Xinyue Wu

Collaborative Autoencoder for Recommender Systems

2017 · arXiv (Cornell University)

In recent years, deep neural networks have yielded state-of-the-art performance on several tasks. Although some recent works have focused on combining deep learning with recommendation, we highlight three issues of existing works. First, most works …

Efficient Logical Reasoning in Large Language Models through Program-Guided Learning

2024

Language models have achieved remarkable success in generating coherent and contextually appropriate text, but they continue to face significant challenges when applied to tasks that require formal logical reasoning. Introducing structured guidance into the training …