Search papers, labs, and topics across Lattice.
2
0
5
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.
FlashDiff slashes diffusion model serving latency by up to 97% while boosting throughput by over 2x through intelligent regional execution and scheduling.
