Pedro Zuidberg Dos Martires

APC-RL: Exceeding data-driven behavior priors with adaptive policy composition

Adversarial Co-Evolution of LLM-Generated Policies and Environments via Two-Player Zero-Sum Game

KLay: Accelerating Arithmetic Circuits for Neurosymbolic AI

Have Large Language Models Learned to Reason? A Characterization via 3-SAT

REvolve: Reward Evolution with Large Language Models using Human Feedback

Can Large Language Models Reason? A Characterization via 3-SAT

The Normalized Float Trick: Numerical Stability for Probabilistic Circuits without the LogSumExp Trick