Positive-Augmented Contrastive Learning for Vision-and-Language Evaluation and Training

Documenti analoghi

• BRIDGE: Bridging Gaps in Image Captioning Evaluation with Stronger Visual Cues
  di: Sarto, Sara, et al.
  Pubblicazione: (2024)
• Wiki-LLaVA: Hierarchical Retrieval-Augmented Generation for Multimodal LLMs
  di: Caffagni, Davide, et al.
  Pubblicazione: (2024)
• Augmenting Multimodal LLMs with Self-Reflective Tokens for Knowledge-based Visual Question Answering
  di: Cocchi, Federico, et al.
  Pubblicazione: (2024)
• Recurrence-Enhanced Vision-and-Language Transformers for Robust Multimodal Document Retrieval
  di: Caffagni, Davide, et al.
  Pubblicazione: (2025)
• Revisiting Image Captioning Training Paradigm via Direct CLIP-based Optimization
  di: Moratelli, Nicholas, et al.
  Pubblicazione: (2024)