| Student |
Thesis | Content |
| Afzal Khan, R.N. (Raaed) | Mutually Intelligible, Separate Outcomes: Linguistic Bias Between Hindi and Urdu in Sentiment Classification | |
| Agbaria, L. (Laith) | Meta-overfitting and Overtuning of Small Language Models Fine-Tuning | |
| Ahmedov, T. (Tolunay) | Evaluating Causal Inference Methods in Natural Experiment Setup | |
| Al-Amodi, H. (Hussein) | Surface or Substance? A Controlled Experiment on How Contextual Signals Sway LLM Peer Review Judgements in CS | |
| Alonso Cancela, A. (Antia) | Analysis of Sycophancy Across Questioning Styles: A Comparative Study of Sycophancy Across Prompting Architectures and Large Language Models | |
| Amirani, K. (Kasra) | A Unified Toolkit for Evaluating Nonlinear Dimensionality Reduction Techniques | |
| Baggen, P. (Pepijn) | Morphometric Read-outs from Neurite Segmentation in a Cardiac Innervation Chip Using U-Net | |
| Bahšteins, M. (Matīss) | Constraint-Verified Agentic Loop for FPV Drone Component Compatibility | |
| Benke, P. (Péter) | Cloud vs. Local Multimodal Models for Embodied Task Planning: Evaluating Trade-offs in Success, Latency, and Energy Consumption | |
| Berkel, F. van (Foppe) | Analysis of the Behavior of Algorithms on Proxy Functions for Replacing Real World Optimization Problems | |
| Bernotas, R. (Rapolas) | Benchmarking Established and Recent Object Detectors for Road Scene Detection | |
| Bobrova, A. (Aleksandra) | Reinforcement Learning for Minimum-Energy Path Discovery on Low-Dimensional Potential Energy Surfaces | |
| Bol, E. (Emile) | Engagement-driven Strategies on Social Media: User Perceptions and Implications for a Digital Advice Tool | |
| Bouman, T. (Thijmen) | The Effect of GenAI-Tools on Knowledge Management, Workload and Productivity in the Salvation Army | |
| Brouwer, R. (Rens) | Performance Assessment of Within-Season Crop Type Mapping Methods Using Satellite Image Time Series | |
| Calame, S. (Saar) | Exploring Synthetic Non-Contrast Brain CT Generation and Deep-Learning Classification for Intracranial Haemorrhage Detection | |
| Canavea, M. (Matei) | Weighing the Possibilities: Scalable Simulation of Quantum Convolutional Neural Networks using Weighted Model Counting | |
| Chatterjee, A. D. (Aditya Dev) | Reading Between the Lines: The Communication of Corporate Sustainability in CEO Statements Across Regions from 2013 to 2022 | |
| Chen, H. (Hao) | Understanding Label Errors and Ambiguous Samples in Earth Observation Benchmarks: A Case Study on EuroSAT | |
| Cordova Niewold, R. (Rafael) | Privacy-Preserving Collaborative Vulnerability Assessment using Secure Multi Party Computation | |
| Czapska, G. (Gabriela) | Comparison of Classical, Hybrid Quantum-Classical, and Quantum Generative Models on the Low-Dimensional Bars and Stripes Dataset | |
| Diaconu, S.I. (Stefan-Ioan) | A Synthetic, Observability-Annotated Dataset for Viewpoint-Dependent Vehicle Damage Detection | |
| Diermen, A. van (Anneroos) | Validating LiNT Readability Formula on Various Text Categories | |
| Dinh, N. (Natascha) | Teaching Machines to See Seasonal Color: An Explainable Approach for Automated Personal Color Analysis | |
| Dorland, R. (Ryan) | Extended Hypervolume Improvement Distributions for Constrained Multi-Objective Bayesian Optimization with Correlated Gaussian Processes | |
| Dunsky, N. (Noam) | Simulating Depression with Reinforcement Learning | |
| Dziewonski, J. (Jan) | Emergent Communication in Aging Populations | |
| Emekçi, D. (Duru) | Evaluating Counterfactual Robustness Across Independently Trained Predictive Models: A Multi-Dimensional Framework for Healthcare | |
| Epprecht, K. (Kai) | A Cross-Cultural Analysis of Humor Detection and Interpretation in Large Language Models | |
| Fu, J. (Jingya) | Building Trust in Automotive Intrusion Detection Systems Through XAI Methods | |
| Gahr, W. (Wesley) | Probing, Attribution, and Attention in a Siamese Mouse-Dynamics Biometric Encoder | |
| Gebe, M.B. (Márton Bálint) | Robustness of Guitar Tablature Transcription under Signal-Level Acoustic Degradation | |
| Georgieva, V. (Viktoria) | Multi-Task Simulation for Evaluating Generalization under Dynamic Task Execution | |
| Gloesener, M. (Max) | Safe Scanning of Proprietary Operational Technology Protocols | |
| Hamza, K. (Khayri) | Comparing Traditional and Deep Learning-Based Meta-Features for Algorithm Selection | |
| Harell, M. (Max) | Beyond Scalar Fitness: Behavioural Feedback for LLM-Driven Metaheuristic Evolution | |
| Hartman, K. (Kaier) | Fractal Analysis as a Quantitative Explainability Tool for CNN Decision Making in Breast Cancer Cell Classification | |
| Hermelijn, D. (Djamey) | Random Forest Induced Diverse Subgroup Discovery | |
| Im, A.J.H. (Adrien Joon-Ha) | Design and Evaluation of an Active Vision System for Surgical Instrument Detection and State Classification | |
| Inan, A. (Alphan) | Adaptive Music in Minecraft and its Impact on the Player Experience | |
| Johannsen, L. (Lenard) | Efficient Small-Object Video Detection via Quantization-Aware Training | |
| Jolevski, T. (Tome) | MyGraine: The Utility of Machine Learning Approaches for Personalized Migraine Attack Onset Prediction Among Episodic Migraine Patients | |
| Jonas, D. (Dani) | How Effective are Simple Machine Learning Models in Accurately Predicting Structural Properties of 2D Perovskites Directly from Crystal Structure Data? | |
| Jong, K. de (Kaya) | Reconstructing Holocene ENSO Variability through the Harmonization of Heterogeneous Proxy Records using a Gaussian Process Regression Framework | |
| Kamalzadeh, D. (Dalia) | Evaluating the Impact of Pre-processing Choices on CNN-Based Dolphin Vocalization Classification in Passive Acoustic Monitoring | |
| Kamerbeek, J. (Jesse) | Truly Unordered Rule Sets for Delivery Delay Prediction: Analyzing the Performance–Interpretability Trade-off | |
| Klioštoraitis, B. (Benas) | Reducing Stagnation in PCA-Assisted Bayesian Optimization | |
| Koghee, N.X.X. (Nadia) | Hands-on Retrieval Insight and Trust in Legal AI: A Study of Law Students Interacting with RAG Systems | |
| Komeili Zadeh, K. (Koorosh) | Adaptive Data Profiling with ML-Based Quality Checks for ETL Pipeline Quality and Cost Optimization | |
| Koster, D. de (Dominieq) | Solving the Shape Ambiguity and Domain Gap Problem Using Multiple-View Classifiers and Domain Adaptation Methods | |
| Kowalczyk, E. (Ewelina) | Magnitude Symbolism Without Sound: Investigating Phonetic Size-Symbolic Associations in Large Language Models | |
| Krajanowski, J. (Jakub) | Sentiment Analysis of Moroccan Darija Arabizi: A Comparison of Pretrained Transformer Encoders and a Classical Baseline | |
| Kravcenko, A. (Artemijs) | Parameter Sensitivity Analysis of the Heston Stochastic Volatility Model | |
| Kuurstra, D. (Dean) | The Identification of Spectral Patterns in Low Resolution XP Spectra of Gaia DR3 Using Compression-Based Pattern Mining | |
| Kwakernaak, J.F. (Joni) | Moral Priming: Effect of Moral Framing on Political Alignment of Large Language Models | |
| Latuff, C. M. (Christian) | Icy Displacement: Integrating Glacier Fluctuation and Species Occurrence Data to Study Distribution Shifts Near Retreating Glaciers | |
| Leppäkorpi, J. (Johannes) | Multi-Objective Stochastic Electric Vehicle Routing Problem with Time Windows | |
| Lev, Y. (Yotam) | Lens Optimisation Using the LLaMEA Framework Specifically for Optical Lens Design | |
| Li, J. (Jingbo) | Can Repeated Sampling Help Smaller Language Models Outperform Larger Models under a Generation-Time Budget? | |
| Li, X. (Xiaosai) | Dynamic Shape-IoU : Addressing Scale Variance | |
| Lichota, P. (Piotr) | NQS-Bench-101: Benchmarking Neural Architecture Search for Neural Quantum States | |
| Liem, K. (Katherine) | Thinking Deliberately or Thinking Too Much? Investigating the Tradeoff Between Theory-of-Mind Performance of Agentic-LLMs Using Mental State Modeling and Model Expenses | |
| Lopez Ruiz, A. (Alejandro) | Ecosystem Simulation for Environmental Policies using Reinforcement Learning | |
| Lu, S. (Shengan) | Does Structured Grounded Generation Improve Consumer Response to AI-Generated Social Media Posts? Evidence from a Randomized Online Experiment and Implications for Outcome-Based Pricing | |
| Luchini, E. (Enrico) | Efficient Anomaly Detection for Industrial Purposes: A Comparative Study of Transformers and CNNs | |
| Ludlage, N. (Nika) | Does it Matter Who is Rude? Exploring Politeness and Perceived Agency in Chatbot Conversations | |
| Marini, A. (Anna) | Pruning-Aware Shapley Values Estimation for Large Language Models Nonuniform Semistructured Pruning | |
| McMahon, H.B. (Hazel Buckley) | “Why Are You Arguing With Me?”: The Effect of Linguistic (Mis)Alignment on Trust and Persuasion in a Human-AI Debate | |
| Mediavilla Sáez, A. (Alejandro) | A Linear Programming Approach to EV Charging Power Supply Optimization: Performance, Scalability, and Service Trade-Offs | |
| Mendes, C.E.M. (Carlos) | Scalable Evolutionary Strategies for Deep Reinforcement Learning via Integer-Only Neural Networks using Low-Rank Updates | |
| Meurs, J. (Justin) | Analyzing DropConnect Retention Rates and the Block Structure of Parameter Correlation Matrices in Feed-Forward Networks | |
| Micu, R.L. (Roxana-Laura) | ChatGPT: Become Human, A Taxonomy of LLM Morality in Choice-Based Video Games | |
| Moerman, F. (Fiona) | Evaluating the Impact of Underwater Image Enhancement on Object Tracking for Autonomous Underwater Vehicles | |
| Molnár, M.T. (Máté) | Scaling Archival Research with Agentic AI: A Reproducible Pipeline for IPO Team Data Enrichment | |
| Moussa, C. (Christiaan) | Extending the Training Free VPint2 Framework for Multi-Temporal Cloud Removal in Satellite Image Time Series | |
| Mścisz, K.P. (Kamil) | Comparing Local and Global Forecasting Models on Highly Intermittent Time Series in Manufacturing | |
| Munck, V. de (Victor) | Luhmannian Society Digitized: A Study on Structured Creativity as an Autopoeitic Process within the DIFI Framework | |
| Nasrollahi, G. (Ghazaleh) | AI-Assisted Coding, NDAs, and Confidentiality Boundaries | |
| Nathie, R. (Rajeev) | The Capabilities of LLMs in Assisting in a Language Production Task | |
| Nguyen, S. (Sofia) | Dinner Party Conversations with an LLM: Reducing the Echo Chamber Effect | |
| Nizielski, K. (Kacper) | Through the PRISM: Privacy-Region Investigation for Surveillance Media in Video Action Recognition | |
| Noordenne, K. van (Kay) | Optimization for Food Delivery Under Uncertainty | |
| Nour, B. (Bilal) | A Data-Driven Analysis of Personalized Performance Predictors in Competitive Endurance Runners | |
| Oleksa, M. (Mateusz) | Trust Me, I’m a Chatbot: The Effect of Parasocial Cues on the Conformance to AI Chatbot Advice | |
| Otte, J. (Jacob) | Classifying Play Styles in Online Multiplayer Video Games | |
| Paul, M. (Marit) | Exploring Disjunctive Queries in Subgroup Discovery | |
| Peng, Y. (Yihui) | EEG-based ROI Selection for Accelerating Vision-Language Models in Visual Question Answering | |
| Perski, P. (Piotr) | Uncertainty Quantification in Deep Learning via Predictive Coding | |
| Pluutus, M. (Mariela) | Monitoring Effort Overruns in Software Maintenance | |
| Politylo, M. (Maria) | Zebrafish 3D Reconstruction: Optimization of the Current Pipeline for Brightfield and Fluorescent Imaging | |
| Qalyoen, S. (Sami) | The Influence of AI Systems on Military Decision-Making | |
| Ramos Fernandez, N. (Nicolas) | Probing Cross-Lingual Differences in how LLMs Represent Natural Language Inference | |
| Reitter, CJ | Conformity, Comfortability, and Chatbots: How Virtual Avatars Affect the Likeability of an Agent | |
| Richtr, J. (Jan) | Investigating the Transferability of Reinforcement Learning-Based Hyperparameter Optimisation Methods | |
| Rietveld, A. (Anthony) | Generative AI as a Content Generator for Educational Games | |
| Riezebos, E. (Elle) | Bridging the Gap Between the Traditional and the Digital: Assessing the Authenticity of AI-Generated and Digital Art | |
| Rojewska, N. (Nina) | Predicting Human Semantic Priming Using Multilingual Large Language Models | |
| Rooij, L. de (Lars) | True Colours: Vision Transformers Classifying Art Beyond Hue | |
| Rosenmann, A. (Alma) | Reinforcement Learning for Quantum Error Correction | |
| Ruesink, V. (Victor) | The Impact of Stated Reasoning Monitoring on Sycophantic Response Tendencies in LLMs | |
| Schelven, Q. van (Quinten) | Comparing Trust in Large Language Models Using the Game Codenames | |
| Scholten, W. (Willem) | Investigating Local Robustness of TabPFN on Small Numerical Binary Classification Tasks | |
| Semenova, D. (Daria) | Measuring Human-Model Alignment of Post-Hoc Deepfake Evidence Under Controlled Compression | |
| Seryano, T. (Talya) | Evaluating the Reliability of Explainable AI Methods for CNN and Vision Transformer Models in COVID-19 Chest X-Ray Classification | |
| Shileeva, K. (Ksenia) | Classical-to-Quantum Encoding Strategies for Binary Classification | |
| Simantiris, O.L. (Odysseas) | Optimization Algorithm Ranking Preservation Using Surrogate Models in the MECHBench Framework | |
| Sips, A. (Anna) | Mechanistic Interpretability in Deep Learning-Based Side-Channel Attacks | |
| Smit, P.G.A. (Priya) | Detecting Android Malware Using Graph Neural Networks: A Comparison Between an Inductive and Transductive Learning Approach | |
| Snepvangers, A. (Alexander) | LLM Performance on Multi-Interlocutor NLI Tasks | |
| Spek, A.M. van der (Anna Michelle) | LLaMEA for Clustering Problems | |
| Steeg, P. van der (Peter) | Optimizing SubDisc Subgroup Quality: A Comparative Study of Search Methods Across Interval Sizes | |
| Szekeres-Kovács, V. (Veronika) | Evaluating the Intrinsic Interpretability of Time-Conditioned Contraction Matching | |
| Tomić, V. (Vuk) | Utility and Trustworthiness of Generative AI in Peer Review | |
| Tudora, M.T. (Maria Teodora) | Data Mining and Machine Learning for Online Prediction of Vessel Arrival Time Residuals | |
| Uzun, E.M. (Emine Melisa) | The Effect of Emotional Explicitness on Cognitive and Affective Empathy in Large Language Model Responses | |
| Valint, B. (Bence) | Optimizing the Accuracy–Calibration Trade-off with Multi-Objective Genetic Algorithms in Transformer-Based Forecasting for the Hungarian Energy Balancing Market | |
| Verberne, T. (Tim) | Changing the Narrative: Improving NPC Dialogue Consistency Using a Single LLM | |
| Vinasiththamby, T. (Thulashikaa) | Analyzing Representation and Bias in Face Recognition Datasets & The Role of Documentation in Enhancing Transparency | |
| Wang, C. (Cindy) | Collecting a State-of-the-Art Event-Based Dataset for In-Vehicle Gesture Recognition | |
| Wang, J. (Jinnan) | YOLO26-Based Pollen Detection and Classification in Brightfield Microscopy Images | |
| Wang, L. (Lei) | Gaze-Driven Efficient Inference for Vision-Language Models | |
| Wang, X. (Xinyue) | Dynamics of Reassurance-Seeking in Human LLM Interaction: A Computational Benchmark and Risk Analysis | |
| Westerbeek, B. (Bram) | Order-Regularized Fourier Features for Spectral Bias and Adversarial Robustness | |
| Wilk, M. (Mateusz) | Attention-based Reinforcement Learning for the Container Stowage Planning Problem | |
| Wünsch, D. (David) | Transfer Learning of Robustness for Image Classification Neural Networks | |
| Xie, Z. (Zhemin) | Automatic Detection and Whole-Roll Localization of Deep Quilting in Rewinding Videos of Silicon Anode Material | |
| Yuan, R. (Ruike) | AI-driven Smart User Interface Generation from UMLs for Model-Driven Engineering | |
| Yüksel, F. (Faruk) | Generating High Resolution CT Images with GANs | |
| Zagoritis, E. (Emmanouil) | Predicting Futures, Not a Future: Diverse Next Action Anticipation | |
| Zhang, J.J. (Jia Jia) | Network Structure of Skincare Formulations and its Association with Product Popularity | |
