About Me
Hi there! I’m Yuchen Wu, a Computer Science Ph.D. student at the University of Illinois Urbana–Champaign, advised by Prof. Eshwar Chandrasekharan.
I work at the intersection of Human-Centered AI and Human-Computer Interaction (HCI), designing interactive AI systems that align with human values, respond to human needs, and effectively support decision-making in real-world contexts. My research takes a twofold approach:
- On the modeling side, I study how human preferences can be represented and integrated into machine learning models, developing methods such as reward modeling to align model behavior with human values.
- On the system design side, I build interactive AI systems that connect these models with real users, exploring how human–AI collaboration can foster more informed, value-sensitive, and trustworthy interactions in real-world contexts.
Previously, I was an undergraduate student at Tsinghua University majoring in Computer Science, advised by Prof. Chun Yu. During my undergraduate studies, I was also fortunate to be advised by Prof. Sauvik Das at Carnegie Mellon University, and Prof. John F. Canny at UC Berkeley.
Publications
[Under Review] Beyond Likes: How Normative Feedback Complements Engagement Signals on Social Media
[UIST '25] Imago Obscura: An Image Privacy AI Co-pilot to Enable Identification and Mitigation of Risks
Paper Webpage Demo Video[UIST '24 Demo] Manipulate to Obfuscate: A Privacy-Focused Intelligent Image Manipulation Tool for End-Users
Paper Teaser Video Demo Video[NIPS '23] Imagereward: Learning and evaluating human preferences for text-to-image generation
Paper