Menu

PhD Student

Julien Siems

Postal address

Institut für Informatik
Albert-Ludwigs-Universität Freiburg
Sekretariat Hutter/Maschinelles Lernen
Georges-Köhler-Allee 074
79110 Freiburg, Germany

Office

Building 074, Room 00-014
LinkedInGoogleScholar

I am a PhD student at the University of Freiburg supervised by Prof. Frank Hutter. My research interests are in optimization and interpretability, as part of my PhD I will focus on developing interpretability methods for in-context learning applied to prior data fitted networks (PFNs).

After finishing my Masters with Frank in 2021, I gained diverse research experience during an applied science internship at AWS, as research assistant for the University of Zurich and the Technical University of Munich and most recently as a Machine Learning Researcher at Merantix Momentum.

Publications

2024

Grazzi, Riccardo; Siems, Julien; Franke, Jörg K. H.; Zela, Arber; Hutter, Frank; Pontil, Massimiliano

Unlocking State-Tracking in linear RNNs through Negative Eigenvalues Inproceedings

In: NeurIPS 2024 Workshop on Mathematics of Modern Machine Learning Workshop (M3L), 2024, (Oral Presentation).

Bhethanabhotla, Sathya Kamesh; Swelam, Omar; Siems, Julien; Salinas, David; Hutter, Frank

Mamba4Cast: Efficient Zero-Shot Time Series Forecasting with State Space Models Inproceedings

In: NeurIPS 2024 TSALM Workshop, 2024, (Spotlight Presentation).

Müller, Andreas; Siems, Julien; Nori, Harsha; Salinas, David; Zela, Arber; Caruana, Rich; Hutter, Frank

GAMformer: Exploring In-Context Learning for Generalized Additive Models Inproceedings

In: NeurIPS 2024 TRL Workshop, 2024.

Grazzi, Riccardo; Siems, Julien; Schrodi, Simon; Brox, Thomas; Hutter, Frank

Is Mamba Capable of In-Context Learning? Inproceedings

In: Proceedings of the Third International Conference on Automated Machine Learning (AutoML 2024), Methods Track, 2024.

Grazzi, Riccardo; Siems, Julien; Schrodi, Simon; Brox, Thomas; Hutter, Frank

Is Mamba Capable of In-Context Learning? Inproceedings

In: Mathematical and Empirical Understanding of Foundation Models (ME-FoMo) Workshop, 2024.

2023

Siems, Julien; Ditschuneit, Konstantin; Ripken, Winfried; Lindborg, Alma; Schambach, Maximilian; Otterbach, Johannes; Genzel, Martin

Curve Your Enthusiasm: Concurvity Regularization in Differentiable Generalized Additive Models Inproceedings

In: Thirty-seventh Conference on Neural Information Processing Systems (NeurIPS 2023), 2023.

Siems, Julien; Schambach, Maximilian; Schulze, Sebastian; Otterbach, Johannes

Interpretable Reinforcement Learning via Neural Additive Models for Inventory Management Conference

AI4ABM Workshop at ICLR 2023, 2023.

Weissteiner, Jakob; Heiss, Jakob; Siems, Julien; Seuken, Sven

Bayesian Optimization based Combinatorial Assignment Inproceedings

In: AAAI 2023, 2023.

2022

Weissteiner, Jakob; Heiss, Jakob; Siems, Julien; Seuken, Sven

Monotone-Value Neural Networks: Exploiting Preference Monotonicity in Combinatorial Assignment Inproceedings

In: IJCAI-ECAI, 2022.

Zela, Arber; Siems, Julien; Zimmer, Lucas; Lukasik, Jovita; Keuper, Margret; Hutter, Frank

Surrogate NAS Benchmarks: Going Beyond the Limited Search Spaces of Tabular NAS Benchmarks Inproceedings

In: International Conference on Learning Representations (ICLR), 2022.

2021

Siems, Julien; Klein, Aaron; Archambeau, Cedric; Mahsereci, Maren

Dynamic Pruning of a Neural Network via Gradient Signal-to-Noise Ratio Conference

AutoML Workshop at ICML 2021, 2021.

2020

Siems, Julien; Zimmer, Lucas; Zela, Arber; Lukasik, Jovita; Keuper, Margret; Hutter, Frank

NAS-Bench-301 and the Case for Surrogate Benchmarks for Neural Architecture Search Journal Article

In: NeurIPS 4th Workshop on Meta-Learning, 2020.

Zela, Arber; Siems, Julien; Hutter, Frank

NAS-Bench-1Shot1: Benchmarking and Dissecting One-shot Neural Architecture Search Inproceedings

In: International Conference on Learning Representations, 2020.

2019

Zimmermann, Roland; Siems, Julien

Faster training of Mask R-CNN by focusing on instance boundaries Journal Article

In: Computer Vision and Image Understanding, 2019.