The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2608. 18339v1 Announce Type: cross Abstract: Vision-language models (VLMs) have demonstrated remarkable zero-shot capabilities yet remain sensitive to real-world distribution shifts during inference.
Multi-label recognition with frozen Vision-Language Models (VLMs) is brittle under distribution shift: standard zero-shot inference scores labels independently, ignoring co-occurrence structure and producing incoherent label sets where dominant concepts suppress weaker but compatible labels. We introduce Bayesian Conditional Priors (BCP) Estimation, a gradient-free test-time adaptation method that injects label dependency without tuning the backbone.
arXiv:2606. 06943v1 Announce Type: cross Abstract: Vision-language models (VLMs) such as CLIP achieve strong zero-shot recognition but remain highly fragile under adversarial perturbations.
arXiv:2505.12912v2 Announce Type: replace Abstract: Pre-trained vision-language models, such as contrastive language-image pre-training (CLIP), have demonstrated a remarkable generalizability, enabli...
arXiv:2609.02039v1 Announce Type: new Abstract: Vision-language models (VLMs) have achieved remarkable performance by leveraging complementary information from large-scale image-text pairs. However,...
Vision-language models (VLMs) have achieved remarkable performance by leveraging complementary information from large-scale image-text pairs. However, missing-modality inputs are commonly encountered...