4 papers
XMix: Combating Extremely Noisy Labels via Local Smoothness in Self-Supervised Feature Space
Chengqi Li, Yangdi Lu, Zhihao Shi +3
Supervised deep learning models rely on large, accurately labeled datasets, yet noisy annotations are often unavoidable and can severely degrade performance under high noise levels…
A Realistic Protocol for Evaluation of Weakly Supervised Object Localization
Shakeeb Murtaza, Soufiane Belharbi, Marco Pedersoli +1
Weakly Supervised Object Localization (WSOL) allows training deep learning models for classification and localization (LOC) using only global class-level labels. The absence of bou…
Understanding the Rejection of Fixes Generated by Agentic Pull Requests -- Insights from the AIDev Dataset
Mahmoud Abujadallah, Ali Arabat, Mohammed Sayagh
AI coding agents are increasingly used to generate pull requests (PRs) that propose code fixes in software projects. From a first exploration of the AIDev dataset, we find that 46.…
Toward Instructions-as-Code: Understanding the Impact of Instruction Files on Agentic Pull Requests
Ali Arabat, Mohammed Sayagh
AI-agents (e.g., GitHub Copilot) collaborate as teammates in different software engineering tasks, including code generation proposed through pull requests (Agentic-PRs). For bette…