Task-Restricted Symmetries in Recurrent Weight Space
S. Dräger.
ICML 2026 · Weight-Space Symmetries Workshop
Simon Dräger
sfdraeger at gmail.com
I study how neural networks compute and develop methods for analyzing complex dynamical systems.
About
I am a researcher at the Computational Neurobiology Laboratory (CNL) at the Salk Institute, led by Prof. Terry Sejnowski.
I obtained my undergraduate degree in Computer Science from University of Düsseldorf in 2022 and an M.S. in Computer Science from UC Davis in 2025.
Research Focus
Neural network dynamics
How do properties of neural networks, such as information encoded in their hidden state, change over time?
Mechanistic interpretability
What computations do neural networks perform internally?
Control theory
Using tools like Model Predictive Control (MPC) and closed-loop control, can we steer neural networks to certain outcomes?
Publications
3DifFusionDet: Diffusion Model for 3D Object Detection with Robust LiDAR-Camera Fusion
X. Xiang, S. Dräger, and J. Zhang.
ICASSP 2026 · Preprint 2023
Causal Dynamic Resonance
C. Lainscsek, P. Salami, S. Dräger, A. R. Bulsara, S. S. Cash, and T. J. Sejnowski.
PNAS · Accepted · Preprint 2025
EffiPerception: A Plug-and-Play Efficiency Enhancement Framework for 2D and 3D Perception Models
X. Xiang, S. Dräger, and J. Zhang.
PRICAI 2025 · Preprint 2024
Evaluating the Impact of Loss Function Variation in Deep Learning for Classification
S. Dräger and J. Dunkelau.
arXiv:2210.16003 · Preprint