Dingmin Wang (汪鼎民）

Biography

I am an applied scientist at AWS AI Labs in the Amazon Q Developer team based in the Bay Area, CA, United States. I am currently working on large language models (LLMs) for code.

I got my DPhil (a.k.a Ph.D) degree at Department of Computer Science , University of Oxford in Jun 2024, where I was fortunate to be supervised by Bernardo Cuenca Grau and Przemysław Andrzej Wałęga. My DPhil studies at Oxford are conducted under the auspices of an EPSRC Studentship. I am also fortunate to be selected as a member of 2020 Oxford Clarendon Scholars. In particular, I gained rich research and development experience through working and interning at multiple top-tier tech companies, including Google Research, Amazon, Microsoft Research, and Tencent (full-time researcher for two years before my Ph.D). I obtained my M.Eng. degree from Department of Computer Science, Tsinghua University in 2018.

Selected Publications

Please see my full list at [Google Scholar Profile]

2024

MTLearn: Extracting Temporal Rules Using Datalog Rule Learners [CODE]
Dingmin Wang, Przemyslaw Walega, Bernardo Cuenca Grau
In Proceedings of the 21st International Conference on the Principles of Knowledge Representation and Reasoning (KR 2024)

Contextual Distillation Model for Diversified Recommendation
Fan Li, Xu Si, Shisong Tang, Dingmin Wang, Kunyan Han, Bing Han, Guorui Zhou, Yang Song, Hechang Chen
In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2024)

Fine-tuning Language Models for Joint Rewriting and Completion of Code with Potential Bugs [CODE]
Dingmin Wang, Jinman Zhao, Hengzhi Pei, Samson Tan, Sheng Zha
In Findings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2024 Findings)

Retrieve What You Need: A Mutual Learning Framework for Open-domain Question Answering [CODE]
Dingmin Wang, Qiuyuan Huang, Matthew Jackson, Jianfeng Gao
Transactions of the Association for Computational Linguistics (TACL 2024)

Working Memory Capacity of ChatGPT: An Empirical Study [CODE]
Dongyu Gong, Xingchen Wan, Dingmin Wang
In Proceedings of the 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)

2023

Calibrate and Boost Logical Expressiveness of GNN Over Multi-Relational and Temporal Graphs [CODE]
Dingmin Wang, Yeyuan Chen
In Proceedings of the Thirty-seventh Annual Conference on Neural Information Processing Systems (NeurIPS 2023)

Efficient Embeddings of Logical Variables for Query Answering over Incomplete Knowledge Graphs [CODE]
Dingmin Wang, Yeyuan Chen, Bernardo Cuenca Grau
In Proceedings of the 38th Annual AAAI Conference on Artificial Intelligence (AAAI 2024)

An Empirical Study of Retrieval-enhanced Graph Neural Networks [CODE]
Dingmin Wang, Shengchao Liu, Hanchen Wang, Bernardo Cuenca Grau, Linfeng Song, Jian Tang, Le Song, Qi Liu
In Proceedings of the 26th European Conference on Artificial Intelligence (ECAI 2023)

Counterfactual Video Recommendation for Duration Debiasing
Shisong Tang, Qing Li, Dingmin Wang, Ci Gao, Wentao Xiao, Dan Zhao, Yong Jiang, Qian Ma, Aoyang Zhang
In Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining (KDD 2023)

2022

Knowledge-based Temporal Fusion Network for Interpretable Online Video Popularity Prediction
Shisong Tang, Qing Li, Xiaoteng Ma, Ci Gao, Dingmin Wang, Yong Jiang, Qian Ma, Aoyang Zhang, Hechang Chen
In Proceedings of the Web Conference 2022 (WWW 20222)

MeTeoR: Practical Reasoning in Datalog with Metric Temporal Operators [CODE]
Dingmin Wang, Pan Hu, Przemysław Andrzej Wałęga, Bernardo Cuenca Grau
In Proceedings of the 37th AAAI Conference on Artificial Intelligence (AAAI 2022)

2021 and before

Fast and Scalable Dialogue State Tracking with Explicit Modular Decomposition
Dingmin Wang, Chenghua Lin, Qi Liu, Kam-Fai Wong.
In Proceedings of 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL 2021)

A Template-guided Hybrid Pointer Network for Knowledge-based Task-oriented Dialogue Systems [CODE]
Dingmin Wang, Ziyao Chen, Wanwei He, Li Zhong, Yunzhe Tao, Min Yang.
ACL 2021 Workshop on Document-Grounded Dialogue and Conversational Question Answering (DialDoc@ACL 2021)

Confusionset-guided Pointer Networks for Chinese Spelling Check[CODE]
Dingmin Wang, Yi Tay, Li Zhong.
In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (ACL 2019)

A Hybrid Approach to Automatic Corpus Generation for Chinese Spelling Check[CODE]
Dingmin Wang, Yan Song, Jing Li, Jialong Han, Haisong Zhang.
In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP 2018)