Accelerating Multimodal Large Language Models via Dynamic Visual-Token Exit and the Empirical Findings

Ähnliche Einträge

• Not All Attention is Needed: Parameter and Computation Efficient Transfer Learning for Multi-modal Large Language Models
  von: Wu, Qiong, et al.
  Veröffentlicht: (2024)
• Fit and Prune: Fast and Training-free Visual Token Pruning for Multi-modal Large Language Models
  von: Ye, Weihao, et al.
  Veröffentlicht: (2024)
• Grounded Chain-of-Thought for Multimodal Large Language Models
  von: Wu, Qiong, et al.
  Veröffentlicht: (2025)
• Routing Experts: Learning to Route Dynamic Experts in Multi-modal Large Language Models
  von: Wu, Qiong, et al.
  Veröffentlicht: (2024)
• Parallel Vision Token Scheduling for Fast and Accurate Multimodal LMMs Inference
  von: Zhan, Wengyi, et al.
  Veröffentlicht: (2025)