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

Jacob Devasier

1 indexed paper

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

Publications per year

1
26

Top categories

NLP×1AI×1

Frequent co-authors

Qing Wang1×
Chengkai Li1×

Research Timeline

2026
What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation

This paper analyzes the decoding process of masked diffusion models for graph-to-text generation, finding that structural fine-tuning disrupts natural entity-first generation and proposing a structural decoding method to fix it.

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIRecentMay 29, 2026

What Gets Unmasked First? Trajectory Analysis of Diffusion Models for Graph-to-Text Generation

Qing Wang, Jacob Devasier, Chengkai Li

This paper analyzes the decoding process of masked diffusion models for graph-to-text generation, finding that structural fine-tuning disrupts natural entity-first generation and proposing a structura…

View →