robustness assessment

4 papers

• Fix False Transparency by Noise Guided Splatting
• MMLongBench: Benchmarking Long-Context Vision-Language Models Effectively and Thoroughly
• Transferable Black-Box One-Shot Forging of Watermarks via Image Preference Models
• Worse than Zero-shot? A Fact-Checking Dataset for Evaluating the Robustness of RAG Against Misleading Retrievals