Token Time Continuous Diffusion for Language Modeling

  • 类型:arxiv
  • 标识:2607.14106
  • 链接:https://arxiv.org/abs/2607.14106
  • 主分类:multimodal
  • 形态:method
  • 被引:0
  • 被引来源:Semantic Scholar
  • S2被引:0
  • 影响力被引:0
  • TLDR:This paper introduces token time continuous diffusion (TTCD), a new diffusion language model which operates in continuous space, deterministically mapping Gaussian noise to a final token canvas with no further sampling, and incorporates a new notion of per-token times.
  • 待LLM分类:否
  • 标题中文:用于语言建模的 Token 时间连续扩散
  • TLDR中文:本文提出 token 时间连续扩散 (TTCD),一种新的扩散语言模型,运行于连续空间,将高斯噪声确定性地映射到最终的 token canvas 而无需额外采样,并引入每个 token 时间的新概念。
  • 来源文件
  • /inbox/tom/_candidates/2026-07-20-agent-memory-tool-use-candidates.json
  • [S2 enrich]