Tae-Hyun Oh
Tae-Hyun Oh
KAIST · Graduate School of Metaverse
Professor
Prof. 오태현
Professor's page · publicationsAbout
전기및전자공학부 소속으로 Advanced Machine Intelligence Lab을 이끌며 머신러닝, 멀티모달 인식, AI 에이전트를 연구한다. 3D 인식, 영상 이해, 오디오-비주얼 멀티모달 학습과 데이터 효율적 학습이 주요 주제다. MIT CSAIL과 Facebook AI Research를 거쳐 KAIST에 합류했다.
Research keywords
Recent papers
- Hear, Localize, and Reason: Spatially Aware Scene Understanding for Audio-Visual LLMsNewPreprintarXiv (Cornell University) · Oct 15
- Physics-Aware Deepfake Detection via Distance-Speech ConsistencyNewPreprintarXiv (Cornell University) · Oct 13
- FloorSAV: Elucidating Spatial Audio-Visual Context with 2D Floormap for AV-LLMsPreprintarXiv (Cornell University) · Oct 8
From OpenAlex · papers whose author affiliation matches this university
Selected publications
- Toward Interactive Sound Source LocalizationIEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI) · 2025
- Dr. Splat: Directly Referring 3D Gaussian Splatting via Direct Language Embedding RegistrationCVPR · 2025
- Perceptually Accurate 3D Talking Head GenerationCVPR · 2025
- AVHBench: A Cross-Modal Hallucination Benchmark for Audio-Visual Large Language ModelsICLR · 2025
- A unified framework for unsupervised action learning via global-to-local motion transformerPattern Recognition · 2025
- PAVAS: Physics-Aware Video-to-Audio SynthesisCVPR · 2026
Labs doing related research
Labs that recently published on topics this lab's recent papers share
Shared topic: Multimodal Machine Learning Applications
Kim Junmo Lab
KAIST · Electrical Engineering
Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMsNewPreprintarXiv (Cornell University) · Oct 1Generative AI Lab
KAIST · School of Computing
Retrieval Heads Meet Vision: Uncovering How VLMs Locate and Extract Visual InformationPreprintarXiv (Cornell University) · Aug 27Computer Vision and Image Processing Lab
Sogang University · Computer Science and Engineering
SNF-Bench: Separating Static Drift from Natural Flow in Long-Horizon Fixed-Camera Video GenerationPreprintarXiv (Cornell University) · Aug 27
Other labs in this department
- AIRIS LabRecruiting
Sung-Young Kim
Auditory training game, gamified digital therapeutics, Immersive audio for Metaverse
- Music and Audio Computing LabRecruiting
Juhan Nam
Music Technology, AI and Machine Learning for Music, Music Information Retrieval, Audio Signal Processing (AR/VR)
- HCI Tech LabRecruiting
Sang-Ho Yun
HCI, Interaction Techniques, Intelligent User Interfaces
- HCILRecruiting
Ki-Hyuk Lee
Human-Computer Interaction, Augmented Reality, XR, UI/UX
- Lifelike Avatar and Agent LabRecruiting
Sung-Hee Lee
Modeling Digital Human and Avatar, Motion Generation, Telepresence Avatar in AR/VR
- RAPHE LabRecruiting
Jae-Seung Jung
Neuroscience, Brain Science, Computational Neuroscience, Decision Making