Sungnyun Kim
Scholar

Sungnyun Kim

Google Scholar ID: DsWny60AAAAJ
KAIST AI
audio-visual multimodalspoken languagecomputer vision
Homepage↗Google Scholar↗
Citations & Impact
All-time
Citations
466
 
H-index
10
 
i10-index
10
 
Publications
20
 
Co-authors
28
list available
Contact
No contact links provided.
Publications
11 items
PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment
2026
Cited
0
Scalable Frameworks for Real-World Audio-Visual Speech Recognition
2025
Cited
0
Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses
2025
Cited
0
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
2025
Cited
0
Flex-Judge: Think Once, Judge Anywhere
2025
Cited
0
MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation
2025
Cited
0
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
2025
Cited
0
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition
2025
Cited
0
Resume (English only)
Co-authors
28 total
Se Young Yun
Se Young Yun
KAIST
Sangmin Bae
Sangmin Bae
Postdoc at KAIST AI || PhD at KAIST AI
Jongwoo Ko
Jongwoo Ko
Senior Researcher, Microsoft | Ph.D, KAIST AI
Jaehoon Oh
Jaehoon Oh
Samsung Advanced Institute of Technology
Co-author 5
Co-author 5
Tianyi Chen
Tianyi Chen
Principal Research Manager, Microsoft, Johns Hopkins University
Jang Kangwook
Jang Kangwook
KAIST
Jin-Hwa Kim
Jin-Hwa Kim
Leader at NAVER AI Lab & Guest Assistant Professor at the AI Institute of Seoul National University