collaborators

7 papers

cs.CV2026

Rethinking the Fully Hyperbolic Vision Transformer in Polar Coordinates

Ahmad Bdeir, Niels Landwehr

Hyperbolic space can embed intrinsic hierarchies in data with low distortion due to the exponential growth of volume with distance from the origin. However, current Lorentz transfo…

cs.LG2026

NAE: Normalizing AutoEncoder

Muhammad Abdur Rafae, Niels Landwehr

We consider the setting of Normalizing flows with approximate inverses, an established paradigm spanning both full-dimensional () and bottleneck () settings, and group th…

cs.LG2026

SpikF-GO: Spiking Fourier Graph Operators for Multivariate Time Series Forecasting

Jafar Bakhshaliyev, Niels Landwehr

Spiking Neural Networks (SNNs) have emerged as an energy-efficient alternative to conventional neural networks, demonstrating strong performance in computer vision and robotics. Mo…

cs.LG2026

Sliding-Window Reordering with Overlap Averaging: A Simple Time-Domain Augmentation for Multivariate Forecasting

Jafar Bakhshaliyev, Johannes Burchert, Niels Landwehr +1

Augmentation has become a central technique for improving deep forecasting models, but classification-style transformations tend to break the coherence between the look-back window…

cs.LG2026

LAtte: Hyperbolic Lorentz Attention for Cross-Subject EEG Classification

Ahmad Bdeir, Johannes Burchert, Tom Hanika +2

Electroencephalogram (EEG) classification plays a key role in medical diagnosis and brain-computer interfaces, but remains challenging due to low signal-to-noise ratios and high in…

cs.CV2026

HexFormer: Hyperbolic Vision Transformer with Exponential Map Aggregation

Haya Alyoussef, Ahmad Bdeir, Diego Coello de Portugal Mecke +3

Data across modalities such as images, text, and graphs often contains hierarchical and relational structures, which are challenging to model within Euclidean geometry. Hyperbolic…

cs.CV2024

Robust Hyperbolic Learning with Curvature-Aware Optimization

Ahmad Bdeir, Johannes Burchert, Lars Schmidt-Thieme +1

Hyperbolic deep learning has become a growing research direction in computer vision due to the unique properties afforded by the alternate embedding space. The negative curvature a…