About
I am a third-year Computer Science Ph.D. student at UC Berkeley, advised by Sanjit A. Seshia. In 2020, I received my BSc in Computer Engineering from the Middle East Technical University in Ankara, Turkey, where I worked with Ebru Aydin Gol as an undergraduate research assistant for three years. During my undergraduate degree, I did two research internships in Europe. In the summer of 2018, I was a research intern at Max Planck Institute for Software Systems in Kaiserslautern, Germany, advised by Björn B. Brandenburg. In the summer of 2019, I was a research intern at École Polytechnique Fédérale de Lausanne, where I was advised by George Candea. Also, in the summer of 2022 and 2023, I was an applied scientist intern at Amazon Web Services, where I worked with Ankush Desai.
Research
My main research interests are formal methods, cyber-physical systems (with an emphasis on safe robotic systems), and reinforcement learning. Within the scope of formal methods, I am interested in developing techniques that could be applied to learning-based systems to reason about their correctness with respect to specifications of interest. In cyber-physical systems, I focus on applying techniques from formal methods to design safe robotic systems. Finally, in reinforcement learning, I am interested in integrating formal structures into the learning process for developing learning frameworks that could guarantee certain temporal requirements for control tasks.
Teaching
- In the Fall of 2022, I was a teaching assistant (or graduate student instructor in Berkeley terminology) for EECS 149/249A (Introduction to Embedded Systems) at UC Berkeley.
Publications
- Beyazit Yalcinkaya*, Niklas Lauffer*, Marcell Vazquez-Chanlatte, and Sanjit A. Seshia, "Automata Conditioned Reinforcement Learning with Experience Replay," NeurIPS 2023 Workshop on Goal-Conditioned Reinforcement Learning, 2023. *Equal contribution.
- Beyazit Yalcinkaya, Hazem Torfah, Daniel J. Fremont, and Sanjit A. Seshia, "Compositional Simulation-Based Analysis of AI-Based Autonomous Systems for Markovian Specifications," International Conference on Runtime Verification (RV), 2023.
- Ameesh Shah, Jon DeCastro, John Gideon, Beyazit Yalcinkaya, Guy Rosman, and Sanjit A. Seshia, "Specification-Guided Data Aggregation for Semantically Aware Imitation Learning," arXiv preprint arXiv:2303.17010, 2023.
- Beyazit Yalcinkaya, Hazem Torfah, Ankush Desai, and Sanjit A. Seshia, "ULGEN: A Runtime Assurance Framework for Programming Safe Cyber-Physical Systems," IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (TCAD), 2023.
- Niklas Lauffer*, Beyazit Yalcinkaya*, Marcell Vazquez-Chanlatte, Ameesh Shah, and Sanjit A. Seshia, "Learning deterministic finite automata decompositions from examples and demonstrations," Formal Methods in Computer-Aided Design (FMCAD), 2022. *Equal contribution.
- Mert Ergurtuna, Beyazit Yalcinkaya, and Ebru Aydin Gol, "An automated system repair framework with signal temporal logic," Acta Informatica, 2022.
- Beyazit Yalcinkaya and Ebru Aydin Gol, "Clock reduction in timed automata while preserving design parameters," International Conference on Formal Methods in Software Engineering (FormaliSE), 2019.
- Beyazit Yalcinkaya and Ebru Aydin Gol, "ATAC: A Tool for Automating Timed Automata Construction," arXiv preprint arXiv:1905.08169, 2019.
- Beyazit Yalcinkaya, Mitra Nasri, and Björn B. Brandenburg, "An exact schedulability test for non-preemptive self-suspending real-time tasks," Design, Automation and Test in Europe Conference (DATE), 2019.
Contact
Email: My first name at berkeley dot edu
Office: 545S Cory Hall, Berkeley, CA 94720