One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models
arXiv:2609.36101v1 Announce Type: new Abstract: Contrastive vision-language models learn shared embedding spaces by aligning matched image-text pairs, yet their representations remain separated by a modality gap. Prior work reports divergent effects of modifying this gap: reducing it can improve ze…
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-09-30 04:00 · arXiv cs.CV
One Geometry, Different Outcomes: Readout-Dependent Effects of the Modality Gap in Vision-Language Models