2 papers
cs.CV2026
Finding the Correct Visual Evidence Without Forgetting: Mitigating Hallucination in LVLMs via Inter-Layer Visual Attention Discrepancy
Yutong Xie, Zhenglin Hua, Ran Wang +3
Large Vision-Language Models (LVLMs) have shown remarkable performance on a wide range of vision-language tasks. Despite this progress, they are still prone to hallucination, gener…
cs.LG2025
Feature Statistics with Uncertainty Help Adversarial Robustness
Ran Wang, Xinlei Zhou, Meng Hu +3
Despite the remarkable success of deep neural networks (DNNs), the security threat of adversarial attacks poses a significant challenge to the reliability of DNNs. In this paper, b…