About Me
Huawei Singapore · Previously HKUST
I am Hanmo LIU, a researcher in the Search and Recommendation Lab, Huawei Singapore Research Center. I earned my Ph.D. in Data Science and Analytics from the Division of Emerging Interdisciplinary Areas (EMIA) at HKUST in 2026, fortunate to be advised by Prof. CHEN, Lei and Prof. YANG, Can. Previously, I obtained a B.Sc. in Honors Physics and Computer Science from the Department of Physics, HKUST, in 2021.
Research Interests
My research centers on two complementary angles:
- Model Evolution — studying how to make models evolve more efficiently and effectively, spanning continual learning on streaming real-world data and self-driven model redesign empowered by large language models.
- Empirical Science of Large Models — treating large-model research as an empirical science: starting from phenomena observed on real data, forming and verifying hypotheses, and distilling generalizable principles that guide future research.
Email · Google Scholar · ORCID · GitHub
Publications · Teaching · Service · Awards
Publications
* marks corresponding author.
Preprints
ReCast: Recasting Learning Signals for Reinforcement Learning in Generative Recommendation
Peiyan Zhang, Hanmo Liu, Chengxuan Tong, Yuxia Wu, Wei Guo, Yong Liu
Preprint · PaperFlowEvo: Self-Evolving Agents through the Co-Evolution of Workflows and Executable Skills
Zeyu Ren, Ling Yue, Ran Li, Yishu Wang, Hanmo Liu, Shaowu Pan, Shimin Di
Preprint · PaperLearning to Compose for Cross-domain Agentic Workflow Generation
Jialiang Wang, Shengxiang Xu, Hanmo Liu, Jiachuan Wang, Yuyu Luo, Shimin Di, Min-Ling Zhang, Lei Chen
Preprint · PaperRobustFlow: Towards Robust Agentic Workflow Generation
Shengxiang Xu, Jiayi Zhang, Shimin Di, Yuyu Luo, Liang Yao, Hanmo Liu, Jia Zhu, Fan Liu, Min-Ling Zhang
Preprint · Paper
Conference Papers
Beyond Model Base Retrieval: Weaving Knowledge to Master Fine-grained Neural Network Design
Jialiang Wang, Hanmo Liu*, Shimin Di, Zhili Wang, Jiachuan Wang, Lei Chen, Xiaofang Zhou
ICML 2026 · PaperAdaptive Concept Discovery for Interpretable Few-Shot Text Classification
Lifang Zheng, Hanmo Liu, Kani Chen
ICLR 2026 · PaperProficient Graph Neural Network Design by Accumulating Knowledge on Large Language Models
Jialiang Wang, Hanmo Liu, Shimin Di, Zhili Wang, Jiachuan Wang, Lei Chen, Xiaofang Zhou
WSDM 2026 · Oral · PaperA Selective Learning Method for Temporal Graph Continual Learning
Hanmo Liu, Shimin Di, Haoyang Li, Xun Jian, Yue Wang, Lei Chen
ICML 2025 · PaperStructuring Benchmark into Knowledge Graphs to Assist Large Language Models in Retrieving and Designing Models
Hanmo Liu, Shimin Di, Jialiang Wang, Zhili Wang, Jiachuan Wang, Xiaofang Zhou, Lei Chen
ICLR 2025 · PaperSIT: Selective Incremental Training for Dynamic Knowledge Graph Embedding
Zhifeng Jia, Hanmo Liu, Haoyang Li, Lei Chen
ICDE 2025 · PaperWhen Speed meets Accuracy: an Efficient and Effective Graph Model for Temporal Link Prediction
Haoyang Li, Yuming Xu, Yiming Li, Hanmo Liu, Darian Li, Chen Jason Zhang, Lei Chen, Qing Li
VLDB 2025 · PaperEffective Data Selection and Replay for Unsupervised Continual Learning
Hanmo Liu, Shimin Di, Haoyang Li, Shuangyin Li, Lei Chen, Xiaofang Zhou
ICDE 2024 · PaperIncremental Tabular Learning on Heterogeneous Feature Space
Hanmo Liu, Shimin Di, Lei Chen
SIGMOD 2023 · Paper
Teaching
Teaching Assistant at HKUST:
- DSAA 5013 — Advanced Machine Learning (Spring 2024)
- DSAA 5020 — Foundation of Data Science and Analytics (Fall 2023)
- MSBD 5002 — Data Mining and Knowledge Discovery (Spring 2023)
Academic Service
- Program Committee Member — WWW 2026 Demo, WWW 2025 Short Paper
- Conference Reviewer — KDD 2026; ICML 2026; ICLR 2026/2025; MM 2025; WWW 2025; DASFAA 2025/2024
- Journal Reviewer — TKDE, TCSS
Awards & Honors
- DSA Excellence Award (Research) — DSA Thrust, HKUST(GZ), 2025
- Second Prize, Outstanding Paper — Guangdong Computing Association, 2023 / 2024
- HKUST Postgraduate Scholarship — HKUST, 2021–2025
- Paul Ching Wu Chu Scholarship for Outstanding Academic Performance — Department of Physics, HKUST, 2020
