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

Hyundong Jin

2 indexed papers

Recent (6 mo)
2
With code
0
Influential cites
0
Benchmarked
0

Publications per year

2
26

Top categories

AI×2NLP×1

Frequent co-authors

Yo-Sub Han2×
Soohan Lim1×
Joonghyuk Hahn1×

Research Timeline

2026
STAB: Specification-driven Testing for Algorithmic Bottlenecks

STAB is a novel specification-driven pipeline that generates test cases exposing algorithmic bottlenecks by combining constraint-bound maximization and adversarial structure injection, significantly improving bottleneck detection rates across various LLMs.

EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models

The paper proposes EPIC, an efficient and parallel decoding framework that significantly speeds up the process of constraining diffusion language model outputs using Context-Free Grammars (CFG).

Highlighted terms show continued research focus across papers

Papers

cs.CLcs.AIRecentMay 30, 2026

EPIC: Efficient and Parallel Inference under CFG Constraints for Diffusion Language Models

Hyundong Jin, Yo-Sub Han

The paper proposes EPIC, an efficient and parallel decoding framework that significantly speeds up the process of constraining diffusion language model outputs using Context-Free Grammars (CFG).

View →
cs.AIRecentMay 27, 2026

STAB: Specification-driven Testing for Algorithmic Bottlenecks

Soohan Lim, Joonghyuk Hahn, Hyundong Jin, Yo-Sub Han

STAB is a novel specification-driven pipeline that generates test cases exposing algorithmic bottlenecks by combining constraint-bound maximization and adversarial structure injection, significantly i…

View →