AI RESEARCH
Geometry-Preserving Unsupervised Alignment for Heterogeneous Foundation Models
arXiv CS.CV
•
ArXi:2606.04385v1 Announce Type: new Foundation models have driven rapid progress in computer vision, yet the two dominant paradigms, vision-language foundation models (VLMs) and vision-only foundation models (VFMs), remain only partially compatible. VLMs offer language-grounded semantic alignment but are often visually coarse, while VFMs learn discriminative perceptual geometry but lack semantic grounding. We propose GPUA (Geometry-Preserving Unsupervised Alignment), a framework that integrates the complementary strengths of VFMs and VLMs.