Search papers, labs, and topics across Lattice.
3
0
6
0
SVD-Attention slashes the quadratic cost of attention to linear for recommendation tasks by exploiting the inherent low-rank structure of user behavior sequences, without sacrificing softmax.
FlashEvaluator slashes the computational cost of evaluating multiple sequences in Generator-Evaluator frameworks while boosting accuracy by enabling direct cross-sequence comparisons.
Instanton calculations, a cornerstone of modeling molecular tunneling, get a speed boost by orders of magnitude thanks to a clever combination of Gaussian process regression and GPU acceleration.
