A brief introduction.

I am a fourth year PhD student at CSAIL, MIT studying computer vision, machine learning, and AI under Aude Oliva and Phillip Isola. I previously received degrees in Neuroscience, Physics and Math from Bates College.

I enjoy applying methods from computer science, neuroscience and cognitive science to understand and model how perception and cognition are represented in human and machine. I'm eager to give LLMs the ability and agency to carry out scientific and AI research. With the help of these AI scientists, I hope to forward a self-propagating convergence of brain & cognitive sciences and machine learning.

Some of my research interests include:

  • Computational Neuroscience
  • Representation Learning
  • Generative Models
  • Video and Event Understanding
  • LLM interpretability
  • Multimodal LLM/VLM Agents

Email: alexandonian [at] gmail.com OR andonian [at] mit.edu

CV / Google Scholar / GitHub / Twitter

Community Outreach

Some of the organizations I have worked with in the past.

Industry Experience

Places and teams I have worked

Google Blueshift/DeepMind
Amazon Science
Adobe Research
MIT-IBM Watson AI Lab


Where I've studied over the years.


Bates College

BS, Neuroscience, Physics, Math
Advisors: Jason Castro, Travis Gould

Summer 2017

Stanford University

Visiting student in NeuroAI Lab
Mentor: Dan Yamins



Principal Research Assistant
Advisor: Dr. Aude Oliva.



EECS-AI+D, Graduate Student
Schwarzman College of Computing
Advisor: Dr. Aude Oliva.


A collection of side projects, research studies, and course assignments.


An overview of my research interests, publications, etc.


    Machine Learning
    Computer Vision
    Computational Neuroscience

    Application Areas

    Medical disease detection and diagnosis
    Bioimage informatics
    Computational neuroanatomy

  • Past Groups

  • NeuroAI Lab (2017)
    Department of Computer Science
    Stanford University

    Castro Lab (2017)
    Program in Neuroscience
    Bates College

    Rosen Lab (2013)
    Department of Developmental Biology
    Harvard School of Dental Medicine

    Corkey's Lab (2012)
    Obesity Research Center
    Boston University School of Medicine

  • Recent Publications

  • Three ways to improve feature alignment for open vocabulary detection
    Relja Arandjelović*, Alex Andonian*, Arthur Mensch, Olivier J. Hénaff, Jean-Baptiste Alayrac, Andrew Zisserman
    arXiv preprint arXiv:2210.07229, (2022).
    Mass Editing Memory in a Transformer
    Kevin Meng, Arnab Sen Sharma, Alex Andonian, Yonatan Belinkov, David Bau.
    arXiv preprint arXiv:2210.07229, (2022).
    Robust Cross-Modal Representation Learning with Progressive Self-Distillation
    Alex Andonian, Shixing Chen, Raffay Hamid.
    Conference on Computer Vision and Pattern Recognition (CVPR) (oral), 2022.
    Locating and Editing Factual Associations in GPT
    Kevin Meng, David Bau, Alex Andonian, Yonatan Belinkov.
    Advances in Neural Information Processing Systems 35 (2022).
    Generative adversarial networks unlock new methods for cognitive science
    Lore Goetschalckx, Alex Andonian and Johan Wagemans.
    Trends in Cognitive Sciences, 25(9), 788-801. doi:10.1016/j.tics.2021.06.006
    Contrastive Feature Loss for Image Prediction
    Alex Andonian Taesung Park, Bryan Russell, Phillip Isola, Jun-Yan Zhu, Richard Zhang.
    AIM workshop at ICCV 2021.
    The Algonauts Project 2021 Challenge: How the Human Brain Makes Sense of a World in Motion
    Radoslaw Cichy, Kshitij Dwivedi, Benjamin Lahner, Alex Lascelles, Polina Iamshchinina, Monika Graumann, Alex Andonian, Ratan Murty, Kendrick Kay, Gemma Roig, Aude Oliva. arXiv:1905.05675, 2021. PDF Website
    Paint by Word
    David Bau*, Alex Andonian*, Audrey Cui, YeonHwan Park, Ali Jahanian, Aude Oliva, Antonio Torralba.
    arXiv:2103.10951, 2021.
    VA-RED2: Video Adaptive Redundancy Reduction
    Bowen Pan, Camilo Fosco, Alex Andonian, Rameswar Panda, Rogerio S, Feris, Yue Meng, Chung-Ching Lin, Aude Oliva.
    International Conference on Learning Representations (ICLR), 2021..
    Deepfake Caricatures: Using Artifact Amplification to Expose Doctoring
    Alex Andonian*, Camilo Fosco*, Xi Wang, Allen Lee, Aude Oliva.
    To be submitted to a 2021 computer vision conference.
    We Have So Much In Common:
    Modeling Semantic Relational Set Abstractions in Videos
    Alex Andonian*, Camilo Fosco*, Mathew Monfort, Allen Lee, Rogerio Feris, Carl Vondrick, Aude Oliva. European Conference on Computer Vision (ECCV), 2020.
    Unsupervised Learning From Video With Deep Neural Embeddings
    Chengxu Zhuang, Tianwei She, Alex Andonian, Max Sobol Mark, Daniel Yamins. Conference on Computer Vision and Pattern Recognition (CVPR), 2020.
    Spatially organized genomic and physiological heterogeneity of the olfactory bulb mitral cell layer
    Daniel Paseltiner, Henry Loeffler, Alex Andonian, Abigail Leberman, Travis J. Gould, Jason B. Castro. bioRXiv preprint https://doi.org/10.1101/2020.01.13.903823, 2020.
    The Algonauts Project: A Platform for Communication
    between the Sciences of Biological and Artificial Intelligence
    Radoslaw Martin Cichy, Gemma Roig, Alex Andonian, Kshitij Dwivedi, Benjamin Lahner, Alex Lascelles, Yalda Mohsenzadeh, Kandan Ramakrishnan, Aude Oliva. arXiv:1905.05675, 2019. PDF Website
    Ganalyze: Toward visual definitions of cognitive image properties
    Lore Goetschalckx* , Alex Andonian*, Aude Oliva, Phillip Isola.
    International Conference on Computer Vision (ICCV), 2019.
    Multi-moments in time: Learning and interpreting models for multi-action video understanding
    Mathew Monfort, Kandan Ramakrishnan, Alex Andonian, Barry A McNamara, Alex Lascelles, Bowen Pan, Dan Gutfreund, Rogerio Feris, Aude Oliva. In revision for IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2020.
    Cross-View Semantic Segmentation for Sensing Surroundings
    Bowen Pan, Jiankai Sun, Ho Yin Tiga Leung, Alex Andonian, Bolei Zhou.
    IEEE Robotics and Automation Letters, 2020.
    A deep learning based method for large-scale classification, registration, and clustering of in-situ hybridization experiments in the mouse olfactory bulb.
    Alex Andonian, Dan Paseltiner, Travis Gould, Jason Castro.
    Journal of Neuroscience Methods, 2018. PDF Code
    Moments in Time Dataset: one million videos for event understanding.
    Mathew Monfort, Alex Andonian, Bolei Zhou, Kandan Ramakrishnan, Sarah Adel Bargal, Tom Yan, Lisa Brown, Quanfu Fan, Dan Gutfruend, Carl Vondrick, Aude Oliva. IEEE Transaction on Pattern Analysis and Machine Intelligence (TPAMI), 2018.
    PDF Website Code
    N-linked glycosylation of the bone morphogenetic protein receptor type 2 (BMPR2) enhances ligand binding.
    Jonathan W. Lowery, Jose M. Amich, Alex Andonian, Vicki Rosen.
    Cellular and Molecular Life Sciences. 2013.
  • Presentations and Other Papers

    1. A Deep-Learning Pipeline for Studying Olfactory Bulb Molecular Anatomy at Genomic Scale. Alex J. Andonian, Daniel A. Paseltiner, Jason B. Castro. Presented at Society for Neuroscience. November 2017. Poster
    2. Data Driven Approaches for Investigating Molecular Heterogeneity of the Brain. A. Andonian. Mt. David Summit, Bates College, March 2017.
    3. Informatics Tools for Quantifying Intratumor Heterogeneity in Multiplexed Fluorescence Tissue Data. A. Andonian. Council on Undergraduate Research's Research Experiences for Undergraduates Symposium. National Science Foundation's Atrium, Arlington Virginia. October 2016.
    4. Scalable Informatics Tools for Investigating Intra-Tumor Heterogeneity in Breast Cancer. A. Andonian. Summer Undergraduate Research Symposium, University of Pittsburgh and Duquesne University. July 2016. PDF Poster