Shikun Zhang

KIEval offers interactive evaluation to address data contamination in language models.

This article discusses a new framework for assessing hallucinations in LVLMs.

CoderUJB evaluates LLM performance in real-world Java programming tasks.

A look into new methods for ad measurement that prioritize user privacy.

IDAICL improves predictions by refining demonstration quality in in-context learning.

MaVEn enhances AI's ability to process multiple images for better reasoning.

This article highlights noise suppression in quantum systems using coherent quantum feedback techniques.