2 papers
cs.LG2025
SAFEx: Analyzing Vulnerabilities of MoE-Based LLMs via Stable Safety-critical Expert Identification
Zhenglin Lai, Mengyao Liao, Bingzhe Wu +5
Large language models with Mixture-of-Experts (MoE) architectures achieve efficiency and scalability, yet their routing mechanisms introduce safety alignment challenges insufficien…
cs.CL2025
A Dual-Directional Context-Aware Test-Time Learning for Text Classification
Dong Xu, Mengyao Liao, Zhenglin Lai +2
Text classification assigns text to predefined categories. Traditional methods struggle with complex structures and long-range dependencies. Deep learning with recurrent neural net…