Zhaoran Wang

This study combines Large Language Models with Monte-Carlo Tree Search for better game decision-making.

This article discusses the essential aspects of constrained reinforcement learning and its real-world applications.

A new method enhances language models by actively seeking diverse responses.

Introducing a method to minimize overoptimization in models trained with human feedback.

This paper discusses a method for robots to learn safety from human input.

A new method enhances language model training using self-generated feedback.

A new method improves coding models using self-generated tests.

Explore how data's value influences pricing strategies for businesses.

Learn how robots can improve by following human commands and adapting to mistakes.