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 31 papers across top-tier conferences and journals, including ICDE, KDD, NeurIPS, ICLR, AAAI, 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 📄.

📖 Educations

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

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 Prompt-based Framework for Time Series Forecasting

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

2025.06, 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
Reviewer for Journals: TNNLS’25, TIST’25, TMLR’25, TSC’25, ESWA’25
Student Volunteer: AAAI’24