Yankai Chen

I am currently a postdoctoral researcher working with Prof. Xue (Steve) Liu and Prof. Philip S. Yu. Previously, I was a postdoctoral associate at Cornell University and The Chinese University of Hong Kong. I received my Ph.D. degree in Computer Science and Engineering from The Chinese University of Hong Kong in 2023, supervised by Prof. Irwin King. Prior to that, I completed my M.S. degree at The University of Hong Kong in 2018, working with Prof. Reynold Cheng, and received my B.S. degree from Nanjing University in 2016, mentored by Prof. Qizhi Liu.

My research interests lie at the intersection of Human-centered AI and Knowledge Mining. I am dedicated to building intelligent systems that can deeply understand massive-scale data and collaborate with humans effectively, efficiently, and trustworthily. My recent research focuses on:

• Agentic AI, including Agent Memory, Deep Research, and Human-Agent Collaboration.
• LLM Personalization, Retrieval-Augmented Generation.

I also work on topics including:

• Optimal Transport theory and Optimization.
• Representation Learning, including Self-supervised Learning, Semi-supervised Learning.
• Large-scale Graph Data Mining, such as Graph Neural Networks, Knowledge Graph, Graph-text Fusion.
• Information Retrieval and Efficiency Optimization, including Dense Retrieval and Low-bit Quantization, with applications in Search and Recommender Systems

Recent Research Highlight

• Adversarial Encoding Synthesis and Optimization for Set Representation Auxiliary Learning
  Yankai Chen, Xinni Zhang, Henry Peng Zou, Yangning Li, Philip S. Yu, Irwin King, and Xue Liu
  In Proceeding of International Conference on Learning Representations (ICLR), 2026

• Pedagogically-Inspired Data Synthesis for Language Model Knowledge Distillation
  Bowei He, Yankai Chen, Xiaokun Zhang, Linghe Kong, Philip S. Yu, Xue Liu, and Chen Ma
  In Proceeding of International Conference on Learning Representations (ICLR), 2026

• RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback
  Chunyu Miao, Henry Peng Zou, Yangning Li, Yankai Chen^#, Yibo Wang, Fangxin Wang, Yifan Li, Wooseong Yang, Bowei He, Xinni Zhang, et al.
  In Proceeding of International Conference on Learning Representations (ICLR), 2026

• MUSE: Model-Agnostic Tabular Watermarking via Multi-Sample Selection
  Liancheng Fang, Aiwei Liu, Henry Peng Zou, Yankai Chen, Hengrui Zhang, Zhongfen Deng, and Philip S. Yu
  In Proceeding of International Conference on Learning Representations (ICLR), 2026

• Generative Archetype-Grounded Item Representations for Sequential Recommendation
  Yifan Li, Jiahong Liu, Xinni Zhang, Hao Chen, Yankai Chen, Wenhao Yu, Jianting Chen, Irwin King
  In Proceeding of The Web Conference (WWW), 2026