English

A Diffusion-Based Framework for Configurable and Realistic Multi-Storage Trace Generation

Computer Vision and Pattern Recognition 2025-09-04 v1 Performance

Abstract

We propose DiTTO, a novel diffusion-based framework for generating realistic, precisely configurable, and diverse multi-device storage traces. Leveraging advanced diffusion techniques, DiTTO enables the synthesis of high-fidelity continuous traces that capture temporal dynamics and inter-device dependencies with user-defined configurations. Our experimental results demonstrate that DiTTO can generate traces with high fidelity and diversity while aligning closely with guided configurations with only 8% errors.

Keywords

Cite

@article{arxiv.2509.01919,
  title  = {A Diffusion-Based Framework for Configurable and Realistic Multi-Storage Trace Generation},
  author = {Seohyun Kim and Junyoung Lee and Jongho Park and Jinhyung Koo and Sungjin Lee and Yeseong Kim},
  journal= {arXiv preprint arXiv:2509.01919},
  year   = {2025}
}
R2 v1 2026-07-01T05:16:34.936Z