{"slug": "token-time-continuous-diffusion-for-language-modeling", "title": "Token Time Continuous Diffusion for Language Modeling", "summary": "Researchers introduced token time continuous diffusion (TTCD), a new diffusion language model that operates in continuous space and uses per-token times to improve generation speed and quality. TTCD outperforms discrete models at high speedups in both unconditional and conditional generation, as demonstrated with a 160M parameter model trained on OpenWebText.", "body_md": "arXiv:2607.14106v1 Announce Type: new\nAbstract: In this paper we introduce token time continuous diffusion (TTCD), a new diffusion language model which (a) operates in continuous space, deterministically mapping Gaussian noise to a final token canvas with no further sampling, and crucially (b) incorporates a new notion of per-token times, with some tokens proceeding from noise to token at a faster rate than others. Continuous space modeling helps TTCD avoid the parallel sampling of multiple tokens, which is a key source of inaccuracy at high speedups for models that iterate purely in discrete space. The notion of per-token times helps TTCD to better model conditional generation, allows for more sure tokens to proceed at a faster rate, and allows for differentiated inter-token influences during refinement. TTCD outperforms discrete models at high speedups. We train a 160M parameter TTCD model on OpenWebText, and then self-distill it; we find that at high speedups we are comparable in unconditional generation quality, and outperform in conditional generation, several existing models of similar size trained, on the same data, and self-distilled. We achieve similar gains in Sudoku solving as well.", "url": "https://wpnews.pro/news/token-time-continuous-diffusion-for-language-modeling", "canonical_source": "https://arxiv.org/abs/2607.14106", "published_at": "2026-07-17 04:00:00+00:00", "updated_at": "2026-07-17 04:04:12.063343+00:00", "lang": "en", "topics": ["artificial-intelligence", "machine-learning", "large-language-models", "generative-ai", "ai-research"], "entities": ["OpenWebText"], "alternates": {"html": "https://wpnews.pro/news/token-time-continuous-diffusion-for-language-modeling", "markdown": "https://wpnews.pro/news/token-time-continuous-diffusion-for-language-modeling.md", "text": "https://wpnews.pro/news/token-time-continuous-diffusion-for-language-modeling.txt", "jsonld": "https://wpnews.pro/news/token-time-continuous-diffusion-for-language-modeling.jsonld"}}