Sung-Bin Kim

32 papers A* 5A 3Misc 1Journal 20Unranked 3
YearRankTypeTitle / Venue / Authors
2026 J jnl
Efficient Hyper-Parameter Search for LoRA via Language-aided Bayesian Optimization.
CoRR
Seong-Eun Baek, JungMok Lee, Sung-Bin Kim, Tae-Hyun Oh
2025 A* conf
AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models.
ICLR
Sung-Bin Kim, Oh Hyun-Bin, JungMok Lee, Arda Senocak, Joon Son Chung, Tae-Hyun Oh
2025 A* conf
AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation.
ACM Multimedia
Jeongsoo Choi, Ji-Hoon Kim, Sung-Bin Kim, Tae-Hyun Oh, Joon Son Chung
2025 J jnl
AlignDiT: Multimodal Aligned Diffusion Transformer for Synchronized Speech Generation.
CoRR
Jeongsoo Choi, Ji-Hoon Kim, Sung-Bin Kim, Tae-Hyun Oh, Joon Son Chung
2025 J jnl
FacEDiT: Unified Talking Face Editing and Generation via Facial Motion Infilling.
CoRR
Sung-Bin Kim, Joohyun Chang, David Harwath, Tae-Hyun Oh
2025 A* conf
Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics.
CVPR
Lee Chae-Yeon, Oh Hyun-Bin, Han EunGi, Sung-Bin Kim, Suekyeong Nam, Tae-Hyun Oh
2025 J jnl
Perceptually Accurate 3D Talking Head Generation: New Definitions, Speech-Mesh Representation, and Evaluation Metrics.
CoRR
Lee Chae-Yeon, Oh Hyun-Bin, Han EunGi, Sung-Bin Kim, Suekyeong Nam, Tae-Hyun Oh
2025 A* conf
SoundBrush: Sound as a Brush for Visual Scene Editing.
AAAI
Sung-Bin Kim, Kim Jun-Seong, Junseok Ko, Yewon Kim, Tae-Hyun Oh
2025 J jnl
SoundBrush: Sound as a Brush for Visual Scene Editing.
CoRR
Sung-Bin Kim, Kim Jun-Seong, Junseok Ko, Yewon Kim, Tae-Hyun Oh
2025 J jnl
VoiceCraft-Dub: Automated Video Dubbing with Neural Codec Language Models.
CoRR
Sung-Bin Kim, Jeongsoo Choi, Puyuan Peng, Joon Son Chung, Tae-Hyun Oh, David Harwath
2024 J jnl
A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization.
Trans. Mach. Learn. Res.
Kim Youwang, Lee Hyun, Sung-Bin Kim, Suekyeong Nam, Janghoon Ju, Tae-Hyun Oh
2024 J jnl
AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language Models.
CoRR
Sung-Bin Kim, Oh Hyun-Bin, JungMok Lee, Arda Senocak, Joon Son Chung, Tae-Hyun Oh
2024 A conf
Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert.
INTERSPEECH
Han EunGi, Oh Hyun-Bin, Sung-Bin Kim, Corentin Nivelet Etcheberry, Suekyeong Nam, Janghoon Ju, Tae-Hyun Oh
2024 J jnl
Enhancing Speech-Driven 3D Facial Animation with Audio-Visual Guidance from Lip Reading Expert.
CoRR
Han EunGi, Oh Hyun-Bin, Sung-Bin Kim, Corentin Nivelet Etcheberry, Suekyeong Nam, Janghoon Joo, Tae-Hyun Oh
2024 A conf
LaughTalk: Expressive 3D Talking Head Generation with Laughter.
WACV
Sung-Bin Kim, Lee Hyun, Da Hye Hong, Suekyeong Nam, Janghoon Ju, Tae-Hyun Oh
2024 A conf
MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset.
INTERSPEECH
Sung-Bin Kim, Lee Chae-Yeon, Gihun Son, Oh Hyun-Bin, Janghoon Ju, Suekyeong Nam, Tae-Hyun Oh
2024 J jnl
MultiTalk: Enhancing 3D Talking Head Generation Across Languages with Multilingual Video Dataset.
CoRR
Sung-Bin Kim, Lee Chae-Yeon, Gihun Son, Oh Hyun-Bin, Janghoon Ju, Suekyeong Nam, Tae-Hyun Oh
2024 J jnl
Revisiting Learning-based Video Motion Magnification for Real-time Processing.
CoRR
Hyunwoo Ha, Oh Hyun-Bin, Kim Jun-Seong, Byung-Ki Kwon, Sung-Bin Kim, Linh-Tam Tran, Ji-Yun Kim, Sung-Ho Bae, Tae-Hyun Oh
2024 — conf
SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models.
NAACL-HLT (Findings)
Lee Hyun, Sung-Bin Kim, Seungju Han, Youngjae Yu, Tae-Hyun Oh
2024 J jnl
Sound2Vision: Generating Diverse Visuals from Audio through Cross-Modal Latent Alignment.
CoRR
Sung-Bin Kim, Arda Senocak, Hyunwoo Ha, Tae-Hyun Oh
2024 J jnl
The devil in the details: simple and effective optical flow synthetic data generation.
Vis. Comput.
Byung-Ki Kwon, Sung-Bin Kim, Tae-Hyun Oh
2023 J jnl
A Large-Scale 3D Face Mesh Video Dataset via Neural Re-parameterized Optimization.
CoRR
Kim Youwang, Lee Hyun, Sung-Bin Kim, Suekyeong Nam, Janghoon Ju, Tae-Hyun Oh
2023 J jnl
LaughTalk: Expressive 3D Talking Head Generation with Laughter.
CoRR
Sung-Bin Kim, Lee Hyun, Da Hye Hong, Suekyeong Nam, Janghoon Ju, Tae-Hyun Oh
2023 Misc conf
Prefix Tuning for Automated Audio Captioning.
ICASSP
Minkyu Kim, Sung-Bin Kim, Tae-Hyun Oh
2023 J jnl
Prefix tuning for automated audio captioning.
CoRR
Minkyu Kim, Sung-Bin Kim, Tae-Hyun Oh
2023 J jnl
SMILE: Multimodal Dataset for Understanding Laughter in Video with Language Models.
CoRR
Lee Hyun, Sung-Bin Kim, Seungju Han, Youngjae Yu, Tae-Hyun Oh
2023 A* conf
Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment.
CVPR
Sung-Bin Kim, Arda Senocak, Hyunwoo Ha, Andrew Owens, Tae-Hyun Oh
2023 J jnl
Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment.
CoRR
Sung-Bin Kim, Arda Senocak, Hyunwoo Ha, Andrew Owens, Tae-Hyun Oh
2023 J jnl
The Devil in the Details: Simple and Effective Optical Flow Synthetic Data Generation.
CoRR
Byung-Ki Kwon, Sung-Bin Kim, Tae-Hyun Oh
2022 J jnl
Lightweight Speaker Recognition in Poincaré Spaces.
IEEE Signal Process. Lett.
Jieun Lee, Sung-Bin Kim, Seokhyeong Kang, Tae-Hyun Oh
2009 — conf
Analytic Models for Peak Current Computation in General Interconnect Circuits.
CDES
Ki-Young Kim, Sung-Bin Kim, Se-Jin Ko, Seok-Yoon Kim
2009 — conf
Reducing the Far-end Crosstalk Using Advanced Guard Trace in PCB Transmission Lines.
CDES
Sung-Bin Kim, Se-Jin Ko, Ki-Young Kim, Seok-Yoon Kim