Visual Riddles: a Commonsense and World Knowledge Challenge for Large Vision and Language Models

Documenti analoghi

• RefVNLI: Towards Scalable Evaluation of Subject-driven Text-to-image Generation
  di: Slobodkin, Aviv, et al.
  Pubblicazione: (2025)
• Bridging the Visual Gap: Fine-Tuning Multimodal Models with Knowledge-Adapted Captions
  di: Yanuka, Moran, et al.
  Pubblicazione: (2024)
• GRADE: Quantifying Sample Diversity in Text-to-Image Models
  di: Rassin, Royi, et al.
  Pubblicazione: (2024)
• Contrastive Sequential-Diffusion Learning: Non-linear and Multi-Scene Instructional Video Synthesis
  di: Ramos, Vasco, et al.
  Pubblicazione: (2024)
• Video-STaR: Self-Training Enables Video Instruction Tuning with Any Supervision
  di: Zohar, Orr, et al.
  Pubblicazione: (2024)