Mengmeng Ma

I am a Ph.D. student at the University of Delaware, fortunate to be advised by Professor Xi Peng. My career goal is to advance the robustness and explainability of Machine Learning. Currently, my focus is on Multimodal Learning, particularly in addressing missing modalities; Federated Learning, where I develop methods for out-of-federation generalization; and Explainable Machine Learning, with an emphasis on rationale prediction. I am a fan of Slow Science.

Google Scholar

CV

Publications

• DEAL: Disentangle and Localize Concept-level Explanations for VLMs
  Tang Li, Mengmeng Ma, Xi Peng.
  European Conference on Computer Vision (ECCV), 2024.

• Beyond the Federation: Topology-aware Federated Learning for Generalization to Unseen Clients
  Mengmeng Ma, Tang Li, Xi Peng.
  International Conference on Machine Learning (ICML), 2024.

• Are Data-driven Explanations Robust Against Out-of-distribution Data?
  Tang Li, Fengchun Qiao, Mengmeng Ma, Xi Peng.
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023.

• Are Multimodal Transformers Robust to Missing Modality?
  Mengmeng Ma, Jian Ren, Long Zhao, Davide Testuggine, Xi Peng.
  IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022.

• SMIL: Multimodal Learning with Severely Missing Modality
  Mengmeng Ma, Jian Ren, Long Zhao, Sergey Tulyakov, Cathy Wu, Xi Peng.
  AAAI Conference on Artificial Intelligence (AAAI), 2021.

Services

Conference Reviewer:

• Annual Conference on Neural Information Processing Systems (NeurIPS), 2024

• IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2023 –2024

• International Conference on Computer Vision (ICCV), 2023

• European Conference on Computer Vision (ECCV), 2024

• British Machine Vision Conference (BMVC), 2024

• ACM International Conference on Multimedia (ACM MM), 2019–2024

Journal Reviewer:

• ACM Computing Surveys

• Neural Networks

Teaching

• Teaching Assistant for CISC 683/483 (Data Mining), Fall 2020-2021, Spring 2021-2022

• Teaching Assistant for CISC 642/442 (Computer Vision), Fall 2020

Contact

I’m always interested in hearing about opportunities to collaborate or apply research to real-world problems!
Feel free to reach out.

Email: mengma [at] udel (dot) edu
Address: 591 Collaboration Way, FinTech Innovation Hub Suite 416, Newark, DE 19713