Muhao Chen

A new method safeguards decision privacy in language models while maintaining performance.

A new approach to protect language models from harmful data triggers.

Addressing contradictions in AI dialogues for better communication.

This study examines how LLMs handle changes in summarization tasks.

This study examines how visual and textual data affect model performance.

Concerns grow over backdoor attacks in language models, impacting safety and reliability.

Analyzing the storytelling capabilities of large language models compared to human authors.

A new method enhances language model performance by streamlining external information.

A new soft robot imitates dolphin movements for improved underwater exploration.

Explore how bioinspired metamaterials can transform industries and improve human life.