Meng Cao

Analyzing the evolution of fairness in social network recommendations over time.

A new method improves alignment of LLMs with minimal human feedback.

This article discusses using LLMs to enhance adult literacy education and prediction accuracy.

This article explains how language models produce incorrect information and studies their causes.

SLRL offers new insights into effective multi-view data grouping.

Research reveals type-II Dirac cones and exceptional rings in photonic lattices.

A detailed look at the MMAU benchmark for language models.

MUSE improves video retrieval accuracy through multi-scale feature learning.

This article discusses strategies to improve learning performance data accuracy.

AI models that learn continuously without forgetting previous knowledge are changing the game.

Researchers use gaming glitches to teach AI about physical commonsense.

EACO reduces AI errors and enhances reasoning for better performance.