Skip to content
DraconiticResearch
Search Sources API
203,952 studies31 sourcesUpdated 30 min ago
Peer-reviewedLicence not statedProceedings of machine learning research

The Convergent Representation of Contrastive Vision-Language Models: Geometry, Modality Gap and Shared Space Alignment

  • Lingjie Yi1
  • Raphael Douady2
  • Chao Chen1
  1. 1Stony Brook University
  2. 2CNRS, University Paris 1 Pantheon-Sorbonne.
Read full textCite

Related

  1. Rethinking Representation Geometry in Supervised Contrastive Learning under Long-Tailed Data
    Joonhyeok Jeong, Jy-yong Sohn, Kibok Lee
    arXivPreprintarXiv licenceFull textStatisticsarXiv
  2. Label-Aware Entropic Distributional Contrastive Alignment for Multimodal Sentiment Analysis
    Mengyao Wang, Xiuyang Meng, Chunling Wang
    Entropy (Basel, Switzerland)Peer-reviewedCC BYFull textEurope PMC
  3. CLIVeg: Contrastive Image-Vegetation Alignment for Botany-Aware Earth Observation Representations
    Selene Cerna, Sara Si-Moussi, Hadrien Hendrikx +2
    NeurocomputingPeer-reviewedPublisher termsFull textEcologyEnvironmental science & pollutionHAL
  4. Katalyst: knowledge-guided semantic alignment via contrastive learning for enzyme turnover prediction
    Ruilin Li, Senyu Tang, Jiaqi Deng +4
    BioinformaticsPeer-reviewedCC BY 4.0Full textMolecular biology & gene regulationCrossref
  5. Contrastive Astromer: Two-Stage Contrastive Representation Learning for Astronomical Light Curve Classification
    Justin Minggan Wei, Pavlos Protopapas, Guillermo Cabrera-Vives
    arXivPreprintCC BY 4.0Full textInstrumentation & methodsarXiv

Cite

BibTeXRIS
BibTeX
@article{yi2026convergent,
  title = {{The Convergent Representation of Contrastive Vision-Language Models: Geometry, Modality Gap and Shared Space Alignment}},
  author = {Lingjie Yi and Raphael Douady and Chao Chen},
  journal = {Proceedings of machine learning research},
  year = {2026},
  month = nov,
  url = {https://pmc.ncbi.nlm.nih.gov/articles/PMC13729033/},
}
RIS
TY  - JOUR
TI  - The Convergent Representation of Contrastive Vision-Language Models: Geometry, Modality Gap and Shared Space Alignment
AU  - Lingjie Yi
AU  - Raphael Douady
AU  - Chao Chen
PY  - 2026
DA  - 2026/11/04
JO  - Proceedings of machine learning research
UR  - https://pmc.ncbi.nlm.nih.gov/articles/PMC13729033/
SN  - 2640-3498
ER  -