Past the Statevector Wall? Out-of-Core Relational Simulation and Spill Behaviour for Dense Quantum Circuits

By Andrei Ilinescu

Simulation of quantum circuits with array-like DBMSs: An Empirical Case Study of SciDB versus Relational DBMSs

By Bruno Faliszewski

Sparse-Exploration Reinforcement Learning for Control of Quantum Error Correction

By Jeroen Krijgsman

Exploiting Y-Biased Noise Correlations with a DEM-Informed Graph Neural Network Decoder for the Distance-3 Surface Code

By Matei Dumitrescu

Algorithms for Resource Exchange in Networks

Supervisors: George Iosifidis, Livia Elena Chatzieleftheriou

Intertemporal Resource Exchange: How Local Storage Shapes Decentralized Sharing Markets open_in_newPreview File

By Efe Ayna

Community-Maximising Allocation Strategies in P2P Sharing Economies

By Joeri Geuzinge

Memory-Bounded Reciprocity in Decentralized Exchange Networks

By Lars paulussen

Agents’ Strategy

By Max Eradus

Resource Exchange and Link Formation in Decentralized Networks

By Mihai Marcu

Analysis of Results in the ML Research Field

Supervisors: David Tax, Chenxu Hao, Hayley Hung, Nergis Tomen

Evaluating the Ability of Large Language Models to Classify Scientific Papers as Empirical or Theoretical using the NeurIPS Checklist

By Adam Wielinga

Analysis of results in the ML research field; Investigating the Efficacy of LLMs in Extracting Stated Research Limitations

By Alexia Predoi

Analysis of Results in the ML Research Field; How well can an LLM decide the reproducibility of a paper?

By Andrei Opriţoiu

Large Language Models for Reviewing Research Papers; Evaluating Claim-Level Completeness in Machine Learning Research

By Simona Ivanova Simeonova

Analysis of results in the ML research field; LLM assistance in peer reviewing ML papers

By Stefan Dood

Assertion Impossible: Evaluating LLMs for Generating Test Assertions

Supervisors: Annibale Panichella, Mitchell Olsthoorn

Evaluating Self-Correcting LLM Agents for Robust Test Assertion Generation

By Horia Galitianu

Evaluating the Impact of Software Context on the Quality of LLM-Generated Test Oracles

By Hugo Klijn

Beyond the Exact Match: Investigating the Relationship Between Syntactic and Semantic Equivalence in Human and LLM Test Assertions

By Ruben van der Giessen

Can Small Beat Big? Evaluating Fine-Tuned CodeT5 Models on Assertion Generation Quality and Efficiency

By Thimo van Leeuwen

An Empirical Study of Assertion Generation Strategies for LLM-Based Test Oracles

By Vanesa Mitseva

Augmenting Atomic Multicast

Supervisors: Jeremie Decouchant

BlindSkeen: Towards Coordination-Structure Privacy in Atomic Multicast via Zero-Knowledge Membership Proofs

By Amanda Andree

Atomic Multicast in Asymmetric Byzantine Quorum Systems

By Cosmin-Adrian Moldoveanu

MoveCast: An Atomic Multicast Protocol with Object Migration

By Riad Zaid

WeightCast: Accelerating Atomic Multicast with Weighted Voting

By Stanisław Malinowski

Fairly Ordered Atomic Multicast: Preventing Cross-Shard Front-Running

By Yunus-Mert Aliskan

Autotuning Geo-Distributed Systems

Supervisors: Oto Mráz, Asterios Katsifodimos

Control-Based Dynamic Data Movement for Geo-Distributed Systems

By Arpad Jakab

Autotuning Geo-Distributed Systems: Time series forecasting for resource allocation

By Frank Verkoren

Privacy in Geo-Distributed Systems

By Kevin Che

Adaptive Resource Allocation in Stateful Stream Processing: A Control-Based Autoscaling Policy for the Styx Runtime

By Mihai-Valentin Nicolae

A Contextual Bandit for Dynamic Data Movement in Detock

By Rares-Andrei Popa

Benchmarking Retrieval-Augmented Generation for Dutch General Practice Guidelines

Supervisors: Jie Yang, Yannick Ter Heerdt

Benchmarking Open-Source vs. Closed-Source LLMs for Dutch Medical Guidelines

By Abdelrahman Tageldin

Generating and Evaluating an Automated Dutch Clinical QA Benchmark Grounded in the NHG Guidelines

By Anne-Sophie Straathof

Automated Benchmark Construction for Factual Question Answering over NHG Guidelines

By Charlene Bakker

Creating a Retrieval-Augmented Generation Pipeline for the Guidelines of the Dutch College of General Practitioners

By Leander Bindt

Failure analysis of RAG in healthcare

By Nathaniel Apawti

Benchmarking the Unobserved

Supervisors: Matej Havelka, Jesse Krijthe

Applying Informal Benchmarking to the f-Sensitivity Model

By Adrians Slics

How does sample size influence Informal Benchmarking?

By Maja Czerwińska

Leave-Multiple-Out Informal Benchmarking

By Nayden Borodjiev

When the Propensity Model Is Wrong

By Roland Vizner

Coverage of Formal Omitted-Variable Bounds under Benchmark Calibration

By Viktor Popdonchev

Bridging computer science and learning science: an interdisciplinary research project

Supervisors: Rafael Bidarra, Martin Skrodzki, Xiaoqi Feng

Investigating Students’ Teamwork Experiences in Collaborative Software Projects

By Axl Jacob Mostert

Students' Experiences with Generative AI for Programming Tasks and Independent Problem-Solving

By Diman Stanimirov Uzunov

Interdisciplinary Learning in Computer Science

By Eirini Zambarta

Investigating Student Experiences with Curriculum Coherence

By Noe Narayudha Purwanto

Learning strategies students adopt during programming-heavy and theory-heavy assessments: Critical Thinking Drives Both

By Sebastian Iacovino Spitaleri

Channel Your Inner Physicist: Sense using WiFi

Supervisors: Arash Asadi, Fabian Portner

WiFi Sensing Using Environmental Context

By Andriy Teslenko

Position Robustness in WiFi-Based Human Activity Recognition

By Jokūbas Viršilas

PIPE: Teaching WiFi Sensing to Ignore Position

By Kenzo Heijman

Physics-Informed Learning for CSI-Based Sensing

By Konstantinos Baktalias

When WiFi Packets Miss a Beat

By Rune Van Huffel

CheckMate: Automated guidance and verification for paediatric drug preparation

Supervisors: Xucong Zhang, Nergis Tömen

Vision-Assisted Medication Preparation: Improving Syringe Detection Models Using Synthetic Data

By Bas Bruijnis

Geometric versus Learned Scale Localization for Volume Estimation of Handheld Syringes in Clinical Video

By Jan Maris

Automated Liquid-Line Detection in Handheld Syringe Videos

By Jorūnė Babarskaitė

Fine-Tuning Object Detection Models for Syringe Detection in Pediatric Medication Preparation Video

By Viktor Krastev

Vision Assisted Pediatric Medication Verification: OCR vs End to End Classification

By Vlad Cioculeasa

Chemistry through the computer scientist's lens

Supervisors: Sebastijan Dumančić, Reuben Gardos Reid

Substructure-Aware Program Synthesis for Automated Chemical Reaction Network Discovery

By Adam Szymaniak

Reaction Templates as a constraint in Program Synthesis of Chemical Reaction Networks

By Alexandru-Daniel Dumitru

From Post-Validation to Grammar-Level Pruning: Valence Constraints for Molecule Synthesis

By Midas van Veen

Bond-Energy-Guided Program Synthesis for Chemical Reaction Network Discovery

By Thomas Bood

Database-Guided Program Synthesis of Chemical Reaction Networks

By Tymon Jastrzemski

Computational Modeling of Optical Effects in Gaussian Splatting Representations

Supervisors: Michael Weinmann, Emir Demirović

Post-Training Depth of Field in 3D Gaussian Splatting

By Adam Sztanó

Specular reflection and Mirror Insertion in Learned 3D Gaussian Scene Representations

By Arnon Zandt

Through the Looking Glass: Refractive Gaussian Splatting for Transparent Container Reconstruction

By Joan Llanos

ReLightGS: Relighting Existing 3D Gaussian Splatting Scenes Without Retraining

By Kaan Altıntaş

CTRL3DGS: Controlling Sensitive Information in 3D Gaussian Splatting

By Olaf Herman

Concurrency and Async Practices in Real-World Rust

Supervisors: Andreea Costea, Ruben Backx

Asynchronous Programming in Rust

By Benjamin Dockx

Concurrency and Async Practices in Real-World Rust: How are lock-free and atomic-based concurrency techniques used in Rust crates?

By David Potskhishvili

Empirical Analysis of Rayon Usage in Rust

By Fedrick Rosellon Prakoso

Understanding Shared-Memory Concurrency Usage in Rust Systems

By Lotte Trijbels

Message Passing in Rust Applications

By Mare Pegels

Constraint Programming Algorithms for NPHard Problems

Supervisors: Emir Demirović, Imko Marijnissen

Articulation-Based Propagation for the Circuit Constraint: Implementation and Evaluation in the Pumpkin LCG Solver

By Ágoston Szabó

Propagating Regular Counting with Lazy Clause Generation: DFA vs counter-DFA for finite domain satisfaction problems

By Daniël Ravensbergen

Strong Bridges for the Circuit Constraint

By Martijn van Leest

AllDifferent inside Circuit: An Experimental Evaluation of Propagation strength and Explanation quality inside Lazy Clause Generation

By Mireia Carrió Cortada

NFA vs DFA Representations for the Regular Constraint in Lazy Clause Generation: A Comparative Evaluation

By Ross Mackay

DDoS amplification honeypots

Supervisors: Harm Griffioen

Analyzing the CoAP DDoS Amplification Attack Ecosystem: A Honeypot Study

By Anton Kalpakchiev

The Modern Abuse of Network Time Protocol in Denial of Service Attacks

By Duncan Hill

Catalogued but Dormant: A Honeypot Measurement of Residual Memcached Amplification Abuse

By Maxim Hájek

DNS Amplification Attacks in the Wild

By Ruben van Unen

Monitoring and Analyzing SSDP DDoS Amplification Attacks

By Tim Guldenmundt

Data quality improvement through data cleaning and augmentation methods

Supervisors: Rihan Hai, Yuandou Wang

Benchmarking Multivariate Time-Series Imputation in 6G Networks

By Alessandro Neri

Imputing Missing Values in 6G Datasets with Tabular Methods

By Kenneth Chan

Outlier and Anomaly-Handling for 6G Wireless

By Matei-Alexandru Stanescu

Tabular and Time-Series Position Encodings in 6G Network Data

By Pelayo Fernández Luengo

Evaluating Tabular and Time-Series Data Augmentation for 6G-Relevant Network-Performance Regression

By Quinton den Haan

Deep-network Problem Archetypes

Supervisors: David Tax, Casper van Engelenburg

Content Is All You Select: Isolating the Selective-Routing Inductive Bias of the Transformer

By Bruno Romero Pérez

First Things First: Isolating the Order-Sensitivity Inductive Bias of LSTMs

By Maurice Fifis

Topological Blindness in Deep Learning: Isolating the Relational Inductive Bias of Graph Convolutional Networks

By Nicholas Hammer

The Parallel Diagonal Dataset: A CNN Problem Archetype

By Pelle van der Knaap

Breaking Under Pressure? Scalability and Robustness of Kolmogorov-Arnold Networks

By Runan Han

Deliberative AI: how can LLM-based conversational agents support reflections and consensus in multi-stakeholder decision-making for public safety?

Supervisors: Willem-Paul Brinkman, Michaël Grauwde

Extracting Value, Value Tensions, and Points of Agreement From Deliberation

By Ananya Singh

Scaling Deliberative-Quality Measurement with Large Language Models

By Feiyang Liu

Comparing Local LLM-Based Extraction of Stakeholder Values for Value Model Visualization in Deliberations

By Maximiliaan van der Veek

How to design post-reflection dialogue from transcripts using the identified values, value tensions, and consensus points?

By Victor-Emanuel Clătici

Detecting osteophytes in hip X-ray images with weakly supervised learning

Supervisors: Gijs van Tulder, Jesse Krijthe

Optimizing labeling

By Alvin Ye

Annotation-Efficient Osteophyte Severity Estimation in Hip X-rays

By David-Andrei Gogoana

Evaluating Baseline and Anatomically Guided Preprocessing for Weakly Supervised Hip Osteophyte Classification

By Ege Yarar

Anatomical Priors for Weakly Supervised Osteophyte Detection and Localization in Hip X-rays

By Iulian-Mihai Onea

Landmark-Based Anatomical Priors as Penalty Masks in Weakly Supervised Learning

By Michel Chen

Efficient Auditory Coding: Auditory Kernels

Supervisors: Jorge Martinez, Dimme de Groot

Efficient Auditory Coding under Reverberation: Effects of Reverberation on Sparse Auditory Kernel Representations of Speech

By Andrei-Rares Patrut

Efficient Auditory Coding in Speech Categorization

By Edwin van der Heijden

Auditory kernels informed by cochlear processing

By Mihai Bratu

Scaling Auditory Kernel Dictionaries: The Sparsity-Fidelity Trade-off in Speech Reconstruction

By Prarthana Badiger

Auditory Efficient Coding for Bat Vocalisations

By Tom Huisman

Efficient Embedded Intelligence

Supervisors: Qing Wang, Braden Refalo, Nitish Kumar

Through-Screen Finger Localization and Tracking using Reflected Light

By Andrei Grigore Croitoru

Efficient Embedded Intelligence: Exploring the Width-Precision Trade-Off in Binary-Quantized Vision Transformers

By Ivar van Loon

Transformer Inference using MAD vs LUT Kernels

By Mustafa Batu Eren

Training Strategies for Binary/Ternary Neural Networks

By Robin Kiemes

Multi-Object State Estimation using Probabilistic Belief-Based Trackers

By Vitalii Mashkov

Efficient learning through programmatic representations

Supervisors: Sebastijan Dumančić, Dekel Zak

How can we better find the matches between input and output objects in BEN?

By Alexandra Zaghăr

Improving transformation search in BEN

By Daria Condratov

Seeing the Gaps: Improving Object Segmentation for Abstract Visual Reasoning in Julia

By Franciszek Howard

Anytime Program Synthesis for the BEN ARC Solver

By Jakub Florek

Optimized Concept Learning in BEN: Better identifying when transformations apply in a program synthesis agent

By Jonas Duifs

Enhancing Financial Algorithms With Machine Learning Techniques

Supervisors: Fenghui Yu, Frans Oliehoek

Enhancing Pairs Trading with Reinforcement-Learning Constrained Portfolio Optimization

By Cristian Petre-Luca

Reinforcement Learning for Regime-Dependent Optimal Stopping in Pairs Trading

By Mihail Bankov

Multiple Pairs Trading for Portfolio Optimization with Reinforcement Learning

By Radoslav Georgiev

Regime-Switching Reinforcement Learning for Portfolio Allocation in Pairs Trading

By Tsvetelina Ilieva

Cointegration Aware Pairs Trading with Reinforcement Learning Based Optimal Stopping

By Tudor Pagu

Evaluating LLM Performance on Malware Analysis Across Code Representations

Supervisors: Soham Chakraborty, Przemyslaw Pawelczak

Chain-of-Thought LLM-Based Code Translation

By Blago Gunev

Malware-Domain Continued Pre-Training for Binary Malware Classification

By Costin Teodorescu

Can LLMs Consistently Describe Programs Across Source Code, Assembly, and Binary Representations?

By Matīss Bērziņš

LLM-driven Malware Analysis across Code Representations

By Sil Folkertsma

LLM-Based Autonomous Agents for Dynamic Malware Analysis

By Thomas Crull

Evaluating LLM-Based Test Generation for Libraries Across Code Representations

Supervisors: Sebastian Proksch, Cathrine Paulsen

LLM-Based Unit Test Generation Without Source Code

By Anna Glodek

How does LLM-based test generation for Java libraries perform when full source code is available?

By Cao Minh Nguyen

LLM Test Generation for Java Libraries in Low Context Settings

By Ipshit Raychaudhuri

LLM-Based Test Generation from Bytecode

By Julian Overmars

Experimenting with different clustering algorithms for energy system optimization

Supervisors: Maaike Elgersma, Germán Morales España

Improving Time Series Aggregation in Capacity-Expansion Models through Per-Cluster Artificial Worst-Case Periods

By Alexandru Theodor Tarcuta

Experimenting with Blended Weights and Extreme Representative Periods for Energy System Optimization

By Georgios Kalliakmanis Danassis

Real Worst-Case Period Selection in Time Series Aggregation for Energy System Planning

By Naman Choudhary

Selecting Real Best-Case Representative Periods for Energy System Optimization

By Noam Dickmann

Impact of Considering Artificial Worst-Case Scenarios Within Clustering Algorithms

By Roman Petar Luka Novosel

Exploring Contextual Cues for Audio-visual Emotion Recognition

Supervisors: Sayak Mukherjee, Bernd Dudzik

Situation Context in Context-Aware Emotion Recognition

By Aksu Kaypmaz

Subjectivity in Emotional Perception: Systematic Review on the Influence of Perceiver Characteristics

By Anastasia Rokoma

Sender Context in Contemporary Emotion Recognition Systems and Databases: a Systematic Review

By Christo Vasilev

What are specific cues and traits within the sender’s context that shape human emotion expression and how do these cues influence and bias emotion perception?

By Georges Ataya

Beyond the Face: A Taxonomy of Situation Context Cues in Audio-Visual Emotion Perception

By Teodor Neagoe

Exploring the Acceptance Criteria for AI Chatbots for Human-Centered Task Training in Engineering Education

Supervisors: Gosia Migut, Aleksander Buszydlik

Good Enough to Talk To? Exploring the Acceptance and Social Presence of AI Chatbots for Human-Centered Task Training in Electrical Engineering Education

By Behdad Etezadi

Good Enough to Talk To? Perceived Usefulness and Social Confidence development in a GenAI Simulated Team Interaction Study

By Ioana Forfotă

Simulating Stakeholders: Design Students’ Acceptance of and Empathy Towards LLM-Based Roleplay for Design Interview Education

By Manu Looij

Simulating Stakeholders: Generative AI Chatbots in Architecture Education Perceived Usefulness and Diversity Awareness in a Simulated Interview Study

By Ruxandra Stoica

Fault Localization in LLM-Based Multi-Agent Systems

Supervisors: Burcu Kulahcioglu Ozkan, Annibale Panichella, Zahra Seyedghorban

Interaction Pattern-Based Fault Localization in Multi-Agent Systems: Correlating Agent Execution Sequences with System Failures

By Bogdan-Stelian Duminica

Can Timing Localize Agent Failures?: Incorperating a temporal dimension into spectrum-based fault localization for LLM multi-agent systems

By Hein Schouwenaars

Spectrum-based Fault Localization for LLM-based Multi-Agent Systems: Identifying Faulty Agent Roles through Spectrum Analysis of Execution Traces

By Le Kha Dan Nguyen

Specification-Based Fault Localization for LLM-Based Multi-Agent Systems

By Mete Aksoy

Fault Localization in LLM-Based Multi-Agent Systems: Scope-Guided LLM Judging for Responsible-Agent and Failure-Step Attribution

By Yavor Pachedzhiev

Fostering Responsible Opinion Formation Among Young Adults in the Age of Generative AI

Supervisors: Ujwal Gadiraju, Esra de Groot, Marije van Dalen, Shreyan Biswas

Can AI and Media Literacy Guidance Improve AI-Generated Content Detection?

By Iustin-Nicolae Tudor

Trust in Information in the Age of Generative AI

By Jeremiasz Drohomirecki

When AI Flatters Too Much: An Exploratory Study into Trust, Perceived Trustworthiness, and Opinion Formation on Simulated Users

By Melissa Hu

Too Distracted to Think Straight? How Does External Cognitive Load Affect Young Adults' Ability to Evaluate AI-Generated Content?

By Wojciech Glinkowski

Hashing in Quantum Decision Diagrams

Supervisors: Tim Coopmans, Juul Sanders

Specializing the hash table of a quantum decision diagram simulator for graph states

By Antoni Spaanderman

Hashing in Quantum Decision Diagrams

By Caspar Backx

Efficient Node Lookup in Quantum Decision Diagrams

By Lukas Milieška

Beyond General-Purpose Hashing: Circuit-Driven Unique-Table Design for QMDD Simulation

By Maria Zmpainou

Hashing in Quantum Decision Diagrams: Hash-Table Design for QMDD Simulation of Grover's Algorithm with SAT Oracles

By Matei Aruxandei

How is it possible machines can learn from malware images?

Supervisors: Tom Viering, Akash Amalan

An analysis of different xAI methods for explaining malware image classifications

By Bram de Jonge

Why Does Aggressive Resizing Preserve Malware Image Classification Performance?

By Cristina Mitu

Malware Through the Lens of Computer Vision

By Martim Lopes Cardeira

Classifying Packed Malware with Convolutional Neural Networks

By Tristan Rietveldt

Robustness of CNN-based malware byteplot classification under standard image transformations

By Tudor Tănăsescu

Illustration Practices in Mathematics Textbooks for Computer Science: An Exploratory Analysis

Supervisors: Mrinal Dhume, Martin Skrodzki

The Transition from Geometry to Abstraction: Illustration Practices in Linear Algebra Textbooks

By Amin Abid

The Evolution of Textbook Illustrations in Probability and Statistics: A Comparison

By Berke Aygülhan

Roles of Illustrations in Propositional Logic Textbooks

By Evan L.G. Pacini

A Comparison of Rigour and Intuition in Illustrations in Calculus and Analysis Textbooks

By Harsh K. Mishra

Communicative role of trees in Algorithms and Data Structures Textbooks: Illustration Practices in Computer Science Textbooks

By Péter Aszalós

Improving speech recognition for children with developmental language disorders using synthetic data

Supervisors: Odette Scharenborg, YuanYuan Zhang

Improving automatic speech recognition for Dutch childrenwith DLD using cross-lingual voice conversion

By Jannes Kelso

Improving Automatic Speech Recognition for Dutch Children with Developmental Language Disorder Using Cross-Lingual Child-to-Child Voice Conversion

By Julie van Montfrans

Augmenting Dutch Adult Dysarthric Speech into Child-like Speech using Traditional Digital Signal Processing Techniques

By Stephanie Gilbert

Improving Automatic Speech Recognition for Dutch Children with Developmental Language Disorder using Synthetic Data

By Wendy Hu

Improving ASR for Dutch Children with DLD through Voice Conversion of Dysarthric Adult Speech

By Yulia Waarsenburg

Integrating property-based testing and verification for agda2hs

Supervisors: Jesper Cockx, Nathaniel Burke

Specified Agda is Testable Haskell

By Aleksandra Kierska

Translating Type Class Laws from Agda2Hs to QuickCheck

By Giovanni Grandi

Bridging the gap in software verification: Agda proofs to Haskell test case generators

By Mateusz Olszewski

Mutation testing effectiveness for checking QuickCheck tests derived from Agda type signatures

By Mateusz Pietrzak

Proving with the Help of Property-Based Testing

By Maurits Sloof

Interactive EEG biomarker analytics: boosting the performance of high‑dimensional statistics and brain‑map rendering

Supervisors: Ricardo Marroquim, Arthur Ervin Avramiea

Visualizing EEG data in cloud environments

By Erik Koprivanacz

Topological Consistency, Not Fidelity, Bounds the Cost Relief of Simplified EEG Brain Maps

By Friso B. H. van der Veen

Vector Rendering of Biomarker Topomaps

By Guney Bayindir

Memory-aware Optimization of Mass-univariate EEG Statistical Inference

By Pepijn van Egmond

Minimising Data-Layout and Copy Overhead

By Sem Lelie

Internet Periodic Timeouts: Why Do They Occur?

Supervisors: Giovane Moura

DNS Timeouts: Analysis of Root DNS Servers F and G

By Horia-Andrei Botezatu

Understanding Timeouts in Root DNS Measurements: Causes and Recommendations

By Jesse Prins

At the Root of Timeouts

By Joshua Gort

Internet Timeouts, Why Do They Occur for the Root DNS Servers E and M?

By Radu Daniel Burchel

Comparing Timeout Behavior and Reachability at I-root and L-root

By Serban Orza

LLM value-action gap and persona profiles

Supervisors: Amir Homayounirad, Luciano Cavalcante Siebert

Evaluating the Value-Action Gap in Small Language Models using Moral Foundations Theory: The Impact of Moral Persona Prompting on Behavioral Alignment

By Philip Lekkerkerker

Exploring the value-action gap: language models and cultural-political personas

By Rein Lakerveld

Virtue Profiles and Value-Aligned Actions in Language Model Decision-Making: A Study of Cardinal Virtue Conditioning and Value-Action Alignment in LLMs

By Ruben Schnell

Can Social Concepts Support Value Conflict Resolution in Language Models?

By Sebastian-Remus Biro

Exploring the value-action gap: language models and cultural-political personas

By Sinan Onen

Learning Curves of Graph Neural Networks

Supervisors: Mohamed Jebali, Chengen Liu

Learning Curves of GNNs vs. MLP vs. Tikhonov

By Calin Radoi

How Training Label Noise Affects the Learning Curves of Graph Neural Networks

By Ivan Markov

How Much Does Label Sampling Move a GNN Learning Curve?

By Radu Zidaru

Capacity Scaling and Learning Curves in Graph Neural Networks

By Tudor Pipernea

Do Graph Neural Networks Follow Power Laws?

By Vasil Georgiev

Learning extended deterministic finite automata

Supervisors: Dr.ir. S.E. Verwer

Finding distinguishing suffixes in DFA learning

By Bálint Kollmann

Monte Carlo Tree Search for Deterministic Finite Automaton Inference: A New Search Strategy in the Red-Blue Framework

By Björn Zandvliet

Evaluating Extended Automata for Sequential Regression: A comparison against standard baselines

By Job Vonck

Analyzing the Impact of Search Orders in Extended State Machine Learning for Anomaly Detection

By Sam van Beek

Adapting the Gini Impurity Criterion for Splitting and Merging Strategies in Extended Automata Learning

By Tobiasz Zalewski

Linguistic sources of performance disparities among diverse Dutch speakers in automatic speech recognition

Supervisors: YuanYuan Zhang, Odette Scharenborg

Which Word Categories Contribute to Higher ASR Error Rates for Native Dutch Children Than for Native Dutch Teenagers?

By Adomas Valiukevičius

Linguistic sources of performance disparities in Dutch Automatic Speech Recognition for non-native adults

By Kiarash Karimi

Utterance Length and ASR Performance Disparities between Native and Non-Native Dutch-Speaking Children in Read and Human-Machine Interaction Speech

By Zev Comvalius

Lost Without GPS? Silent Drone Navigation in Jammed Environments

Supervisors: Florian Kosterhon, Arash Asadi

Propagation of Heterogeneous Receiver Self-Positioning Uncertainty to Target Localisation and Tracking in Airborne Multistatic Passive Radar

By Bartlomiej Dudek

Comparison of Efficient FPGA-Oriented Direction-of-Arrival Algorithms on an RFSoC 4x2 Board

By István Váradi

Passive RF Self-Localization of UAVs Using Signals of Opportunity: A Survey and Evaluation Study

By Jort Kuipers

Cooperative Drift Mitigation for UAV Swarms in GNSS-Denied Environments

By Matei-Alexandru Pânzariu

Lightweight Distance and Relative Radial Velocity Estimation with a Passive RF Receiver

By Milán Székely

Microbiome foundation models: the universal language of bacterial communities

Supervisors: Thomas Abeel, Bianca-Maria Cosma

Benchmarking Microbiome Classifiers Across Studies and Disease Contexts

By Ayoub Acharki

A systematic comparison of deep learning architectures for microbiome representation learning

By María Rosuero Esparza

Benchmarking Compositional Preprocessing for Microbiome-Based IBD Classification

By Stefan Maniu Secuiu

Explainability across classical and deep learning models in gut microbiome contexts

By Stefan Tudor Lupsan

Mining Reproducible Dependency Updates Across Ecosystems

Supervisors: Sebastian Proksch, Cathrine Paulsen

Cross-project alignment of dependency updates

By Dylan Hu

Mining Reproducible Cargo Dependency Updates

By Lyuben Todorov

Mining Reproducible Dependency Updates Across Ecosystems

By Paras Khan

How Reproducible Are Build, and Test Outcomes of Dependency Updates in JavaScript/npm Projects?

By Vlad Maksymiuk

Model Checking: Applications and Limitations

Supervisors: Benedikt Ahrens, Anna Lukina

Applications and Limitations of the SPIN model checker

By Ksawery Piotr Radziwiłowicz

Distance-Vector Routing Protocols in mCRL2

By Mert Yılmaz

Exploring The Relationship Between Unwind Bound and Model Checking Complexity in CBMC

By Mihai-Filip Frânculescu

Performance Evaluation of Specification Type in NuSMV

By Oana-Teodora Mirea

Rewriting TLA+ Fairness Conditions for Symbolic Model Checking

By Sage Łuszczyk

Multi-label node classification in graph structured data

Supervisors: Megha Khosla, Elena Congeduti

From Multi-Class to Multi-Label: Revisiting Edge Dropping for Graph Neural Networks

By Alexandru Andrei

Evaluating Graph Neural Additive Networks for Multi-Label Node Classification

By Arsenie Vlas

Heterophilic Methods on Multi-Label Graphs

By Cristian Turcan

Per-Node k-Hop Label Homophily Predicts GNN Accuracy in Multi-Label Node Classification

By Veaceslav Guzun

Property-Driven Comparison of GNNs on Multi-Label Graphs

By Victor Paiu

Multiplane Images as a Graphics Primitive

Supervisors: Petr Kellnhofer

Real-time Building of Multiplane Images from RGBD Data

By Floris van Onna

The impact of dense layer compression of MPIs on image quality

By Ilker Kiliç

Fast view-dependent view synthesis via decoupled geometry and fixed-basis appearance

By Jochem Gebraad

Improving Multiplane Images with Deformable Layers

By Lachezar Topalov

Semantic and Geometry-Aware Depth Discretization for Multiplane Image Construction

By Lucas Paul

Network Representations of Single Cells to Understand Alzheimer's Disease

Supervisors: Bram Pronk, Timo Verlaan, Marcel Reinders

The Geography of Gene Regulation in Alzheimer's Disease

By Duco Lam

Stability of Cell-Specific Gene Regulatory Networks Inferred by ScReNI

By Eduard Cimpean

Cell-specific Gene Regulatory Networks in Alzheimer’s Disease

By Ivo Haršáni

Assessing the Added Value of scATAC-seq Data in Cell-Specific Gene Regulatory Network Inference for Alzheimer's Disease

By Leo Lin

Analysis of HVG use in the ScReNI pipeline

By Mihnea-Matei Gusu

Observability for Intelligent Fault Management in Cloud-native Beyond 5G Networks

Supervisors: Sehan Samarakoon Mudiyanselage, Nitinder Mohan

A Cross-Layer Fault Atlas for Cloud-Native 5G Core Networks

By Boyan Bonev

Multi-Modal Correlation of Observability Signals in Cloud-Native 5G Core Networks

By David Ghergut

Assessing ML-based anomaly detection across individual telemetry modalities in Cloud-native B5G Networks

By Stoyan Kutsarov

Pull-based Scraping vs. eBPF Auto-instrumentation: Overhead, Coverage, and Trade-offs

By Victor Ilchev

Investigating log reduction strategies for cloud-native 5G networks

By Yana Mihaylova

OpenClaw - Create your own Blockchain from scratch for agents

Supervisors: Johan Pouwelse, Bulat Nasrulin

An Owner-Sovereign Integrity Layer for an AI Agent

By Lucas Pereira Barrios

Proof-of-Descendancy: Identity for Self-Replicating LLM Agents

By Mohab Ahmed

Self-Evolving Agent Communication Protocols

By Nikola Emilov

VukZero: Zero-Trust for Autonomous LLM Agents

By Vuk Pejić

Parameter-Efficient Adaptation of Vision Foundation Models for Geophysical Data Processing

Supervisors: Dr. Jing Sun, Dr. Tiexing Wang, Dr. Eric Verschuur, Jiahua Zhao

Seeing Through Seismic Noise with Soft Spatial Blending

By Alexis FIMEYER

Improving Generalization Of VFMs On Denoising Seismic Data Through The GRQO RL-based Fine-Tuning Method

By Andrei Oprescu

Reconstructing missing seismic traces on BP 2007 and Viking Line 12

By Jaouad Hidayat

Where Does Adaptation Matter? Layer-wise Importance of Parameter-Efficient Adaptation of Vision Foundation Models to Seismic Denoising

By Okan Demir Baykal

Learning from Neighboring Seismic Slices: Parameter-Efficient 2.5D Adaptation of DINOv3 for Seismic Denoising

By Pablo Varela Bernal

Physical Intelligence: Backpropagation-Free Learning for Physical Systems

Supervisors: Stephanie Tan, Yaqi Guo

Incorporating temporal spike stability into the Forward-Forward algorithm

By Alexandru-Mihai Radu

Adapting Mono-Forward with Zeroth-Order Gradient Estimation for Automatic Differentiation-Free Training

By Ateş Görpelioğlu

Comparative Analysis of Internal Representations in Hebbian Learning Algorithms

By Dumitru-Sebastian Mustață

When does the leading eigenvector agree with cluster means? A fixed-point analysis of Oja’s and SoftHebb’s streaming rules

By Ovidiu-Alexandru Argherie

Hybrid Equilibrium Propagation: Trading Estimator Bias for Compute

By Ștefan Stoian

Physics-Informed Learning for Computational Fluid Dynamics Surrogate Modeling and Neural Operator Methods

Supervisors: Jing Sun, Tiexing Wang

Inverse Reconstruction with Physics-Informed Neural Operators for Darcy Flow

By Christopher Wilczewski

Accuracy, Performance, and Robustness of Physics-Informed Surrogate Models

By Filip Nedić

Comparison of surrogate model classes on out-of-distribution data

By Joris Timmermans

Can Physics-Informed Training Improve Neural-Operator Data Efficiency?

By Samuel Campos Vilar

Polarisation and influence in online social networks

Supervisors: Anna Latour

Recovering from Viral Narratives Delayed Interventions and Strategic Seeding in Polarised Networks

By Alexandru Galoiu

Annealed Heuristic Search for Local Community Detection in Probabilistically Weighted Graphs

By Andrei Bardas

Detecting polarisation using cross-community social ties

By Calin-Mihai Olaru

Node Removal Effect on Polarization in Social Networks

By Iancu Popp

Diversity-Aware Reranking of Node2vec-based Recommendations in Social Networks

By Teodora Mihaila

Privacy Preservation in Event-Based Vision: Risks, Methods, and Trade-offs

Supervisors: Nergis Tömen, Tunahan Parlayici

Effect or Privacy Preservation Strategies on Event-to-Image Reconstruction

By Arda Tamgaç

Encryption of Event Camera Data for Visual Localisation

By Bink Boëtius

Structural Information Leakage in Event-Based Camera Streams Without Explicit Reconstruction

By Ilinca Mocanu

The effect of applying perturbations on the privacy and visual naturalness of face images reconstructed from event-based data

By Matei Oprescu

Privacy Risks in Event-Based Cameras: The Role of Sensor Configuration

By Sofyan Ali

Quantitative Analysis of Microglia Morphology and Spatial Distribution in Mouse Brains

Supervisors: Michael Weinmann, Helene F. E. Gleitz, Hector Tejeda Mora

Quantitative Analysis of Microglia Morphology and Spatial Distribution in Mouse Brains

By Stella Marlene Schultz

Reducing Data in Visual AI

Supervisors: Jan van Gemert, Alex Manolache, Petter Reijalt

Reducing Data in visual AI: Assessing the Data Efficiency of Masked Autoencoders in Resource-Constrained Environments

By Dimo Terziev

Reducing Data for Vision Foundation Models. Data-Efficiency of Self-Supervised Learning with DINO Multi-Crop

By Leonid Margulis

Reducing Data for Vision Foundation Models: Data-Efficiency of Self-Supervised Learning with Momentum Contrast

By Makar Kuleshov

Reducing Data in Visual AI: Optimizing I-JEPA for Data Efficiency

By Maksim Plotnikov

How Does the Downstream Accuracy of Barlow Twins Scale with Pre-training Dataset Size?

By Yan Olerinskiy

Reinforcement Learning for Quantum Compilation

Supervisors: Sebastian Feld, Matthijs Spaan

Curriculum Learning for Qubit Mapping Across Hardware Topologies

By Aleksandr Govenko

Observation and Action Encodings for Reinforcement Learning–Based Qubit Routing: A Controlled Ablation Study in qgym

By Andaç Durmaz

Quantum Circuit Routing Optimises the Wrong Metric

By Dan Cernatinschi

Reward Engineering for RL-Based Initial Qubit Mapping

By Federico Lentini

Hardware-informed Reinforcement Learning for Quantum Gate Scheduling

By Jakub Pietrzak

Representation learning for high-dimensional single-cell genomics with variational autoencoders

Supervisors: Marcel Reinders, Kirti Biharie, Inez den Hond

Associating Single-Cell Latent Factors with Genetic Risk

By “Antonios” “Tsoukas”

Predicting treatment of rheumatoid arthritis with LIVI

By “Esther” “Wit”

Multi-omic Latent Interaction Modelling at Single-Cell Resolution

By “Jakub” “Fręchowicz”

Capturing Clinical Heterogeneity in Rheumatoid Arthritis

By “Patrick” “Lo”

Risk‑bounded, human‑aware autonomy: Safe reinforcement learning and predictive control in a post-disaster search and rescue testbed

Supervisors: Sven Schoonebeek, Anahita Jamshidnejad

Perception-Driven Tube Scaling for State-Dependent Dynamic Tube-Based MPC

By Filip Keerberg

MPC-Shielded Reinforcement Learning for Safe Autonomous Exploration in Search and Rescue

By Jokubas Dimsa

Human-Robot Interaction in Search and Rescue: Modeling Victim Behaviour and Trust

By Maria Grouev

Effects of Online Disturbance Tube Adaptation on Conservativeness and the Safety-Performance Trade-off

By Nicolas Laplagne

Coordination-Aware Task Allocation Via a Lightweight Supervisory Layer

By Tigo Schutgens

Robot Interaction Strategies in Creative Group Ideation

Supervisors: Ruben Weijers, Catharine Oertel

Asking the right question: How Robot Elicitation Strategies Shape Engagement and Substantive Contribution in Creative Group Ideation

By Bogdan-Andrei Micu

When Should Robots Speak? Effects of Proactive and Reactive Robot Interventions on Perceived Autonomy During Creative Group Ideation

By Darius Corlade

The Hidden Influence of Robots: How Robot Interaction Strategies Shape Human-Human Interaction and Perception in Creative Ideation

By Hristian Semerdzhiev

The Impact of Conversational Delivery Styles on Perceived Autonomy during Collaborative Ideation with Social Robots

By Jae Hyung Seo

When Robots Brainstorm With Us Robot Facilitation and Social Comparison in Creative Group Ideation

By Musy Ayoub

Smart farming: improving automated broccoli head size estimation

Supervisors: Jeroen Wildenbeest, Cynthia Liem

Smart Farming: Using End-To-End Deep Learning to Estimate the Size of Broccoli Heads

By Aron Rijken

SMART FARMING: Using human-in-the-loop methods to streamline broccoli head annotation.

By Ferdi Helvensteijn

STAR-YOLO26: Synthetically Trained Amodal Recovery of Broccoli Heads

By Giorgos Christofi

Smart Farming: Improving Automated Broccoli Head Size Estimation

By Huan Yi Ma

An Evaluation Template for Broccoli Head Segmentation

By Pieter B.A. van den Haspel

Teaching Machine Learning foundations using different modalities

Supervisors: Gosia Migut, Ilinca Rențea

Teaching Principal Component Analysis Through Multiple Representations - Impacts on Conceptual Understanding, Problem Solving and Knowledge Transfer

By Cristiana Vlădăreanu

Teaching Gradient Descent - An Exploratory Study on Classic Textbook vs. Multiple Representations Approaches

By Fabiana-Maria Severin

Does Representation Matter? Comparing Algebraic and Geometric Approaches to Teaching L1/L2 Regularization

By Ivan Nikolov

Teaching Decision Trees using multiple representations

By Oanh Tran

Teamwork Learning Goals and Teaching Methods in CS curricula

Supervisors: Sole Pera, Merel Steenbergen

Teaching and assessment methods in Dutch Computer Science curricula

By Ellie Bleeker

The High-Low Divide: How Teamwork Learning in Undergraduate Computer Science Is Shaped By Cultural Context

By George-Matei Andrei

Mapping Competency Categories in Dutch Bachelor’s Computer Science Curricula

By Mihnea Nedelcu

A Method for Describing Declared Teamwork Instruction in a Computer Science Bachelor Curriculum

By Mohammed Shomis

Teamwork in Capstone Courses: A Comparative Analysis of Dutch Universities

By Wilhelmina van Hage

Techniques for Bayesian RL on Graph Domains

Supervisors: Frans A. Oliehoek, Andreea Minculescu

Comparing POMDP Solvers for active search on graphs with known and unknown topology

By Andrei Mosescu

Active Search on Post-Compromise Graphs: When Does Topology-Aware Planning Help?

By Kostas Stefanopoulos

Learning Latent Representations for Active Search on Partially Observable Graphs

By Stefan Voicila

VIBE-GAS: Variational Informed Belief Estimation for Graph Active Search

By Teim Giesen

Observation Design for Active Search over Uncertain Graphs

By Tudor Şucaliuc

The Alignment of Large Language Models' Responses to Subjective Variations in Hate Speech

Supervisors: Pradeep Murukannaiah, Urja Khurana

What Types of Hate Speech Samples Do LLMs Struggle With?

By Mara Dragomir

Tailoring In-Context Learning Techniques for Definition-Based Hate Speech Detection in Large Language Models

By Parham Bateni

Evaluating the Impact of Explicit Hate Speech Definitions on the Stability of LLM-based Hate Speech Classification

By Rodrigo Santos

Comparing Alignment to Real-Life-Inspired Definitions in Zero-Shot Hate Speech Classification

By Viktoria Bunovska

Which definition of hate speech does the default behaviour of large language models align with most closely?

By Yuanze Xiong

Think-aloud data for automatic trust assessment

Supervisors: Dr. Myrthe Tielman, Charlotte Ning

Retrospective Think-Aloud Data as a Window into Performance Trust

By Adrian Todorov

How Concurrent Think-Aloud Data Reflects a User's Morality Trust in an Agent

By Arda Cengaver

Think-aloud data for automatic trust assessment: RTA x Morality

By Calin Gheorghe

Concurrent Think-aloud Data for Automatic Performance Trust Assessment

By Defne Kösecioğlu

Tiny AI on Tiny Devices: Build an Energy-Smart Pipeline for AI deployment on Microcontrollers

Supervisors: Nicole Rosi, Hao Liu, Marco Zuniga Zamalloa

Efficient mmWave Point-Clouds for Embedded Devices

By Andreas Nicolaou

Hardware-Aware Energy Estimator pipeline for µNAS

By Martynas Šmitas

Efficient Embedded mmWave Human Pose Estimation

By Robin Verver

Extending AIfES with Depthwise Convolution

By Zico Krassenburg

Low Power Event Detection on Microcontrollers

By Zion Corbanie

Tiny Machine Learning for Sensing and Healthcare

Supervisors: Qing Wang, Shun Zhuge, Bo Yang, Amund Kiste

Exploring the feasibility of short-range VLC schemes in MIMO systems

By Alexandru Lolea

Adapting Mamba Models for Deployment on Microcontrollers

By Bartosz Drabiński

Structured Degradation in Visible Light Positioning

By Jasper van Arkel

Embedded Trustworthy AI for Healthcare

By Luca Tompea

ScreenSense: Utilizing Communication Signals for Dynamic Finger Tracking for On-Screen Antennas

By Satyam Gupta

Training-Free Personalisation of Large Language Models Toward Situated Human Values

Supervisors: Enrico Liscio, Jie Yang, Anne Arzberger, Carolin Brandt

Personalized Pre-Decoding Alignment for Training-Free Toxicity Reduction

By Alina Florea

STEER-Away: Personalized Safety Alignment via Decoding-Time Logit Steering

By Andrei Trache

Value-Aware Post-Decoding Reranking for Training-Free Personalisation of LLM Outputs to User-Specific Toxicity Standards

By Iulia Slanina

Personalised Classifier-Guided Decoding: Steering LLM Toxicity Along User-Specified Directions

By Miruna Coroi

Training-Free Personalisation of LLMs using Representation Engineering

By Rares Diaconescu

Trustworthy Financial Crime Detection v2.0

Supervisors: Zekeriya Erkin

SMURF: Privacy-Preserving Multi-Party Graph Mining for AML

By Dhruvan Gnanadhandayuthapani

A Bridge Between Private Set Intersection Algorithms

By Maciej Kozik

The AES-128 Decryption Circuit for Transciphering in TFHE

By Max Tanis

Securely Characterising Fraudulent Cycles

By Rodrigue Vande Capelle

The Impact of Subsampling on Differentially Private Fraud Detection

By Storm van Wassenaar

Vulnerability of Information Transport on Hypergraphs to Hyperlink/Node Removal

Supervisors: Bart Peters, Renze Dijkhuizen, Huijuan Wang

How can the Diffusion of Information in Hypergraphs be improved via the addition of Hyperlinks?

By André Taiki Mestieri Shiguematu

Hyperedge Properties for Estimating Diffusion Backbone Weights in Hypergraphs under SICP spreading

By Daan van der Aar

Rewiring Hypergraphs to Improve Information Propagation

By Jelmer Stolwijk

Inhibiting Spread in Hypergraphs through Community-Aware and Process-Based Node Removal

By Quint Winthagen

Vulnerability of Information Transport on Hypergraphs to Hyperlink Removal - An Empirical Study of Shortest-Path Routing Robustness

By Simeon Nedelkov

What can we learn from software enhancement proposals

Supervisors: Diomidis Spinellis

Analyzing the evolution of major categories in Enhancement Proposals in Software Ecosystems

By Cas Ebels

What features of software enhancement proposals are correlated with acceptance and implementation?

By Catalin Moldovan

How software enhancement proposals evolve alongside their target projects

By Kajus Kuncaitis

Quantifying Open-Source Governance through Software Enhancement Proposals

By Stijn Risseeuw

Evaluating Decision-Making Processes of Software Enhancement Proposals

By Tim Raaymakers