MAD: Modality-Adaptive Decoding for Mitigating Cross-Modal Hallucinations in Multimodal Large Language Models

Documenti analoghi

• Enhanced Vision-Language Models for Diverse Sensor Understanding: Cost-Efficient Optimization and Benchmarking
  di: Chung, Sangyun, et al.
  Pubblicazione: (2024)
• What if...?: Thinking Counterfactual Keywords Helps to Mitigate Hallucination in Large Multi-modal Models
  di: Kim, Junho, et al.
  Pubblicazione: (2024)
• Learning What to Attend First: Modality-Importance-Guided Reasoning for Reliable Multimodal Emotion Understanding
  di: Rha, Hyeongseop, et al.
  Pubblicazione: (2025)
• CODE: Contrasting Self-generated Description to Combat Hallucination in Large Multi-modal Models
  di: Kim, Junho, et al.
  Pubblicazione: (2024)
• Cross-Modal Consistency in Multimodal Large Language Models
  di: Zhang, Xiang, et al.
  Pubblicazione: (2024)