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

Taesung Kwon

1 indexed paper

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

Publications per year

1
26

Top categories

ML×1AI×1Vision×1

Frequent co-authors

Jaa-Yeon Lee1×
Yeobin Hong1×
Jong Chul Ye1×

Research Timeline

2026
Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models

The paper proposes Alignment-Guided Score Matching (AGSM), a lightweight, reward-free post-training method that integrates contrastive alignment guidance directly into the score-matching objective of diffusion models to improve text-image alignment and fix common failure modes.

Highlighted terms show continued research focus across papers

Papers

cs.LGcs.AIcs.CVRecentMay 28, 2026

Alignment-Guided Score Matching for Text-to-Image Alignment in Diffusion Models

Jaa-Yeon Lee, Yeobin Hong, Taesung Kwon, Jong Chul Ye

The paper proposes Alignment-Guided Score Matching (AGSM), a lightweight, reward-free post-training method that integrates contrastive alignment guidance directly into the score-matching objective of…

View →