Divide and Conquer: Accelerating Diffusion-Based Large Language Models via Adaptive Parallel Decoding

Documenti analoghi

• Learning to Parallel: Accelerating Diffusion Large Language Models via Learnable Parallel Decoding
  di: Bao, Wenrui, et al.
  Pubblicazione: (2025)
• Control Large Language Models via Divide and Conquer
  di: Li, Bingxuan, et al.
  Pubblicazione: (2024)
• d$^2$Cache: Accelerating Diffusion-Based LLMs via Dual Adaptive Caching
  di: Jiang, Yuchu, et al.
  Pubblicazione: (2025)
• Divide and Conquer: A Hybrid Strategy Defeats Multimodal Large Language Models
  di: Mao, Yanxu, et al.
  Pubblicazione: (2024)
• CreditDecoding: Accelerating Parallel Decoding in Diffusion Large Language Models with Trace Credit
  di: Wang, Kangyu, et al.
  Pubblicazione: (2025)