publications

* denotes equal contribution

An up-to-date list is available on Google Scholar.

PhD thesis

  1. Ph.D.
    Principles of Learning in Multitask Settings: A Probabilistic Perspective
    M. Al-Shedivat
    Carnegie Mellon University, 2021

preprints

  1. arXiv
    Few-step Cofolding with All-Atom Flow Maps
    G. Scarpellini, R. Shprints, P. Holderrieth, J. Nam, P. Murugan, R. Gómez-Bombarelli, T. Jaakkola, M. Al-Shedivat, N. M. Boffi, and A. J. Bose
    arXiv preprint, 2026
  2. arXiv
    Pearl: A Foundation Model for Placing Every Atom in the Right Location
    Genesis Research Team
    arXiv preprint, 2025
  3. arXiv
    A Field Guide to Federated Optimization
    J. Wang, Z. Charles, Z. Xu, G. Joshi, H. B. McMahan, B. Aguera y Arcas, M. Al-Shedivat, and others
    arXiv preprint, 2021

conference & journal papers

2026

  1. Triangle Multiplication Is All You Need for Biomolecular Structure Representations
    J. Ouyang-Zhang, P. Murugan, D. J. Diaz, G. Scarpellini, R. S. Bowen, N. Gruver, A. Klivans, P. Krähenbühl, A. Faust, and M. Al-Shedivat
    In International Conference on Learning Representations (ICLR), 2026

2021

  1. EMNLP Oral
    Knowledge-Aware Meta-learning for Low-Resource Text Classification
    H. Yao, Y.-X. Wu, M. Al-Shedivat, and E. Xing
    In Conference on Empirical Methods in Natural Language Processing (EMNLP), 2021
  2. NAACL Oral
    Progressive Generation of Long Text with Pretrained Language Models
    B. Tan, Z. Yang, M. Al-Shedivat, E. Xing, and Z. Hu
    In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2021
  3. Federated Learning via Posterior Averaging: A New Perspective and Practical Algorithms
    M. Al-Shedivat, J. Gillenwater, E. Xing, and A. Rostamizadeh
    In International Conference on Learning Representations (ICLR), 2021
  4. AISTATS
    On Data Efficiency of Meta-learning
    M. Al-Shedivat, L. Li, E. Xing, and A. Talwalkar
    In International Conference on Artificial Intelligence and Statistics (AISTATS), 2021

2020

  1. Regularizing Black-box Models for Improved Interpretability
    G. Plumb, M. Al-Shedivat, A. Cabrera, A. Perer, E. Xing, and A. Talwalkar
    In Advances in Neural Information Processing Systems (NeurIPS), 2020
  2. Contextual Explanation Networks
    M. Al-Shedivat, A. Dubey, and E. P. Xing
    Journal of Machine Learning Research (JMLR), 2020
    Press: NLP Highlights.

2019

  1. NAACL Full Oral
    Consistency by Agreement in Zero-shot Neural Machine Translation
    M. Al-Shedivat and A.P. Parikh
    In Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2019
  2. A Baseline for Any Order Gradient Estimation in Stochastic Computation Graphs
    J.* Mao, J.* Foerster, T. Rocktäschel, M. Al-Shedivat, G. Farquhar, and S. Whiteson
    In International Conference on Machine Learning (ICML), 2019

2018

  1. ICML Full Oral
    Learning Policy Representations in Multiagent Systems
    A. Grover, M. Al-Shedivat, J.K. Gupta, Y. Burda, and H. Edwards
    In International Conference on Machine Learning (ICML), 2018
  2. ICML Full Oral
    DiCE: The Infinitely Differentiable Monte-Carlo Estimator
    J.N. Foerster, G.* Farquhar, M.* Al-Shedivat, T. Rocktäschel, E. P. Xing, and S. Whiteson
    In International Conference on Machine Learning (ICML), 2018
  3. Learning with Opponent-Learning Awareness
    J. N.* Foerster, R. Y.* Chen, M. Al-Shedivat, S. Whiteson, P. Abbeel, and I. Mordatch
    In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2018
  4. ICLR Best Paper
    Continuous Adaptation via Meta-Learning in Nonstationary and Competitive Environments
    In International Conference on Learning Representations (ICLR), 2018
    Press: WIRED, Quartz.

2017

  1. Learning Scalable Deep Kernels with Recurrent Structure
    M. Al-Shedivat, A.G. Wilson, Y. Saatchi, Z. Hu, and E. Xing
    Journal of Machine Learning Research (JMLR), 2017

2016

  1. Learning HMMs with Nonparametric Emissions via Decompositions of Continuous Matrices
    K.* Kandasamy, M.* Al-Shedivat, and E.P. Xing
    In Advances in Neural Information Processing Systems (NeurIPS), 2016
  2. ADIOS: Architectures Deep In Output Space
    M. Cissé, M. Al-Shedivat, and S. Bengio
    In International Conference on Machine Learning (ICML), 2016
  3. Frontiers
    Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines
    Frontiers in Neuroscience, 2016

2015

  1. Stochasticity Modeling in Memristors
    R. Naous, M. Al-Shedivat, and K.N. Salama
    IEEE Transactions on Nanotechnology, 2015
  2. Memristors Empower Spiking Neurons With Stochasticity
    M. Al-Shedivat, R. Naous, G. Cauwenberghs, and K. N. Salama
    IEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2015
  3. NER
    Inherently Stochastic Spiking Neurons for Probabilistic Neural Computation
    M. Al-Shedivat, R. Naous, E. Neftci, G. Cauwenberghs, and K. N. Salama
    In International IEEE/EMBS Conference on Neural Engineering (NER), 2015
  4. Learning Non-deterministic Representations with Energy-based Ensembles
    M. Al-Shedivat, E. Neftci, and G. Cauwenberghs
    In International Conference on Learning Representations (ICLR), workshop track, 2015

2014

  1. Supervised Transfer Sparse Coding
    M. Al-Shedivat, J. J.-Y. Wang, M. Alzahrani, J. Z. Huang, and X. Gao
    In AAAI conference on Artificial Intelligence, 2014

technical reports & short papers

  1. medRxiv
    Discriminative Subtyping of Lung Cancers from Histopathology Images via Contextual Deep Learning
    B.* Lengerich, M.* Al-Shedivat, A. Alavi, J. Williams, S. Labbaki, and E. Xing
    medRxiv preprint, 2020
  2. arXiv
    Learning from Imperfect Annotations
    E. A. Platanios, M. Al-Shedivat, E. Xing, and T. Mitchell
    arXiv preprint, 2020
  3. On the Complexity of Exploration in Goal-Driven Navigation
    M.* Al-Shedivat, L.* Lee, R. Salakhutdinov, and E.P. Xing
    In Relational Representation Learning Workshop, NeurIPS, 2018
  4. Contextual Explanation Networks Enable Integrated Analysis Of Imaging And Genomic Data
    B.J. Lengerich, M. Al-Shedivat, A. Dubey, A. Alavi, J. Williams, and E.P. Xing
    In 26th conference on Intelligent Systems for Molecular Biology (ISMB), 2018
  5. Evaluating Generalization in Multiagent Systems using Agent-Interaction Graphs
    A. Grover, M. Al-Shedivat, J. Gupta, Y. Burda, and H. Edwards
    In International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2018
  6. NeurIPS Spotlight
    The Intriguing Properties of Model Explanations
    M. Al-Shedivat, A. Dubey, and E.P. Xing
    In Symposium on Interpretable Machine Learning, NeurIPS, 2017
  7. NeurIPS Spotlight
    Personalized Survival Prediction with Contextual Explanation Networks
    M. Al-Shedivat, A. Dubey, and E.P. Xing
    In Machine Learning for Healthcare Workshop, NeurIPS, 2017
  8. Scalable GP-LSTMs with Semi-Stochastic Gradients
    M. Al-Shedivat, A.G. Wilson, Y. Saatchi, Z. Hu, and E.P. Xing
    In Bayesian Deep Learning Workshop, NeurIPS, 2016
  9. Learning Diverse Overcomplete Dictionaries via Determinantal Priors
    M. Al-Shedivat, Y.J. Choe, N. Spencer, and E.P. Xing
    In Geometry in Machine Learning Workshop, ICML, 2016
  10. Neural Generative Models with Stochastic Synapses Capture Richer Representations
    M. Al-Shedivat, E. Neftci, and G. Cauwenberghs
    In Computational and Systems Neuroscience (Cosyne), 2015
  11. FiO/LS
    Shaping of Femtosecond Laser Pulses with Plasmonic Crystals
    M. Shcherbakov, P. Vabishchevich, V. Zubjuk, M. Al-Shedivat, T. Dolgova, and A. Fedyanin
    In Frontiers in Optics, 2013

other theses

  1. M.Sc.
    Brain-inspired Stochastic Models and Implementations
    M. Al-Shedivat
    KAUST, 2015
  2. B.Sc.
    Фемтосекундная динамика преобразования поляризации света хиральными плазмонными метаматериалами
    Маруан Аль-Шедиват
    МГУ им. М.В. Ломоносова, 2013