Continual Learning for Embodied Agents: Methods, Evaluation and Practical Use: a Systematic Literature Review

By Andrei Dascalu

Embodiment and Human-Inspired Socio-Cognitive Mechanisms in Artificial Agents: A Systematic Scoping Review

By Kaushik Karthikeyan

Applications of The Active Inference and The Free-Energy Principle Frameworks for Mimicking Social Human Behaviours on Intelligent Agents

By Lara Sakarya

Open-endedness and intrinsic motivation in embodied virtual agents: A Systematic Literature Review

By Mircea Lică

A Survey of Interrater Agreement in Datasets for Automatic Affect Prediction

Supervisors: Bernd Dudzik

A Survey of Interrater Agreement in Datasets for Audio Visual Automatic Affect Prediction: A Systematic Literature Review

By Alexandru Preda

A Survey of Interrater Agreement in Datasets for Facial Automatic Affect Prediction

By Mana Mahmoudi

A Systematic Review of Datasets Presenting Various Agreement Measures and Affect Representation Schemes

By Oana Mădălina Fron

Survey of Interrater Agreement in Automatic Affect Prediction for Speech Emotion Recognition

By Oscar Wezenaar

Analyzing the Wild-West of Interrater Agreement in Affective Content Analysis on Text: A Systematic Literature Review

By Violeta Mara Macsim

Adapting unconstrained spiking neural networks to explore the effects of time discretization on network properties

Supervisors: Nergis Tömen, Aurora Micheli

The role of membrane time constant in the training of spiking neural networks: Improving accuracy by per-neuron learning

By Adam Pazderka

The effects of the time step size on the accuracy, sparsity and latency of the SNN

By Alexandru Cojocaru

The effects of time-discretization on spike-based backpropagation as opposed to membrane-potential backpropagation

By Lubov Chalakova

How are the training accuracy and training speed (in epochs and time) of a spiking neural network affected...

By Max Guichard

Correlation between step size and accuracy for real world task

By Zheija Hu

Adaptive algorithm for resource generation in a quantum network

Supervisors: Gayane Vardoyan, Bethany Davies

Adaptable Resource Generation Protocols For Quantum Networks

By Aksel Tacettin

Optimising Adaptive Resource Generation in Near-Term Quantum Networks

By Boris Goranov

Adaptive Algorithm for Resource Generation in a Quantum Network

By Ioana-Lisandra Draganescu

A Heuristic Approach for Resource Generation in a Quantum Network with Purifications

By Qu Tianchen

Effects of parameter drift and induced decoherence in entangled quantum link generation on RL based policy performance

By Radu-Ionut Ciobanu

Algorithms and Applications for Optimal Decision Trees

Supervisors: Emir Demirović, Koos van der Linden

P-STreeD: A Multithreaded Approach for DP Optimal Decision Trees

By Albert Sandu

Optimal Decision Trees for non-linear metrics

By Bogdan Bancuta

Optimal Decision Trees for the Algorithm Selection Problem: Balancing Performance and Interpretability

By Daniël Poolman

Optimal Survival Trees With the Iterative Breslow Estimator and the Integrated Brier Score Objective

By Izzy Van der Giessen

Optimal Cox Survival Trees

By Matei Mihai Mirica

Approximating Nearest Neighbors in Hyperbolic Space

Supervisors: Martin Skrodzki, Elmar Eisemann

Accelerating Hyperbolic t-SNE using the Lorentz Model

By Daniel Peter

Accelerating hyperbolic t-SNE Quadtree generalization for the upper half-plane model

By Dido Dimitrov

Accelerating hyperbolic t-SNE in the Klein Disk model

By Jochem Lippes

Accelerating t-SNE using a uniform grid-based approximation

By Milan Otten

Hyperbolic t-SNE with a Quadtree Splitting in the Cartesian Coordinate System

By Yehor Kozyr

Architectural Decisions for Language Modelling with (Small) Transformers

Supervisors: Arie van Deursen, Maliheh Izadi, Aral de Moor

Evaluating Adaptive Activation Functions in Language Models

By Filip Ignijic

Exploring Speed/Quality Trade-offs in Dimensionality of Attention Mechanism

By Khalit Gulamov

Pushing the Limits of the Compressive Memory Introduced in Infini-Attention

By Lauri Kesküll

Tokenization Matters: Training your Tokenizer Right

By Rafael Braga Medeiros Mota Borges

Sparse Transformers are (in)Efficient Learners: Comparing Sparse Feedforward Layers in Small Transformers

By Yijun Wu

Automated Processing of Scanned Historic Watermarks

Supervisors: Martin Skrodzki, Jorge Martinez Castaneda

Binarization of Historical Watermarks: A Review of Thresholding Techniques Applied to Historical Watermark Images

By Anna Lantink

Text Removal Using Wavelet Transform and Morphological Operations

By Diana Banță

Pre-trained Models on Scanned Historic Watermarks

By Marin Alexandru Remus

A Comparison of Feature Extraction Techniques for Binarized Content-Based Image Retrieval

By Sydney Kho

Curve Reconstruction and Approximation in Binarised Scanned Historic Watermark Images

By Vladimir Petkov

Behavior-agnostic Reinforcement Learning: We Have Data! Now What?

Supervisors: Frans Oliehoek, Stephan Bongers

SimuDICE: Offline Policy Optimization Through Iterative World Model Updates and DICE Estimation

By Cătălin Brița

Impact of state visitation mismatch methods on the performance of on policy reinforcement learning methods

By Hongwoo Cho

The Effect of State-visitation Mismatch on Off-policy Evaluation in Behaviour-agnostic Reinforcement Learning

By Kevin Chen

The Impact of Initial Start Distribution Mismatch on Policy Evaluation in Behavior-agnostic Reinforcement Learning

By Tiberiu Sabău

How does the use of sample-splitting and cross-fitting techniques mitigate the effects...

By Yaren Aslan

Biologically Interpretable Deep Learning for Metabolomics

Supervisors: Marcel Reinders, Gennady V. Roshchupkin

Biologically Interpretable Deep Learning for Metabolomics: Predicting Depression with Biological Insight

By Tom Kitak

Bug Buster: Augmenting Test Assertions using Large Language Models

Supervisors: Annibale Panichella, Mitchell Olsthoorn

How Effective is GPT-4o at Generating Test Assertions?

By Adomas Bagdonas

EvoLLve'M: Improving Test Assertions and Mutations Score using ChatGPT-4o and EvoSuite

By Arda Turhan

Evaluating the Effectiveness of Meta Llama 3 70B for Unit Test Generation

By Reinier Schep

Using local LLMs in constrained environments for increasing mutation score

By Roelof van der Geest

Bug Buster Enhancing Unit Tests using ChatGPT-3.5

By Stefan Creastă

Collaborative Projects in Virtual Reality Environments

Supervisors: Ricardo Marroquim, Amir Zaidi

Dynamically Transparent Ghost Instructors and Their Effect on Learning and Skill Retention in Virtual Reality Environments

By Cassandra M.S. Visser

Effect of Facial Realism on Presence in Collaborative Virtual Environments

By Joshua B. Slik

Matching gestures on word-gesture keyboards in VR with Bézier curves

By Stiliyan Nanovski

Reducing lag in a distributed physics system through ahead-of-time simulation: An initial implementation

By Timothy Zonnenberg

Communicating trust-based beliefs and decisions in human-AI teams

Supervisors: Myrthe Tielman, Carolina Centeio Jorge

Communicating trust-based beliefs and decisions in human-AI teams using real-time visual_explanations

By Elena Dumitrescu

Communicating trust-based beliefs and decisions in human-AI teams

By Elena Uleia

The impact of textual summary of changes of the artificial agent's mental model on the human teammate's trust in the agent and overall satisfaction

By Razvan Loghin

Communicating Trust-based Beliefs and Decisions in Human-AI Teams using Visual Summaries of Explanations

By Sahar Marossi

Communicating Trust-based Beliefs and Decisions in Human-AI Teams

By Tamer Sahin

Correct-by-construction Implementation of Type Checkers

Supervisors: Jesper Cockx, Sára Juhošová

Correct-by-Construction Implementation of Typecheckers: Typechecking records with depth and width subtyping

By Kazimierz Ciaś

An Exceptional Type-Checker: Advancing Type-Checker Reliability with the Correct-by-Construction Approach...

By Mariusz Kicior

Correct-by-Construction Type-Checking for Algebraic Data Types: Implementing a Type-Checker in Agda

By Miloš Ristić

Correct-by-construction Type Checking for Substructural Type Systems

By Vince Szabó

Eliminating bugs in type inference algorithms by describing them with precise types

By Vincent Pikand

Curriculum Strategies for Faster Meta-Learning

Supervisors: Matthijs Spaan, Joery de Vries

Application of Self-Paced learning for Noisy Meta-Learning

By Árpád Aszalós

Teaching How to Learn to Learn: Teacher-Student Curriculum Learning for Efficient Meta-Learning

By Bertold Kovács

Exploring an Evolutionary Approach for Task Generation in Meta-Learning with Neural Processes

By Kerem Yoner

Comparative Analysis of Curriculum Strategies in training Meta-Learning

By Maria Mihai

Dataset/Database Watermarking

Supervisors: Zeki Erkin, Devriş İşler

Enhancing XML Zero-Watermarking Robustness Using Usability Queries and Functional Dependencies

By Benedek Székács

Watermarking of numerical datasets used for ML

By Marius-Cosmin Crăciun

Extending Null Embedding for Deep Neural Network (DNN) Watermarking

By Kaan Altınay

3D mesh object watermarking

By Matthijs van Andel

Watermarking time-series data using DWT

By Mike Raave

Deciphering the Secret Language of Gesture in Social Interactions in the Wild

Supervisors: Hayley Hung, Ivan Kondyurin, Zonghuan Li

Hand Gestures Classification in Crowded Environments

By Alexandru Grigore

Analysing Hand Gestures in Real-World Interactions

By Franciszek Latała

Deciphering the Meaning of Gestures In the Wild

By Irene Aldabaldetrecu

Deep Learning for Automated segmentation of the hip joint in X-ray images (collaboration with Erasmus MC)

Supervisors: Jesse Krijthe, Gijs van Tulder, Myrthe van den Berg

Challenges in Domain Adaptation for Medical Image Segmentation

By Adam Bayle

A study of the accuracy of a ResUNet-based approach for predicting the minimum joint space width ...

By Dragos Ileana

SuperLoss: A Superpixel-Guided Loss for Noisy Label Semantic Segmentation in X-Ray Images

By Giannis Lazarou

Segmentation of the hip joint space based on a radial projection originating from the center of the femoral head

By Kees Blok

Improving Generalizability in X-Ray Segmentation of the femur

By Roland Bockholt

Detecting Collaborative Scanners

Supervisors: Georgios Smaragdakis, Harm Griffioen

Detecting Collaborative Scanners Using Clustering Methods

By Andrei Ionescu

Detecting Collaborative Scanners based on Shared Behavioral Features

By Andrei-Iulian Vişoiu

Detecting Collaborative ZMap Scans

By Fatih Açıkkollu

Iteratively Detecting Collaborative Scanner Fingerprints: An Iterative Approach to Identifying Fingerprints using Stratified Sampling

By Jelt Jongsma

An Investigation into Collaborative Scanners

By Matyáš Kollert

Detection of Cancer Using Blood

Supervisors: Marcel Reinders, Stavros Makrodimitris, Bram Pronk, Daan Hazelaar

Quantifying complementarity between different cfDNA features

By Amr Farooq

Key Fragmentomics Features for Cancer Detection

By David Peța

The Impact of Pre-processing Data on Fragmentomics Analysis Used in Cancer Screening

By Mirko Boon

Understanding The Influence of DNA Fragment Lengths in Detecting Cancer

By Monica Paun

Analysis of cell deconvolution methods: A comparison of reference-based and reference-free cell deconvolution

By Stanisław Howard

Don't follow the leader: Independent thinkers create scientific innovation

Supervisors: Hayley Hung, Chenxu Hao, Vandana Agarwal

The dissociation of researchers from superstars through a new metric

By Filip Marchidan

Independent Thinkers and Scientific Progress: An Analysis of Superstar Influence on Computer Science Research Dynamics

By Filip Plonka

Visualizing Collaboration with Superstars: A Novel Approach to Visualizing Collaboration

By Preston Hull

Dynamic Algorithmic Fairness in Machine Learning

Supervisors: Anna Lukina

The SMICT algorithm for Enhancing fairness in Dynamic Datasets

By Bogdan Badale

Adaptive Runtime Fairness Monitoring for Credit Scoring During Economic Fluctuations

By Eigard Alstad

The Effect of Ageing of Datasets in Long Term Fairness

By Jorden van Schijndel

Analysing Data Features on Algorithmic Fairness in Machine Learning

By Pavlos Markesinis

Efficiency in Compiler Architecture

Supervisors: Soham Chakraborty, Dennis Sprokholt

Beyond Traditional Lexing

By Alexandru Bolfa

Comparative Analysis of Linking Efficiency

By Anna Szymkowiak

Efficient Task Scheduling in Build Systems

By Arav Khanna

Memory Layout Optimisation on Abstract Syntax Trees

By Iannis de Zwart

Efficient Term-Rewriting Super-Optimisation

By Mark Ardman

Estimating the Amplification Factor of Cyber Attacks in the Wild

Supervisors: Georgios Smaragdakis, Harm Griffioen

Exploring DDoS amplification attack vectors prevalent in the Dutch IP range

By Konstantin Dimitrov

Estimating the Amplification Factors in the Network Infrastructure of France...

By Panayiotis Hadjiioannou

Amplification Detection: Determining DDoS Abuse Potential of Your Network

By Piotr Politowicz

Estimating the Amplification Factor of Three Common Protocols in DRDoS Attacks...

By Rares Toader

Investigating the Amplification Potential of Common UDP-Based Protocols in DDoS Attacks across Belgium and Luxembourg

By Vlad Nitu

Evaluating Algorithmic Fairness Solutions

Supervisors: Jie Yang, Sarah Carter

Capturing Power: Feminist Considerations about Machine Learning Fairness

By Alexandru Postu

Influence of Data Processing on the Algorithm Fairness vs. Accuracy Trade-offs...

By Andres Salvi

From Data to Decision: Investigating Bias Amplification in Decision-Making Algorithms

By Elena Mihalache

A study on bias against women in recruitment algorithms: Surveying the fairness literature in the search for a solution

By Johan van den Berg

Algorithmic Fairness: Encouraging Exclusionary Diversity (instead of Inclusionary Pluriversality)

By Kyon Caldera

Explainable AI for human supervision over firefighting robots

Supervisors: Myrthe L. Tielman, Ruben S. Verhagen

How Do Textual and Visual Explanations Affect Human Supervision and Trust in the Robot?

By Bogdan Pietroianu

Influence of Global Explanations on Human Supervision and Trust in Agent

By Dafni Pandeva

How do adaptive explanations that become more abstract over time influence human supervision over and trust in the robot?

By Elena Ibanez

The influence of on-demand explanations on human trust

By Elena Negrila

Adding contrastive explanations to feature attributions

By Yi Wu

Explainable graph models for biological and chemical applications

Supervisors: Megha Khosla, Jana Weber

Comparing GNN explainer faithfulness quantitatively in molecular property prediction

By Heli Pajari

Influence of graph neural network architecture on explainability

By Hubert Janczak

Modified GNN-SubNet: leveraging local versus global Graph Neural Network explanations for disease subnetwork detection

By Oana Milchi

Evaluating the explainability of graph neural networks for disease subnetwork detection

By Sucharitha Rajesh

Influence of molecular structures on graph neural network explainers’ performance

By Tim Stols

Exploring Bandit Algorithms in User-Interactive Systems

Supervisors: Julia Olkhovskaia

Comparing bandit algorithms in static and changing environments

By Cody Boon

Influence of Delay on Contextual Multi-Armed Bandits

By Dragos Arsene

How kernelized Multi-Armed Bandit algorithms compare to other algorithms with fixed kernelized reward and noisy observations

By Marijn Herrebout

Exploring Bandit Algorithms in Sparse Environments

By Rafal Owczarski

Evaluating Performance of Bandit Algorithms in Non-stationary Environments

By Weicheng Hu

Exploring state-of-the-art speech recognisers for low-resource atypical speech

Supervisors: Zhengjun Yue, Yuanyuan Zhang

Automatic Dysarthria Severity Assessment using Whisper-extracted Features

By Christopher Charlesworth

Reducing Bias in State-of-the-Art ASR Systems for Child Speech

By Franz Zeisler

Evaluating Alternative Metrics for Dysarthric Speech Recognition

By H.C. Filip Nguyen Duc

Improving State-of-the-Art ASR Systems for Speakers with Dysarthria

By Mirella Günther

How Does OpenAI's Whisper Interpret Dysarthric Speech?

By Orhan Agaoglu

Extending and Evaluating a Rank Similarity Measure

Supervisors: Julián Urbano Merino, Matteo Corsi

On the Extrapolation of Rank-Biased Overlap and the Assumption of Constant Agreement

By Konstantin-Asen Yordanov

Effects of the Assumption on Ties in Unseen Parts of a Ranking

By Lukas Roels

Average RBO Between Independent Rankings

By Mark Dragnev

On Rank-Biased Overlap with Finite and Conjoint Domains

By Oscar Kriebel

Adaptive Synthetic Generation of Indefinite Rankings

By Som Sinha

Fake force feedback for telemanipulation

Supervisors: Ranga Rao Venkatesha Prasad, Kees Kroep

Approximating hard physical transitions for haptic bilateral teleoperation

By Daniel de Klein

Solving liquids by discarding fluid dynamics: Predicting force feedback of liquids for haptic bilateral teleoperation

By Lukasz Rek

Predicting Force Feedback for interactions with Objects in Motion

By Olaf Heijl

Predicting force feedback of cutting interactions for haptic bilateral teleoperation

By Robert Kurvits

Predicting model deformations for predictive force feedback in haptic bilateral teleoperation applications...

By Stefan Stoicescu

Fast Simulation of Federated and Decentralized Learning Algorithms

Supervisors: Jérémie Decouchant, Bart Cox

Improving the Accuracy of Federated Learning Simulations

By Alexander Nygård

Correct Timings and Inspection of States for Federated Learning Simulations

By Marko Putnik

Exploring the Impact of Client Mobility on Decentralized Federated Learning Performance

By Santiago de Heredia Tenorio

Scheduling Algorithms for Minimisation of Variability in Federated Learning Simulations

By Todor Slavov

Foundation models for gene and cell biology

Supervisors: Marcel Reinders, Niek Brouwer

As a cell, is it better to be single?

By Alan Kuźnicki

Attention on Genes

By Marian Trützschler von Falkenstein

Comparative Analysis of Geneformer and Traditional Machine Learning...

By Michal Krkoska

Strategies for Fine-Tuning Geneformer to Predict the Exposure Level of Cancer Cells to Treatments

By Octavian-Teodor Dragon

Evaluating Machine Learning Approaches to Drug Response Prediciton in Cancer Cells

By Samuel Banas

Generative Federated Learning Approaches for Non-IID Data

Supervisors: David Tax, Swier Garst

Analysing the Performance of Generative Models Trained in a Federated Manner

By Alexandru-Nicolae Ojica

Addressing Statistical Heterogeneity through Generative Similarity-Based Comparison in Federated Learning

By Henry Page

Effect of Different Data Augmentation Strategies on Performance In Federated Learning Systems

By Lohithsai Yadala Chanchu

A Benchmark of Concept Shift Impact on Federated Learning Models

By Matei Tudor Ivan

Enhancing Federated Models with Synthetic Data

By Pil Kyu Cho

Graph Neural Networks for Traffic Forecasting

Supervisors: Elena Congeduti

Graph Neural Networks Training Set Analysis

By Alex Păcurar

Scalability of Graph Neural Networks in Traffic Forecasting

By Danae Natalie Savvidi

Regional Transferability of Graph Neural Networks for Traffic Forecasting

By Ivans Kravcevs

Graph Neural Networks for Long-Term Traffic Forecasting

By Vlad Vrânceanu

Effectiveness of Graph Neural Networks and Simpler Network Models in Various Traffic Scenarios

By Wiktor Grzybko

How good are state-of-the-art automatic speech recognition systems in recognizing Dutch diverse speech?

Supervisors: Odette Scharenborg, YuanYuan Zhang

Google Chirp vs. Whisper: Evaluating ASR performance on Dutch Native vs. Non-Native Teenager Speech

By Anish Jaggoe

Comparing Performance of ASR Systems on Native Dutch Children and Teenagers: Google vs. Microsoft

By Gert van Dijk

State-of-the-art Automatic Speech Recognition Systems on Dutch Regional Dialects

By Simon Kasdorp

How do ASR systems of Google and Microsoft compare when recognizing Dutch spoken by native speakers over the age of 60?

By Thomas de Valck

An Evaluation of Meta MMS and OpenAI Whisper on Native and Non-Native Dutch Speech

By Yiming Chen

How to measure bias in automatic speech recognition?

Supervisors: Odette Scharenborg, Jorge Martinez Castaneda

Discovering Bias in Dutch Automatic Speech Recognition by Clustering Interpretable Acoustic and Prosodic Features

By Kayleigh Jones

Exploring the Relationship Between Bias and Speech Acoustics in Automatic Speech Recognition Systems

By Piotr Cichoń

How to measure bias in automatic speech recognition system? A bias metric without a reference group

By Tereza Ležovičová

Integrating Base Performance and Performance Differences in Automatic Speech Recognition Metrics

By Vincent van Vliet

How to reduce the labeling effort for deep learned object detectors

Supervisors: Jan van Gemert, Osman S. Kayhan

The effect of grouping classes into hierarchical structures for object detection

By Jordy del Castilho

Every human makes mistakes: Exploring the sensitivity of deep-learned object detectors to human annotation noise

By Laurens Michielsen

Object Roughly There: CAM-based Weakly Supervised Object Detection

By Petra Postelnicu

Identifying Labeling Errors Without Access to Ground Truth

By Zeryab Alam

Effects of adding unlabeled training data through pseudo-labeling: Reducing labeling effort for deep learned object detectors

By Zygimantas Liutkus

Image Processing with the Bilateral Filter

Supervisors: Elmar Eisemann, Mathijs Molenaar

Predictable blur behaviour for the bilateral filter

By Bram Snelter

Curvature-Based Bilateral Filter for Image Smoothing

By Dmytro Maksymchuk

Edge-aware Bilateral Filtering

By Glenn Weeland

On-Mesh Bilateral Filtering

By Mihnea Bernevig

Frequency-based Bilateral Filter on Graphics Cards

By Simeon Atanasov

Imperceptible Backdoor Attacks on Deep Regression Models

Supervisors: Guohao Lan, Lingyu Du

Imperceptible Backdoor Attacks on Deep Regression Using the WaNet Method

By Alan Styslavski

Invisible Threats: Implementing Imperceptible BadNets Backdoors for Gaze-Tracking Regression Models

By Daniël Bentsnijder

Imperceptible backdoor attack on deep regression models

By Erik Vidican

The susceptibility of deep regression models to imperceptible backdoor attacks

By J.G.C. van de Meene

Imperceptible Backdoor Attacks for Deep Regression Models Adapting the SIG Backdoor Attack to the Head Pose Estimation Task

By Konstantin Mirinski

Implementation of web-server application to visualize interactions between Single Nucleotide Polymorphisms (SNP) and Structural Variants (SV)

Supervisors: Marcel Reinders, Niccolo Tesi

Implications of the Associations Between Structural Variants and Single Nucleotide Polymorphisms for Coronary Artery Disease Risk

By Boris Pavić

Utilising SNP-SV Correlations to find Structural variants Associated with Alzheimer’s Disease

By Joris Belder

ZygosDB: An efficient read-only database for Genome-Wide Association Studies (GWAS)

By Nick van Luijk

A novel way of visualising eQTLs relative to SNP-SV pairs using Gosling.js

By Sonny Ruff

Visualisation of Interactions between Single Nucleotide Polymorphisms and Structural Variants

By Tom Jacobs

Increasing gender diversity in Computer Science

Supervisors: Fenia Aivaloglou, Shirley de Wit

Gender biases in assignments for Computer Organization and Reasoning and Logic at the TU Delft

By Nienke Schenkelaars

Are the course materials of the first year of the Computer Science Bachelor representing documented stereotypes for computer scientists?

By Nina Immig

A Systematic Literature Review of Interventions in Primary and Secondary Education

By Radu-Stefan Ezaru

Higher Education Policies for Female Retention in Computer Science

By Vladimir Pavlov

A research on gender inclusivity in materials provided during the matching and selection process

By Yifei Lu

Integrating Large Language Models in Games With A Purpose (GWAPs) for Enhanced Knowledge Elicitation

Supervisors: Ujwal Gadiraju, Shreyan Biswas

Game design paradigms for knowledge elicitation using LLMs

By Maciej Lichocki

Leveraging large language models in games with a purpose for enhanced knowledge elicitation

By Tommy Hu

New directions to be explored in integrating Large Languge Models for knowledge elicitation

By Vlad Luca Sebastian Spataru

Types of Knowledge Elicited from Games With A Purpose Using Large Language Models

By Wout Burgers

Large Language Models and the Elicitation of Tacit Knowledge

By Yanzhi Chen

Investigating Inverse Reinforcement Learning (IRL) and Reinforcement Learning from Human Feedback (RLHF)

Supervisors: Luciano Cavalcante Siebert, Antonio Mone

Exploring the Synergy Between Inverse Reinforcement Learning and...

By Ana Bătrîneanu

The Role of Feedback Variety in Reinforcement Learning from Human Feedback

By Ivan Makarov

Addressing Diversity in Reinforcement Learning from Human Feedback

By Javier Paez Franco

Conflict in the World of Inverse Reinforcement Learning...

By Petar Koev

Decreasing the number of demonstrations required for Inverse Reinforcement Learning...

By Zanyar Ogurlu

Investigating the Stability of Graph Neural Networks to Topological Perturbations

Supervisors: Elvin Isufi, Mohammad Sabbaqi, Maoshen Yang

Stability of Graph Neural Network with respect to different types of topological perturbations

By Alexander Brown

Investigation of Stability Property of Graph Neural Network Architectures Under Domain Perturbations

By Khoa Nguyen

Beyond Spectral Graph Theory: An Explainability-Driven Approach to Analyzing the Stability of GNNs to Topology Perturbations

By Rauno Arike

Comparing Graph Neural Network task choices on their stability in face of perturbations

By Vladimir Rullens

An Experimental Look at the Stability of Graph Neural Networks against Topological Perturbations

By Yigit Colakoglu

LLM of Babel: Evaluation of LLMs on code for non-English use-cases

Supervisors: Arie van Deursen, Maliheh Izadi, Jonathan Katzy

An analysis of the behavior of large language models when performing Java code summarization in Dutch

By Gopal-Raj Panchu

Evaluation of LLMs on code for Non-English use cases

By Maksym Ziemlewski

Evaluation of LLMs on code for Non-English use cases

By Paris Loizides

Evaluating CodeGemma-7B for Dutch Code Comment Generation

By Sander Vermeulen

Evaluation of LLMs on code for Non-English use cases

By Yongcheng Huang

Learning Patterns in Train Position Data

Supervisors: Mathijs de Weerdt, Issa Hanou

Detecting Patterns in Train Position Data of Trains in Shunting Yards

By Amanda Krudde

Automatic Detection of Whether a Solution of the Train Unit Shunting Problem (TUSP) is a Week or a Weekend Day

By Ilia Tomov

Classifying Locations by Identifying Station Specific Patterns

By Ivan Smilenov

Analysis of Shunting Yard Usage and Train Unit Clustering

By Ivo Yordanov

Examining Manual Solutions of the Train Unit Shunting Problem to find Train Type Patterns

By Mitchell van Pelt

Learning models from data for sequential decision making

Supervisors: Frans Oliehoek, Jinke He

Understanding the effects of discrete representations in Model-Based Reinforcement Learning

By Mihai Mitrea

See Clearly, Act Intelligently: Transformers in Transparent Environments

By Omar Elamin

Generalisation Ability of Proper Value Equivalent Models in Model-Based Reinforcement Learning

By Severin Bratus

Acting in the Face of Uncertainty: Pessimism in Model-Based Reinforcement Learning

By Sten van Wolfswinkel

Leveraging Large Language Models for Classifying Deliberative Elements in Public Discourse

Supervisors: Luciano Cavalcante Siebert, Amir Homayounirad, Enrico Liscio

Leveraging Large Language Models for Classifying Subjective Arguments in Public Discourse

By Adina Dobrinoiu

Leveraging LLMs for Classifying Subjective Topics Behind Public Discourse

By Ana Cristiana Marcu

Using Large Language Models to Detect Deliberative Elements in Public Discourse

By Bente Zuurbier

Leveraging LLMs for subjective value detection in argument statements

By Joosje Gorter

Decoding Sentiment with Large Language Models

By Timur Oberhuber

Machine Learning Algorithms for Caching Systems

Supervisors: Georgios Iosifidis, Naram Mhaisen, Fatih Aslan

Forecasting in Online Caching

By Gareth Kit

Optimistic Discrete Caching with Switching Costs

By Lucian Tosa

Meta-Learning the Best Caching Expert

By Maik de Vries

Online Learning for Caching with Heterogeneous miss-costs

By Robert Vadastreanu

Models for parametric acoustic scene characterization

Supervisors: Jorge Martinez Castaneda, Dimme de Groot

Evaluation of Perceptual Accuracy in Simulated Room Impulse Responses

By Bendik Christensen

Estimating Reverberation Time by a Function of Intrusive Speech Intelligibility Measures

By Maxim de Groot

Extracting Absorption Coefficients from a Room Impulse Response using a Convolutional Neural Network with Domain Adaptation

By Ties Bloemen

Blind Reverberation Time Estimation Using A Convolutional Neural Network with Encoder

By Xingyu Han

Monitoring people without cameras: privacy is important!

Supervisors: Marco Zuñiga Zamalloa, Girish Vaidya

People Counting from mmWave Radar Point Clouds with Graph Neural Networks

By Bernadett Bakos

Temporal Dynamics in Human Pose Estimation Models

By Dan Savastre

Tracking People for an mmWave-Based Interactive Game: Reducing Stationary Target Noise in Tracking and Movement Reconstruction

By Kaloyan Fachikov

Exploring the Spatial Characteristics of MARS: Assessing the Impact of Neural Net Depth Increase and PointNet Architecture Integration on MARS Performance

By Kevin Hoxha

Temporal Dynamics Modelling for People Counting in Point Clouds: An Extension on PointNet and MARS through LSTM Integration

By Marina Escribano Esteban

Multi-task Offline Reinforcement Learning

Supervisors: Matthijs Spaan, Max Weltevrede

Multi-Task Offline Reinforcement Learning: Experimental Evaluation of the Generalizability of the Soft Actor-Critic + Behavioral Cloning Algorithm

By Axel Geist

Generalization in Offline Reinforcement Learning: Comparing Implicit Q-Learning with Behavioral Cloning

By Juan Tarazona

Multi-task Offline Reinforcement Learning with CQL

By Laimonas Lipinskas

Zero-Shot Generalization in Offline Reinforcement Learning with WSAC-N

By Maxime Museur

Performance of Decision Transformer in multi-task offline reinforcement learning

By Piotr Bieszczad

Multiview image recognition through 3D Gaussian Splats

Supervisors: Xucong Zhang

Self-Supervised Cross-modality Feature Learning using 3D Gaussian Splatting

By Andrei Simionescu

3D Gaussian Splatting for PointNet Object Classification

By Dirk van Dale

Semantic 3D segmentation of 3D Gaussian Splats

By Karol Jurski

Application of Photogrammetry to Gaussian Splatting for mesh and texture reconstruction

By Ken Kiisa

How can we reduce the effect of noise on 3D Gaussian Splats?

By Tijmen Meijer

Reducing Overfitting in 3D Gaussian Splatting using Depth Supervision

By Tygo Spanhoff

Music Recommender Systems & Youngsters

Supervisors: Sole Pera, Robin Ungruh

Exploring the prominence of specific musical features in music listened by children of different age ranges

By Athanasios Christopoulos

Using the listening history of youngsters to predict the features of the perfect song

By Borislav Semerdzhiev

Recommending Appropriate Lyrics to Youngsters

By Jasper Heijne

Evaluating the performance of a Factorisation Machine-based music recommender using musical features for child listeners

By Konrad Barbers

Smart Tunes for Kids, comparing deep learning with traditional models in music recommendation for children

By Lennart Verstegen

Neural Ranking Models

Supervisors: Avishek Anand, Jurek Leonhardt

The impact of the semantic matching within interpolation-based re-ranking

By Alexandru Nistor

The Impact of the Retrieval Stage in Interpolation-based Re-Ranking

By Dan-Cristian Ciacu

Exploring methods to improve effectiveness of ad-hoc retrieval systems for long and complex queries

By Dorian Erhan

Ranking Fusion Functions in Neural Ranking Models

By Gayeon Jee

Evaluating the Suitability of Interpolation-based Re-Ranking for Ad-Hoc Retrieval

By Lucia Navarčíková

Optical flow estimation using event-based cameras

Supervisors: Nergis Tömen, Hesam Araghi

E-GMFlow: Time granularity for transformer architectures in event-based optical flow

By Anca Badiu