2026
Contamination Detection for VLMs Using Multi‑Modal Semantic Perturbations
ICLR 2026poster
Recent advances in Vision–Language Models (VLMs) have achieved state-of-the-art performance on numerous benchmark tasks. However, the use of internet-scale, often proprietary, pretraining corpora raises a critical concern for both practitioners and users: inflated performance due to \emph{test-set l…