IDPruner: Harmonizing Importance and Diversity in Visual Token Pruning for MLLMs

Documenti analoghi

• Does Visual Token Pruning Improve Calibration? An Empirical Study on Confidence in MLLMs
  di: Tan, Kaizhen
  Pubblicazione: (2026)
• HAWK: Head Importance-Aware Visual Token Pruning in Multimodal Models
  di: Zhu, Qihui, et al.
  Pubblicazione: (2026)
• GridPrune: From "Where to Look" to "What to Select" in Visual Token Pruning for MLLMs
  di: Duan, Yuxiang, et al.
  Pubblicazione: (2025)
• Beyond Attention or Similarity: Maximizing Conditional Diversity for Token Pruning in MLLMs
  di: Zhang, Qizhe, et al.
  Pubblicazione: (2025)
• Flash-DMD: Towards High-Fidelity Few-Step Image Generation with Efficient Distillation and Joint Reinforcement Learning
  di: Chen, Guanjie, et al.
  Pubblicazione: (2025)