36 citations · 120 across the 25 of their papers we have counts for
28 papers
An Exact Generate - Transform Decomposition of Small-LLM Team Scaling Across Orchestration Architectures
Blaz Bertalanic, Carolina Fortuna
Replacing one LLM agent with a collaborating team can raise accuracy, but whether scaling the team helps, and which architecture to scale, is unclear. Sweeping eight agent orchestr…
Multi-agent Scaling Across Disjunctive and Compensatory Tasks
Carolina Fortuna, Blaz Bertalanic
Multi-agent LLM systems are often expected to improve as team size increases, yet the scaling behavior may depend on task structure. Our central contribution is to introduce Steine…
Where Should Agents Live? Energy-Memory Characterization of Agentic AI for the Edge-Cloud Continuum
Carolina Fortuna, Vid Hanžel, Tim Strnad +1
As telecommunication networks evolve toward autonomous 5G-Advanced and 6G operations, agentic artificial intelligence (AI) workflows, where large language models (LLMs) execute mul…
Monotonic Kolmogorov-Arnold Networks: A Theoretical and Empirical Study of Monotonicity as an Inductive Bias
Mikhail Krasnov, Blaž Bertalanič, Carolina Fortuna
Monotonicity has been a long-running architectural inductive bias for neural networks, motivated by tabular, scientific, and economic settings where outputs are known to respond mo…
The Ringelmann Effect in Multi-Agent LLM Systems: A Scaling Law for Effective Team Size
Blaž Bertalanič, Carolina Fortuna
Inference-time multi-agent LLM scaling lacks a shared unit: counting nominal agents conflates cost with independent evidence. We derive a two-parameter scaling law $R(N) = N_\text{…
The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate
Blaž Bertalanič, Carolina Fortuna
Multi-agent debate, where teams of LLMs iteratively exchange rationales and vote on answers, is widely deployed under the assumption that peer review filters hallucinations. Yet th…
An Indoor Radio Mapping Dataset Combining 3D Point Clouds and RSSI
Ljupcho Milosheski, Kuon Akiyama, Blaž Bertalanič +2
The growing number of smart devices supporting bandwidth-intensive and latency-sensitive applications, such as real-time video analytics, smart sensing, Extended Reality (XR), etc.…
A Configuration-First Framework for Reproducible, Low-Code Machine Learning: a Localization Use Case
Tim Strnad, Blaž Bertalanič, Carolina Fortuna
As machine learning underpins more critical applications, the value of a reported result depends on whether it can be compared and repeated. In practice, this remains difficult: re…
Label-Free Concept Drift Assessment for Reliable AI in Emerging Wireless Applications
Athanasios Tziouvaras, Carolina Fortuna, George Floros +4
Machine learning models deployed in non-stationary environments degrade silently, since as the input distribution drifts their accuracy decays without an error signal and without l…
Multi-agent Reinforcement Learning-based In-place Scaling Engine for Edge-cloud Systems
Jovan Prodanov, Blaž Bertalanič, Carolina Fortuna +4
Modern edge-cloud systems face challenges in efficiently scaling resources to handle dynamic and unpredictable workloads. Traditional scaling approaches typically rely on static th…
Data Model Design for Explainable Machine Learning-based Electricity Applications
Carolina Fortuna, Gregor Cerar, Blaz Bertalanic +2
The transition from traditional power grids to smart grids, significant increase in the use of renewable energy sources, and soaring electricity prices has triggered a digital tran…
Graph Neural Networks Based Anomalous RSSI Detection
Blaž Bertalanič, Matej Vnučec, Carolina Fortuna
In today's world, modern infrastructures are being equipped with information and communication technologies to create large IoT networks. It is essential to monitor these networks…
MRM3: Machine Readable ML Model Metadata
Andrej Čop, Blaž Bertalanič, Marko Grobelnik +1
As the complexity and number of machine learning (ML) models grows, well-documented ML models are essential for developers and companies to use or adapt them to their specific use…
A Network Science Approach to Granular Time Series Segmentation
Ivana Kesić, Carolina Fortuna, Mihael Mohorčič +1
Time series segmentation assigns a label to each part of a sequence. We formulate dense univariate segmentation as node classification on a graph whose nodes are the original time…
A Representation Learning Approach to Feature Drift Detection in Wireless Networks
Athanasios Tziouvaras, Blaz Bertalanic, George Floros +3
AI is foreseen to be a centerpiece in next generation wireless networks enabling enabling ubiquitous communication as well as new services. However, in real deployment, feature dis…
Exploring Kolmogorov-Arnold Networks for Interpretable Time Series Classification
Irina Barašin, Blaž Bertalanič, Mihael Mohorčič +1
Time series classification is a relevant step supporting decision-making processes in various domains, and deep neural models have shown promising performance in this respect. Desp…
An Overview and Solution for Democratizing AI Workflows at the Network Edge
Andrej Čop, Blaž Bertalanič, Carolina Fortuna
With the process of democratization of the network edge, hardware and software for networks are becoming available to the public, overcoming the confines of traditional cloud provi…
Natural Language Interaction with a Household Electricity Knowledge-based Digital Twin
Carolina Fortuna, Vid Hanžel, Blaž Bertalanič
Domain specific digital twins, representing a digital replica of various segments of the smart grid, are foreseen as able to model, simulate, and control the respective segments. A…
Towards Data-Driven Electricity Management: Multi-Region Harmonized Data and Knowledge Graph
Vid Hanžel, Blaž Bertalanič, Carolina Fortuna
Due to growing population and technological advances, global electricity consumption, and consequently also CO2 emissions are increasing. The residential sector makes up 25% of glo…
Dealing with zero-inflated data: achieving SOTA with a two-fold machine learning approach
Jože M. Rožanec, Gašper Petelin, João Costa +5
In many cases, a machine learning model must learn to correctly predict a few data points with particular values of interest in a broader range of data where many target values are…
Deep Feature Learning for Wireless Spectrum Data
Ljupcho Milosheski, Gregor Cerar, Blaž Bertalanič +2
In recent years, the traditional feature engineering process for training machine learning models is being automated by the feature extraction layers integrated in deep learning ar…
Energy Efficient Deep Multi-Label ON/OFF Classification of Low Frequency Metered Home Appliances
Anže Pirnat, Blaž Bertalanič, Gregor Cerar +2
Non-intrusive load monitoring (NILM) is the process of obtaining appliance-level data from a single metering point, measuring total electricity consumption of a household or a busi…
XAI for Self-supervised Clustering of Wireless Spectrum Activity
Ljupcho Milosheski, Gregor Cerar, Blaž Bertalanič +2
The so-called black-box deep learning (DL) models are increasingly used in classification tasks across many scientific disciplines, including wireless communications domain. In thi…
Resource-aware Deep Learning for Wireless Fingerprinting Localization
Gregor Cerar, Blaž Bertalanič, Carolina Fortuna
Location based services, already popular with end users, are now inevitably becoming part of new wireless infrastructures and emerging business processes. The increasingly popular…