Greetings! I am a Machine Learning Scientist at Amazon working on multimodal large language models and responsible AI. Before joining Amazon, I was an AI researcher at Siemens Research, with a particular emphasis on language models and knowledge reasoning. I have completed my Ph.D. study with a specialization in Machine Learning at the University of Munich, supervised by Prof. Volker Tresp.
My research interests include language modeling, multimodal reasoning, and responsible AI. I have published 20+ papers at top conferences, e.g.,ICLR, NeurIPS, ACL, EMNLP, NAACL, etc. In 2021, I have been selected as 1 of 51 national winners to receive a national research grant (100K Euros) from the German Federal Ministry of Education and Research. With this funding, I'm leading a small research team focusing on murltimodal language modeling and reasoning. Besides, I have been honored the Best Paper Runner-Up Award at AKBC, an esteemed international knowledge graph conference, in both 2020 and 2022.
Prior to LMU Munich, I acquired the M.Sc. in 2019 from the Technical University of Munich and the B.Sc. in 2016 from Karlsruhe Institute of Technology. From 2013 to 2018, I were awarded a full scholarship from the German Academic Exchange Service.
If you are interested in collaborating with me, please feel free to drop me an email through hanzhen02111 at 163 dot com or zhenhz at amazon dot co dot uk.
News
I will co-organize the first Bridging Neuro-symbolic and LLMs Workshop at COLING 2024 (homepage).
One conference paper and one workshop paper have been accepted by NeurIPS 2023.
We released a systematic survey of prompt engineering on vision-language foundation models (preprint, github).
A paper has been accepted by the ACL 2023 Findings.
Invited talk at SIAM Conference on Computational Science and Engineering 2023, MS162 (March 1, 2023).
Invited talk at the Machine Learning Meeting by Prof. Dr. Thomas Kuhr at the Faculty of Physics at the University fo Munich (Oct. 27, 2022).
Yesterday's News
I have finished my Ph.D. with a specialization in machine learning at the University of Munich (Sept. 16, 2022).
I have been selected as 1 of 51 national winners to receive a research grant (100,000 Euros) from the German Federal Ministry of Education and Research (BMBF). The funding project started on April 1. 2022.
Our paper titled "Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Information" has been selected as one of two honorable mention papers at the Automated Knowledge Base Construction Conference 2022 (with Zifeng Ding, Jingpei Wu, Bailan He, Yunpu Ma, Volker Tresp).
Invited speaker at the Youth Forum 2021 of Wangxuan Institute of Computer Technology, Peking University (Dec. 2021).
Our paper titled "Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs" the Best Paper Runner-up award at the Automated Knowledge Base Construction Conference 2020 (with Yunpu Ma, Yuyi Wang, Stephan Günnemann, and Volker Tresp).
Graduate with distinction (German grade: 1.1/1.0) at the Karlsruher Institute of Technology (2019).
Selected Publication
Zhen Han, Yunpu Ma, Yuyi Wang, Stephan Günnemann, Volker Tresp. Graph Hawkes Neural Network for Forecasting on Temporal Knowledge Graphs (best paper nominee). In Proceedings of the Conference on Automated Knowledge Base Construction (AKBC), 2020 [video].
Zhen Han, Peng Chen, Yunpu Ma, Volker Tresp. DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2020 .
Zhen Han, Peng Chen, Yunpu Ma, Volker Tresp. Explainable Subgraph Reasoning for Forecasting on Temporal Knowledge Graphs. In Proceedings of the International Conference on Learning Representations (ICLR), 2021 [video].
Zhen Han, Zifeng Ding, Yunpu Ma, Jiayu Gu, Volker Tresp. Learning Neural Ordinary Equations for Forecasting Future Links on Temporal Knowledge Graphs. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
Zhen Han, Gengyuan Zhang, Yunpu Ma, Volker Tresp. Time-dependent Entity Embedding is not All You Need: A Re-Evaluation of Temporal Knowledge Graph Completion Models under a Unified Framework. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
Zhen Han, Ruotong Liao, Beiyan Liu, Yao Zhang, Zifeng Ding, Heinz Köppl, Hinrich Schütze, Volker Tresp. Enhanced Temporal Knowledge Embeddings with Contextualized Language Representations. Under review at the 61st Annual Meeting of the Association for Computational Linguistics, 2023.
Yue Feng, Zhen Han, Mingming Sun, Ping Li. Multi-Hop Open-Domain Question Answering over Structured and Unstructured Knowledge. In Proceedings of Findings of the North American Chapter of the Association for Computational Linguistics (NAACL Findings), 2022.
Haohai Sun, Jialun Zhong, Yunpu Ma, Zhen Han, Kun He. TimeTraveler: Reinforcement Learning for Temporal Knowledge Graph Forecasting. In Proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021.
Jin Guo*, Zhen Han*, Zhou Su, Jiliang Li, Volker Tresp, Yuyi Wang. Continuous Temporal Graph Networks for Event-based Graph Data. In Proceedings of the Workshop on Deep Learning on Graphs for Natural Language Processing at the 2022 Conference of the North American Chapter of the Association for Computational Linguistics (DLG4NLP@NAACL).
Zifeng Ding, Ruoxia Qi, Zongyue Li, Bailan He, Jingpei Wu, Yunpu Ma, Zhao Meng, Zhen Han†, Volker Tresp†. Forecasting Question Answering over Temporal Knowledge Graphs. Under review at the 61st Annual Meeting of the Association for Computational Linguistics, 2023. †: corresponding author.
Zifeng Ding, Jingpei Wu, Bailan He, Yunpu Ma, Zhen Han†, Volker Tresp†. Few-Shot Inductive Learning on Temporal Knowledge Graphs using Concept-Aware Information. In Proceeding of the 2022 Conference on Automated Knowledge Base Construction (AKBC) (best paper nominee), 2022. †: corresponding author.