Yi Xie

This paper introduces personalized empathy, a capability for LLMs to adapt empathetic strategies based on individual user history, and proposes PereGRM, a reward modeling framework that significantly enhances this personalized empathy.

This study evaluates LLMs in conversational tutoring to identify high-confidence social biases, finding that state-of-the-art models are often overconfident in their incorrect assessments of stereotypical bias.

This paper presents GRAIL, a digital generation pipeline that synthesizes human-object interactions for humanoid robots.

This paper introduces Agents-K1, an end-to-end knowledge orchestration pipeline that converts raw documents into agent-native scientific knowledge graphs.