Search papers, labs, and topics across Lattice.
3
0
7
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.
ChemBack reveals that even with rigorous admission protocols, chemically valid backdoors can still pose significant risks to molecular graph neural networks.
Achieving state-of-the-art results in Vietnamese speech tasks, ViP-VL redefines efficiency in self-supervised speech models with groundbreaking subsampling techniques.
