Publications
2024
Leveraging Low-Rank and Sparse Recurrent Connectivity for Robust Closed-Loop Control
Neehal Tumma, Mathias Lechner, Noel Loo, Ramin Hasani, Daniela Rus
International Conference on Learning Representations (ICLR), 2024 (Oral Presentation – Top 5%)
Understanding Reconstruction Attacks with the Neural Tangent Kernel and Dataset Distillation
Noel Loo, Ramin Hasani, Mathias Lechner, Alexander Amini, Daniela Rus
International Conference on Learning Representations (ICLR), 2024
Overparametrization helps offline-to-online generalization of closed-loop control from pixels
Mathias Lechner, Ramin Hasani, Alexander Amini, Tsun-Hsuan Wang, Thomas Henzinger, Daniela Rus
2024 IEEE International Conference on Robotics and Automation (ICRA), 2024
Learning with Chemical versus Electrical Synapses – Does it Make a Difference?
Monika Farsang, Mathias Lechner, David Lung, Ramin Hasani, Daniela Rus, Radu Grosu
2024 IEEE International Conference on Robotics and Automation (ICRA), 2024
2023
Gigastep – One Billion Steps per Second Multi-agent Reinforcement Learning
Mathias Lechner, Lianhao Yin, Tim Seyde, Tsun-Hsuan Wang, Wei Xiao, Ramin Hasani, Joshua Rountree, Daniela Rus
Conference on Neural Information Processing Systems (NeurIPS) Datasets & Benchmarks, 2023
On the Size and Approximation Error of Distilled Datasets
Alaa Maalouf, Murad Tukan, Noel Loo, Ramin Hasani, Mathias Lechner, Daniela Rus
Conference on Neural Information Processing Systems (NeurIPS), 2023
Interpreting Neural Policies with Disentangled Tree Representations
Tsun-Hsuan Wang, Wei Xiao, Tim Seyde, Ramin Hasani, Daniela Rus.
Conference on Robot Learning (CoRL), 2023 [link] (Oral Presentation – Top 6%)
Robust Flight Navigation Out-of-Distribution with Liquid Neural Networks
Makram Chahine*, Ramin Hasani*, Patrick D. Kao*, Aaron Ray*, Ryan Shubert, Mathias Lechner, Alexander Amini, Daniela Rus. Science Robotics, 2023 [link] [cover]
On the Forward Invariance of Neural ODEs
Wei Xiao, Tsun-Hsuan Wang, Ramin Hasani, Mathias Lechner, Daniela Rus.
International Conference on Machine Learning (ICML) 2023 [link]
Dataset Distillation with Convexified Implicit Gradients
Noel Loo, Ramin Hasani, Mathias Lechner, Daniela Rus.
International Conference on Machine Learning (ICML) 2023
Towards Cooperative Flight Control Using Visual-Attention
Lianhao Yin, Makram Chahine, Tsun-Hsuan Wang, Tim Niklas Seyde, Chao Liu, Mathias Lechner, Ramin Hasani, Daniela Rus
IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2023
Learning Stability Attention in Vision-based End-to-end Driving Policies
Tsun-Hsuan Wang, Wei Xiao, Makram Chahine, Alexander Amini, Ramin Hasani, Daniela Rus
5th Annual Learning for Dynamics & Control Conference (L4DC) 2023.
BarrierNet: Differentiable Control Barrier Functions for Learning of Safe Robot Control
Wei Xiao, Tsun-Hsuan Wang, Ramin Hasani, Makram Chahine, Alexander Amini, Xiao Li, Daniela Rus
IEEE Transactions on Robotics Journal (T-RO), 2023.
Liquid Structural State-Space Models
Ramin Hasani*, Mathias Lechner*, Tsun-Hsuan Wang, Makram Chahine, Alexander Amini, Daniela Rus.
International Conference on Learning Representations (ICLR) 2023 [link]
Infrastructure-based End-to-End Learning and Prevention of Driver Failure
Noam Buckman*, Shiva Sreeram*, Mathias Lechner, Yutong Ban, Ramin Hasani, Sertac Karaman, Daniela Rus. Accepted to IEEE 2023 International Conference on Robotics and Automation (ICRA), 2023 [Also featured at the NeurIPS 2022 Workshop on Robot Learning, 2022]
2022
PyHopper: Hyperparameter Optimization
Mathias Lechner, Ramin Hasani, Sophie Neubauer, Philipp Neubauer, Daniela Rus.
Preprint, 2022 [link]
Are All Vision Models Created Equal? A Study of the Open-Loop to Closed-Loop Causality Gap
Mathias Lechner, Ramin Hasani, Tsun-Hsuan Wang, Alexander Amini, Thomas Henzinger, Daniela Rus.
Preprint, 2022 [link]
Efficient Dataset Distillation using Random Feature Approximation
Noel Loo, Ramin Hasani, Alexander Amini, Daniela Rus.
Conference on Neural Information Processing Systems (NeurIPS), 2022
Evolution of Neural Tangent Kernels under Benign and Adversarial Training
Noel Loo, Ramin Hasani, Alexander Amini, Daniela Rus.
Conference on Neural Information Processing Systems (NeurIPS), 2022
Closed-form Continuous-time Neural Networks
Ramin Hasani*, Mathias Lechner*, Alexander Amini, Lucas Liebenwein, Aaron Ray, Max Tschaikowski, Gerald Teschl, Daniela Rus.
Nature Machine Intelligence, 2022 [link]
Entangled Residual Mappings
Mathias Lechner, Ramin Hasani, Zahra Babaiee, Radu Grosu, Daniela Rus, Thomas A. Henzinger, and Sepp Hochreiter.
Preprint, 2022 [link]
Differentiable Control Barrier Functions for Vision-based End-to-End Autonomous Driving
Wei Xiao*, Tsun-Hsuan Wang*, Makram Chahine, Alexander Amini, Ramin Hasani, Daniela Rus.
Preprint, 2022. [link]
BarrierNet: A Safety-Guaranteed Layer for Neural Networks
Wei Xiao, Ramin Hasani, Xiao Li, Daniela Rus.
Preprint, 2022. [link]
GoTube: Scalable Stochastic Verification of Continuous-Depth Models
Sophie Gruenbacher, Mathias Lechner, Ramin Hasani, Daniela Rus, Thomas Henzinger, Scott Smolka, Radu Grosu
AAAI Conference on Artificial Intelligence (AAAI), 2022. [link] [pdf]
Latent Imagination Improves Real-World Deep Reinforcement Learning
Axel Brunnbauer*, Luigi Berducci*, Andreas Brandstätter*, Mathias Lechner, Ramin Hasani, Daniela Rus, Radu Grosu
IEEE 2022 International Conference on Robotics and Automation (ICRA), 2022. [link]
2021
Sparse Flows: Pruning Continuous-depth Models
Lucas Liebenwein*, Ramin Hasani*, Alexander Amini, Daniela Rus
Conference on Neural Information Processing Systems (NeurIPS), 2021. [link]
Causal Navigation by Continuous-time Neural Networks
Charles Vorbach*, Ramin Hasani*, Alexander Amini, Mathias Lechner, Daniela Rus
Conference on Neural Information Processing Systems (NeurIPS), 2021. [link]
On-Off Center-Surround Receptive Fields for Accurate and Robust Image Classification
Zahra Babaei, Ramin Hasani, Mathias Lechner, Daniela Rus, Radu Grosu
International Conference on Machine Learning (ICML), 2021. [link]
Interactive Analysis of CNN Robustness
Stefan Sietzen, Mathias Lechner, Judy Borowski, Ramin Hasani, and Manuela Waldner.
In Computer Graphics Forum (CGF), vol. 40, no. 7, pp. 253-264. 2021.
Model-based versus Model-free Reinforcement Learning for Autonomous Racing Cars
Axel Brunnbauer*, Luigi Berducci*, Andreas Brandstätter*, Mathias Lechner, Ramin Hasani, Daniela Rus, Radu Grosu
Preprint, 2021. [link]
Adversarial Training is Not Ready for Robot Learning
Mathias Lechner, Ramin Hasani, Radu Grosu, Daniela Rus, Thomas Henzinger
IEEE 2021 International Conference on Robotics and Automation (ICRA), 2021. [link]
Liquid Time-constant Networks
Ramin Hasani*, Mathias Lechner*, Alexander Amini, Daniela Rus, Radu Grosu
35th AAAI Conference on Artificial Intelligence (AAAI), 2021. [link]
*equal contributions
On the Verification of Neural ODEs with Stochastic Guarantees
Sophie Grünbacher, Ramin Hasani, Mathias Lechner, Jacek Cyranka, Scott A. Smolka, Radu Grosu.
35th AAAI Conference on Artificial Intelligence (AAAI), 2021. [link]
2020
Neural Circuit Policies Enabling Auditable Autonomy
Mathias Lechner*, Ramin Hasani*, Alexander Amini, Thomas Henzinger, Daniela Rus, Radu Grosu
Nature Machine Intelligence, 2020. [link] [pdf]
*equal contributions
Learning Long-Term Dependencies in Irregularly-Sampled Time Series
Mathias Lechner, Ramin Hasani
Arxiv [Paper][code]
Liquid Time-constant Networks
Ramin Hasani*, Mathias Lechner*, Alexander Amini, Daniela Rus, Radu Grosu
Preprint 2020, [link]
*equal contributions
Plug-and-play Supervisory Control Using Muscle and Brain Signals for Real-time Gesture and Error Detection
Joseph DelPreto, Andres F. Salazar-Gomez, Stephanie Gil, Ramin Hasani, Frank H. Guenther, Daniela Rus
Journal of Autonomous Robots, 2020
[link]
A Natural Lottery Ticket Winner: Reinforcement Learning with Ordinary Neural Circuits
Ramin Hasani*, Mathias Lechner*, Alexander Amini, Daniela Rus, Radu Grosu
Proceedings of the International Conference on Machine Learning (ICML), 2020
*equal contributions
[link]
Interpretable Recurrent Neural Networks in Continuous-time Control Environments
Ramin Hasani
Ph.D. Dissertation, Technische Universität Wien, May 2020
[link][pdf]
Gershgorin Loss Stabilizes the Recurrent Neural Network Compartment of an End-to-end Robot Learning Scheme
Mathias Lechner*,Ramin Hasani*, Daniela Rus, Radu Grosu
IEEE 2020 International Conference on Robotics and Automation (ICRA)
*equal contributions
[link]
2019
Designing Worm-inspired Neural Networks for Interpretable Robotics Control
Mathias Lechner*,Ramin Hasani*, Manuel Zimmer, Thomas Henzinger, Radu Grosu
Proceedings of 2019 IEEE International Conference on Robotics and Automation (ICRA)
*equal contributions
[link]
Response Characterization for Auditing Cell Dynamics in Long Short-term Memory Networks
Ramin Hasani*, Alexander Amini*, Mathias Lechner, Felix Naser, Radu Grosu, Daniela Rus
IEEE 32nd International Joint Conference on Neural Networks (IJCNN), 2019
*equal contributions
[The paper was presented at the NeurIPS 2018 workshop on Interpretability and robustness (IRASL)]
[link][pdf]
A Machine Learning Suite for Machine Components’ Health-Monitoring
Ramin Hasani*, Guodong Wang*, and Radu Grosu
The Thirty-First AAAI Conference on Innovative Applications of Artificial Intelligence (AAAI-IAAI), Honolulu, Hawaii, USA, 2019
*equal contributions
2018
Re-purposing Compact Neuronal Circuit Policies to Govern Reinforcement Learning Tasks
Ramin Hasani*, Mathias Lechner*, Alexander Amini, Daniela Rus, Radu Grosu
ArXiv:1809.04423 [cs.LG]
[link][pdf]
Plug-and-Play Supervisory Control Using Muscle and Brain Signals for Real-Time Gesture and Error Detection
Joseph DelPreto, Andres F. Salazar-Gomez, Stephanie Gil, Ramin Hasani, Frank H. Guenther, Daniela Rus
14th Robotics Science and Systems (RSS) Conference, Pittsburg, USA, 2018
[link][pdf]
c302: a multiscale framework for modeling the nervous system of C. elegans
Padraig Gleeson, David Lung, Radu Grosu, Ramin Hasani, Stephen Larson
Phil. Trans. R. Soc. B 373 (1758), 20170379, 2018
[link]
OpenWorm: overview and recent advances in integrative biological simulation of C. elegans
Gopal P Sarma, Chee Wai Lee, Tom Portegys, Vahid Ghayoomie, Travis Jacobs, Bradly Alicea, Matteo Cantarelli, Michael Currie, Richard C Gerkin, Shane Gingell, Padraig Gleeson, Richard Gordon, Ramin Hasani, Giovanni Idili, Sergey Khayrulin, David Lung, Andrey Palyanov, Mark Watts, Stephen D Larson
Phil. Trans. R. Soc. B 373 (1758), 20170382, 2018
[link]
Interpretable Neuronal Circuit Policies for Reinforcement Learning Environments
Mathias Lechner*, Ramin Hasani*, and Radu Grosu *equal contributions
IJCAI/ECAI Workshop on Explainable Artificial Intelligence (XAI), Stockholm, Sweden, 2018
[link]
2017
Worm-level Control through Search-based Reinforcement Learning
Mathias Lechner, Radu Grosu, Ramin Hasani.
Deep Reinforcement Learning Symposium at the 31st Neural Information Processing Systems (NIPS) Conference, Long Beach, CA, USA, 2017.
[link] [pdf]
A Simplified Cell Network for the Simulation of C. elegans’ Forward Crawling
David Lung, Stephen Larson, Andrey Palyanov, Sergey Khayrulin, Padraig Gleeson, Manuel Zimmer, Radu Grosu, and Ramin Hasani.
Workshop on Worm’s Neural Information Processing at the 31st Neural Information Processing Systems (NIPS) Conference, Long Beach, CA, USA, 2017.
[link] [pdf]
Searching for Biophysically Realistic Parameters for Dynamic Neuron Models by Genetic Algorithms from Calcium Imaging Recording
Magdalena Fuchs, Manuel Zimmer, Radu Grosu and Ramin Hasani.
Workshop on Worm’s Neural Information Processing at the 31st Neural Information Processing Systems (NIPS) Conference, Long Beach, CA, USA, 2017.
[link] [pdf]
Compositional Neural-Network Modeling of Complex Analog Circuits
Ramin Hasani, Dieter Haerle, Christian F. Baumgartner, Alessio R. Lomuscio, and Radu Grosu.
Proceedings of 30th International Joint Conference on Neural Networks (IJCNN 2017), IEEE, Anchorage, Alaska, USA, 2017.
[link]
SIM-CE: An Advanced Simulation Platform for Studying the brain of Caenorhabditis elegans
Ramin Hasani, Victoria Beneder, Magdalena Fuchs, David Lung, and Radu Grosu.
Workshop on Computational Biology, 34th International Conference on Machine Learning (ICML), Sydney, Australia, 2017.
[link] [pdf]
Modeling a Simple Non-Associative Learning Mechanism in the Brain of Caenorhabditis elegans
Ramin Hasani, Magdalena Fuchs, Victoria Beneder, Radu Grosu.
2nd International Workshop on Biomedical Informatics with Optimization and Machine Learning (BOOM 2017), In conjunction with 26th International Joint Conference on Artificial Intelligence (IJCAI), Melbourne, Australia, 2017.
Towards Deterministic and Stochastic Computations with Izhikevich Spiking Neuron Model
Ramin Hasani, Guodong Wang, and Radu Grosu.
Proceedings of 14th International Work-Conference on Artificial Neural Networks (IWANN 2017), Springer, Cadiz, Spain, 2017. [link]
Computing with Biophysical and Hardware-efficient Neural Models
Konstantin Selyunin, Ramin Hasani, Denise Ratasich, Ezio Bartocci, and Radu Grosu.
Proceedings of 14th International Work-Conference on Artificial Neural Networks (IWANN 2017), Springer, Cadiz, Spain, 2017. [link]
An Automated Auto-encoder Correlation-based Health Monitoring and Prognostic Method for Machine Bearings
Ramin Hasani, Guodong Wang, Radu Grosu
arXiv:1703.06272 [cs.LG], 2017.
[link]
SIM-CE: An Advanced Simulink Platform for Studying the Brain of Caenorhabditis elegans
Ramin Hasani, Victoria Beneder, Magdalena Fuchs, David Lung, Radu Grosu
arXiv:1703.06270 [q-bio.NC], 2017.
[link] [pdf]
Non-Associative Learning Representation in the Nervous System of the Nematode Caenorhabditis elegans
Ramin Hasani, Magdalena Fuchs, Victoria Beneder, Radu Grosu
arXiv:1703.06264 [q-bio.NC], 2017.
[link] [pdf]
Control of the Correlation of Spontaneous Neuron Activity in Biological and Noise-Activated CMOS Artificial Neural Microcircuits
Ramin Hasani, Giorgio Ferrari, Hideaki Yamamoto, Sho Kono, Koji Ishihara, Soya Fujimori, Takashi Tanii, Enrico Prati.
arXiv:1702.07426v1 [cs.NE], 2017.
[link]
2016
Efficient Modeling of Complex Analog Integrated Circuits Using Neural Networks
Ramin Hasani, Dieter Haerle, and Radu Grosu.
12th Conference on Ph. D. Research in Microelectronics and Electronics (PRIME), Lisbon, Portugal, 2016, pp. 1-4. IEEE, 2016.
[link]
Probabilistic Reachability Analysis of the Tap-Withdrawal Circuit in Caenorhabditis elegans
Md Ariful Isla, Qinsi Wang, Ramin Hasani, Ondrej Balun, Edmund M. Clarke, Radu Grosu, and Scott A. Smolka.
18th IEEE International High-Level Design Validation and Test Workshop (HLDVT), pp. 170-177. IEEE, 2016.
[link]
Investigations on the Nervous System of Caenorhabditis elegans
Ramin Hasani, Lukas Esterle, and Radu Grosu.
39th German Conference on Artificial Intelligence (KI 2016) – Current AI Research in Austria Workshop (CAIRA), Klagenfurt, Austria, 2016.
[link]
My Theses
Ph.D. Thesis
Interpretable Recurrent Neural Networks in Continuous-time Control Environments
Ramin Hasani
Cyber-Physical-Systems Research Group, TU Wien, Feb 2016 – May 2020.
[link]
M.Sc. Thesis
Design of CMOS Silicon Neurons for Noise-Assisted Computations in Spiking Neural Networks
Ramin Hasani
Dipartimento di Elettronica, Informazione e Bioingegneria (DEIB), Politecnico di Milano, 2015.
[link]