Image Tokens Matter: Mitigating Hallucination in Discrete Tokenizer-based Large Vision-Language Models via Latent Editing

Documenti analoghi

• SeCoKD: Aligning Large Language Models for In-Context Learning with Fewer Shots
  di: Wang, Weixing, et al.
  Pubblicazione: (2024)
• MINT: Mitigating Hallucinations in Large Vision-Language Models via Token Reduction
  di: Wang, Chao, et al.
  Pubblicazione: (2025)
• Feature Distribution Shift Mitigation with Contrastive Pretraining for Intrusion Detection
  di: Wang, Weixing, et al.
  Pubblicazione: (2024)
• PAINT: Paying Attention to INformed Tokens to Mitigate Hallucination in Large Vision-Language Model
  di: Arif, Kazi Hasan Ibn, et al.
  Pubblicazione: (2025)
• Generalized Categories Discovery for Long-tailed Recognition
  di: Li, Ziyun, et al.
  Pubblicazione: (2023)