Distilled Large Language Model-Driven Dynamic Sparse Expert Activation Mechanism

Documenti analoghi

• Dynamic Eraser for Guided Concept Erasure in Diffusion Models
  di: Gong, Qinghui
  Pubblicazione: (2026)
• Sparse Shortcuts: Facilitating Efficient Fusion in Multimodal Large Language Models
  di: Zhang, Jingrui, et al.
  Pubblicazione: (2026)
• HyperLLaVA: Dynamic Visual and Language Expert Tuning for Multimodal Large Language Models
  di: Zhang, Wenqiao, et al.
  Pubblicazione: (2024)
• Hyperbolic and Evidence-Prioritized Experts for Large Vision-Language Models
  di: Zhou, Zijie, et al.
  Pubblicazione: (2026)
• Quant Experts: Token-aware Adaptive Error Reconstruction with Mixture of Experts for Large Vision-Language Models Quantization
  di: Jia, Chenwei, et al.
  Pubblicazione: (2026)