Eric Hsiung
Papers
2
Total Citations
15
H-Index
2
About
Eric Hsiung is shaping the future of human-robot interaction by tackling a fundamental challenge: how can machines learn social norms and values from people? His research sits at the intersection of artificial intelligence, robotics, and cognitive science, focusing on reward learning and human-centered teaching strategies. Hsiung’s major contribution lies in developing frameworks that allow robots to learn from a blend of human feedback—combining instructive guidance, such as explicit demonstrations, with evaluative signals like praise or correction. This dual-channel approach, detailed in his highly cited works “Norm Learning with Reward Models from Instructive and Evaluative Feedback” (9 citations) and “Learning Reward Functions from a Combination of Demonstration and Evaluative Feedback” (6 citations), mirrors how humans naturally teach one another. By enabling agents to interpret diverse teaching styles, Hsiung’s work paves the way for robots that can adapt to real-world social settings, from homes to workplaces. His research is particularly notable for its human-first perspective, emphasizing that technology should bend to how people communicate, not the other way around. For students and researchers, Hsiung’s work offers a compelling blueprint for building socially aware AI that learns not just from data, but from the rich, nuanced feedback of human interaction.
Research Focus
Key Achievements
Top Papers
- 1
- 2