3 papers
cs.CV2026
Adversarial Attacks Already Tell the Answer: Directional Bias-Guided Test-time Defense for Vision-Language Models
Liangsheng Liu, Si Chen, Jiamin Wu +5
Vision-Language Models (VLMs), such as CLIP, have shown strong zero-shot generalization but remain highly vulnerable to adversarial perturbations, posing serious risks in real-worl…
cs.CV2026
SRUG: A Fusion-Driven Generator Network for Medical Image Translation
Xihe Qiu, Yang Dai, Xiaoyu Tan +4
MRI sequence synthesis aims to recover missing image contrast while preserving patient-specific anatomy. The choice of generation mechanism affects both optimization and the way so…
cs.CV2025
OR-VSKC: Resolving Visual-Semantic Knowledge Conflicts in Operating Rooms with Synthetic Data-Guided Alignment
Weiyi Zhao, Xiaoyu Tan, Liang Liu +3
Automated identification of surgical safety risks is critical for improving patient outcomes; however, Multimodal Large Language Models (MLLMs) frequently suffer from Visual-Semant…