Task-Related Token Compression in Multimodal Large Language Models from an Explainability Perspective

Documenti analoghi

• Egocentric Instruction-oriented Affordance Prediction via Large Multimodal Model
  di: Ji, Bokai, et al.
  Pubblicazione: (2025)
• DeCo: Decoupling Token Compression from Semantic Abstraction in Multimodal Large Language Models
  di: Yao, Linli, et al.
  Pubblicazione: (2024)
• Next Token Is Enough: Realistic Image Quality and Aesthetic Scoring with Multimodal Large Language Model
  di: Li, Mingxing, et al.
  Pubblicazione: (2025)
• LaCo: Efficient Layer-wise Compression of Visual Tokens for Multimodal Large Language Models
  di: Liu, Juntao, et al.
  Pubblicazione: (2025)
• TokenCarve: Information-Preserving Visual Token Compression in Multimodal Large Language Models
  di: Tan, Xudong, et al.
  Pubblicazione: (2025)