Variation-aware Vision Token Dropping for Faster Large Vision-Language Models

Documenti analoghi

• Global Compression Commander: Plug-and-Play Inference Acceleration for High-Resolution Large Vision-Language Models
  di: Liu, Xuyang, et al.
  Pubblicazione: (2025)
• VGDiffZero: Text-to-image Diffusion Models Can Be Zero-shot Visual Grounders
  di: Liu, Xuyang, et al.
  Pubblicazione: (2023)
• Filter, Correlate, Compress: Training-Free Token Reduction for MLLM Acceleration
  di: Han, Yuhang, et al.
  Pubblicazione: (2024)
• TinyDrop: Tiny Model Guided Token Dropping for Vision Transformers
  di: Wang, Guoxin, et al.
  Pubblicazione: (2025)
• HERO: Rethinking Visual Token Early Dropping in High-Resolution Large Vision-Language Models
  di: Li, Xu, et al.
  Pubblicazione: (2025)