Open-ended VQA benchmarking of Vision-Language models by exploiting Classification datasets and their semantic hierarchy

Ähnliche Einträge

• Using Knowledge Graphs to harvest datasets for efficient CLIP model training
  von: Ging, Simon, et al.
  Veröffentlicht: (2025)
• Learning to Read Where to Look: Disease-Aware Vision-Language Pretraining for 3D CT
  von: Ging, Simon, et al.
  Veröffentlicht: (2026)
• Two Effects, One Trigger: On the Modality Gap, Object Bias, and Information Imbalance in Contrastive Vision-Language Models
  von: Schrodi, Simon, et al.
  Veröffentlicht: (2024)
• Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations
  von: Srivastava, Archita, et al.
  Veröffentlicht: (2025)
• NegVQA: Can Vision Language Models Understand Negation?
  von: Zhang, Yuhui, et al.
  Veröffentlicht: (2025)