One Token Is Enough: Improving Diffusion Language Models with a Sink Token

Documenti analoghi

• Decouple Searching from Training: Scaling Data Mixing via Model Merging for Large Language Model Pre-training
  di: Li, Shengrui, et al.
  Pubblicazione: (2026)
• Targeted Remasking: Replacing Token Editing with Token-to-Mask Refinement in Discrete Diffusion Language Models
  di: Yao, Lin
  Pubblicazione: (2026)
• Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models
  di: Zhong, Linhao, et al.
  Pubblicazione: (2026)
• Token Constraint Decoding Improves Robustness on Question Answering for Large Language Models
  di: Yao, Jui-Ming, et al.
  Pubblicazione: (2025)
• Counting Ability of Large Language Models and Impact of Tokenization
  di: Zhang, Xiang, et al.
  Pubblicazione: (2024)