Minghao Wu

Minghao Wu

Postdoc at The University of North Carolina at Chapel Hill, USA.

Minghao Wu - The University of North Carolina at Chapel Hill

I am currently a Postdoctoral Research Associate at The University of North Carolina at Chapel Hill, working with Prof. Mohit Bansal. I obtained my Ph.D. degree in Computer Science from Monash University in 2025, where I was advised by Prof. Gholamreza (Reza) Haffari. Before that, I received my M.Eng. degree in Information Technology from The University of Melbourne in 2018, under the supervision of Prof. Trevor Cohn, and my B.Sc. degree in Statistics and Information Systems from The University of Sydney in 2016.

My research interests mainly lie in the following areas:

  • Language Agents: My primary research interest is currently focused on multi-agent communication and collaboration. My recent work (Wu et al., 2025) proposed a multi-agent framework that mimics human translation workflows using language agents, achieving state-of-the-art results in literary translation tasks.
  • Data Efficiency: I have explored data-efficient methods for training language models, including fine-tuning large language models with heterogeneous data sources (Wu et al., 2024, Wang et al., 2025), leveraging a bipartite graph to balance quality and diversity in data selection (Wu et al., 2025), and synthesizing large-scale datasets for fine-tuning language models (Wu et al., 2023).
  • Multilinguality and Machine Translation: I have conducted research on multilinguality and machine translation, including multilingual supervised fine-tuning for large language models (Li et al., 2023), activation steering for cross-lingual transfer in multilingual language models (Wang et al., 2025, Wang et al., 2025), multilingual process reward modeling (Wang et al., 2025), document-level machine translation (Wu et al., 2023, Wu et al., 2024, Wu et al., 2024), and multilingual evaluation (Wu et al., 2025).
  • Miscellaneous: Additionally, I have contributed to various other topics, including large language model evaluation (Wu and Aji, 2024), multi-modal large language models (Lyu et al., 2023, Wang et al., 2024), and recommender systems (Zhang et al., 2024).

My CV can be downloaded from here.

Education

  • Ph.D. Computer Science, Monash University, 2022 - 2025, supervised by Prof. Gholamreza (Reza) Haffari.
  • M.Eng. Information Technology, The University of Melbourne, 2016 - 2018, supervised by Prof. Trevor Cohn.
  • B.Sc. Statistics and Information Systems, The University of Sydney, 2013 - 2016.

Work Experience

  • Jun. 2025 - Present: Postdoc at The University of North Carolina at Chapel Hill, supervised by Prof. Mohit Bansal.
  • Nov. 2024 - Apr. 2025: Research Intern at Alibaba Group, supervised by Dr. Longyue Wang.
  • Jul. 2023 - Oct. 2023: Research Intern at Tencent AI Lab, supervised by Dr. Longyue Wang.
  • Apr. 2023 - Jul. 2023: Visiting Researcher at Mohamed bin Zayed University of Artificial Intelligence, supervised by Dr. Alham Fikri Aji.
  • Jul. 2020 - Jul. 2021: Research Intern at Huawei Noah’s Ark Lab, supervised by Dr. Meng Zhang.
  • Aug. 2018 - Jul. 2019: Research Engineer at JD AI Research of JD.com, Inc, supervised by Dr. Xiaodong He.

Selected Publications

You can find the complete list of my articles on my Google Scholar profile.