2 papers
cs.CV2025
Vision language models have difficulty recognizing virtual objects
Tyler Tran, Sangeet Khemlani, J. G. Trafton
Vision language models (VLMs) are AI systems paired with both language and vision encoders to process multimodal input. They are capable of performing complex semantic tasks such a…
cs.CV2025
Vision language models are unreliable at trivial spatial cognition
Sangeet Khemlani, Tyler Tran, Nathaniel Gyory +6
Vision language models (VLMs) are designed to extract relevant visuospatial information from images. Some research suggests that VLMs can exhibit humanlike scene understanding, whi…