I am visiting the Stanford Trustworthy AI Research Lab (STAIR). I’ll present our work on empirical alignment and incentive-aware AI regulation – both motivated from a statistical perspective on alignment and regulation. Drop me a message if you’re in the Bay Area and would like to attend and/or meet up afterwards!
Our research on personalizing exosuits via interpretable Bayesian optimization was covered by Börsen-Zeitung, Germany’s main newspaper on financial markets.
I’m on my way to Porto to attend the European Conference on Machine Learning ECML-PKDD (Europe’s flagship conference on Machine Learning) in order to present...
Happy to share that today’s my first day at the Rational Intelligence (RI) Lab at CISPA Helmholtz Center for Information Security in Saarbrücken, Germany. Th...
Our paper “GUARD: Glocal Uncertainty-Aware Robust Decoding for Effective and Efficient Open-Ended Text Generation” has been accepted to the findings track of...
