3 papers
cs.CV2025
SmartSight: Mitigating Hallucination in Video-LLMs Without Compromising Video Understanding via Temporal Attention Collapse
Yiming Sun, Mi Zhang, Feifei Li +2
Despite Video Large Language Models having rapidly advanced in recent years, perceptual hallucinations pose a substantial safety risk, which severely restricts their real-world app…
cs.LG2025
InfoCons: Identifying Interpretable Critical Concepts in Point Clouds via Information Theory
Feifei Li, Mi Zhang, Zhaoxiang Wang +1
Interpretability of point cloud (PC) models becomes imperative given their deployment in safety-critical scenarios such as autonomous vehicles. We focus on attributing PC model out…
cs.CV2025
Detect-and-Guide: Self-regulation of Diffusion Models for Safe Text-to-Image Generation via Guideline Token Optimization
Feifei Li, Mi Zhang, Yiming Sun +1
Text-to-image diffusion models have achieved state-of-the-art results in synthesis tasks; however, there is a growing concern about their potential misuse in creating harmful conte…