Peer-reviewer for International Conference on Machine Learning

Reviewed seven paper submissions for the Second Workshop on Agents in the Wild: Safety, Security, and Beyond (AIWILD), an official workshop at the International Conference on Machine Learning (ICML) 2026 in Seoul. The workshop examines how intelligent agents can operate safely and securely in real-world settings, spanning agentic safety and alignment, security and privacy, interpretability, fairness, multi-agent coordination, and responsible deployment. I completed my reviews on 21 May 2026, assessing each paper for technical soundness, clarity, and contribution.