HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models

Ähnliche Einträge

• Pyramid Token Pruning for High-Resolution Large Vision-Language Models via Region, Token, and Instruction-Guided Importance
  von: Liang, Yuxuan, et al.
  Veröffentlicht: (2025)
• Global Semantic-Guided Sub-image Feature Weight Allocation in High-Resolution Large Vision-Language Models
  von: Liang, Yuxuan, et al.
  Veröffentlicht: (2025)
• Instruction-Guided Fusion of Multi-Layer Visual Features in Large Vision-Language Models
  von: Li, Xu, et al.
  Veröffentlicht: (2024)
• ResPrune: Text-Conditioned Subspace Reconstruction for Visual Token Pruning in Large Vision-Language Models
  von: Li, Xu, et al.
  Veröffentlicht: (2026)
• Variation-aware Vision Token Dropping for Faster Large Vision-Language Models
  von: Chen, Junjie, et al.
  Veröffentlicht: (2025)