Search papers, labs, and topics across Lattice.
2
0
6
1
Late-interaction retrieval just got a whole lot faster and cheaper: Flash-MaxSim slashes memory usage by 16x and speeds up inference by 4.7x on an H100 by ditching the massive similarity tensor.
Layout-preserving text beats pixel-level visual cues for structured data extraction from documents, according to a new benchmark spanning 1,771 unique schemas.
