Publications

1st or Corresponding Author

Topics

2026

Perception-Inspired Bayesian Causal Fusion for Audiovisual Source Localization
Kyung Yun Lee, Sungnyun Kim, Sebastian J. Schlecht, Tae-Hyun Oh, Vesa Välimäki
Preprint 2026
- Multimodal
- Spatial/Social Intelligence
- Paper
- Abstract
PerMix-RLVR: Preserving Persona Expressivity under Verifiable-Reward Alignment
Jihwan Oh*, Soowon Oh*, Murad Aghazada, Minchan Jeong, Myeongseok Kang, Sungnyun Kim†, Se-Young Yun†
Preprint 2026
- LLM
- Spatial/Social Intelligence
- Paper
- Abstract
FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMs
Kyeongrae Kim, Sungnyun Kim†, Tae-Hyun Oh†
NeurIPS Workshop 2026
- Multimodal
- Spatial/Social Intelligence
- Abstract
Conversation Is a Two-Body Problem: Dyadic Evaluation of Full-Duplex Dialogue Models
Sungnyun Kim†, Sungwoo Cho, Jihwan Oh, Se-Young Yun
NeurIPS Workshop 2026
- Speech Processing
- Spatial/Social Intelligence
- Abstract
Two Heads Are Better Than One: Audio-Visual Speech Error Correction with Dual Hypotheses
Sungnyun Kim*, Kangwook Jang*, Sungwoo Cho, Joon Son Chung, Hoirin Kim, Se-Young Yun
ACL Findings 2026
- LLM
- Speech Processing

2025

Flex-Judge: Text-Only Reasoning Unleashes Zero-Shot Multimodal Evaluators
Jongwoo Ko*, Sungnyun Kim*, Sungwoo Cho, Se-Young Yun
NeurIPS 2025
- Multimodal
Mixture-of-Recursions: Learning Dynamic Recursive Depths for Adaptive Token-Level Computation
Sangmin Bae*, Yujin Kim*, Reza Bayat*, Sungnyun Kim, Tal Schuster, Adam Fisch, Hrayr Harutyunyan, Ziwei Ji, Jiyoun Ha, Aaron Courville, Se-Young Yun
NeurIPS 2025
- LLM
MAVFlow: Preserving Paralinguistic Elements with Conditional Flow Matching for Zero-Shot AV2AV Multilingual Translation
Sungwoo Cho, Jeongsoo Choi, Sungnyun Kim, Se-Young Yun
ICCV 2025
- Multimodal
- Speech Processing
- Paper
- Abstract
MoHAVE: Mixture of Hierarchical Audio-Visual Experts for Robust Speech Recognition
Sungnyun Kim, Kangwook Jang, Sangmin Bae, Sungwoo Cho, Se-Young Yun
ICML 2025
- Multimodal
- Speech Processing
- Paper
- Abstract
DistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
Jongwoo Ko, Tianyi Chen, Sungnyun Kim, Tianyu Ding, Luming Liang, Ilya Zharkov, Se-Young Yun
ICML 2025(Oral)
- LLM
Multi-Task Corrupted Prediction for Learning Robust Audio-Visual Speech Representation
Sungnyun Kim, Sungwoo Cho, Sangmin Bae, Kangwook Jang, Se-Young Yun
ICLR 2025
- Multimodal
- Speech Processing
FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning
Seongyoon Kim, Minchan Jeong, Sungnyun Kim, Sungwoo Cho, Sumyeong Ahn†, Se-Young Yun†
TMLR 2025
- Machine Learning
DiffBlender: Composable and Versatile Multimodal Text-to-Image Diffusion Models
Sungnyun Kim, Junsoo Lee, Kibeom Hong, Daesik Kim, Namhyuk Ahn
ESWA 2025
- Multimodal

2024

Learning Video Temporal Dynamics with Cross-Modal Attention for Robust Audio-Visual Speech Recognition
Sungnyun Kim*, Kangwook Jang*, Sangmin Bae, Hoirin Kim, Se-Young Yun
SLT 2024
- Multimodal
- Speech Processing
DocKD: Knowledge Distillation from LLMs for Open-World Document Understanding Models
Sungnyun Kim*†, Haofu Liao*, Srikar Appalaraju, Peng Tang, Zhuowen Tu, Ravi Kumar Satzoda, R. Manmatha, Vijay Mahadevan, Stefano Soatto
EMNLP 2024
- LLM
Diffusion-based Episodes Augmentation for Offline Multi-Agent Reinforcement Learning
Jihwan Oh, Sungnyun Kim, Gahee Kim, SeongHwan Kim, Se-Young Yun
ICML Workshop 2024
- Machine Learning
- Paper
- Abstract
DistiLLM: Towards Streamlined Distillation for Large Language Models
Jongwoo Ko, Sungnyun Kim, Tianyi Chen, Se-Young Yun
ICML 2024
- LLM
STaR: Distilling Speech Temporal Relation for Lightweight Speech Self-Supervised Learning Models
Kangwook Jang, Sungnyun Kim, Hoirin Kim
ICASSP 2024(Best Student Paper)
- Speech Processing
- Representation Learning

2023

Recycle-and-Distill: Universal Compression Strategy for Transformer-based Speech SSL Models with Attention Map Reusing and Masking Distillation
Kangwook Jang*, Sungnyun Kim*, Se-Young Yun, Hoirin Kim
Interspeech 2023
- Speech Processing
- Representation Learning
Patch-Mix Contrastive Learning with Audio Spectrogram Transformer on Respiratory Sound Classification
Sangmin Bae*, June-Woo Kim*, Wonyang Cho, Hyerim Baek, Soyoun Son, Byungjo Lee, Changwan Ha, Kyungpil Tae, Sungnyun Kim†, Se-Young Yun†
Interspeech 2023
- Representation Learning
Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning
Sungnyun Kim*, Sangmin Bae*, Se-Young Yun
CVPR 2023
- Representation Learning
Self-Contrastive Learning: Single-viewed Supervised Contrastive Framework using Sub-network
Sangmin Bae*, Sungnyun Kim*, Jongwoo Ko, Gihun Lee, Seungjong Noh, Se-Young Yun
AAAI 2023(Oral)
- Representation Learning

2022

Understanding Cross-Domain Few-Shot Learning Based on Domain Similarity and Few-Shot Difficulty
Jaehoon Oh*, Sungnyun Kim*, Namgyu Ho*, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun
NeurIPS 2022
- Representation Learning
Calibration of Few-Shot Classification Tasks: Mitigating Misconfidence From Distribution Mismatch
Sungnyun Kim, Se-Young Yun
IEEE Access 2022
- Machine Learning
Revisiting the Updates of a Pre-trained Model for Few-shot Learning
Yujin Kim*, Jaehoon Oh*, Sungnyun Kim, Se-Young Yun
ICML Workshop 2022(Oral)
- Machine Learning
- Paper
- Abstract
Real-time and Explainable Detection of Epidemics with Global News Data
Sungnyun Kim*, Jaewoo Shin*, Seongha Eom, Jihwan Oh, Se-Young Yun
PMLR Workshop 2022(Oral)
- Machine Learning
ReFine: Re-randomization before Fine-tuning for Cross-domain Few-shot Learning
Jaehoon Oh*, Sungnyun Kim*, Namgyu Ho*, Jin-Hwa Kim, Hwanjun Song, Se-Young Yun
CIKM 2022
- Representation Learning

2020

MixCo: Mix-up Contrastive Learning for Visual Representation
Sungnyun Kim*, Gihun Lee*, Sangmin Bae*, Se-Young Yun
NeurIPS Workshop 2020
- Representation Learning