Andreas Plesner
YOU?
Author Swipe
View article: Light Differentiable Logic Gate Networks
Light Differentiable Logic Gate Networks Open
Differentiable logic gate networks (DLGNs) exhibit extraordinary efficiency at inference while sustaining competitive accuracy. But vanishing gradients, discretization errors, and high training cost impede scaling these networks. Even with…
View article: The Unwinnable Arms Race of AI Image Detection
The Unwinnable Arms Race of AI Image Detection Open
The rapid progress of image generative AI has blurred the boundary between synthetic and real images, fueling an arms race between generators and discriminators. This paper investigates the conditions under which discriminators are most di…
View article: Recurrent Deep Differentiable Logic Gate Networks
Recurrent Deep Differentiable Logic Gate Networks Open
While differentiable logic gates have shown promise in feedforward networks, their application to sequential modeling remains unexplored. This paper presents the first implementation of Recurrent Deep Differentiable Logic Gate Networks (RD…
View article: Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks
Mind the Gap: Removing the Discretization Gap in Differentiable Logic Gate Networks Open
Modern neural networks demonstrate state-of-the-art performance on numerous existing benchmarks; however, their high computational requirements and energy consumption prompt researchers to seek more efficient solutions for real-world deplo…
View article: Human Aligned Compression for Robust Models
Human Aligned Compression for Robust Models Open
Adversarial attacks on image models threaten system robustness by introducing imperceptible perturbations that cause incorrect predictions. We investigate human-aligned learned lossy compression as a defense mechanism, comparing two learne…
View article: Synthetic Data for Blood Vessel Network Extraction
Synthetic Data for Blood Vessel Network Extraction Open
Blood vessel networks in the brain play a crucial role in stroke research, where understanding their topology is essential for analyzing blood flow dynamics. However, extracting detailed topological vessel network information from microsco…
View article: Detecting Railway Track Irregularities with Data-driven Uncertainty Quantification
Detecting Railway Track Irregularities with Data-driven Uncertainty Quantification Open
This study addresses the critical challenge of assessing railway track irregularities using advanced machine learning techniques, specifically convolutional neural networks (CNNs) and conformal prediction. Leveraging high-fidelity sensor d…
View article: Universality Frontier for Asynchronous Cellular Automata
Universality Frontier for Asynchronous Cellular Automata Open
In this work, we investigate the computational aspects of asynchronous cellular automata (ACAs), a modification of cellular automata in which cells update independently, following an asynchronous schedule. We introduce flip automata networ…
View article: ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting
ACORD: An Expert-Annotated Retrieval Dataset for Legal Contract Drafting Open
Information retrieval, specifically contract clause retrieval, is foundational to contract drafting because lawyers rarely draft contracts from scratch; instead, they locate and revise the most relevant precedent. We introduce the Atticus …
View article: Sybil Detection using Graph Neural Networks
Sybil Detection using Graph Neural Networks Open
This paper presents SYBILGAT, a novel approach to Sybil detection in social networks using Graph Attention Networks (GATs). Traditional methods for Sybil detection primarily leverage structural properties of networks; however, they tend to…
View article: Seeing Through the Mask: Rethinking Adversarial Examples for CAPTCHAs
Seeing Through the Mask: Rethinking Adversarial Examples for CAPTCHAs Open
Modern CAPTCHAs rely heavily on vision tasks that are supposedly hard for computers but easy for humans. However, advances in image recognition models pose a significant threat to such CAPTCHAs. These models can easily be fooled by generat…
View article: Accurate Computation of the Logarithm of Modified Bessel Functions on GPUs
Accurate Computation of the Logarithm of Modified Bessel Functions on GPUs Open
Bessel functions are critical in scientific computing for applications such as machine learning, protein structure modeling, and robotics. However, currently, available routines lack precision or fail for certain input ranges, such as when…
View article: On the problem of the dynamical reactions of a rolling wheelset to real track irregularities
On the problem of the dynamical reactions of a rolling wheelset to real track irregularities Open
We investigate numerically the dynamical reactions of a moving wheelset model to real measured track irregularities. The background is to examine whether the dynamics are suitable as the input to the inverse problem: determine the true tra…
View article: Correction of Fluorescent Probe Degradation in Biodistribution Studies
Correction of Fluorescent Probe Degradation in Biodistribution Studies Open
Fluorescence microscopy can be used for evaluating distribution of medical compounds in animal tissue. Fluorescence intensity decays in time and due to scanning, but correcting for this can improve accuracy. We present a mixed-effects mode…