Kristian Kersting

A new framework to improve AI agents' learning through modified Atari games.

A new system assesses safety risks in images generated by AI models.

A novel approach combines learning and logic for better AI reasoning.

A new method to define rewards for reinforcement learning agents using language models.

A new method improves efficiency in language processing by simplifying tokenization.

Characteristic Interventional Sum-Product Networks improve causal inference in mixed data.

This article explores the NL-DAR framework for improving diagnostic reasoning with AI.

Learn how company fundamentals and forecasting influence investment decisions.

Scar enhances language models by reducing toxic language in text generation.

CNA method enhances GNNs by tackling oversmoothing and improving performance.

This article examines shortcut learning issues in machine learning and how to address them.

M-ALERT tests language models for safety across five languages.

Linking logic programming with neural networks for faster AI solutions.