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

Shaorong Zhang

1 indexed paper

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

Publications per year

1
26

Top categories

NLP×1

Frequent co-authors

Longxuan Yu1×
Yu Fu1×
Hui Liu1×
Yue Dong1×
Greg Ver Steeg1×

Research Timeline

2026
Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models

The paper introduces D3IM, a novel parameter-free sampler that enables direct revision of visible tokens in Masked Diffusion Language Models, and proposes SCOPE to mitigate the model's tendency to perpetuate errors.

Highlighted terms show continued research focus across papers

Papers

cs.CLRecentMay 31, 2026

Revise, Don't Freeze: Sampler-Matched Training for Self-Correcting Masked Diffusion Language Models

Longxuan Yu, Shaorong Zhang, Yu Fu, Hui Liu +2 more

The paper introduces D3IM, a novel parameter-free sampler that enables direct revision of visible tokens in Masked Diffusion Language Models, and proposes SCOPE to mitigate the model's tendency to per…

View →