Jinsong Chen

Existing security scanners misidentify nearly half of MCP server risks, challenging the reliability of current security assessments in LLM applications.

A novel assessment framework reveals that traditional methods fail to capture true dimensionality, while a new gain rule accurately recovers latent structures in factor analysis.

Text embeddings can predict item difficulty with surprising accuracy, but the predictability of other parameters is limited by their inherent reliability ceilings.

Blind cross-sensor spectral super-resolution can achieve unprecedented accuracy by learning the spectral transformation function directly from data, rather than relying on fixed assumptions.