Publications
A complete list of my publications can be found on my Google Scholar. Below is a list of selected publications:
Papers
Closed-form continuous-time neural networks
Ramin Hasani, Mathias Lechner, Alexander Amini, Lucas Liebenwein, Aaron Ray, Max Tschaikowski, Gerald Teschl, Daniela Rus. In Nature Machine Intelligence, 1-12, 2022.
[PDF], [Code], [BibTex], [Proceedings]
Pruning by Active Attention Manipulation
Sensitivity-Informed Provable Pruning of Neural Networks
Cenk Baykal*, Lucas Liebenwein*, Igor Gilitschenski, Dan Feldman, Daniela Rus. In SIAM Journal on Mathematics of Data Science 4, no. 1, 26-45, 2022.
[PDF], [Code], [BibTex], [Proceedings]
Compressing Neural Networks: Towards Determining the Optimal Layer-wise Decomposition
![[Poster]](https://lucasliebenwein.com/wp-content/uploads/2023/06/20211203_Alds_NeurIPSPoster.png){kind=link}
Sparse flows: Pruning continuous-depth models
Lucas Liebenwein, Ramin Hasani, Alexander Amini, Daniela Rus. In Advances in Neural Information Processing Systems 34, 22628-22642 (NeurIPS), 2021.
[PDF], [Code], [Poster], [BibTex], [Proceedings]
Low-Regret Active Learning
Lost in Pruning: The Effects of Pruning Neural Networks beyond Test Accuracy
Provable Filter Pruning for Efficient Neural Networks
Lucas Liebenwein*, Cenk Baykal*, Harry Lang, Dan Feldman, Daniela Rus. In International Conference on Learning Representations, 2020.
[PDF], [Code], [Slides], [Video/ICLR], [Video/Workshop], [BibTex], [Proceedings], [News Article]
Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space
Wilko Schwarting*, Tim Seyde*, Igor Gilitschenski*, Lucas Liebenwein, Ryan Sander, Sertac Karaman, Daniela Rus. In Conference on Robot Learning (CoRL), 2020.
[PDF], [Code], [Video], [BibTex], [Proceedings], [News Article]
Machine Learning-based Estimation of Forest Carbon Stocks to increase Transparency of Forest Preservation Efforts
Björn Lütjens, Lucas Liebenwein, Katharina Kramer. In NeurIPS Workshop Tackling Climate Change with Machine Learning, 2019.
[PDF], [BibTex], [Proceedings]
Data-Dependent Coresets for Compressing Neural Networks with Applications to Generalization Bounds
Cenk Baykal*, Lucas Liebenwein*, Igor Gilitschenski, Dan Feldman, Daniela Rus. In International Conference on Learning Representation (ICLR), 2019.
[PDF], [Code], [BibTex], [Proceedings]
Sampling-Based Approximation Algorithms for Reachability Analysis with Provable Guarantees
Lucas Liebenwein*, Cenk Baykal*, Igor Gilitschenski, Sertac Karaman, Daniela Rus. In Robotics: Science and Systems XIV (RSS), 2018.
[PDF], [Video], [Slides], [BibTex], [Proceedings]
Counterexample-Guided Safety Contracts for Autonomous Driving
Jonathan A DeCastro*, Lucas Liebenwein*, Cristian-Ioan Vasile, Russ Tedrake, Sertac Karaman, and Daniela Rus. In International Workshop on the Algorithmic Foundations of Robotics (WAFR), 2018.
[PDF], [Slides], [BibTex], [Proceedings]
Compositional and Contract-Based Verification for Autonomous Driving on Road Networks
Lucas Liebenwein, Wilko Schwarting, Cristian-Ioan Vasile, Jonathan DeCastro, Javier Alonso-Mora, Sertac Karaman, Daniela Rus. In International Symposium on Robotics Research (ISRR), 2017.
[PDF], [Video], [Slides], [BibTex], [Proceedings]
Theses
Efficient Deep Learning: From Theory to Practice
Contract-Based Safety Verification for Autonomous Driving
Autonomous Pairing of Distributed Flight Array Modules
Projects
This is a non-comprehensive list of projects I have worked on over the years. This list does not include any projects that are not part of the public domain.
Torchprune
A research library for pytorch-based neural network pruning, compression, and more. It contains my PhD research.
Sustainable AI
We estimate tree-sequestered carbon with deep-learning-based algorithms on satellite and drone imagery.
Distributed Flight Array
A distributed flying platform that is able to drive, dock with their peers, and fly in a coordinated fashion.
Autonomous Driving
The Toyota-CSAIL Joint Research Center is aimed at furthering the development of autonomous vehicle technologies.
Coresets
The goal of this projects is to design novel data compression techniques to accelerate popular machine learning algorithms.
Gentou
A smart bottle cage that acts as a personal coach to coach professional cyclists how to stay hydrated during races.
Lucas Liebenwein
Passionate about making machine learning more efficient and ubiquitously available to improve our everyday lives.