13. DOI
Milan Čugurović: Prediction of Program Execution Profiles Using Machine Learning Techniques. Invited talk at INFORMATIKA 2026: New Trends in the Development of Information Systems, Serbian Informatics Society. URL
2025
Milan Čugurović, Milena Vujošević Janičić, Aleksandar Prokopec, Boris Spasojević, Vojin Jovanović: Machine Learning Method Hotness Classification in Optimizing Compilers. US Letter Patent Application (filed).
Milan Čugurović, Milena Vujošević Janičić, Vojin Jovanović, Thomas Würthinger: Machine Learning Based Static Profiling. US Letter Patent Application (published), US20250244979A1. URL
Ivan Ristović, Milan Čugurović, Strahinja Stanojević, Marko Spasić, Vesna Marinković, Milena Vujošević Janičić: Machine Learning-Driven Prediction of Optimal Control Flow Graph Traversal Strategy. Serbian Journal of Electrical Engineering, 22(3), 353–376. DOI
Milan Čugurović, Ivan Ristović, Strahinja Stanojević, Marko Spasić, Vesna Marinković, Milena Vujošević Janičić: ML-Driven Prediction of Optimal Control Flow Graph Traversal Algorithm in Modern Applications. 2025 12th International Conference on Electrical, Electronic and Computing Engineering (IcETRAN), 1–6. DOI
Lazar Milikić, Milan Čugurović, Vojin Jovanović: GraalNN: Context-Sensitive Static Profiling with Graph Neural Networks. Proceedings of the 23rd ACM/IEEE International Symposium on Code Generation and Optimization, 123–136. DOI
Stefan Milenković, Milan Čugurović, Milena Vujošević Janičić: Improving ML-Based Static Profiling Using Method Names. Book of Abstracts of the 15th Symposium "Mathematics and Applications", 36. URL
Milan Čugurović: Prediction of Program Profiles Using Machine Learning Techniques. Doctoral Dissertation, Faculty of Mathematics, University of Belgrade. URL
2024
Milan Čugurović, Milena Vujošević Janičić, Vojin Jovanović, Thomas Würthinger: GraalSP: Polyglot, efficient, and robust machine learning-based static profiler. Journal of Systems and Software, 213, 112058. DOI
Marko Spasić, Ivan Ristović, Strahinja Stanojević, Milan Čugurović, Milica Karličić, Milena Vujošević Janičić: Evaluating GraalVM Compiler Performance using a Distributed Computing Cluster. Proceedings of the 15th Serbian Mathematical Congress, 114. URL
Ivan Ristović, Milan Čugurović, Strahinja Stanojević, Marko Spasić, Vesna Marinković, Milena Vujošević Janičić: Efficient Control-Flow Graph Traversal. Proceedings of the 30th YU INFO Conference, 89–94. URL
Milan Čugurović, Milena Vujošević Janičić: GraalSP Profiles Logger: A Tool for Analyzing and Interpreting Predictions of the ML-Based Static Profilers. Artificial Intelligence: Book of Abstracts, 15–16. URL
2023
Milan Čugurović: Dynamic Profiling and Static Prediction of the Program Execution Profiles in the Context of Compiler Optimizations. InfoM: Journal of Information Technology and Multimedia Systems, 23(78), 17–27. URL
Milan Čugurović, Ivan Ristović, Strahinja Stanojević, Marko Spasić, Vesna Marinković, Milena Vujošević Janičić: Comparative Analysis of Program Control Flow Graph Traversal Algorithms. Proceedings of the 13th Symposium "Mathematics and Applications", 79. URL
Milan Čugurović, Milena Vujošević Janičić: Creation and Analysis of a Dataset for Predicting Execution Probabilities of Virtual Methods in Object-Oriented Programs. Artificial Intelligence: Book of Abstracts, 126–127. URL
2022
Milan Čugurović: Prediction of Program Profiles Using Machine Learning Techniques. Seminar for Artificial Intelligence, Mathematical Institute SASA. URL
