Skip to content
View blisky-li's full-sized avatar
🎯
Focusing
🎯
Focusing
  • Institute of Computing Technology, CAS
  • Baidu, Beijing, China

Block or report blisky-li

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
blisky-li/README.md

Hi! I'm Yujie Lee πŸ‘‹

Ph.D. Student, Institute of Computing Technology, Chinese Academy of Sciences
Researcher in Time Series, Spatio-Temporal Learning, and AI for Science

I work on data-centric machine learning for scientific discovery, with a particular focus on time series forecasting, spatio-temporal modeling, and robust evaluation of AI systems. I am also engaged in foundational research on frontier applications of large models at Baidu.

πŸ”¬ Research Interests

Time series forecasting, spatio-temporal learning, AI for Science, data-centric AI, and robust model evaluation.

πŸ“Œ Selected Work

  • ARIES arxiv β€” Time-series modeling and evaluation
  • APT AAAI26 β€” Predictive modeling under distribution drift
  • BLAST KDD25 β€” Balanced corpus construction for time series
  • STA-GANN CIKM25 β€” Spatio-temporal kriging
  • DFDGCN ICASSP24β€” Dynamic graph learning for spatio-temporal prediction
  • TULMGAT PR25 β€” Trajectory user linking

πŸ”­ Ongoing Directions

  • Benchmarking for time series foundation models;
  • Pattern-aware corpus construction and evaluation;
  • Distribution shift and model robustness;
  • Scientific AI systems for real-world applications.

🀝 Collaboration

Open to research collaborations in related areas.

✨ Links

GitHub Streak

Ashutosh's github activity graph

Popular repositories Loading

  1. STAGANN STAGANN Public

    STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach

    Python 8

  2. ARIES ARIES Public

    Relation Assessment and Model Recommendations for Time Series Forecasting

    Python 8 1

  3. APT APT Public

    APT: Affine Prototype-Timestamp For Time Series Forecasting Under Distribution Shift

    Python 8

  4. TULMGAT TULMGAT Public

    A novel model for solving the TUL problem. Accepted by Pattern Recognition

    Python 2

  5. DFDGCN DFDGCN Public

    Forked from GestaltCogTeam/DFDGCN

    Author's Dynamic frequency domain graph convolution for traffic prediction

    Jupyter Notebook 1

  6. vector-quantize vector-quantize Public

    Forked from nikitus20/vector-quantize

    (Disappearance of original author) Huge Vector (and Scalar) Quantization Library with most prominent tricks

    Python 1