Search papers, labs, and topics across Lattice.
2
0
4
2
Achieving near-autoregressive accuracy while boosting decoding speed by over 2.4 times could redefine efficiency benchmarks in generative reasoning tasks.
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.
