Study Traces Origins of the Modality Gap in Vision-Language Models
A new paper investigates whether differences in information processing and retrieval underlie the modality gap observed in vision-language models.
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-11-10 05:00 · arXiv cs.LG
Process then Retrieve: Investigating the Origins of the Modality Gap in Vision-Language Models