Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Chenqi Ye

Chenqi Ye

1 indexed paper

Recent (6 mo)
1
With code
0
Influential cites
0
Benchmarked
0

Publications per year

1
26

Top categories

ML×1Stats ML×1

Frequent co-authors

Shengzhi Deng1×
Yanze Guo1×

Research Timeline

2026
Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality

This paper investigates the effect of pseudorandom number generator orbits on diffusion models' training and generation, revealing learnable input and significant impact on loss and quality.

Highlighted terms show continued research focus across papers

Papers

cs.LGstat.MLEmpiricalRecentAug 3, 2026

Pseudorandom Streams within Diffusion Models Act as Learnable Inputs That Affect Generation Quality

Shengzhi Deng, Chenqi Ye, Yanze Guo

This paper investigates the effect of pseudorandom number generator orbits on diffusion models' training and generation, revealing learnable input and significant impact on loss and quality.

View →