Suyu Ge

Your thoughts tell who you are: Characterize the reasoning patterns of LRMs

2025 · arXiv (Cornell University)

Current comparisons of large reasoning models (LRMs) focus on macro-level statistics such as task accuracy or reasoning length. Whether different LRMs reason differently remains an open question. To address this gap, we introduce the LLM-proposed …

Reviews Meet Graphs: Enhancing User and Item Representations for Recommendation with Hierarchical Attentive Graph Neural Network

2019

Chuhan Wu, Fangzhao Wu, Tao Qi, Suyu Ge, Yongfeng Huang, Xing Xie. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). …

Neural News Recommendation with Multi-Head Self-Attention

2019

Chuhan Wu, Fangzhao Wu, Suyu Ge, Tao Qi, Yongfeng Huang, Xing Xie. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). …

Graph Enhanced Representation Learning for News Recommendation

2020

With the explosion of online news, personalized news recommendation becomes increasingly important for online news platforms to help their users find interesting information. Existing news recommendation methods achieve personalization by building accurate news representations from …