Our setup is further extended to hybrid logical-neural constraints for capturing very complexconstraints,likegraphreachability.

AI models are increasingly prevalent in high-stakes environments, necessitating1 thorough assessment oftheir capabilities and risks.

Adversarially Trained End-to-End Korean Singing Voice Synthesis System.

How do we program home robots to perform a wide variety of personalized everyday tasks?

To address this, we propose a new probabilistic framework for DG where the goal is to learn predictors that perform wellwith highprobability.