Scholar
Yang Shu
Google Scholar ID: VdyHmIwAAAAJ
Assistant Professor, East China Normal University
Citations & Impact
Citations
1,080
H-index
12
i10-index
13
Publications
20
Co-authors
17
list available
Contact
Publications
Resume (English only)
Academic Achievements
- Preprint: Transferability in Deep Learning: A Survey
- Publication 1: TSFM-Bench: A Comprehensive and Unified Benchmarking of Foundation Models for Time Series Forecasting, KDD 2025
- Publication 2: Towards a General Time Series Forecasting Model with Unified Representation and Adaptive Transfer, ICML 2025
- Publication 3: LightGTS: A Lightweight General Time Series Forecasting Model, ICML 2025
- Publication 4: Enhancing Diversity for Data-free Quantization, CVPR 2025 (oral)
- Publication 5: AimTS: Augmented Series and Image Contrastive Learning for Time Series Classification, ICDE 2025
- Publication 6: AID-SQL: Adaptive In-Context Learning of Text-to-SQL with Difficulty-Aware Instruction and Retrieval-Augmented Generation, ICDE 2025 (accepted)
- Publication 7: Towards a General Time Series Anomaly Detector with Adaptive Bottlenecks and Dual Adversarial Decoders, ICLR 2025
- Publication 8: Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation, ICLR 2025
- Publication 9: RCRank: Multimodal Ranking of Root Causes of Slow Queries in Cloud Database Systems, VLDB 2025
- Publication 10: Assessing Pre-trained Models for Transfer Learning through Distribution of Spectral Components, AAAI 2025
- Publication 11: Boosting Transferability and Discriminability for Time Series Domain Adaptation, NeurIPS 2024
Research Experience
- Currently an Assistant Professor (Chenhui Scholar) at the School of Data Science and Engineering, East China Normal University.
Education
- Ph.D. from School of Software, Tsinghua University, advised by Mingsheng Long; B.S. from Department of Automation, Tsinghua University.
Background
- Research Interests: Transfer learning, out-of-distribution (OOD) generalization, domain adaptation, and few-shot learning. Related areas: Foundation models, time series analysis, and multi-modal learning.
