AI RESEARCH
Semantic Richness or Geometric Reasoning? The Fragility of VLM's Visual Invariance
arXiv CS.CV
•
ArXi:2604.01848v1 Announce Type: new This work investigates the fundamental fragility of state-of-the-art Vision-Language Models (VLMs) under basic geometric transformations. While modern VLMs excel at semantic tasks such as recognizing objects in canonical orientations and describing complex scenes, they exhibit systematic failures at a fundamental level: lack of robust spatial invariance and equivariance required to reliably determine object identity under simple rotations, scaling, and identity transformations.