GEASS: Gated Evidence-Adaptive Selective Caption Trust for Vision-Language Models

Documenti analoghi

• Low-hallucination Synthetic Captions for Large-Scale Vision-Language Model Pre-training
  di: Zhang, Xinsong, et al.
  Pubblicazione: (2025)
• From Captions to Rewards (CAREVL): Leveraging Large Language Model Experts for Enhanced Reward Modeling in Large Vision-Language Models
  di: Dai, Muzhi, et al.
  Pubblicazione: (2025)
• Vision Language Model-based Caption Evaluation Method Leveraging Visual Context Extraction
  di: Maeda, Koki, et al.
  Pubblicazione: (2024)
• To Trust Or Not To Trust Your Vision-Language Model's Prediction
  di: Dong, Hao, et al.
  Pubblicazione: (2025)
• A-VL: Adaptive Attention for Large Vision-Language Models
  di: Zhang, Junyang, et al.
  Pubblicazione: (2024)