- Introducing RSESS: An Open Source Enumerative Sphere Shaping Implementation Coded in Rust
https://arxiv.org/abs/2402.08771
https://arxiv.org/abs/2402.08771
arXiv.org
Introducing RSESS: An Open Source Enumerative Sphere Shaping...
In this work, we present an open-source implementation of the enumerative sphere shaping (ESS) algorithm used for probabilistic constellation shaping (PCS). PCS aims at closing the shaping gap...
- FLASH: Federated Learning Across Simultaneous Heterogeneities
https://arxiv.org/abs/2402.08769
https://arxiv.org/abs/2402.08769
arXiv.org
FLASH: Federated Learning Across Simultaneous Heterogeneities
The key premise of federated learning (FL) is to train ML models across a diverse set of data-owners (clients), without exchanging local data. An overarching challenge to this date is client...
- Who is driving the conversation? Analysing the nodality of British MPs and journalists on Twitter
https://arxiv.org/abs/2402.08765
https://arxiv.org/abs/2402.08765
arXiv.org
Who is driving the conversation? Analysing the nodality of British...
Who sets the policy agenda? In this paper, we explore the roles of policy actors in agenda setting by studying their relative influence in policy-related discussions. Our approach builds on...
- A Dataset for the Detection of Dehumanizing Language
https://arxiv.org/abs/2402.08764
https://arxiv.org/abs/2402.08764
arXiv.org
A Dataset for the Detection of Dehumanizing Language
Dehumanization is a mental process that enables the exclusion and ill treatment of a group of people. In this paper, we present two data sets of dehumanizing text, a large, automatically collected...
- Enhancing Robustness of Indoor Robotic Navigation with Free-Space Segmentation Models Against Adversarial Attacks
https://arxiv.org/abs/2402.08763
https://arxiv.org/abs/2402.08763
arXiv.org
Enhancing Robustness of Indoor Robotic Navigation with Free-Space...
Endeavors in indoor robotic navigation rely on the accuracy of segmentation models to identify free space in RGB images. However, deep learning models are vulnerable to adversarial attacks, posing...
- JAMDEC: Unsupervised Authorship Obfuscation using Constrained Decoding over Small Language Models
https://arxiv.org/abs/2402.08761
https://arxiv.org/abs/2402.08761
arXiv.org
JAMDEC: Unsupervised Authorship Obfuscation using Constrained...
The permanence of online content combined with the enhanced authorship identification techniques calls for stronger computational methods to protect the identity and privacy of online authorship...
- Bayesian Strategic Classification
https://arxiv.org/abs/2402.08758
https://arxiv.org/abs/2402.08758
arXiv.org
Bayesian Strategic Classification
In strategic classification, agents modify their features, at a cost, to ideally obtain a positive classification from the learner's classifier. The typical response of the learner is to carefully...
- Learning How To Ask: Cycle-Consistency Refines Prompts in Multimodal Foundation Models
https://arxiv.org/abs/2402.08756
https://arxiv.org/abs/2402.08756
arXiv.org
Learning How To Ask: Cycle-Consistency Refines Prompts in...
When LLMs perform zero-shot inference, they typically use a prompt with a task specification, and generate a completion. However, there is no work to explore the possibility of the reverse - going...
- LLM-driven Imitation of Subrational Behavior : Illusion or Reality?
https://arxiv.org/abs/2402.08755
https://arxiv.org/abs/2402.08755
arXiv.org
LLM-driven Imitation of Subrational Behavior : Illusion or Reality?
Modeling subrational agents, such as humans or economic households, is inherently challenging due to the difficulty in calibrating reinforcement learning models or collecting data that involves...
- On-the-Fly Syntax Highlighting: Generalisation and Speed-ups
https://arxiv.org/abs/2402.08754
https://arxiv.org/abs/2402.08754
arXiv.org
On-the-Fly Syntax Highlighting: Generalisation and Speed-ups
On-the-fly syntax highlighting is the task of rapidly associating visual secondary notation values with each character of a language derivation. Research in this domain is driven by the prevalence...
- Forecasting for Swap Regret for All Downstream Agents
https://arxiv.org/abs/2402.08753
https://arxiv.org/abs/2402.08753
arXiv.org
Forecasting for Swap Regret for All Downstream Agents
We study the problem of making predictions so that downstream agents who best respond to them will be guaranteed diminishing swap regret, no matter what their utility functions are. It has been...
- Nearest Neighbor Representations of Neural Circuits
https://arxiv.org/abs/2402.08751
https://arxiv.org/abs/2402.08751
arXiv.org
Nearest Neighbor Representations of Neural Circuits
Neural networks successfully capture the computational power of the human brain for many tasks. Similarly inspired by the brain architecture, Nearest Neighbor (NN) representations is a novel...
- Towards the Detection of AI-Synthesized Human Face Images
https://arxiv.org/abs/2402.08750
https://arxiv.org/abs/2402.08750
arXiv.org
Towards the Detection of AI-Synthesized Human Face Images
Over the past years, image generation and manipulation have achieved remarkable progress due to the rapid development of generative AI based on deep learning. Recent studies have devoted...
- Automated detection of motion artifacts in brain MR images using deep learning and explainable artificial intelligence
https://arxiv.org/abs/2402.08749
https://arxiv.org/abs/2402.08749
arXiv.org
Automated detection of motion artifacts in brain MR images using...
Quality assessment, including inspecting the images for artifacts, is a critical step during MRI data acquisition to ensure data quality and downstream analysis or interpretation success. This...
- Nearest Neighbor Representations of Neurons
https://arxiv.org/abs/2402.08748
https://arxiv.org/abs/2402.08748
arXiv.org
Nearest Neighbor Representations of Neurons
The Nearest Neighbor (NN) Representation is an emerging computational model that is inspired by the brain. We study the complexity of representing a neuron (threshold function) using the NN...
- Rationality of Learning Algorithms in Repeated Normal-Form Games
https://arxiv.org/abs/2402.08747
https://arxiv.org/abs/2402.08747
arXiv.org
Rationality of Learning Algorithms in Repeated Normal-Form Games
Many learning algorithms are known to converge to an equilibrium for specific classes of games if the same learning algorithm is adopted by all agents. However, when the agents are...
- An impossibility result for strongly group-strategyproof multi-winner approval-based voting
https://arxiv.org/abs/2402.08746
https://arxiv.org/abs/2402.08746
arXiv.org
An impossibility result for strongly group-strategyproof...
Multi-winner approval-based voting has received considerable attention recently. A voting rule in this setting takes as input ballots in which each agent approves a subset of the available...
- ADS: Approximate Densest Subgraph for Novel Image Discovery
https://arxiv.org/abs/2402.08743
https://arxiv.org/abs/2402.08743
arXiv.org
ADS: Approximate Densest Subgraph for Novel Image Discovery
The volume of image repositories continues to grow. Despite the availability of content-based addressing, we still lack a lightweight tool that allows us to discover images of distinct...
- Unveiling Hidden Energy Anomalies: Harnessing Deep Learning to Optimize Energy Management in Sports Facilities
https://arxiv.org/abs/2402.08742
https://arxiv.org/abs/2402.08742
arXiv.org
Unveiling Hidden Energy Anomalies: Harnessing Deep Learning to...
Anomaly detection in sport facilities has gained significant attention due to its potential to promote energy saving and optimizing operational efficiency. In this research article, we investigate...
- SEASONS: Signal and Energy Aware Sensing on iNtermittent Systems
https://arxiv.org/abs/2402.08739
https://arxiv.org/abs/2402.08739
arXiv.org
SEASONS: Signal and Energy Aware Sensing on iNtermittent Systems
Both energy-aware, batteryless intermittent systems and signal-aware adaptive sampling algorithms (ASA) aim to maximize sensor data accuracy under energy constraints in edge devices. Intuitively,...