AI RESEARCH
Trustworthy AI: Ensuring Reliability and Accountability from Models to Agents
arXiv CS.LG
•
ArXi:2605.08964v1 Announce Type: new In this thesis, we develop algorithms with theoretical guarantees for ensuring reliability and accountability of Machine Learning (ML) systems. As ML systems evolve from predictive models to generative models and autonomous agents, the landscape of trustworthy AI has shifted. This thesis