Kimia Hamidieh

I am a third-year PhD student at MIT, working with Marzyeh Ghassemi. My research focuses on data-centric approaches to reliable and safe AI. I am broadly interested in how choices about data—what we pretrain on, how we shape learning targets and feedback signals, and how we evaluate—affect model behavior. I build methods that turn these insights into practical ways to improve reliability and performance. Among other directions, I have previously worked on problems in uncertainty quantification, data-efficient post-training, and training data composition.

During my PhD, I have interned at Microsoft Research New England and Google DeepMind. I previously completed my M.Sc. in Computer Science from the University of Toronto and Vector Institute and B.Sc. in Computer Engineering from Sharif University of Technology.

news

Jun 01, 2025	Started research internship at Microsoft Research New England working with David Alvarez-Melis on data-centric AI.
Dec 01, 2024	Two papers accepted to NeurIPS 2024!
Jun 01, 2024	Started as a student researcher at Google DeepMind (GenAI) working on active prompt selection for online direct preference learning.

selected publications

NeurIPS

Improving Subgroup Robustness via Data Selection

Saachi Jain^*, Kimia Hamidieh^*, Kristian Georgiev^*, Andrew Ilyas, Marzyeh Ghassemi, and Aleksander Madry

Advances in Neural Information Processing Systems, 2024

arXiv BIB

@article{jain2024improving,
  title = {Improving Subgroup Robustness via Data Selection},
  author = {Jain, Saachi and Hamidieh, Kimia and Georgiev, Kristian and Ilyas, Andrew and Ghassemi, Marzyeh and Madry, Aleksander},
  journal = {Advances in Neural Information Processing Systems},
  volume = {37},
  pages = {94490--94511},
  year = {2024},
}

NeurIPS

BendVLM: Test-Time Debiasing of Vision-Language Embeddings

Walter Gerych, Haoran Zhang, Kimia Hamidieh, Eileen Pan, Maanas K Sharma, Tom Hartvigsen, and Marzyeh Ghassemi

Advances in Neural Information Processing Systems, 2024

arXiv BIB

@article{gerych2024bendvlm,
  title = {BendVLM: Test-Time Debiasing of Vision-Language Embeddings},
  author = {Gerych, Walter and Zhang, Haoran and Hamidieh, Kimia and Pan, Eileen and Sharma, Maanas K and Hartvigsen, Tom and Ghassemi, Marzyeh},
  journal = {Advances in Neural Information Processing Systems},
  volume = {37},
  pages = {62480--62502},
  year = {2024},
}

AIES

Identifying Implicit Social Biases in Vision-Language Models

Kimia Hamidieh, Haoran Zhang, Walter Gerych, Thomas Hartvigsen, and Marzyeh Ghassemi

In Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, 2024

arXiv BIB

@inproceedings{hamidieh2024identifying,
  title = {Identifying Implicit Social Biases in Vision-Language Models},
  author = {Hamidieh, Kimia and Zhang, Haoran and Gerych, Walter and Hartvigsen, Thomas and Ghassemi, Marzyeh},
  booktitle = {Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society},
  volume = {7},
  pages = {547--561},
  year = {2024},
}

ICLR

Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation

Kimia Hamidieh, Haoran Zhang, Swami Sankaranarayanan, and Marzyeh Ghassemi

In The Twelfth International Conference on Learning Representations, 2024

arXiv BIB

@inproceedings{hamidiehviews,
  title = {Views Can Be Deceiving: Improved SSL Through Feature Space Augmentation},
  author = {Hamidieh, Kimia and Zhang, Haoran and Sankaranarayanan, Swami and Ghassemi, Marzyeh},
  booktitle = {The Twelfth International Conference on Learning Representations},
  year = {2024},
}

ICLR

Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning

Natalie Dullerud, Karsten Roth, Kimia Hamidieh, Nicolas Papernot, and Marzyeh Ghassemi

In International Conference on Learning Representations, 2022

arXiv BIB

@inproceedings{dullerudfairness,
  title = {Is Fairness Only Metric Deep? Evaluating and Addressing Subgroup Gaps in Deep Metric Learning},
  author = {Dullerud, Natalie and Roth, Karsten and Hamidieh, Kimia and Papernot, Nicolas and Ghassemi, Marzyeh},
  booktitle = {International Conference on Learning Representations},
  year = {2022},
}