Ítems similars

• Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data
  per: Zhang, Yuhui, et al.
  Publicat: (2024)
• Automated Generation of Challenging Multiple-Choice Questions for Vision Language Model Evaluation
  per: Zhang, Yuhui, et al.
  Publicat: (2025)
• Ask, Pose, Unite: Scaling Data Acquisition for Close Interactions with Vision Language Models
  per: Bravo-Sánchez, Laura, et al.
  Publicat: (2024)
• Test-Time Spectrum-Aware Latent Steering for Zero-Shot Generalization in Vision-Language Models
  per: Dafnis, Konstantinos M., et al.
  Publicat: (2025)
• Why are Visually-Grounded Language Models Bad at Image Classification?
  per: Zhang, Yuhui, et al.
  Publicat: (2024)