T. Konstantin Rusch

According to our database, T. Konstantin Rusch authored at least 23 papers between 2021 and 2026.

Collaborative distances:

• Dijkstra number of four.
• Erdős number of four.

2026

The Key to State Reduction in Linear Attention: A Rank-based Perspective.

Philipp Nazari, T. Konstantin Rusch

CoRR, February, 2026

2025

Quantifying Memory Use in Reinforcement Learning with Temporal Range.

Rodney S. Lafuente Mercado, Daniela Rus, T. Konstantin Rusch

CoRR, December, 2025

Neural Low-Discrepancy Sequences.

Michael Etienne Van Huffel, Nathan Kirk, Makram Chahine, Daniela Rus, T. Konstantin Rusch

CoRR, October, 2025

The Curious Case of In-Training Compression of State Space Models.

Makram Chahine, Philipp Nazari, Daniela Rus, T. Konstantin Rusch

CoRR, October, 2025

On the optimization of discrepancy measures.

François Clément, Nathan Kirk, Art B. Owen, T. Konstantin Rusch

CoRR, August, 2025

Learning to Move in Rhythm: Task-Conditioned Motion Policies with Orbital Stability Guarantees.

Maximilian Stölzle, T. Konstantin Rusch, Zach J. Patterson, Rodrigo Pérez-Dattari, Francesco Stella, Josie Hughes, Cosimo Della Santina, Daniela Rus

CoRR, July, 2025

Learning to Dissipate Energy in Oscillatory State-Space Models.

Jared Boyer, T. Konstantin Rusch, Daniela Rus

CoRR, May, 2025

Low Stein Discrepancy via Message-Passing Monte Carlo.

Nathan Kirk, T. Konstantin Rusch, Jakob Zech, Daniela Rus

CoRR, March, 2025

Oscillatory State-Space Models.

T. Konstantin Rusch, Daniela Rus

Proceedings of the Thirteenth International Conference on Learning Representations, 2025

2024

How does over-squashing affect the power of GNNs?

Francesco Di Giovanni, T. Konstantin Rusch, Michael M. Bronstein, Andreea Deac, Marc Lackenby, Siddhartha Mishra, Petar Velickovic

Trans. Mach. Learn. Res., 2024

Relaxed Equivariance via Multitask Learning.

Ahmed A. A. Elhag, T. Konstantin Rusch, Francesco Di Giovanni, Michael M. Bronstein

CoRR, 2024

Improving Efficiency of Sampling-based Motion Planning via Message-Passing Monte Carlo.

Makram Chahine, T. Konstantin Rusch, Zach J. Patterson, Daniela Rus

CoRR, 2024

Message-Passing Monte Carlo: Generating low-discrepancy point sets via Graph Neural Networks.

T. Konstantin Rusch, Nathan Kirk, Michael M. Bronstein, Christiane Lemieux, Daniela Rus

CoRR, 2024

2023

A Survey on Oversmoothing in Graph Neural Networks.

T. Konstantin Rusch, Michael M. Bronstein, Siddhartha Mishra

CoRR, 2023

Multi-Scale Message Passing Neural PDE Solvers.

Léonard Equer, T. Konstantin Rusch, Siddhartha Mishra

CoRR, 2023

Neural Oscillators are Universal.

Samuel Lanthaler, T. Konstantin Rusch, Siddhartha Mishra

Proceedings of the Advances in Neural Information Processing Systems 36: Annual Conference on Neural Information Processing Systems 2023, 2023

Gradient Gating for Deep Multi-Rate Learning on Graphs.

T. Konstantin Rusch, Benjamin Paul Chamberlain, Michael W. Mahoney, Michael M. Bronstein, Siddhartha Mishra

Proceedings of the Eleventh International Conference on Learning Representations, 2023

2022

Graph-Coupled Oscillator Networks.

T. Konstantin Rusch, Ben Chamberlain, James Rowbottom, Siddhartha Mishra, Michael M. Bronstein

Proceedings of the International Conference on Machine Learning, 2022

Long Expressive Memory for Sequence Modeling.

T. Konstantin Rusch, Siddhartha Mishra, N. Benjamin Erichson, Michael W. Mahoney

Proceedings of the Tenth International Conference on Learning Representations, 2022

2021

Higher-Order Quasi-Monte Carlo Training of Deep Neural Networks.

Marcello Longo, Siddhartha Mishra, T. Konstantin Rusch, Christoph Schwab

SIAM J. Sci. Comput., 2021

Enhancing Accuracy of Deep Learning Algorithms by Training with Low-Discrepancy Sequences.

Siddhartha Mishra, T. Konstantin Rusch

SIAM J. Numer. Anal., 2021

UnICORNN: A recurrent model for learning very long time dependencies.

T. Konstantin Rusch, Siddhartha Mishra

Proceedings of the 38th International Conference on Machine Learning, 2021

Coupled Oscillatory Recurrent Neural Network (coRNN): An accurate and (gradient) stable architecture for learning long time dependencies.

T. Konstantin Rusch, Siddhartha Mishra

Proceedings of the 9th International Conference on Learning Representations, 2021