Jiawen Zhang
Researcher @ Microsoft Research Asia
To build AI that holds up when the world changes.
About
I am a researcher at Microsoft Research Asia Singapore. My research interests center on adaptive AI systems that can operate reliably under uncertainty and change. I am particularly interested in how models can use tools, seek information, learn from feedback, and generalize to complex real-world environments. My previous work has explored related questions through time series and real-world data, including cross-domain generalization, robust forecasting, and modeling irregular observations.
Research collaborations and discussions are always welcome. If you are interested in applying for a research internship, please send your CV to jiawenzhang@microsoft.com.
Research Interests
- Interactive and agentic AI. How models can use tools, seek information, and act effectively across multi-turn interactions.
- Generalization and adaptation. How AI systems can remain effective under distribution shifts, changing environments, and limited feedback.
- Reliable AI for real-world data. Robust modeling and reasoning over messy, structured, and temporal data.
Publications
See Google Scholar for the full publication list. (* denotes equal contribution.)
- Y. Huang*, J. Zhang*, M. Dai, X. Su, S. Gao, Z. Wang, M. Zitnik. (2026). Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking. arXiv. [paper][code][project]
- S. Messica, J. Zhang*, K. Li*, T. Tsiligkaridis, M. Zitnik. (2026). Adaptive Time Series Reasoning via Segment Selection. ICML 2026. [paper][code]
- X. Hong, J. Zhang, W. Li, S. Lu, J. Li. (2025). Unify and Anchor: A Context-Aware Transformer for Cross-Domain Time Series Forecasting. arXiv. [paper]
- Z. Zhang, J. Zhang, S. Zheng, Y. Gu, J. Bian. (2025). Does Cross-Domain Pre-Training Truly Help Time-Series Foundation Models? ICLR Workshop on Foundation Models in the Wild. [paper]
- J. Zhang, S. Zheng, X. Wen, X. Zhou, J. Bian and J. Li. (2024). ElasTST: Towards Robust Varied-Horizon Forecasting with Elastic Time-Series Transformer. NeurIPS 2024. [paper][code]
- J. Zhang, X. Wen, Z. Zhang, S. Zheng, J. Li and J. Bian. (2024). ProbTS: Benchmarking Point and Distributional Forecasting across Diverse Prediction Horizons. NeurIPS 2024. [paper][code]
- J. Zhang, S. Zheng, W. Cao, J. Bian and J. Li. (2023). Warpformer: A Multi-scale Approach for Irregularly Sampled Multivariate Time Series. KDD 2023. [paper][code]
- J. Zhang, J. Zhu, Y. Yang, W. Shi, C. Zhang and H. Wang. (2021). Knowledge-Enhanced Domain Adaptation in Few-Shot Relation Classification. KDD 2021. [paper][code]