miccunifi

miccunifi/Cross-the-Gap

[ICLR 2025] - Cross the Gap: Exposing the Intra-modal Misalignment in CLIP via Modality Inversion

⭐ 70 ⑂ 1 Python · 2025-12-01推送
https://openreview.net/forum?id=VVVfuIcmKR
clipcontrastive-learningimage-classificationimage-retrievalmultimodaltextual-inversionvision-languagevision-language-modelvlmiclr2025sigliptext-retrievalinter-modalintra-modalintra-modal-misalignmentmodality-gapmodality-inversionotiovivisual-inversion
70
Watchers
0
贡献者
0
Commits
0
Releases
0
Open Issues
2025-12-01
最近推送
原文 中文
暂无 README