Tuan Nguyen

This work revisits RAG compression from a data-mining perspective by aggregating historical query--document--model interactions into reusable evidence views and proposes Reusable Evidence View Aggregation (REVA), a framework that mines the target generator's historical attention traces into a document-keyed, budget-agnostic score store.

Surface phonon polaritons can dramatically enhance the thermal dissociation rates of polyatomic molecules in microcavities, shifting the balance between radiative and collisional activation.

The model's learned representations reveal a surprising dominance of spectral and prosodic features, reshaping our understanding of acoustic encoding in pathological speech assessment.