Diffusion LLM with Native Variable Generation Lengths: Let [EOS] Lead the Way

Documenti analoghi

• Self Speculative Decoding for Diffusion Large Language Models
  di: Gao, Yifeng, et al.
  Pubblicazione: (2025)
• Mask Tokens as Prophet: Fine-Grained Cache Eviction for Efficient dLLM Inference
  di: Huang, Jianuo, et al.
  Pubblicazione: (2025)
• Thinking Inside the Mask: In-Place Prompting in Diffusion LLMs
  di: Jin, Xiangqi, et al.
  Pubblicazione: (2025)
• dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching
  di: Liu, Zhiyuan, et al.
  Pubblicazione: (2025)
• $ρ$-$\texttt{EOS}$: Training-free Bidirectional Variable-Length Control for Masked Diffusion LLMs
  di: Yang, Jingyi, et al.
  Pubblicazione: (2026)