Semantic Richness or Geometric Reasoning? The Fragility of VLM's Visual Invariance
This reveals a systematic gap between semantic understanding and spatial reasoning in current VLMs, highlighting a need for stronger geometric grounding in future multimodal systems.
The paper investigates the fundamental fragility of state-of-the-art Vision-Language Models (VLMs) under basic geometric transformations, showing they systematically fail to maintain object identity under simple rotations, scaling, and identity transformations, with performance dropping sharply as semantic content becomes sparse.
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 more fundamental level: lack of robust spatial invariance and equivariance required to reliably determine object identity under simple rotations, scaling, and identity transformations. We demonstrate this limitation through a systematic evaluation across diverse visual domains, including symbolic sketches, natural photographs, and abstract art. Performance drops sharply as semantic content becomes sparse, and this behavior is observed across architectures, model capacities, and prompting strategies. Overall, our results reveal a systematic gap between semantic understanding and spatial reasoning in current VLMs, highlighting the need for stronger geometric grounding in future multimodal systems.