CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models

Documenti analoghi

• CoreInfer: Accelerating Large Language Model Inference with Semantics-Inspired Adaptive Sparse Activation
  di: Wang, Qinsi, et al.
  Pubblicazione: (2024)
• Keyframe-oriented Vision Token Pruning: Enhancing Efficiency of Large Vision Language Models on Long-Form Video Processing
  di: Liu, Yudong, et al.
  Pubblicazione: (2025)
• SpeechPrune: Context-aware Token Pruning for Speech Information Retrieval
  di: Lin, Yueqian, et al.
  Pubblicazione: (2024)
• KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systems
  di: Ye, Hancheng, et al.
  Pubblicazione: (2025)
• HippoMM: Hippocampal-inspired Multimodal Memory for Long Audiovisual Event Understanding
  di: Lin, Yueqian, et al.
  Pubblicazione: (2025)