Zhining Xie — accepted AI-conference papers

2026

Interpreting and Enhancing Emotional Circuits in Large Vision-Language Models via Cross-Modal Information Flow

Chengsheng Zhang, Chenghao Sun, Zhining Xie, Xinmei Tian

ICML 2026poster

Large Vision-Language Models (LVLMs) represent a significant leap towards empathetic agents, demonstrating remarkable capabilities in emotion understanding. However, the internal mechanisms governing how LVLMs translate abstract visual stimuli into coherent emotional narratives remain largely unexpl…

Cited by 0 Source ↗Scholar ↗

2026

Tracing the Persona Circuit: How Large Language Models Encode and Express Character Traits

Guanzheng Qin, Chenghao Sun, Zhining Xie, Xinmei Tian

ICML 2026poster

Large Language Models (LLMs) demonstrate remarkable potential in role-playing tasks but frequently suffer from personality decay—termed "Out-of-Character" (OOC) behavior—during prolonged interactions. While heuristic strategies exist to align model behaviors, the internal computational dynamics driv…

Cited by 0 Source ↗Scholar ↗