activity
20212026
most citedHyperCube: Implicit Field Representations of Voxelized 3D Models

2 citations · 3 across the 6 of their papers we have counts for

collaborators

7 papers

cs.LG2026

AIMing for Standardised Explainability Evaluation in GNNs: A Framework and Case Study on Graph Kernel Networks

Magdalena Proszewska, N. Siddharth

Graph Neural Networks (GNNs) have advanced significantly in handling graph-structured data, but a comprehensive framework for evaluating explainability remains lacking. Existing ev…

cs.LG2026

WavesFM: Hierarchical Representation Learning for Longitudinal Wearable Sensor Waveforms

Peng Cao, Zhijian Yang, Tennison Liu +17

Wearable sensors enable the continuous acquisition of high-resolution physiological waveforms, such as photoplethysmography and accelerometry, under free-living conditions. However…

cs.LG2025

On Designing Diffusion Autoencoders for Efficient Generation and Representation Learning

Magdalena Proszewska, Nikolay Malkin, N. Siddharth

Diffusion autoencoders (DAs) are variants of diffusion generative models that use an input-dependent latent variable to capture representations alongside the diffusion process. The…

cs.LG2025

B-XAIC Dataset: Benchmarking Explainable AI for Graph Neural Networks Using Chemical Data

Magdalena Proszewska, Tomasz Danel, Dawid Rymarczyk

Understanding the reasoning behind deep learning model predictions is crucial in cheminformatics and drug discovery, where molecular design determines their properties. However, cu…

cs.CV2023★ 1 cited

Face Identity-Aware Disentanglement in StyleGAN

Adrian Suwała, Bartosz Wójcik, Magdalena Proszewska +3

Conditional GANs are frequently used for manipulating the attributes of face images, such as expression, hairstyle, pose, or age. Even though the state-of-the-art models successful…

cs.CV2021★ 2 cited

HyperCube: Implicit Field Representations of Voxelized 3D Models

Magdalena Proszewska, Marcin Mazur, Tomasz Trzciński +1

Recently introduced implicit field representations offer an effective way of generating 3D object shapes. They leverage implicit decoder trained to take a 3D point coordinate conca…