Search papers, labs, and topics across Lattice.
Affiliation:
4
3
3
12
ICON decomposition reveals the true reliance of deep models on concepts, debunking misleading correlations that traditional methods often overlook.
A relevance-based concept atlas reveals how tissue morphology directly influences spatial transcriptomics predictions, enhancing interpretability in pathology.
Activation steering turns interpretability into a hands-on debugging tool, but watch out for unintended consequences and limited generalization.
CLIP models exhibit surprising reliance on latent components encoding polysemous words, visual typography, and dataset artifacts, revealing hidden biases that can be amplified in downstream tasks.
