PolyGen: Fully Synthetic Vision-Language Training via Multi-Generator Ensembles

Documenti analoghi

• Auto-Comp: An Automated Pipeline for Scalable Compositional Probing of Contrastive Vision-Language Models
  di: Sbrolli, Cristian, et al.
  Pubblicazione: (2026)
• Your Image Generator Is Your New Private Dataset
  di: Resmini, Nicolo, et al.
  Pubblicazione: (2025)
• Neuro-Symbolic Scene Graph Conditioning for Synthetic Image Dataset Generation
  di: Savazzi, Giacomo, et al.
  Pubblicazione: (2025)
• Federated Knowledge Recycling: Privacy-Preserving Synthetic Data Sharing
  di: Lomurno, Eugenio, et al.
  Pubblicazione: (2024)
• No Captions, No Problem: Captionless 3D-CLIP Alignment with Hard Negatives via CLIP Knowledge and LLMs
  di: Sbrolli, Cristian, et al.
  Pubblicazione: (2024)