6 papers
Revis: Sparse Latent Steering to Mitigate Object Hallucination in Large Vision-Language Models
Jialin Wu, Wei Shi, Han Shen +5
Despite the advanced capabilities of Large Vision-Language Models (LVLMs), they frequently suffer from object hallucination. One reason is that visual features and pretrained textu…
VLMShield: Efficient and Robust Defense of Vision-Language Models against Malicious Prompts
Peigui Qi, Kunsheng Tang, Yanpu Yu +7
Vision-Language Models (VLMs) face significant safety vulnerabilities from malicious prompt attacks due to weakened alignment during visual integration. Existing defenses suffer fr…
SafeGuider: Robust and Practical Content Safety Control for Text-to-Image Models
Peigui Qi, Kunsheng Tang, Wenbo Zhou +5
Text-to-image models have shown remarkable capabilities in generating high-quality images from natural language descriptions. However, these models are highly vulnerable to adversa…
PoseGuard: Pose-Guided Generation with Safety Guardrails
Kongxin Wang, Jie Zhang, Peigui Qi +3
Pose-guided video generation has become a powerful tool in creative industries, exemplified by frameworks like Animate Anyone. However, conditioning generation on specific poses in…
FinRipple: Aligning Large Language Models with Financial Market for Event Ripple Effect Awareness
Yuanjian Xu, Jianing Hao, Kunsheng Tang +4
Financial markets exhibit complex dynamics where localized events trigger ripple effects across entities. Previous event studies, constrained by static single-company analyses and…
GenderCARE: A Comprehensive Framework for Assessing and Reducing Gender Bias in Large Language Models
Kunsheng Tang, Wenbo Zhou, Jie Zhang +7
Large language models (LLMs) have exhibited remarkable capabilities in natural language generation, but they have also been observed to magnify societal biases, particularly those…