Fractal Wave Text Diffusion

Fractal Wave Text Diffusion introduces a hierarchical two-axis discrete diffusion framework for natural language generation in PyTorch. Instead of generating text linearly from left to right or unmasking tokens randomly, the model expands language by order of informational priority across two orthogonal axes simultaneously: the Sentence Axis (Macro-Diffusion) and the Word Axis (Micro-Diffusion).

Authors

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-14
DOI
https://doi.org/10.5281/zenodo.24209686
Primary Topic
Topic Modeling
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Fractal Wave Text Diffusion

Arvin Golshahi
Zenodo (CERN European Organization for Nuclear Research)
Topic Modeling
article

Fractal Wave Text Diffusion

Arvin Golshahi
article en

Abstract

Fractal Wave Text Diffusion introduces a hierarchical two-axis discrete diffusion framework for natural language generation in PyTorch. Instead of generating text linearly from left to right or unmasking tokens randomly, the model expands language by order of informational priority across two orthogonal axes simultaneously: the Sentence Axis (Macro-Diffusion) and the Word Axis (Micro-Diffusion).

Zenodo (CERN European Organization for Nuclear Research)
Topic Modeling
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon