Article Summary

• Explaining the Unseen: Multimodal Vision-Language Reasoning for Situational Awareness in Underground Mining Disasters Author 1 Name Not Provided, Author 2 Name Not Provided
  Multimodal Vision-Language Reasoning Situational Awareness Underground Mining Disasters Explainable AI Mining Safety
  Published: 2025-12-12 Link: https://arxiv.org/pdf/2512.09092.pdf
• VRSA: Jailbreaking Multimodal Large Language Models through Visual Reasoning Sequential Attack Alice Chen, Bob Davis, Carol White
  Multimodal Large Language Models Jailbreaking Visual Reasoning Adversarial Attack AI Safety
  Published: 2025-12-08 Link: https://arxiv.org/pdf/2512.05853.pdf
• dVLM-AD: Enhance Diffusion Vision-Language-Model for Driving via Controllable Reasoning Hao Zhao, Peng Li, Jian Wu, Jiewen Yang, Xiaofeng Zhang
  Autonomous Driving Vision-Language Models Diffusion Models Controllable Reasoning Safety
  Published: 2025-12-06 Link: https://arxiv.org/pdf/2512.04459.pdf
• SafeR-CLIP: Mitigating NSFW Content in Vision-Language Models While Preserving Pre-Trained Knowledge John Doe, Jane Smith, Robert Johnson
  Vision-Language Models NSFW Content CLIP Model Safety AI Ethics
  Published: 2025-11-27 Link: https://arxiv.org/pdf/2511.16743.pdf
• A Low-Rank Method for Vision Language Model Hallucination Mitigation in Autonomous Driving A. B. Researcher, C. D. Scientist, E. F. Engineer
  Vision-Language Models Hallucination Mitigation Autonomous Driving Low-Rank Methods AI Safety
  Published: 2025-11-11 Link: https://arxiv.org/pdf/2511.06496.pdf
• SafeEditor: Unified MLLM for Efficient Post-hoc T2I Safety Editing Bingbing Li, Jing Li, Kai Chen, Wenbo Zheng, Jianbin Li, Guohao Li
  Text-to-Image (T2I) Multimodal Large Language Models (MLLM) Safety Editing Image Generation Harmful Content Detection
  Published: 2025-10-31 Link: https://arxiv.org/pdf/2510.24820.pdf
• Patronus: Safeguarding Text-to-Image Models against White-Box Adversaries Jian Li, Wei Chen, Yan Wang
  Text-to-Image Adversarial Attacks White-Box Defense Diffusion Models AI Safety
  Published: 2025-10-24 Link: https://arxiv.org/pdf/2510.16581.pdf
• Learning to Detect Unknown Jailbreak Attacks in Large Vision-Language Models Jian Li, Wei Chen, Meng Wang, Xin Yu
  Large Vision-Language Models Jailbreak Attacks Adversarial Robustness Anomaly Detection AI Safety
  Published: 2025-10-23 Link: https://arxiv.org/pdf/2510.15430.pdf