arXiv cs.CV
· Papers
Majorization-Guided Test-Time Adaptation for Vision-Language Models under Modality-Specific Shift
arXiv:2604.24602v4 Announce Type: replace Abstract: Vision--language models can face asymmetric visual and textual shifts at deployment. These shifts expose a multimodal failure mode in which an unreliable branch remains overconfident, dominates fusion, and causes entropy-based test-time adaptation to sharpen an incorr