VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language ModelsJan 1, 2026·Rohit Saxena,Alessandro Suglia,Pasquale Minervini· 1 min read Cite DOI URLTypeJournal articlePublicationInternational Conference on Machine Learning 2026A comprehensive study of Vision-Language Models’ behavioural robustness.Last updated on Jan 1, 2026 ← Same Answer, Different Representations: Hidden instability in VLMs Jan 1, 2026CROPE: Evaluating In-Context Adaptation of Vision and Language Models to Culture-Specific Concepts Apr 1, 2025 →
