4 papers
From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs
Anh Ho, Thanh Le-Cong, Bach Le +1
[...] Since then, various APR approaches, especially those leveraging the power of large language models (LLMs), have been rapidly developed to fix general software bugs. Unfortuna…
CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases
Anh Nguyen Hoang, Minh Le-Anh, Bach Le +1
Given a large and evolving codebase, the ability to automatically generate holistic, architecture-aware documentation that captures not only individual functions but also cross-fil…
Tight Robustness Certificates and Wasserstein Distributional Attacks for Deep Neural Networks
Bach C. Le, Tung V. Dao, Binh T. Nguyen +1
Wasserstein distributionally robust optimization (WDRO) provides a framework for adversarial robustness, yet existing methods based on global Lipschitz continuity or strong duality…
EnseSmells: Deep ensemble and programming language models for automated code smells detection
Anh Ho, Anh M. T. Bui, Phuong T. Nguyen +2
A smell in software source code denotes an indication of suboptimal design and implementation decisions, potentially hindering the code understanding and, in turn, raising the like…