Stop Looking for Important Tokens in Multimodal Language Models: Duplication Matters More

Documenti analoghi

• Token Pruning in Multimodal Large Language Models: Are We Solving the Right Problem?
  di: Wen, Zichen, et al.
  Pubblicazione: (2025)
• Efficient Multi-modal Large Language Models via Progressive Consistency Distillation
  di: Wen, Zichen, et al.
  Pubblicazione: (2025)
• Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction
  di: Zhang, Qintong, et al.
  Pubblicazione: (2024)
• OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
  di: Zhang, Junyuan, et al.
  Pubblicazione: (2024)
• Prune2Drive: A Plug-and-Play Framework for Accelerating Vision-Language Models in Autonomous Driving
  di: Xiong, Minhao, et al.
  Pubblicazione: (2025)