Mostly Text, Smart Visuals: Asymmetric Text-Visual Pruning for Large Vision-Language Models

Documenti analoghi

• Towards Visual Text Grounding of Multimodal Large Language Model
  di: Li, Ming, et al.
  Pubblicazione: (2025)
• Visual Text Matters: Improving Text-KVQA with Visual Text Entity Knowledge-aware Large Multimodal Assistant
  di: Penamakuri, Abhirama Subramanyam, et al.
  Pubblicazione: (2024)
• ReadBench: Measuring the Dense Text Visual Reading Ability of Vision-Language Models
  di: Clavié, Benjamin, et al.
  Pubblicazione: (2025)
• Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
  di: Li, Yue, et al.
  Pubblicazione: (2025)
• Evaluating Text-to-Visual Generation with Image-to-Text Generation
  di: Lin, Zhiqiu, et al.
  Pubblicazione: (2024)