Lifan Zhao
PhD candidate
Shanghai Jiao Tong University
About Me
I am a final-year Ph.D. student in Computer Science at Shanghai Jiao Tong University, supervised by Prof. Yanyan Shen. I am broadly interested in meta-learning, online learning, and post-training for foundation models. My previous work mainly focus on data-driven applications including time series forecasting and recommender systems. I recently worked on agent memory at Alibaba Tongyi Lab and sales forecasting at ByteDance. I have joined the Tencent Project Up at WeiXin Group to develop personal agent techniques and products.
Interests
- Meta-Learning
- Online Learning
- Data-Centric AI
- LLM Post-Training
Education
Ph.D. in Computer Science
Shanghai Jiao Tong University
B.Eng. in Software Engineering
Shandong University
Recent Publications
(2025).
Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning.
The Thirty-ninth Annual Conference on Neural Information Processing Systems (NeurIPS'25).
(2025).
Proactive Model Adaptation Against Concept Drift for Online Time Series Forecasting.
Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'25).
(2024).
Rethinking Channel Dependence for Multivariate Time Series Forecasting: Learning from Leading Indicators.
The Twelfth International Conference on Learning Representations (ICLR'24).
(2024).
StockCL: Selective Contrastive Learning for Stock Trend Forecasting via Learnable Concepts.
Database Systems for Advanced Applications: 29th International Conference (DASFAA'24).
(2023).
DoubleAdapt: A Meta-learning Approach to Incremental Learning for Stock Trend Forecasting.
Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD'23).
(2023).
RESUS: Warm-up Cold Users via Meta-learning Residual User Preferences in CTR Prediction.
ACM Transactions on Information System (TOIS).
(2023).
Methods for Acquiring and Incorporating Knowledge into Stock Price Prediction: A Survey.
ACM Computing Surveys.
(2022).
Mixed Information Flow for Cross-Domain Sequential Recommendations.
ACM Transactions on Knowledge Discovery from Data (TKDD).
Experience
Researcher (Project Up)
Tencent WeChatIntern (Soaring Star Talent Program)
ByteDanceResearch Intern
TongYi Lab, Alibaba Group
Education
Ph.D. in Computer Science
Shanghai Jiao Tong UniversitySupervised by Prof. Yanyan Shen,
B.Eng. in Software Engineering
Shandong University