Draft Model Knows When to Stop: Self-Verification Speculative Decoding for Long-Form Generation

Documenti analoghi

• Trust, But Verify: A Self-Verification Approach to Reinforcement Learning with Verifiable Rewards
  di: Liu, Xiaoyuan, et al.
  Pubblicazione: (2025)
• LongSpec: Long-Context Lossless Speculative Decoding with Efficient Drafting and Verification
  di: Yang, Penghui, et al.
  Pubblicazione: (2025)
• Dancing with Critiques: Enhancing LLM Reasoning with Stepwise Natural Language Self-Critique
  di: Li, Yansi, et al.
  Pubblicazione: (2025)
• SpecTr-GBV: Multi-Draft Block Verification Accelerating Speculative Decoding
  di: Lin, Yijun, et al.
  Pubblicazione: (2026)
• Draft on the Fly: Adaptive Self-Speculative Decoding using Cosine Similarity
  di: Metel, Michael R., et al.
  Pubblicazione: (2024)