arXiv cs.AI
· Papers
Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models
arXiv:2608.04190v1 Announce Type: new Abstract: Deploying pre-trained perception models in novel environments degrades their accuracy under distributional shift, and assembling them alone does not recover it: combiners such as majority voting trade recall for precision and are brittle to coordinated failures. Prior met