PhD Position in Test-Time Adaptation and Agentic AI at Aarhus University

🚀 Fully funded PhD position at Aarhus University in the Department of Electrical and Computer Engineering, within the newly established A3 Lab – Adaptive & Agentic AI. The project focuses on developing trustworthy machine learning systems that can adapt safely at test time under real-world distribution shifts. Research topics include test-time adaptation for multimodal foundation models, agentic decision-making, uncertainty estimation, calibration, out-of-distribution detection, and feedback-driven adaptation. The successful candidate will work on novel algorithms, theory, and large-scale empirical evaluations, with opportunities for international collaboration and publication at top venues such as NeurIPS, ICML, ICLR, CVPR, and ECCV. Preferred start date: 1 August 2026 or later. Application deadline: 1 June 2026.