Flickr30K

PROVE (Prompt Recovery with Verified Evidence), a training-free, black-box prompt inversion attack introduced in arXiv:2608.13671v1, reconstructs prompts by composing verifiable scene descriptions and…

Researchers introduced the Semantic-Enhanced Patch Slimming (SEPS) framework to improve vision-language alignment by reducing patch redundancy and ambiguity, outperforming existing methods by 23% to 8…

Researchers have developed IN2R, a new framework that corrects mismatched image-text pairs in large web-harvested datasets by synthesizing continuous supervision signals from intra-modal data relation…