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

Sukmin Yun

1 indexed paper

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

Publications per year

1
26

Top categories

Vision×1AI×1ML×1Multimedia×1

Frequent co-authors

Shentong Mo1×

Research Timeline

2026
Improving Visual Representation Alignment Generation with GRPO

The paper proposes VRPO, a reinforcement learning-based optimization strategy that replaces static alignment losses in diffusion models, significantly improving both convergence and image fidelity.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.AIcs.LGRecentMay 30, 2026

Improving Visual Representation Alignment Generation with GRPO

Shentong Mo, Sukmin Yun

The paper proposes VRPO, a reinforcement learning-based optimization strategy that replaces static alignment losses in diffusion models, significantly improving both convergence and image fidelity.

View →