Language-Guided Token Compression with Reinforcement Learning in Large Vision-Language Models

Documenti analoghi

• RCP: Representation Consistency Pruner for Mitigating Distribution Shift in Large Vision-Language Models
  di: Zhang, Jianwei, et al.
  Pubblicazione: (2026)
• Relaxing Anchor-Frame Dominance for Mitigating Hallucinations in Video Large Language Models
  di: Liu, Zijian, et al.
  Pubblicazione: (2026)
• Immunizing 3D Gaussian Generative Models Against Unauthorized Fine-Tuning via Attribute-Space Traps
  di: Zhang, Jianwei, et al.
  Pubblicazione: (2026)
• LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models
  di: Zheng, Pengcheng, et al.
  Pubblicazione: (2026)
• Topology-Aware Layer Pruning for Large Vision-Language Models
  di: Zheng, Pengcheng, et al.
  Pubblicazione: (2026)