Mathew Monfort

I am a research scientist at the Computer Science and Artificial Intelligence Laboratory (CSAIL) at the Massachusetts Institute of Technology (MIT). Previously I was a postdoctoral associate at MIT CSAIL working with Aude Oliva, Antonio Torralba, and Wojciech Matusik.

I am currently working on deep learning approaches to scene understanding and visual navigation with the Toyota-CSAIL Research Center and the IBM-MIT Laboratory for Brain-inspired Multimedia Machine Comprehension (BM3C).

While earning my PhD I researched scalable inverse optimal control as part of the Purposeful Prediction Lab at the University of Illinois at Chicago (UIC) under Brian Ziebart.



  • We released our new dataset for video understanding, The Moments in Time Dataset.

  • Our work on "Asynchronous Data Aggregation" was presented at the 2017 ICML workshops on Lifelong Learning and Reinforcement Learning.

  • I co-organized a workshop on Learning from Demonstration in High-Dimensional Feature Spaces at the 2017 conference on Robotics: Science and Systems (RSS) with Arunkumar Byravan (UW), Jim Mainprice (MPI), Roberto Calandra (UC Berkeley), and Stefan Schaal (USC, MPI).

  • Publications

    Moments in Time Dataset: one million videos for event understanding.
    Mathew Monfort, Bolei Zhou, Sarah Adel Bargal, Alex Andonian, Tom Yan,
    Kandan Ramakrishnan, Lisa Brown, Quanfu Fan, Dan Gutfruend, Carl Vondrick, Aude Oliva
    arXiv:1801.03150, 2018. [PDF]

    A Deep Learning Approach to Identifying Shock Locations in Turbulent Combustion Tensor Fields.
    Mathew Monfort, Timothy Luciani, Jon Komperda, Brian D. Ziebart, Farzad Mashayek, G. Elisabeta Marai
    Modeling, Analysis, and Visualization of Anisotropy, Springer, 2017. [PDF]

    Asynchronous Data Aggregation for Training End to End Visual Control Networks.
    Mathew Monfort, Matthew Johnson, Aude Oliva, Katja Hofmann
    International Conference on Autonomous Agents and Multiagent Systems (AAMAS), 2017. [PDF]

    Goal-Predictive Robotic Teleoperation from Noisy Sensors.
    Christopher Schultz, Sanket Gaurav, Mathew Monfort, Lingfei Zhang, Brian Ziebart
    IEEE International Conference on Robotics and Automation (ICRA), 2017. [PDF]

    Adversarial Inverse Optimal Control for General Imitation Learning Losses and Embodiment Transfer.
    Xiangli Chen, Mathew Monfort, Brian D. Ziebart, Peter Carr
    Uncertainty in Artificial Intelligence (UAI), 2016. [PDF]

    End to End Learning for Self-Driving Cars.
    Mariusz Bojarski, Davide Del Testa, Daniel Dworakowski, Bernhard Firner, Beat Flepp, Prasoon Goyal,
    Lawrence D. Jackel, Mathew Monfort, Urs Muller, Jiakai Zhang, Xin Zhang, Jake Zhao, Karol Zieba
    arXiv:1604.07316, 2016. [PDF]

    Robust Covariate Shift Regression.
    Xiangli Chen, Mathew Monfort, Anqi Liu, Brian Ziebart
    Artificial Intelligence and Statistics (AISTATS), 2016. [PDF]

    Softstar: Heuristic-Guided Probabilistic Inference.
    Mathew Monfort, Brenden M Lake, Brian Ziebart, Patrick Lucey, Josh Tenenbaum
    Advances in Neural Information Processing Systems (NIPS), 2015. [PDF]

    Graph-based inverse optimal control for robot manipulation.
    Arunkumar Byravan, Mathew Monfort, Brian Ziebart, Byron Boots, Dieter Fox
    International Joint Conference on Artificial Intelligence (IJCAI), 2015. [PDF]

    Intent Prediction and Trajectory Forecasting via Predictive Inverse Linear-Quadratic Regulation.
    Mathew Monfort, Anqi Liu, Brian D Ziebart
    Advances in Artificial Intelligence (AAAI), 2015. [PDF]

    “Quality vs Quantity”: Improved Shot Prediction in Soccer using Strategic Features from Spatiotemporal Data.
    Patrick Lucey, Alina Bialkowski, Mathew Monfort, Peter Carr, Iain Matthews
    MIT Sloan Sports Analytics Conference, 2014. [PDF]

    Layered Hybrid Inverse Optimal Control for Learning Robot Manipulation from Demonstration.
    Arunkumar Byravan, Mathew Monfort, Brian Ziebart, Byron Boots, Dieter Fox
    NIPS Workshop on Autonomously Learning Robots, 2014. [PDF]

    Trajectory Forecasting and Intent Recognition via Predictive Inverse Linear-Quadratic Regulation.
    Mathew Monfort, Anqi Liu, Brian D Ziebart
    IROS Workshop on Assistance and Service Robotics in a Human Environment, 2014.

    Predictive Inverse Optimal Control in Large Decision Processes via Heuristic-based Search.
    Mathew Monfort, Brenden M Lake, Brian Ziebart, Josh Tenenbaum
    ICML Workshop on Robot Learning, 2014. [PDF]


    Methods in Large Scale Inverse Optimal Control.
    Mathew Monfort
    PhD Thesis. Department of Computer Science, University of Illinois at Chicago, 2016. [PDF]

    An Ensemble of Convolutional Neural Networks for the Recognition of Handwritten Digits.
    Mathew Monfort
    Master's Thesis. Department of Computer Science, Florida State University, 2011. [PDF]