Muchao Ye

4

papers

8

total citations

papers (4)

VERA: Explainable Video Anomaly Detection via Verbalized Learning of Vision-Language Models

VQAttack: Transferable Adversarial Attacks on Visual Question Answering via Pre-trained Models

UniT: A Unified Look at Certified Robust Training against Text Adversarial Perturbation

VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Models

NeurIPS 2023arXiv