Search papers, labs, and topics across Lattice.
2
0
3
6
Doubling the knowledge transfer ratio from trillion-parameter foundation models to recommendation systems is now possible without real-time FM inference, unlocking significant conversion improvements in large-scale industrial settings.
Meta's new hierarchical indexing method lets you deploy massive recommendation models without sacrificing speed or accuracy, and it turns out the index itself highlights a high-quality subset of data perfect for test-time training.
