S$^4$C: Speculative Sampling with Syntactic and Semantic Coherence for Efficient Inference of Large Language Models

Documenti analoghi

• FastVID: Dynamic Density Pruning for Fast Video Large Language Models
  di: Shen, Leqi, et al.
  Pubblicazione: (2025)
• More is Better: Deep Domain Adaptation with Multiple Sources
  di: Zhao, Sicheng, et al.
  Pubblicazione: (2024)
• AdaTP: Attention-Debiased Token Pruning for Video Large Language Models
  di: Sun, Fengyuan, et al.
  Pubblicazione: (2025)
• Towards Efficient Vision-Language Tuning: More Information Density, More Generalizability
  di: Hao, Tianxiang, et al.
  Pubblicazione: (2023)
• DiscoVLA: Discrepancy Reduction in Vision, Language, and Alignment for Parameter-Efficient Video-Text Retrieval
  di: Shen, Leqi, et al.
  Pubblicazione: (2025)