2026
A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Models
CVPR 2026
Despite the rapid progress in multimodal models and Large Visual-Language Models (LVLM), they remain highly susceptible to adversarial perturbations, raising serious concerns about their reliability in real-world use. While adversarial training has become the leading paradigm for building models tha