PhD Thesis

• Tatiana Castro Vélez. Towards Automated Software Evolution for Imperative Deep Learning programs using Graph Execution. Ph.D. Thesis. City University of New York (CUNY) Graduate Center, 2025 (Expected)

Conference Publications (Peer-Reviewed)

• Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, and Anita Raja. Hybridize functions: A tool for automatically refactoring imperative Deep Learning programs to graph execution. In Fundamental Approaches to Software Engineering, FASE ’25. ETAPS, May 2025. To appear. (11/31; 35% acceptance rate). Distinguished Paper Award.
• Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, and Anita Raja. Safe automated refactoring for efficient migration of imperative Deep Learning programs to graph execution. In submission to International Conference on the Foundations of Software Engineering, FSE ’25. ACM, ACM, June 2025.
• Raffi Khatchadourian, Tatiana Castro Vélez, Mehdi Bagherzadeh, Nan Jia, and Anita Raja. Towards safe automated refactoring of imperative Deep Learning programs to graph execution. In International Conference on Automated Software Engineering, ASE ’23, Kirchberg, Luxembourg, September 2023. IEEE/ACM. (25/70; 35.7% acceptance rate).
• Tatiana Castro Vélez, Raffi Khatchadourian, Mehdi Bagherzadeh, and Anita Raja. Challenges in migrating imperative Deep Learning programs to graph execution: An empirical study. In International Conference on Mining Software Repositories, MSR ’22. ACM/IEEE, ACM, May 2022. (45/138; 32.6% acceptance rate).

Technical Reports

• Ye Paing, Tatiana Castro Vélez, and Raffi Khatchadourian. QuerTCI: A tool integrating GitHub issue querying with comment classification. Technical Report 707, City University of New York (CUNY) Hunter College, 695 Park Ave, New York, NY 10065 United States, July 2022.ter College, 695 Park Ave, New York, NY 10065 United States, July 2022.