5 papers
Rethinking Training Data for Generating Code Review Comments
Leonardo Centellas-Claros, Estefania Pakarati-Cofre, Juan Pablo Sandoval Alcocer +1
Generating code review comments has become a prominent research direction in automated code review, commonly formulated as a text generation task over diff-comment pairs. Despite a…
Retrieval-Oriented Code Representations in Agentic Bug Localization
Genevieve Caumartin, Tse-Hsun, Chen +1
LLM-based agents are increasingly being used to support software development, yet their performance in repository-level tasks depends on retrieving the right code context. Existing…
ADPerf: Investigating and Testing Performance in Autonomous Driving Systems
Tri Minh-Triet Pham, Diego Elias Costa, Weiyi Shang +1
Obstacle detection is crucial to the operation of autonomous driving systems, which rely on multiple sensors, such as cameras and LiDARs, combined with code logic and deep learning…
Beyond More Context: How Granularity and Order Drive Code Completion Quality
Uswat Yusuf, Genevieve Caumartin, Diego Elias Costa
Context plays an important role in the quality of code completion, as Large Language Models (LLMs) require sufficient and relevant information to assist developers in code generati…
Exploring the Potential of Llama Models in Automated Code Refinement: A Replication Study
Genevieve Caumartin, Qiaolin Qin, Sharon Chatragadda +3
Code reviews are an integral part of software development and have been recognized as a crucial practice for minimizing bugs and favouring higher code quality. They serve as an imp…