I am Yaowen Ye (or Elwin, or 叶耀文), a senior majoring in Computer Science at the University of Hong Kong. I am interested in making human oversight of AI systems reliable on hard tasks and efficient for complex outputs. Currently, I am working in Prof. Jacob Steinhardt's group. Before this, I was fortunate to be advised by Prof. Yixin Zhu at PKU Cognitive Reasoning Lab and Prof. Chao Huang at HKU Data Intelligence Lab.
Links:
[Email] [Give me feedback!]
Research Interests
I am interested in making human oversight of AI systems reliable on hard tasks and efficient for complex outputs. Some questions I am thinking about recently are:
- How can AI help humans give accurate feedback efficiently for complex model outputs that might require group of experts days to understand?
- When human feedback is prone to errors, how can AIs learn to do better than humans instead of replicating their mistakes?
In the past, I also worked on
- Cognitive reasoning: How can we explain humans’ reasoning process such as intuitive physics and abductive reasoning? How do these explanations inspire understanding of AI?
- Learning on graphs: How can we better model graph data for applications like recommender systems? How can we ensure these models are designed equally for different users and responsibly for real-world deployment?
Publications
2024
Placeholder for an upcoming paper.
2023
Graph Masked Autoencoder for Sequential Recommendation.
ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'23)
Yaowen Ye, Chao Huang and Lianghao Xia. [pdf]
Masked Graph Transformer for Recommendation.
ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR'23)
Chaoliu Li, Chao Huang, Lianghao Xia, Xubin Ren, Yaowen Ye and Yong Xu. [pdf]