VisCon-100K: Leveraging Contextual Web Data for Fine-tuning Vision Language Models

Documenti analoghi

• FineLIP: Extending CLIP's Reach via Fine-Grained Alignment with Longer Text Inputs
  di: Asokan, Mothilal, et al.
  Pubblicazione: (2025)
• VisBias: Measuring Explicit and Implicit Social Biases in Vision Language Models
  di: Huang, Jen-tse, et al.
  Pubblicazione: (2025)
• Uni-Mlip: Unified Self-supervision for Medical Vision Language Pre-training
  di: Bawazir, Ameera, et al.
  Pubblicazione: (2024)
• Aligning Modalities in Vision Large Language Models via Preference Fine-tuning
  di: Zhou, Yiyang, et al.
  Pubblicazione: (2024)
• Attribution Analysis Meets Model Editing: Advancing Knowledge Correction in Vision Language Models with VisEdit
  di: Chen, Qizhou, et al.
  Pubblicazione: (2024)