Arman Afrasiyabi
Ph.D., Researcher |

Hi! I am a postdoctoral associate at Yale University, working in the Krishnaswamy Lab. My research lies at the intersection of interpretable multi-modal deep learning, time series analysis, large language models, and representation learning, with applications in neuroscience, biology, and computer vision. Prior to Yale, I received my Ph.D. from Université Laval and Mila (Montreal-based AI Institute), advised by Jean-François Lalonde and Christian Gagné, where my research focused on representation learning and meta-learning in limited data situations. My last Ph.D. project was a collaboration with Hugo Larochelle. Prior to my Ph.D. in Canada, I was with the Image Lab and obtained my M.S. from METU, where I worked on brain decoding.
arı ©

Contact: arman.afrasiyabi@yale[dot]edu

Publications & Preprints

  1. arXiv

    Latent representation learning for multimodal brain activity translation

    Arman Afrasiyabi, Dhananjay Bhaskar, Erica L Busch, Laurent Caplette, Rahul Singh, Guillaume Lajoie, Nicholas B Turk-Browne, Smita Krishnaswamy
    Under Review, 2024
  1. arXiv

    Looking through the mind's eye via multimodal encoder-decoder networks

    Arman Afrasiyabi, Erica Busch, Rahul Singh, Dhananjay Bhaskar, Laurent Caplette, Nicholas Turk-Browne, Smita Krishnaswamy
    Center for Collaborative Arts and Media (CCAM) , 2024
  1. ICCV

    DarSwin: distortion aware radial swin transformer

    Akshaya Athwale, Arman Afrasiyabi, Justin Lague, Ichrak Shili, Ola Ahmad, Jean-François Lalonde
    International Conference on Computer Vision, 2023
  1. CVPR

    Matching feature sets for few-shot image classification

    International Conference on Computer Vision and Pattern Recognition, 2022
  1. ICCV

    Mixture-based feature space learning for few-shot image classification

    International Conference on Computer Vision, 2021
  1. ECCV Spotlight

    Associative alignment for few-shot image classification

    European Conference on Computer Vision, 2020
  1. ICASSP

    Non-euclidean vector product for neural networks

    Arman Afrasiyabi, Diaa Badawi, Baris Nasir, Ozan Yildiz, Fatoş T. Yarman Vural, A Enis Çetin
    International Conference on Acoustics, Speech and Signal Processing, 2018
  1. ICCI*CC

    A sparse temporal mesh model for brain decoding

    15th International Conference on Cognitive Informatics & Cognitive, 2016
[] see my Google Scholar for all the publications.

Reviewer

  • NeurIPS-2023, ICLR-2023, TIP-2023, TNN-2023, CVPR-2023, NeurIPS-2022, CVPR-2022, ECCV-2022, ICLR-2022, ICCV-2021, 3DV-2021, and MAIS-2021.

Talks and presentations

  • In Aug. 2023 I gave a talk on my Postdoc projects to Brain Dynamics Lab at Stanford University.
  • In Feb. 2022, I gave a talk on my PHD projects to Prof. Smita Krishnaswamy's research group at Yale.
  • At CVPR 2022, we are presenting Matching feature sets for few-shot image classification.
  • In 12th Feb. 2022, upon the invitation (invitation link) of Computer Vision Talks, I presented our MixtFSL.
  • At ICCV 2021, I am presenting Mixture-based feature space learning for few-shot... [video]
  • On 26, Feb 2021, I presented Transformers to Prof. Jean-François Lalonde's research group. [my slides]
  • In Feb 2021, I gave a presentation on PMM and Ass. Alignment at IID, Université Laval. [my slides]
  • At ECCV 2020, I presented our work “Associative Alignment for Few-shot Classification”. [video]
  • In July 2020, I gave a talk on "Advances in few-shot learning" at the IFT 6501 course. [my slides]
  • In March 2020, I gave a talk on my last research project at IID

Reports and proposal