Sepehr Dehdashtian

PhD Student in Computer Science

prof_pic.png

428 S Shaw Ln # 3208

East Lansing, MI 48824

Hi there! I’m Sepehr, currently pursuing a PhD in Computer Science at Michigan State University, with a Master’s degree in Electrical Engineering from Sharif University of Technology.

My primary focus is on ensuring fairness in machine learning models, including mitigating bias in CLIP models, exploring utility versus fairness trade-offs in datasets, and auditing models and datasets for bias. I’m also delving into the fundamentals of bias and fairness in generative AI to contribute to the development of more equitable AI systems.

If you’re interested in discussing my research or anything else, feel free to reach out via email or connect with me on social media. You can find more about me and my work on this website and my CV. Additionally, I am actively seeking research internship opportunities and would love to hear from you. Looking forward to connecting!

news

Jul 11, 2024 Thrilled to announce that I've been awarded the STEAMpower Fellowship for 2024! 🎉
Apr 01, 2024 Our paper on The Dark Side of Dataset Scaling: Evaluating Racial Classification in Multimodal Models has been accepted to FAccT 2024.
Feb 26, 2024 Our paper on Utility-Fairness Trade-Offs and How to Find Them has been accepted to CVPR 2024.
Jan 16, 2024 Our paper on FairerCLIP: Debiasing Zero‑Shot Predictions of CLIP in RKHSs has been accepted to ICLR 2024.

selected publications

  1. Preprint
    24_tpami-teaser.png
    Fairness and Bias Mitigation in Computer Vision: A Survey
    Sepehr Dehdashtian*, Ruozhen He*, Yi Li, Guha Balakrishnan, Nuno Vasconcelos, Vicente Ordonez, and Vishnu Naresh Boddeti
    Jul 2024
  2. FAccT’24
    24_facct-teaser.png
    The Dark Side of Dataset Scaling: Evaluating Racial Classification in Multimodal Models
    Abeba Birhane*, Sepehr Dehdashtian*, Vinay Uday Prabhu, and Vishnu Boddeti
    In Proceedings of the 2024 ACM Conference on Fairness, Accountability, and Transparency , Jul 2024
  3. CVPR’24
    24_cvpr-teaser.png
    Utility-Fairness Trade-Offs and How to Find Them
    Sepehr Dehdashtian, Bashir Sadeghi, and Vishnu Boddeti
    In Conference on Computer Vision and Pattern Recognition 2024 , Jun 2024
  4. ICLR’24
    24_iclr-teaser.png
    FairerCLIP: Debiasing CLIP’s Zero-Shot Predictions using Functions in RKHSs
    Sepehr Dehdashtian*, Lan Wang*, and Vishnu Boddeti
    In International Conference on Learning Representations , May 2024
  5. TMLR
    22_tmlr-teaser.png
    On Characterizing the Trade-off in Invariant Representation Learning
    Bashir Sadeghi, Sepehr Dehdashtian, and Vishnu Boddeti
    Transactions on Machine Learning Research, May 2022
    Featured Certification