Vision Token Reduction via Attention-Driven Self-Compression for Efficient Multimodal Large Language Models

Documenti analoghi

• VScan: Rethinking Visual Token Reduction for Efficient Large Vision-Language Models
  di: Zhang, Ce, et al.
  Pubblicazione: (2025)
• Vision-centric Token Compression in Large Language Model
  di: Xing, Ling, et al.
  Pubblicazione: (2025)
• Efficient Self-Improvement in Multimodal Large Language Models: A Model-Level Judge-Free Approach
  di: Deng, Shijian, et al.
  Pubblicazione: (2024)
• On the Limits of Token Reduction for Efficient Unified Vision Language Training
  di: Chen, Siyi, et al.
  Pubblicazione: (2026)
• LEO-MINI: An Efficient Multimodal Large Language Model using Conditional Token Reduction and Mixture of Multi-Modal Experts
  di: Wang, Yimu, et al.
  Pubblicazione: (2025)