I’m Marten Lienen and I care about solving problems and improving efficiency with software and machine learning. Aesthetically pleasing code makes me extra happy. At the moment, I am a PhD student at TUM's DAML group working on spatiotemporal data modeling and ML+Science in general. Before that, I worked at BMW's autonomous driving campus on 3D object detection.
For quite some time, I have also been interested in the various paradigms of thinking about programming that different programming languages have to offer and I like to read obscure books about them. You can find some of my own code on my github profile.
Publications
Unfolding Time: Generative Modeling for Turbulent Flows in 4D AI4Science Workshop, ICML, 2024From Zero to Turbulence: Generative Modeling for 3D Flow Simulation International Conference on Learning Representations, 2024Add and Thin: Diffusion for Temporal Point Processes Neural Information Processing Systems, 2023torchode: A Parallel ODE Solver for PyTorch The Symbiosis of Deep Learning and Differential Equations Workshop, NeurIPS, 2022Learning the Dynamics of Physical Systems from Sparse Observations with Finite Element Networks International Conference on Learning Representations (Spotlight), 2022Scalable Optimal Transport in High Dimensions for Graph Distances, Embedding Alignment, and More International Conference on Machine Learning, 2021FLGR: Fixed Length Gists Representation Learning for RNN-HMM Hybrid-based Neuromorphic Continuous Gesture Recognition Frontiers in Neuroscience, 13 (2019)Rate-Adaptive Link Quality Estimation for Coded Packet Networks 2016 IEEE 41st Conference on Local Computer Networks (LCN)