Self-Correcting Decoding with Generative Feedback for Mitigating Hallucinations in Large Vision-Language Models

Documenti analoghi

• ONLY: One-Layer Intervention Sufficiently Mitigates Hallucinations in Large Vision-Language Models
  di: Wan, Zifu, et al.
  Pubblicazione: (2025)
• InstructPart: Task-Oriented Part Segmentation with Instruction Reasoning
  di: Wan, Zifu, et al.
  Pubblicazione: (2025)
• Spectral-Aware Global Fusion for RGB-Thermal Semantic Segmentation
  di: Zhang, Ce, et al.
  Pubblicazione: (2025)
• Enhancing Vision-Language Few-Shot Adaptation with Negative Learning
  di: Zhang, Ce, et al.
  Pubblicazione: (2024)
• Dual Prototype Evolving for Test-Time Generalization of Vision-Language Models
  di: Zhang, Ce, et al.
  Pubblicazione: (2024)