CS Ph.D. Student @ Northwestern University
Foundation Agent · Trustworthiness · Multimodality
Hi, this is Canyu Chen (陈灿宇). I am a Computer Science Ph.D. student at Northwestern University and a member of the Northwestern MLL Lab, fortunately advised by Prof. Manling Li. I was a graduate visiting researcher at University of California, Berkeley, hosted by Prof. Dawn Song. I received my B.S. from the University of Chinese Academy of Sciences. I have the privilege of collaborating closely with Prof. Dawn Song, Prof. James Evans, and Prof. Philip Torr. I am grateful for the previous mentorship from Prof. Kai Shu. I am a recipient of the prestigious Bloomberg Data Science Ph.D. Fellowship.
My research interest covers Foundation Agent, Trustworthiness, and Multimodality. I aim to pursue Safe and Aligned Artificial General Intelligence in the long run.
- 🤖 FedAgent enables agent learning without sacrificing user data privacy (first author · 🏆 Best Paper Award at the AAAI'26 TrustAgent Workshop · 🏆 Outstanding Paper Award at the AAAI'26 PerFM Workshop)
- 🤝 AgentTrust demonstrates the feasibility to simulate human trust behavior with LLM agents (co-first author · 🏆 Outstanding Paper Award at the CIKM'25 LASS Workshop)
- 📰 LLMFake shows that LLM-generated misinformation can be more deceptive than human-written misinformation (first author · 🏆 Didactic Paper Award at the NeurIPS'23 ICBINB Workshop)
- I am one organizer of the ResponsibleFM community, dedicated to advancing socially responsible and trustworthy foundation models (language and multimodal).
- I started and led the LLMs Meet Misinformation initiative, aiming to combat misinformation in the age of LLMs.
I am always happy to chat and discuss potential collaborations, or give talks about my research in related seminars. Feel free to reach out:
- 📧 Email: canyuchen [at] u.northwestern.edu
- 💬 WeChat: alexccychen
- 🔗 Homepage: canyuchen.com