Qinru Qiu

Adversarially Robust Abductive Fusion of Pre-trained Transformer-based Perception Models

This work frames the fusion of multiple imperfect ViT-based detectors as a consistency-based abduction problem solved at test time by an exact Integer Program (IP) and a polynomial-time heuristic and shows that this metacognitive layer can be learned without any domain knowledge by exploiting vector-space geometry.