Spec-LLaVA: Accelerating Vision-Language Models with Dynamic Tree-Based Speculative Decoding

Documenti analoghi

• ViSpec: Accelerating Vision-Language Models with Vision-Aware Speculative Decoding
  di: Kang, Jialiang, et al.
  Pubblicazione: (2025)
• Dynamic-LLaVA: Efficient Multimodal Large Language Models via Dynamic Vision-language Context Sparsification
  di: Huang, Wenxuan, et al.
  Pubblicazione: (2024)
• SQ-LLaVA: Self-Questioning for Large Vision-Language Assistant
  di: Sun, Guohao, et al.
  Pubblicazione: (2024)
• SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
  di: Lin, Yijun, et al.
  Pubblicazione: (2026)
• X-LLaVA: Optimizing Bilingual Large Vision-Language Alignment
  di: Shin, Dongjae, et al.
  Pubblicazione: (2024)