Index-Preserving Lightweight Token Pruning for Efficient Document Understanding in Vision-Language Models

Ähnliche Einträge

• CoViPAL: Layer-wise Contextualized Visual Token Pruning for Large Vision-Language Models
  von: Tang, Zicong, et al.
  Veröffentlicht: (2025)
• TransPrune: Token Transition Pruning for Efficient Large Vision-Language Model
  von: Li, Ao, et al.
  Veröffentlicht: (2025)
• Efficient Vision-Language Models by Summarizing Visual Tokens into Compact Registers
  von: Wen, Yuxin, et al.
  Veröffentlicht: (2024)
• CAPTURe: Evaluating Spatial Reasoning in Vision Language Models via Occluded Object Counting
  von: Pothiraj, Atin, et al.
  Veröffentlicht: (2025)
• On the Limits of Token Reduction for Efficient Unified Vision Language Training
  von: Chen, Siyi, et al.
  Veröffentlicht: (2026)