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

Chang D. Yoo

2 indexed papers

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

Publications per year

2
26

Top categories

NLP×2Vision×1Audio and Speech Processing×1

Frequent co-authors

Hee Suk Yoon1×
Eunseop Yoon1×
Jaehyun Jang1×
SooHwan Eom1×
Ji Woo Hong1×
Mark Hasegawa-Johnson1×

Research Timeline

2026
Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding

The paper proposes Visual Gradient Steering (VGS), a method that decomposes the distillation loss into language and visual components and steers the optimization to prioritize visual grounding, significantly improving vision-language reasoning.

SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors

SALSA is a lightweight adaptation method that learns layer-wise steering vectors to significantly improve the performance of speech-aware LLMs on out-of-domain speech tasks.

Highlighted terms show continued research focus across papers

Papers

cs.CVcs.CLRecentMay 30, 2026

Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding

Hee Suk Yoon, Eunseop Yoon, Jaehyun Jang, SooHwan Eom +5 more

The paper proposes Visual Gradient Steering (VGS), a method that decomposes the distillation loss into language and visual components and steers the optimization to prioritize visual grounding, signif…

View →
cs.CLeess.ASRecentMay 30, 2026

SALSA: Speech Aware LLM Adaptation via Learned Steering Activation Vectors

Yekaterina Yegorova, Argyrios Gerogiannis, Haolong Zheng, Julia Hockenmaier +2 more

SALSA is a lightweight adaptation method that learns layer-wise steering vectors to significantly improve the performance of speech-aware LLMs on out-of-domain speech tasks.

View →