Hello 👋, My name is Ching Chang, also known as Jason Chang, and I am a PhD candidate (ABD) in Computer Science at National Yang Ming Chiao Tung University (NYCU), Taiwan, advised by Prof. Wen-Chih Peng. Currently, I am a Visiting Graduate Researcher in Computer Science at UCLA, working with Prof. Wei Wang.

My research focuses on Time Series Analysis, Large Foundation Models, Causal Discovery, and Multimodal Reasoning. I have published multiple papers in top AI and data science conferences and journals, including NeurIPS, AAAI, ICDE, CIKM, and ACM TIST, with total . I have also served as a reviewer for 49 papers across top-tier conferences and journals, including ICML, KDD, NeurIPS, ICLR, AAAI, WWW, TNNLS, and ACM TIST.

If you’re interested in collaboration, feel free to contact me at blacksnail789521@gmail.com. You can also check out my CV here 📄.

📖 Education

• 2021.09 – 2026.03 (Expected), National Yang Ming Chiao Tung University (NYCU), Taiwan, PhD in Computer Science (ABD)
• 2025.02 – 2026.02 (Expected), University of California, Los Angeles (UCLA), USA, Visiting Graduate Researcher in Computer Science
• 2016.09 – 2018.09, National Chiao Tung University (NCTU), Taiwan, MSc in Computer Science and Engineering
• 2012.09 – 2016.06, National Chiao Tung University (NCTU), Taiwan, BSc in Electrical and Computer Engineering

💻 Work Experience

• 2022.09 – 2025.02, Research Scientist (Intern), TSMC, Hsinchu, Taiwan
  Root Cause Analysis · Causal Discovery · Time Series Analysis

• 2021.01 – 2025.01, Research Scientist (Intern), GoEdge.ai, Hsinchu, Taiwan
  Time Series Analysis · Large Foundation Models · Causal Discovery

• 2019.07 – 2020.12, Machine Learning Engineer, TSMC, Hsinchu, Taiwan
  Root Cause Analysis

• 2018.04 – 2018.09, Machine Learning Engineer (Intern), EPISTAR, Hsinchu, Taiwan
  Root Cause Analysis

• 2016.07 – 2016.08, Software Engineer (Intern), MediaTek, Hsinchu, Taiwan
  Multimedia Firmware

📝 Publications

NeurIPS 2025

Time-IMM: A Dataset and Benchmark for Irregular Multimodal Multivariate Time Series

Ching Chang, Jeehyun Hwang, Yidan Shi, Haixin Wang, Wen-Chih Peng, Tien-Fu Chen, Wei Wang

• Time-IMM is a comprehensive benchmark and open-source library designed for irregular, multimodal time series. It introduces nine real-world datasets across diverse domains and provides tools for fusing asynchronous text with numeric signals, showing that multimodal integration can significantly enhance forecasting in complex, real-world settings.

arXiv 2025

A Survey of Reasoning and Agentic Systems in Time Series with Large Language Models

Ching Chang, Yidan Shi, Defu Cao, Wei Yang, Jeehyun Hwang, Haixin Wang, Jiacheng Pang, Wei Wang, Yan Liu, Wen-Chih Peng, Tien-Fu Chen

• Defines time-series reasoning through a two-level taxonomy (reasoning topology × primary objectives) and a compact attribute tag set (e.g., decomposition, verification, tool use, multimodality, alignment), while curating research and non-research works with guidance on evaluation and deployment.

ACM TIST 2025

LLM4TS: Aligning Pre-Trained LLMs as Data-Efficient Time-Series Forecasters

Ching Chang, Wei-Yao Wang, Wen-Chih Peng, Tien-Fu Chen

• LLM4TS is a framework that adapts pre-trained Large Language Models for multivariate time series forecasting through a two-stage fine-tuning process. It captures multi-scale temporal patterns and achieves state-of-the-art performance across full-shot and few-shot settings.

CIKM 2025

PromptTSS: A Prompting-Based Approach for Interactive Multi-Granularity Time Series Segmentation

Ching Chang, Ming-Chih Lo, Wen-Chih Peng, Tien-Fu Chen

• PromptTSS is a framework that unifies coarse- and fine-grained time series segmentation using prompts for dynamic adaptation. It achieves substantial accuracy gains in segmentation and transfer learning, showing strong effectiveness for hierarchical, evolving time series.

ICDE 2024

TimeDRL: Disentangled Representation Learning for Multivariate Time-Series

Ching Chang, Chiao-Tung Chan, Wei-Yao Wang, Wen-Chih Peng, Tien-Fu Chen

• TimeDRL is a self-supervised learning framework for multivariate time series data that learns disentangled timestamp- and instance-level embeddings without relying on augmentations. It introduces dual-level objectives for predictive and contrastive learning, and achieves strong performance across forecasting and classification tasks, even in low-label scenarios.

• AAAI 2025 (Workshop: AI4TS) PromptTSS: A Unified Model for Time Series Segmentation with Multi-Granularity States, Ching Chang, Ming-Chih Lo, Wen-Chih Peng, Tien-Fu Chen.

• NeurIPS 2024 (Workshop: Time Series in the Age of Large Models) Align and Fine-Tune: Enhancing LLMs for Time-Series Forecasting, Ching Chang, Wei-Yao Wang, Wen-Chih Peng, Tien-Fu Chen, Sagar Samtani.

• NeurIPS 2024 (Workshop: Self-Supervised Learning - Theory and Practice) Self-Supervised Learning of Disentangled Representations for Multivariate Time-Series, Ching Chang, Chan Chiao-Tung, Wei-Yao Wang, Wen-Chih Peng, Tien-Fu Chen.

• NeurIPS 2024 (Workshop: Time Series in the Age of Large Models) Text2Freq: Learning Series Patterns from Text via Frequency Domain, Ming-Chih Lo, Ching Chang, Wen-Chih Peng.

• CIKM 2024 COKE: Causal Discovery with Chronological Order and Expert Knowledge in High Proportion of Missing Manufacturing Data, Ting-Yun Ou, Ching Chang, Wen-Chih Peng.

• AAAI 2024 Root Cause Analysis in Microservice Using Neural Granger Causal Discovery, Zheng-Ming Lin, Ching Chang, Wei-Yao Wang, Kuang-Da Wang, Wen-Chih Peng.

• Preprint Detecting and Ranking Causal Anomalies in End-to-End Complex System, Ching Chang, Wen-Chih Peng.

🎖 Honors and Awards

• 2025.06 Outstanding Reviewer Award (Top 10% of Reviewers), KDD 2025, Toronto, Canada
• 2024.11 Overseas Postgraduate Research Fellowship Program, National Science and Technology Council, Taipei, Taiwan
• 2024.06 International Conference Scholarship, National Yang Ming Chiao Tung University, Taipei, Taiwan
• 2024.05 International Conference Scholarship, National Science and Technology Council, Taipei, Taiwan
• 2024.02 AAAI Student Scholarship, 38th AAAI Conference on Artificial Intelligence, Vancouver, Canada
• 2022.02 Xin Miao Key Technology Doctoral Scholarship, Xin Miao Education Foundation, Taipei, Taiwan
• 2021.09 Industry-Academia Cooperative PhD Project Scholarship, Ministry of Education Republic of China (Taiwan), Taipei, Taiwan

💬 Invited Talks

• 2025.09, Time Series AI for Strategic Business Intelligence and Manufacturing Optimization, TSMC AI4BI Innovation Center

  Delivered a talk on leveraging AI-driven time series analysis to generate actionable business intelligence.

• 2025.06, Advanced Time Series Analysis Techniques for Industrial and Manufacturing Applications, University of Southern California (USC)

  Delivered a talk on cutting-edge time series analysis methods tailored for deployment in industrial and manufacturing settings.

• 2023.08, Time Series Analysis with LLMs, LLM Industry-Academia Technical Exchange Conference, National Center for High-Performance Computing

  Discussed the use of large language models for analyzing time series data and their potential applications in industry.
  Shared the stage with Hung-Yi Lee and Hsiang-Tsung Kung.

🎓 Academic Services

• Reviewer for Conferences: ICDE’24, KDD’24, NeurIPS’24, ICLR’25, AAAI’25, KDD’25, ICML’25, NeurIPS’25, KDD’26, AAAI’26, WWW’26, ICLR’26
• Reviewer for Journals: TNNLS’25, TIST’25, TMLR’25, TSC’25, ESWA’25
• Student Volunteer: AAAI’24

👤 Visitors