MAP: Mitigating Hallucinations in Large Vision-Language Models with Map-Level Attention Processing

Documenti analoghi

• STAR: Stage-Wise Attention-Guided Token Reduction for Efficient Large Vision-Language Models Inference
  di: Guo, Yichen, et al.
  Pubblicazione: (2025)
• Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models
  di: Tang, Kai, et al.
  Pubblicazione: (2025)
• Mitigating Hallucinations in Large Language Models Via Decoder Layer Skipping
  di: Li, Hanze, et al.
  Pubblicazione: (2026)
• Enhancing Layer Attention Efficiency through Pruning Redundant Retrievals
  di: Li, Hanze, et al.
  Pubblicazione: (2025)
• MagicWand: A Universal Agent for Generation and Evaluation Aligned with User Preference
  di: Xu, Zitong, et al.
  Pubblicazione: (2025)