news

Dec 01, 2025 TwelveLabs releases Marengo 3.0, a new standard for foundation models that understand the world in all its complexity.
Apr 01, 2025 One CVPR-2025 EVAL-FoMo 2 Workshop paper: Emergence of Text Readability in Vision Language Models.
Feb 04, 2025 I’ve started a new chapter at TwelveLabs!
Jan 01, 2025 One ICLR-2025 paper to appear: Probabilistic Language-Image Pre-Training.
Dec 01, 2024 One AAAI-2025 paper to appear: Extract Free Dense Misalignment from CLIP.
Jul 04, 2024 One ECCV-2024 oral paper to appear: HYPE: Hyperbolic Entailment Filtering for Underspecified Images and Texts.
Jul 03, 2024 One TMLR paper: CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion
May 01, 2024 One ICML-2024 paper to appear: STELLA: Continual Audio-Video Pre-training with Spatio-Temporal Localized Alignment.
Apr 10, 2024 One CVPR-2024 Synthetic Data for Computer Vision workshop paper: CompoDiff: Versatile Composed Image Retrieval With Latent Diffusion.
Apr 04, 2024 One CHIL-2024 paper to appear: Vision-Language Generative Model for View-Specific Chest X-ray Generation.
Feb 01, 2024 One CVPR-2024 paper to appear: Language-only Efficient Training of Zero-shot Composed Image Retrieval.
Sep 01, 2023 One ICCV-2023 paper to appear: SeiT: Storage-Efficient Vision Training with Tokens Using 1% of Pixel Storage.
Jul 01, 2023 One ICML-2023 Artificial Intelligence & Human Computer Interaction workshop paper: Computational Approaches for App-to-App Retrieval and Design Consistency Check.
May 01, 2023 One ACL-2023 paper: Pivotal Role of Language Modeling in Recommender Systems: Enriching Task-specific and Task-agnostic Representation Learning.
Feb 01, 2023 One ICLR-2023 paper: What Do Self-Supervised Vision Transformers Learn?.
Dec 01, 2022 One BMVC-2022 paper: Correlation between Alignment-Uniformity and Performance of Dense Contrastive Representations.
Jul 01, 2022 One ECCV-2022 paper: ECCV Caption: Correcting False Negatives by Collecting Machine-and-Human-verified Image-Caption Associations for MS-COCO.
Jan 01, 2022 One ICLR-2022 paper: ViDT: An Efficient and Effective Fully Transformer-based Object Detector.
Nov 01, 2021 One CHI-2022 paper: Speeding up Inference with User Simulators through Policy Modulation.
Oct 22, 2021 One NeurIPS-2021 DGM workshop paper: Fourier-based Decoder for Periodic Signals.
May 08, 2021 One ICML-2021 oral paper: Vision-and-Language Transformers (ViLT).
Apr 26, 2021 I joined Naver AI Lab.
Aug 20, 2020 One ECCV-2020 TASK-CV workshop oral paper: Diversified Mutual Deep Metric Learning (DM2).
Sep 03, 2019 One NeurIPS-2019 paper: Dynamics of Attention for Focus Transition (DAFT).
Feb 12, 2018 I completed my M.Sc. at SNU and joined Kakao.