Search papers, labs, and topics across Lattice.
University of Delaware
2
0
6
Model internals, not just outputs, hold the key to predicting generalization: circuit-based metrics beat standard proxies by up to 34% in assessing ViT performance under distribution shift.
Noisy labels tank dynamic pruning performance, but AlignPrune's loss-trajectory alignment recovers up to 6.3% accuracy without architecture or training changes.
