Alexander Amini, PhD http://www.mit.

edu/∼amini
MIT 32-376, Cambridge, MA amini@mit.edu

Education
Massachusetts Institute of Technology (MIT) Cambridge, MA
•
Postdoctoral Research Scientist June 2022 – present
Massachusetts Institute of Technology (MIT) Cambridge, MA
•
Doctor of Philosophy (PhD); Computer Science Aug. 2017 – May 2022
Massachusetts Institute of Technology (MIT) Cambridge, MA
•
Master of Science (SM); Computer Science Aug. 2017 – Jun. 2018
Massachusetts Institute of Technology (MIT) Cambridge, MA
•
Bachelor of Science (SB); Major: EECS, Minor: Mathematics Aug. 2013 – Jun. 2017
Castleknock College Dublin, Ireland
•
Leaving Certification; Honours Concentration in Mathematics and Science Aug. 2010 – Jun. 2012

Experience
Distributed Robotics Laboratory CSAIL, MIT
•
Researcher; Advisor: Prof. Daniela Rus Aug. 2017 - Present
My research focuses on machine learning algorithms for end-to-end decision making (i.e., data-to-decision) of autonomous
systems and formulating reliable and robust uncertainty estimation for these algorithms.
NVIDIA Corporation Holmdell, NJ
•
Deep Learning Researcher; Advisor: Dr. Urs Muller Jun. 2017 - Aug. 2017
Worked with NVIDIA’s end-to-end driving team to design and develop novel confidence measures for estimating the
uncertainty of deep neural networks. My work was deployed on full-scale self-driving vehicles.
MIT 6.S191: Introduction to Deep Learning EECS, MIT
•
Organizer and Lecturer Jan. 2018, 2019, 2020, 2021, 2022
I am the lead lecturer and organizer of the course; including developing the curriculum, teaching lectures, handling
industrial sponsorship, and publishing the content online. My lectures have been viewed over 5 million times.
International Business Machines (IBM) Research Yorktown Heights, NY
•
Summer Internship; Advisor: Dr. Catherine Crawford Jun. 2016 - Sep. 2016
Developed methods for training end-to-end control models in an online and adaptive setting, using a distributed
collection of embedded devices thus accounting for vastly greater numbers of possible conditions a vehicle encounters.
Laboratory for Information & Decision Systems CSAIL, MIT
•
UROP Researcher; Advisor: Prof. Suvrit Sra Jun. 2015 - Sep. 2015
Evaluated state-of-the art gradient based optimization techniques on non-convex deep architectures, and also presented
new variant combo optimization algorithms utilizing variance reduction techniques.
Senseable City Laboratory MIT
•
Research Fellow; Advisor: Prof. Carlo Ratti Sep. 2012 - Jun. 2013
Developed new mathematical models to uncover patterns in human mobility using passive sensing modalities such as
large-scale mobile phone records, credit card transactions, and taxi trips.
CLARITY Research Dublin, Ireland
•
Internship Scholarship; Advisor: Prof. Noel O’Connor Jun. 2011 - Sep. 2011
Developed analytical and learning algorithms for big data from adaptive sensor technologies. Collected 400 GB of tennis
sensor data, developed software tools to extract features, and trained, evaluated and deployed models.

Awards
• JP Morgan Chase Graduate Research Fellowship 2021-2022
• National Science Foundation (NSF) Graduate Research Fellowship 2017-2022
• Best Overall Paper Finalist (2.5%), IEEE Robosoft 2021
Co-Learning of Task and Sensor Placement for Soft Robotics by Spielberg*, Amini*, Chin, Matusik, Rus.
• MIT Outstanding Mentor for Undergraduate Researchers 2020
Annual MIT-wide award to recognize an individual graduate or postdoctoral research mentor who has demonstrated
exceptional guidance and teaching in a research setting.
• Best Overall Paper Finalist (0.1%), IEEE ICRA 2019
Variational End-to-End Navigation and Localization by Amini, Rosman, Karaman, Rus.
• Travel Award, NeurIPS Bayesian Deep Learning 2018
Spatial Uncertainty Sampling for End-to-End Control by Amini, Soleimany, Karaman, Rus.
• Grand Prize Winner, European Union Young Scientist 2011
Top prize winning project: Tennis Sensor Data Analysis: An Automated System for Macro-motion Refinement; which
developed mathematical models for detecting the subtle differences in motion to classify and provide corrective feedback.
• Grand Prize Winner, BT Young Scientist and Technologist 2011
Top prize winner in in Ireland’s national science competition for: Tennis Sensor Data Analysis. Selected to represent the
nation of Ireland at the international level, against 38 different countries, where the work again won the top grand prize.

Selected Publications
* denotes equal contribution
1. Amini, A.*, Wang, T.*, Gilitschenski, I., Schwarting, W., Liu, Z., Han, S., Karaman, S., Rus, D. (2022). VISTA 2.0:
An open, data-driven simulator for multimodal sensing and policy learning for autonomous vehicles. IEEE
International Conference on Robotics and Automation (ICRA).
2. Wang, T.*, Amini, A.*, Schwarting, W., Gilitschenski, I., Karaman, S., Rus, D. (2022). Learning interactive driving
policies via data-driven simulation. IEEE International Conference on Robotics and Automation (ICRA).
3. Xu, Q., Ahmadi, E., Amini, A., Rus, D., Lo, A. W. (2022). Identifying and mitigating potential biases in predicting
drug approvals. Drug Safety, 45(5), 521-533.
4. Tylkin, P., Wang, T. H., Seyde, T., Palko, K., Allen, R., Amini, A., Rus, D. (2022). Autonomous Flight Arcade
Challenge: Single-and Multi-Agent Learning Environments for Aerial Vehicles. In Proceedings of the 21st
International Conference on Autonomous Agents and Multiagent Systems (pp. 1744-1746).
5. Loo, N., Hasani, R., Amini, A., Rus, D. (2022). Evolution of Neural Tangent Kernels under Benign and Adversarial
Training. Neural Information Processing Systems (NeurIPS).
6. Loo, N., Hasani, R., Amini, A., Rus, D. (2022). Efficient Dataset Distillation Using Random Feature
Approximation. Neural Information Processing Systems (NeurIPS).
7. Vorbach, C.*, Hasani, R.*, Amini, A., Lechner, M., Rus, D. (2021). Causal Navigation by Continuous-time Neural
Networks. Neural Information Processing Systems (NeurIPS).
8. Liebenwein, L.*, Hasani, R.*, Amini, A., Rus, D. (2021). Sparse flows: Pruning continuous-depth models. Neural
Information Processing Systems (NeurIPS).
9. Soleimany, A.*, Amini, A.*, Goldman, S.*, Rus, D., Bhatia, S. N., Coley, C. W. (2021). Evidential Deep Learning
for Guided Molecular Property Prediction and Discovery. ACS Central Science, 7(8), 1356-1367.
10. Liu, Z.*, Amini, A.*, Zhu, S., Karaman, S., Han, S., Rus, D. (2021). Efficient and Robust LiDAR-Based
End-to-End Navigation. IEEE International Conference on Robotics and Automation (ICRA).
11. Spielberg, A.*, Amini, A.*, Chin, L., Matusik, W., Rus, D. (2021). Co-Learning of Task and Sensor Placement for
Soft Robotics. IEEE Robotics and Automation Letters (RA-L). Best Paper Finalist: 2.5%, Joint at RA-L & Robosoft
12. Hasani, R., Lechner, M., Amini, A., Rus, D., Grosu, R. (2021). Liquid time-constant networks. AAAI Conference on
Artificial Intelligence. Oral spotlight
13. Amini, A., Schwarting, W., Soleimany, A. and Rus, D. (2020) Deep Evidential Regression. Neural Information
Processing Systems (NeurIPS).
14. Lechner, M.*, Hasani, R. M.*, Amini, A., Henzinger, T., Rus, D., Grosu, R., (2020) Neural Circuit Policies Enabling
Auditable Autonomy. Nature Machine Intelligence, In press.
15. Amini, A., Gilitschenski, I., Phillips, J., Moseyko, J., Banerjee, R., Karaman, S., Rus, D. (2020) Learning Robust
Control Policies for End-to-End Autonomous Driving from Data-Driven Simulation. IEEE Robotics and Automation
Letters (RA-L). Joint acceptance to RA-L & ICRA
16. Amini, A.*, Lipton, J.*, Daniela, R. (2020) Uncertainty Aware Texture Classification and Mapping Using Soft
Tactile Sensors. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).
 17. Hasani, R. M., Lechner, M., Amini, A., Rus, D., Grosu, R. (2020). The natural lottery ticket winner: Reinforcement
learning with ordinary neural circuits. International Conference on Machine Learning (ICML).
18. Amini, A., Rosman, G., Karaman, S., Rus, D. (2019). Variational end-to-end navigation and localization. IEEE
International Conference on Robotics and Automation (ICRA) (pp. 8958-8964). Best Paper Finalist: 0.1%
19. Amini, A.∗ , Soleimany, A.∗ , Schwarting, W., Bhatia, S., Rus, D. (2019). Uncovering and Mitigating Algorithmic
Bias through Learned Latent Structure. AAAI/ACM Conference on AI Ethics and Society (AIES).
20. Gilitschenski, I., Sahoo. R., Schwarting, W., Amini, A., Karaman, S., Rus, D. (2019) Deep Orientation Uncertainty
Learning based on a Bingham Loss. International Conference on Learning Representations (ICLR).
21. Hasani, R. M.∗ , Amini, A.∗ , Lechner, M., Naser, F., Grosu, R., Rus, D. (2018). Response Characterization for
Auditing Cell Dynamics in Long Short-term Memory Networks. International Joint Conference on Neural Networks
(IJCNN). Oral spotlight
22. Amini, A., Paull, L., Balch, T., Karaman, S., Rus, D. (2018). Learning steering bounds for parallel autonomous
systems. IEEE International Conference on Robotics and Automation (ICRA) (pp. 1-8).
23. Amini, A. (2018). Robust end-to-end learning for autonomous vehicles. Masters (SM) dissertation, Massachusetts
Institute of Technology.
24. Amini, A., Schwarting, W., Rosman, G., Araki, B., Karaman, S., Daniela, R. (2018). Variational Autoencoder for
End-to-End Control of Autonomous Driving with Novelty Detection and Training De-biasing. IEEE/RSJ
International Conference on Intelligent Robots and Systems.
25. Amini, A., Soleimany, A., Karaman, S., Rus, D. (2017). Spatial Uncertainty Sampling for End-to-End Control.
Bayesian Deep Learing at Neural Information Processing Systems (NeurIPS). Travel award: 8% and Oral spotlight:
12%
26. Yoshimura, Y., Amini, A., Sobolevsky, S., Blat, J., Ratti, C. (2017). Analysis of pedestrian behaviors through
non-invasive Bluetooth monitoring. Applied Geography, 81, 43-51.
27. Amini, A., Horn, B., Edelman, A. (2016). Accelerated Convolutions for Efficient Multi-Scale Time to Contact
Computation in Julia. arXiv preprint arXiv:1612.08825.
28. Yoshimura, Y., Amini, A., Sobolevsky, S., Blat, J., Ratti, C. (2016). Analysis of Customers Spatial Distribution
Through Transaction Datasets. In Transactions on Large-Scale Data-and Knowledge-Centered Systems XXVII (pp.
177-189). Springer, Berlin, Heidelberg.
29. Amini, A., Kung, K., Kang, C., Sobolevsky, S., Ratti, C. (2014). The impact of social segregation on human
mobility in developing and industrialized regions. EPJ Data Science, 3(1), 6.
30. Pei, T., Sobolevsky, S., Ratti, C., Amini, A., Zhou, C. (2014). Uncovering the directional heterogeneity of an
aggregated mobile phone network. Transactions in GIS, 18, 126-142.
31. Amini, A., Kung, K., Kang, C., Sobolevsky, S., Ratti, C. (2013). The differing tribal and infrastructural influences
on mobility in developing and industrialized regions. Mobile phone data for development-analysis of mobile phone
datasets for the development of Ivory Coast. Orange D4D challenge, 339. Oral spotlight: 16%
32. Amini, A. ”System and method for adaptive delivery of game balls based on player-specific performance data
analysis.” U.S. Patent No. 8,419,560. 16 Apr. 2013.
33. Amini, A. ”System and method for motion analysis and feedback with ongoing dynamic training orientation
determination.” U.S. Patent No. 13/183,306.

Teaching and Mentorship

Lead organizer and lecturer MIT
•
MIT Introduction to Deep Learning, 6.S191 Jan 2018 - present
Developed, organized, and taught MITs official introductory course on deep learning methods and applications. 2021 and
2022 MIT enrollment of 700 students; enrollment of 300+ students per year in each of 2018, 2019, 2020. Over 30,000
registered students globally across 50 countries and over 5 million lecture views.
Masters (MEng) research advisor CSAIL, MIT
•
Distributed Robotics Laboratory Sep 2019 - present
Research mentor to Master’s students to create and complete their MEng thesis and degree work.
 1. Suraj Srinivasan (2022 ): Learning morphology agnostic control of soft robots
2. Jacob Phillips (2021 ): Unsupervised latent debiasing of time-series models.
3. Elaheh Ahmadi (2021 ): Identifying and mitigating the bias in predicting drug development outcomes.
4. Matt Beveridge (2021 ): Video-consistent depth estimation for data-driven simulation, joint with I. Gilitschenski.
5. Alex Knapp (2020 ): AirGuardian: a parallel autonomy approach to self-flying planes.

Undergraduate research (UROP) advisor CSAIL, MIT

•
Distributed Robotics Laboratory Sep 2017 - present
Closely mentored 15 undergraduate students on a variety of research projects I proposed as part of my research, ranging
in themes from robotics, to machine learning, and computer vision. All students were awarded departmental or sponsored
funding for their research.

1. Sadhana Lolla (Jan 2022 - present): Robust uncertainty estimation of deep neural networks
2. Alvin Li (Jan 2021 - present): Uncertainty-aware object detection for robust feature tracking
3. Selena Zheng (Jun 2021 - present): Uncertainty-aware optimization for generalizable intelligence
4. Julia Moseyko (Sep 2018 - present): Depth estimation and reinforcement learning in data-driven simulation
5. Shinjini Ghosh (Feb 2019 - Jun 2022 ): Automating the diagnosis of sepsis from only blood-based computer vision
6. Catherine Zheng (Jan 2021 - Jan 2022 ): Model-based RL with transformers, joint with Gilitschenski, Hasani
7. Charlie Vorbach (Jan 2021 - Sep 2021 ): Causal Navigation by Continuous-time NNs, joint with R. Hasani
8. Jordan Docter (Aug 2020 - Jun 2021 ): Transformers for scalable robot learning, joint with R. Hasani
9. Natasha Maniar (Feb 2021 - Jun 2021 ): UncOpt: uncertainty-guided optimization for robust learning
10. Jacob Phillips (Jun 2018 - Feb 2021 ): Photorealistic data-driven simulation for autonomous vehicles
11. William Chen (Sep 2020 - Feb 2021 ): Multi-agent autonomous drone policy learning, joint with R. Hasani.
12. Roshni Sahoo (Sep 2019 - Oct 2020 ): Deep orientation uncertainty, joint with I. Gilitschenski, W. Schwarting.
13. Diana Voronin (May 2020 - Sep 2020 ): Building an annotation engine for generation of blood-based kymography
14. Daniela Velez (Feb 2020 - June 2020 ): Detecting minor fabric defects with machine learning
15. Baptiste Bouvier (Jan 2019 - Sep 2019 ): Attention-based learning with event-based cameras and CT-RNNs
16. Tom Dudzik (Sep 2017 - Jun 2018 ): Data-driven simulation of perception for autonomous vehicles

MIT PRIMES research advisor CSAIL, MIT

•
Distributed Robotics Laboratory
MIT PRIMES is a year-long program, in which high school students work on individual and group research projects and
participate in reading groups under the guidance of academic mentors.

1. Yuxuan Chen (2020 ): Real world learning from event-based end-to-end autonomous driving

Presentations
• TEDx MIT, Invited talk Dec 2022
• HELIOS Open Source Spotlight Seminar, Invited talk Nov 2022
• MIT Mobility Forum, Department of Civil and Environmental Engineering, Invited talk Oct 2022
• National Institute of Standards and Technology (NIST), Invited talk Aug 2022
• ICRA Workshop on Autonomous Driving, Invited talk May 2022
• Google Brain, Invited talk May 2022
• Waabi Research, Invited talk May 2022
• NVIDIA Research, Invited talk Apr 2022
• MIT, Electrical Engineering and Computer Science, Thesis Defense Apr 2022
• University of Pennsylvania, Electrical Systems Engineering, Invited talk Mar 2022
• Microsoft Research, Invited talk Feb 2022
• The Boeing Company, Invited talk Nov 2021
• CSAIL FinTech Seminar, Invited talk Oct 2021
• CVPR ROADs Workshop, Invited talk Oct 2021
• ICRA Conference, Contributed talk May 2021
• MIT Embodied Intelligence Seminar, Contributed talk Feb 2021
• NeurIPS Bayesian Deep Learning, Poster Dec 2020
• MIT Embodied Intelligence Seminar, Contributed talk Nov 2020
• NVIDIA GTC, Invited talk Sept 2020
• MIT Embodied Intelligence Seminar, Contributed talk Jul 2020
• MIT Airforce Accelerator Seminar, Contributed talk Jun 2020
• ICRA Conference, Contributed talk May 2020
• Toyota Research Institute Annual Conference, Contributed talk, Poster Jan 2020
• Machine Intelligence Community, Invited talk Nov 2019
• ICML Workshop on AI for Autonomous Driving, Oral spotlight Jun 2019
• ICML Workshop on Reinforcement Learning for Real Life Workshop, Oral spotlight Jun 2019
• ICRA Conference, Oral spotlight for Best paper award May 2019
• AAAI AIES Conference, Oral spotlight Jan 2019
• Toyota Research Institute Annual Conference, Contributed talk, Poster Jan 2019
• NeurIPS Bayesian Deep Learning, Oral spotlight, Poster Dec 2018
• IROS Conference, Contributed talk Nov 2018
• NVIDIA GTC, Invited talk Mar 2018
• Toyota Research Institute Annual Conference, Contributed talk, Poster Jan 2018
• Network Mobility Conference (NetMob), Oral spotlight May 2013
• European Union Contest for Young Scientists, Contributed talk, Poster Sep 2011
• BT Young Scientist and Technologist Competition, Poster Jan 2011

Key Skills
• Programming: Python; Tensorflow; Pytorch; OpenCV; Robot Operating System (ROS); Matlab; Java; C/C++; Unix Scripting;
OpenGL; Android/Mobile; SQL; HTML
• Machine Learning/Data Analysis: Deep Learning, including CNNs, RNNs, VAEs, GANs, Bayesian NNs, Transformers,
NeRFs; Machine Learning including SVM, KNN, Fuzzy Rules, Decision Trees, Bayes

References
Daniela Rus, rus@csail.mit.edu
•
Director, CSAIL; Andrew and Erna Viterbi Professor of EECS; Deputy Dean of Research, Schwarzman College of Computing; MIT
Sertac Karaman, sertac@mit.edu
•
Director, LIDS; Charles Stark Draper Associate Professor of Aeronautics and Astronautics; MIT
John Leonard, jleonard@mit.edu
•
Samuel C. Collins Professor of Mechanical and Ocean Engineering; MIT
Larry Jackel, larry.jackel@north-c.com
•
President, North-C Technologies
Igor Gilitschenski, gilitschenski@cs.toronto.edu
•
Assistant Professor, Department of Computer Science; University of Toronto