1 citations · 1 across the 4 of their papers we have counts for
4 papers
Self-Attention as a Covariance Readout: A Unified View of In-Context Learning and Repetition
Haoren Xu, Guanhua Fang
Large language models (LLMs) exhibit two striking and ostensibly unrelated behaviours: in-context learning (ICL) and repetitive generation. In both, the model behaves as though it…
Toward a unified framework for data-efficient evaluation of large language models
Lele Liao, Qile Zhang, Ruofan Wu +1
Evaluating large language models (LLMs) on comprehensive benchmarks is a cornerstone of their development, yet it's often computationally and financially prohibitive. While Item Re…
Transformers as Unsupervised Learning Algorithms: A study on Gaussian Mixtures
Zhiheng Chen, Ruofan Wu, Guanhua Fang
The transformer architecture has demonstrated remarkable capabilities in modern artificial intelligence, among which the capability of implicitly learning an internal model during…
On provable privacy vulnerabilities of graph representations
Ruofan Wu, Guanhua Fang, Qiying Pan +3
Graph representation learning (GRL) is critical for extracting insights from complex network structures, but it also raises security concerns due to potential privacy vulnerabiliti…