Skip to content
View delaykimm's full-sized avatar

Block or report delaykimm

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
delaykimm/README.md

Hi there, I'm Jiyun Kim (Grace)👋

🎓Education

  • Computer Science & Engineering @ Korea University (Mar 2022 - Present)
  • Brain and Cognitive Sciences @ Korea University (Mar 2024 - Present)
  • Exchange Student @ The University of Texas at Austin (Jan 2025 - May 2025)

🔭 Research Experience

Undergraduate Researcher, Data & Adaptive Intelligence Systems Lab (Advisor: Prof. Susik Yoon), Korea University
July 2024 – Dec 2025

  • Conducted research on time-series representation learning with large language models (LLMs).

🔭 Research Projects

Numerical-Token-Grounded Time-Series & Textual Embedding Alignment for Forecasting
July 2025 – Dec 2025
(Individually led research conducted at Data & Adaptive Intelligence Systems Lab under the supervision of Prof. Susik Yoon, Korea University)

  • Identified that existing time-series–text methods rely on naive channel-wise attention without explicit alignment criteria.
  • Proposed a numerical token–based alignment framework by converting time-series values into natural-language descriptions.
  • Aligned timestamp-level time-series embeddings with number-aware textual token embeddings, enabling fine-grained and interpretable cross-modal representations.
  • Validated the framework through basic experiments on ETTh1 and ILI datasets.
  • Manuscript in preparation.

🔭 I'm interested in

  • Interpretable representation learning
  • Multimodal representation learning
  • Brain-inspired AI
  • Scene understanding & structured representation (e.g., scene graph generation)
  • Autonomous driving perception

🛠️ Tech Stack

Python PyTorch NumPy Pandas scikit-learn Transformers HuggingFace HDF5 Matplotlib Linux GitHub

📊 My GitHub Stats

GitHub Stats

📫 Contact

“Keep it simple, but meaningful”

Pinned Loading

  1. time-text-alignment time-text-alignment Public

    Python

  2. 20252R0136DATA30400 20252R0136DATA30400 Public

    final project : hierarchical multi-label text classification

    Python

  3. 20242R0136COSE41600 20242R0136COSE41600 Public

    Pedestrian Detection for Self-Driving Cars

    Python

  4. COSE461-NLP COSE461-NLP Public

    Code for Assignment/Projects for NLP Class

    Jupyter Notebook