Rethinking Pruning for Vision-Language Models: Strategies for Effective Sparsity and Performance Restoration

Documenti analoghi

• Understanding and Harnessing Sparsity in Unified Multimodal Models
  di: He, Shwai, et al.
  Pubblicazione: (2025)
• Hierarchical Safety Realignment: Lightweight Restoration of Safety in Pruned Large Vision-Language Models
  di: Li, Yue, et al.
  Pubblicazione: (2025)
• VLM-Pruner: Buffering for Spatial Sparsity in an Efficient VLM Centrifugal Token Pruning Paradigm
  di: Wu, Zhenkai, et al.
  Pubblicazione: (2025)
• Expand and Prune: Maximizing Trajectory Diversity for Effective GRPO in Generative Models
  di: Ge, Shiran, et al.
  Pubblicazione: (2025)
• CRISP: Hybrid Structured Sparsity for Class-aware Model Pruning
  di: Aggarwal, Shivam, et al.
  Pubblicazione: (2023)