- "Interpretable Vulnerability Detection Reports" accepted at ASE'25.
- Won Best Paper Award with "Are Large Language Models Memorizing Bug Benchmarks" at LLM4Code (co-located with ICSE25).
Conferences: Attended ICSE25 in Ottawa, CA.
Research Experience
No specific work experience or research projects mentioned.
Education
PhD student at Carnegie Mellon University and University of Porto; Advisors: Dr. Claire Le Goues, Dr. Rui Abreu, and Dr. Jose Campos.
Background
Primary interests: Application of Large Language Models to ensure Code Quality and Safety, particularly in vulnerability detection, automated program repair, and patch generation.