AI RESEARCH
Left-Right Symmetry Breaking in CLIP-style Vision-Language Models Trained on Synthetic Spatial-Relation Data
arXiv CS.AI
•
ArXi:2601.12809v2 Announce Type: replace-cross Spatial understanding remains a key challenge in vision-language models. Yet it is still unclear whether such understanding is truly acquired, and if so, through what mechanisms. We present a controllable 1D image-text testbed to probe how left-right relational understanding emerges in Transformer-based vision and text encoders trained with a CLIP-style contrastive objective.