BiVLC: Extending Vision-Language Compositionality Evaluation with Text-to-Image Retrieval

Documenti analoghi

• Adding simple structure at inference improves Vision-Language Compositionality
  di: Miranda, Imanol, et al.
  Pubblicazione: (2025)
• Revisiting Compositionality in Dual-Encoder Vision-Language Models: The Role of Inference
  di: Miranda, Imanol, et al.
  Pubblicazione: (2026)
• Grounding Spatial Relations in Text-Only Language Models
  di: Azkune, Gorka, et al.
  Pubblicazione: (2024)
• Improving Explicit Spatial Relationships in Text-to-Image Generation through an Automatically Derived Dataset
  di: Salaberria, Ander, et al.
  Pubblicazione: (2024)
• TABLET: A Large-Scale Dataset for Robust Visual Table Understanding
  di: Alonso, Iñigo, et al.
  Pubblicazione: (2025)