Minh-Hao Van

AI/ML Engineer, Google

Hao.jpeg

AI/ML Engineer

Google

Hi, my name is Minh-Hao Van, and I am currently an AI/ML Engineer at Google. Before joining Google, I was a Postdoctoral Fellow in Computer Science at the University of Arkansas. I also earned my Ph.D. in Computer Science from the University of Arkansas, advised by Prof. Xintao Wu. My research interests lie at the intersection of responsible AI and AI for science, with a focus on trustworthy machine learning, large vision-language models, and foundation models for scientific discovery. In particular, I am interested in AI robustness, safety, and privacy-preserving learning, as well as resource-efficient adaptation of large models for scientific applications in areas such as materials science and biomedical engineering. I am also actively exploring autonomous AI frameworks and agentic workflows for materials discovery and property prediction. Please see my CV here.

Prior to the University of Arkansas, I earned my B.Eng degree in Computer Science with Honors from HCMC University of Technology (Bach Khoa University), VNUHCM, in 2019. During my undergraduate study, I worked on machine learning methods for predicting cryptocurrency price movements and studying the impact of social media news on price dynamics with Dr. Khuong Nguyen-An.

Feel free to contact me via email or LinkedIn if you are interested in my work.

news

Apr 30, 2026 Happy to share that our paper “Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach” was accepted to the IJCAI 2026 main conference!
Mar 27, 2026 Excited to share that our paper “Vision Language Models for Scientific Image Analysis: An Evaluation Highlighting Opportunities and Challenges” was accepted to npj Computational Materials!
Mar 1, 2026 Starting from March 2026, Minh-Hao Van began a new chapter at Google as an AI/ML engineer!
Dec 1, 2025 Cheerful news from IEEE BigData 2025: three of our papers were accepted!
Nov 1, 2025 Glad to share that our paper “Influence-based approaches for tumor classification in noisy brain MRI with deep learning and vision-language models” was accepted to JDSA!
Oct 3, 2025 Three papers were accepted at NeurIPS workshops :sparkles: (1) Fine-Tuning Vision-Language Models for Multimodal Polymer Property Prediction, accepted at AI4Mat@NeurIPS; (2) CAGUL: Cross-Modal Attention Guided Unlearning in Vision-Language Models, accepted at LockLLM@NeurIPS; (3) A Machine Learning Framework for Automated Computational Ethology Using Markerless Pose Estimation, accepted at Imageomics@NeurIPS
Jun 25, 2025 Check out our new survey of AI for materials science, covering foundation models, LLM agents, datasets and tools to develop AI foundation models for materials science tasks A Survey of AI for Materials Science: Foundation Models, LLM Agents, Datasets, and Tools :smile:
Jan 22, 2025 One paper Soft Prompting for Unlearning in Large Language Models is accepted to main conference at NAACL-2025. Congratulations! :sparkles:
Jan 15, 2025 I will server as reviewers for WWW’25, PAKDD’25 and IJCNN’25.
Sep 24, 2024 Minh-Hao was awarded the Reginald R. ‘Barney’ & Jameson A. Baxter and EECS Graduate Fellowship for the academic year 2024-2025. Congratulations! :sparkles:

selected publications

  1. npjCM
    Vision language models for scientific image analysis: an evaluation highlighting opportunities and challenges
    Prateek Verma, Minh-Hao Van, and Xintao Wu
    npj Computational Materials, 2026
  2. ICLR’26
    Property Prediction of Stacked Bilayer Materials: A Multimodal Learning Approach
    An Vuong, Minh-Hao Van, Chen Zhao, and 1 more author
    In AI for Accelerated Materials Design-ICLR 2026, 2026
  3. NAACL’25
    Soft prompting for unlearning in large language models
    Karuna Bhaila, Minh-Hao Van, and Xintao Wu
    2025
  4. BigData’25
    Fair in-context learning via latent concept variables
    Karuna Bhaila, Minh-Hao Van, Kennedy Edemacu, and 3 more authors
    In 2025 IEEE International Conference on Big Data (BigData), 2025
  5. arXiv
    Detecting and mitigating hateful content in multimodal memes with vision-language models
    Minh-Hao Van, and Xintao Wu
    arXiv preprint arXiv:2505.00150, 2025
  6. JDSA
    Influence-based approaches for tumor classification in noisy brain MRI with deep learning and vision-language models
    Minh-Hao Van, Alycia N Carey, and Xintao Wu
    International Journal of Data Science and Analytics, 2025
  7. arXiv
    A survey of AI for materials science: foundation models, LLM agents, datasets, and tools
    Minh-Hao Van, Prateek Verma, Chen Zhao, and 1 more author
    arXiv preprint arXiv:2506.20743, 2025
  8. arXiv
    Cross-Modal Attention Guided Unlearning in Vision-Language Models
    Karuna Bhaila, Aneesh Komanduri, Minh-Hao Van, and 1 more author
    arXiv preprint arXiv:2510.07567, 2025
  9. BigData’25
    A Machine Learning Framework for Automated Computational Ethology Using Markerless Pose Estimation
    Prateek Verma, Minh-Hao Van, Christopher McEnaney, and 3 more authors
    In 2025 IEEE International Conference on Big Data (BigData), 2025
  10. arXiv
    Fine-Tuning Vision-Language Models for Multimodal Polymer Property Prediction
    An Vuong, Minh-Hao Van, Prateek Verma, and 2 more authors
    arXiv preprint arXiv:2511.05577, 2025
  11. SSRN
    Selecting In-Context Learning Demonstrations Via Influence Analysis
    Vinay MS, Minh-Hao Van, and Xintao Wu
    Available at SSRN 5133763, 2025
  12. arXiv
    In-Context Learning Demonstration Selection via Influence Analysis
    S Vinay M, Minh-Hao Van, and Xintao Wu
    arXiv e-prints, 2024
  13. IJCNN’24
    Evaluating the impact of local differential privacy on utility loss via influence functions
    Alycia N Carey, Minh-Hao Van, and Xintao Wu
    In 2024 International Joint Conference on Neural Networks (IJCNN), 2024
  14. PAKDD’24
    Robust influence-based training methods for noisy brain mri
    Minh-Hao Van, Alycia N Carey, and Xintao Wu
    In Pacific-Asia Conference on Knowledge Discovery and Data Mining, 2024
  15. BigData’24
    Beyond human vision: The role of large vision language models in microscope image analysis
    Prateek Verma, Minh-Hao Van, and Xintao Wu
    In 2024 IEEE International Conference on Big Data (BigData), 2024
  16. CHASE’24
    On large visual language models for medical imaging analysis: An empirical study
    Minh-Hao Van, Prateek Verma, and Xintao Wu
    In 2024 IEEE/ACM conference on connected health: applications, systems and engineering technologies (CHASE), 2024
  17. ICDM’23
    Hint: Healthy influential-noise based training to defend against data poisoning attacks
    Minh-Hao Van, Alycia N Carey, and Xintao Wu
    In 2023 IEEE International Conference on Data Mining (ICDM), 2023
  18. arXiv
    Detecting and correcting hate speech in multimodal memes with large visual language model
    Minh-Hao Van, and Xintao Wu
    arXiv preprint arXiv:2311.06737, 2023
  19. BigData’22
    Defending evasion attacks via adversarially adaptive training
    Minh-Hao Van, Wei Du, Xintao Wu, and 2 more authors
    In 2022 IEEE International Conference on Big Data (Big Data), 2022
  20. DASFAA’22
    Poisoning attacks on fair machine learning
    Minh-Hao Van, Wei Du, Xintao Wu, and 1 more author
    In International Conference on Database Systems for Advanced Applications, 2022
  21. AIIT’20
    Deepvix: Explaining long short-term memory network with high dimensional time series data
    Tommy Dang, Hao Van, Huyen Nguyen, and 2 more authors
    In Proceedings of the 11th international conference on advances in information technology, 2020
  22. ACOMP’19
    Predicting Cryptocurrency Price Movements Based on Social Media
    Van Minh Hao, Nguyen Huynh Huy, Bo Dao, and 2 more authors
    In 2019 International Conference on Advanced Computing and Applications (ACOMP), 2019
  23. BigData’19
    Hackernets: Visualizing media conversations on internet of things, big data, and cybersecurity
    Hao Van, Huyen N Nguyen, Rattikorn Hewett, and 1 more author
    In 2019 IEEE International Conference on Big Data (Big Data), 2019