About Me
I am Wenkai Chen, a PhD student at the Hong Kong University of Science and Technology (Guangzhou), where I am advised by Prof. Chengwei Qin. My doctoral studies are supported by the HKUST(GZ)–PAITH (PhD talent program in AI Through Huawei) Co-Supervision Scheme. Before starting my PhD, I earned my Master’s degree in Artificial Intelligence from Utrecht University under the supervision of Prof. Albert Gatt. During this time, I also spent a year as a visiting student at EPFL, supervised by Prof. Antoine Bosselut. Piror to that, I received my Bachelor’s degree from the School of Computer Science at BUPT. Throughout my academic journey, I have had the privilege of collaborating with outstanding researchers across several leading institutions, and I greatly value the insights gained from these collaborations.
My current research is driven by the goal of building more efficient and capable LLMs. Specifically, my interests includes:
- LLM Pre-training
- Advanced Transformer Architectures
- Long-Context Reasoning
News
Aug 2026: One paper is accepted by EMNLP 2026. Thanks to my co-authors.
Selected Publications
LoopMoE: Unifying Iterative Computation with Mixture-of-Experts for Language Modeling
Published in EMNLP, 2026
Wenkai Chen, Tianshu Li, Wenyong Huang, Yichun Yin, Lifeng Shang, Chengwei Qin [Link]
Common Objects Out of Context (COOCo): Investigating Multimodal Context and Semantic Scene Violations in Referential Communication
Published in TACL, 2026
Filippo Merlo, Ece Takmaz, Wenkai Chen, Albert Gatt [Link]
CASE: Commonsense-Augmented Score with an Expanded Answer Space
Published in EMNLP Findings, 2023
Wenkai Chen, Sahithya Ravi, Vered Shwartz [Link]
A Semantic-based Method for Unsupervised Commonsense Question Answering
Published in ACL, 2021
Yilin Niu, Fei Huang, Jiaming Liang, Wenkai Chen, Xiaoyan Zhu, Minlie Huang [Link]
