Search papers, labs, and topics across Lattice.
Affiliation:
3
0
6
Progressive growth strategies can significantly bias neural network training towards flatter loss landscapes, but flatter does not always mean better performance.
Entity tracking can be sped up by 29% without sacrificing accuracy by exploiting the surprisingly structured sparsity in learned attention.
Bias against certain speaker groups is embedded in self-supervised speech models from the very first layers, complicating efforts to achieve fairness in speech recognition tasks.
