Distributed Computing
ETH Zurich

Theses

Our group has several open research projects that are suitable for a master (M), bachelor (B) or semester (S) theses. In addition, we have group projects, and labs for distributed systems majors; projects marked as B or S are usually also suitable for labs or group projects.

If you have an idea for a project that is not on our list but falls into our research area, we would be excited to hear about it.

Available Theses & Labs

TitleTypeContact/SupervisorAssigned
Homo Moralis Plays a GameM/SDamien Berriaud,
Andrei Constantinescu
available
AlphaZero Meets ARCMAndreas Plesner,
Benjamin Estermann
available
Automated Foosball CommentarySTill Aczel,
Joël Mathys
available
Bring Your Own AlgorithmM/SAndrei Constantinescuavailable
Deep Differentiable Logic Gate NetworksM/STill Aczel,
Andreas Plesner
available
Distributed Graph Problems with Malicious ActorsM/SAnton Paramonov,
Andrei Constantinescu
available
Emergent Architectures: Neuro-symbolic AIMGiacomo Camposampieroavailable
Excellent Students for ML in Robust CV/LLMB/M/SAndreas Plesneravailable
Exceptional Students for ML in Audio/MusicB/M/SLuca Lanzendörfer,
Florian Grötschla
available
Exploring adversarial conceptsM/SAndreas Plesneravailable
IQ of VLMs – can they really reason?SAndreas Plesner,
Frédéric Berdoz
available
Karma EconomicsM/SDamien Berriaudavailable
More Efficient Transformers with high-level multi-token predictionM/SFrédéric Berdoz,
Benjamin Estermann
available
Multiplayer GerrymanderingM/SBorna Simicavailable
Optimizing Inventory ManagementM/SAndreas Plesner,
Benjamin Estermann
available
SAT Solving with Graph Neural NetworksM/SSaku Peltonen,
Joël Mathys
available
Topics in Computational Voting and Game TheoryM/SAndrei Constantinescuavailable
Topics in Graph Neural NetworksM/SFlorian Grötschlaavailable

Current Theses & Labs

TitleTypeContact/SupervisorAssignedStudent(s)
Creating the Next Decentralized ComputerBAnton Paramonov,
Yann Vonlanthen
FS 25
Data AttributionBLuca Lanzendörfer,
Frédéric Berdoz
FS 25
Designing the Next ARC ChallengeMSaku Peltonen,
Andreas Plesner
FS 25
Empirical Analysis of Blockchain Payment SystemsBSaku Peltonen,
Lioba Heimbach
FS 25
Evaluating and Controlling the Political Bias of LLMsMFrédéric BerdozFS 25
Fake Singing Voice DetectionMLuca Lanzendörfer,
Florian Grötschla
FS 25
ML for FashionMLuca Lanzendörfer,
Till Aczel
FS 25
Reasoning Benchmark for LLMsBBenjamin Estermann,
Luca Lanzendörfer
FS 25
RecopmressionBTill AczelFS 25
Scalar Quantization for Audio CompressionSTill Aczel,
Luca Lanzendörfer
FS 25
Video-to-Audio GenerationMLuca Lanzendörfer,
Florian Grötschla
FS 25
Abstract Reasoning Corpus (ARC) ChallengeMFrédéric BerdozHS 24
AI-generated Yield CurvesBDaniela Brauckhoff,
Andreas Plesner
HS 24
Audio EditingMLuca Lanzendörfer,
Florian Grötschla
HS 24
Audio WatermarkingMLuca Lanzendörfer,
Florian Grötschla
HS 24
Chaos Testing Blockchain Networks: Simulating Real-World FailuresMYann VonlanthenHS 24
DAO Governance AggregationBArthur GervaisHS 24
DeepEye: Benchmarking & GeneralizationBArd KastratiHS 24
DeepEye: Benchmarking PlatformBArd KastratiHS 24
Egocentric Action RecognitionMArd KastratiHS 24
Empirical Analysis of Prediction MarketsBLioba Heimbach,
Quentin Kniep
HS 24
Evaluating Fast FeedForward NetworksSAndreas PlesnerHS 24
Foundation Models for Decoding Brain Activity - BenchmarkingBArd KastratiHS 24
Foundation Models for Decoding Brain Activity - ModelsMArd KastratiHS 24
Giving ChatGPT a Virtual BodySArd KastratiHS 24
Human-aligned Compression for Robust ModelsSAndreas Plesner,
Till Aczel
HS 24
Kantian Moralists and AltruistsMDamien Berriaud,
Andrei Constantinescu
HS 24
Layer-2s and MEVBLioba Heimbach,
Yann Vonlanthen
HS 24
Multi-modal Contrastive Learning for Emotion RecognitionMArd KastratiHS 24
Neural Fluid Simulation with GNNsSJoël Mathys,
Florian Grötschla
HS 24
Neural Networks for EEG Data: Compression and Reconstruction ValidationSArd Kastrati,
Luca Lanzendörfer
HS 24
Neural Node Overlap Removal with GNNsBFlorian GrötschlaHS 24
Optimizing Encoding Speed for Image CompressionMTill AczelHS 24
Order Book Reconstruction, Analysis, and VisualizationMLuca LanzendörferHS 24
Recommender Systems for PoliticsSFrédéric Berdoz,
Yann Vonlanthen
HS 24
Stability of Adversarial ExamplesBAndreas PlesnerHS 24
Stock Market PredictionMJoël Mathys,
Ruedi Delacour
HS 24
Text-to-MelBLuca Lanzendörfer,
Florian Grötschla
HS 24
Transfer Learning for Graph Recommendation SystemsBFlorian Grötschla,
Luca Lanzendörfer
HS 24
Unified Model for EEG-based Eye TrackingBArd KastratiHS 24
View-Specific Video CompressionBTill AczelHS 24
Volatility Forecasting and Regime Detection for Options TradingMFrédéric Berdoz,
Ruedi Delacour
HS 24
Voting for CoalitionsBAndrei ConstantinescuHS 24
Wave Function Collapse for Graph GenerationSTill Aczel,
Joël Mathys
HS 24
Game Theory for Games: Algorithms and AxiomsGAndrei ConstantinescuFS 24
Learning from DemonstrationsGBenjamin EstermannFS 24
Puzzle solving with Graph Neural NetworksSJoël Mathys,
Benjamin Estermann
FS 24
The Emergence of Two-Party SystemsGAndrei ConstantinescuFS 24

Past Theses & Labs

TitleTypeContact/SupervisorAssignedStudent(s)
Rethinking Adversarial Examples [confidential]MAndreas PlesnerHS 24
Anomaly Detection for Automated Visual Inspection [confidential]MIoana GiurgiuHS 24
Computing with Asynchronous Cellular Automata [confidential]MFlorian Grötschla,
Andreas Plesner
HS 24
Automated Visual Foosball TrackingBJoël Mathys,
Till Aczel
HS 24
Breaking Image CAPTCHAs and designing a new CAPTCHA [confidential]MAndreas PlesnerHS 24
Leveraging Pre-Trained LMs for Rapid and Accurate Structure Elucidation from 2D NMR Data [confidential]SLuca Lanzendörfer,
Florian Grötschla
HS 24
Symbolic Music Generation with Autoregressive Graph Autoencoder [confidential]SFlorian Grötschla,
Luca Lanzendörfer
HS 24
ACORD: An Expert-Annotated Dataset for Contract Clause Retrieval [confidential]MAndreas PlesnerHS 24
Homo Moralis Plays the Centipede Game [confidential]BDamien Berriaud,
Andrei Constantinescu
HS 24
Exploit Detection in the Evolution of DAppsMBenjamin Estermann,
Ye Wang
FS 24
Breaking Google’s reCAPTCHAv3 [confidential]SAndreas PlesnerFS 24
Breaking Google’s reCAPTCHAv3 - Getting good cookies [confidential]SAndreas PlesnerFS 24
Breaking Google’s reCAPTCHAv3 - How are humans classified [confidential]SAndreas PlesnerFS 24
Building a Multi-Cryptocurrency Node ExplorerSLucianna KifferFS 24
CLLAP: Contrastive Language-Lyrics-Audio Pretraining [confidential]MLuca Lanzendörfer,
Florian Grötschla
FS 24
Compute-Efficient Pretraining of Large EEG Models [confidential]BArd KastratiFS 24
Conditional Generation of WavetablesBLuca Lanzendörfer,
Florian Grötschla
FS 24
Improving the Data Quality of ConfSearch using LLMsSAndreas PlesnerFS 24
Data Driven Anomaly Detection for Rails using In-service Railway VehiclesBAndreas PlesnerFS 24
Data Driven Anomaly Detection of Springs in In-service Railway Vehicles [confidential]BAndreas PlesnerFS 24
Hidden State Aggregation Models with GNN Convolutions Applied to Multivariate Time-Series Forecasting in Energy Markets [confidential]MBenjamin EstermannFS 24
Uncovering Discovery: A Deep Dive Into Ethereum’s Discovery Protocols [confidential]MLucianna Kiffer,
Yann Vonlanthen
FS 24
Byzantine Distributed Stable Matching [confidential]MDiana Ghinea,
Andrei Constantinescu
FS 24
Deep Learning-Based Compression of EEG Data Using Neural Codecs [confidential]SArd Kastrati,
Luca Lanzendörfer
FS 24
Benchmarking Music Generation Models and Metrics via Human Preference Studies [confidential]SLuca Lanzendörfer,
Florian Grötschla
FS 24
Benchmarking Positional Encodings for GNNs [confidential]SFlorian GrötschlaFS 24
Sybil Detection using Graph Neural Networks [confidential]MAndreas PlesnerFS 24
Improving Investment Strategies with GNNs [confidential]SFlorian Grötschla,
Joël Mathys
FS 24
Graph Algorithms for Dynamic Directories [confidential]MAndrei Constantinescu,
Pankaj Khanchandani
FS 24
CLAP Embeddings for Artist Similarity with Graph Neural Networks [confidential]GFlorian Grötschla,
Luca Lanzendörfer
FS 24
Automated Vascular Graph Extraction [confidential]MJoël Mathys,
Andreas Plesner
FS 24
Next Level Message-Passing with Hierarchical Support Graphs [confidential]SFlorian GrötschlaFS 24
Hierarchical Representations for Transformers [confidential]MBenjamin EstermannFS 24
FuzzNet: Imitating Byzantine Behavior in Distributed Systems [confidential]MYann VonlanthenFS 24
Incentivizing Simple Transactions [confidential]BLioba Heimbach,
Andrei Constantinescu
FS 24
Infrastructure Impact on Cryptocurrency NetworksSLucianna KifferFS 24
Jigsaw Puzzle Solver using Machine Learning [confidential]SAndreas Plesner,
Till Aczel
FS 24
Reinforcement Learning for State-Based Algorithms on Graphs [confidential]MFlorian Grötschla,
Joël Mathys
FS 24
LightningBench: A Real-World Payment Network Benchmark for Graph Neural Networks [confidential]MFlorian Grötschla,
Lioba Heimbach
FS 24
Leverage Staking using Liquid Staking Tokens [confidential]BLioba Heimbach,
Robin Fritsch
FS 24
Contrastive Lyrics Alignment with a Timestamp-Informed Loss [confidential]SLuca Lanzendörfer,
Florian Grötschla
FS 24
Lyrics to Vocals Generation [confidential]MLuca Lanzendörfer,
Florian Grötschla
FS 24
High-Fidelity Music Vocoder Using Neural Audio Codecs [confidential]SLuca Lanzendörfer,
Florian Grötschla
FS 24
FunctaFormer: Domain Agnostic Super Resolution [confidential]MLuca Lanzendörfer,
Benjamin Estermann
FS 24
Solving Poisson Equations using Neural Walk-on-Spheres [confidential]MAnima AnandkumarFS 24
Open-LLark: Open-Sourcing And Extending LLark [confidential]BLuca Lanzendörfer,
Florian Grötschla
FS 24
A Contention Aware Routing Algorithm for Analog-In-Memory-Computing Based DNN Accelerators [confidential]MWilliam SimonFS 24
Toward Robust Voting Advice Applications: Lessons from Smartvote [confidential]MYann Vonlanthen,
Frédéric Berdoz
FS 24
Reconstructing ODEs for Railway Vehicles Using Machine Learning [confidential]BAndreas PlesnerFS 24
Mangrove: Fast and Parallelizable Smart Contract Agreement [confidential]MYann Vonlanthen,
Quentin Kniep
FS 24
Analyzing Deep Learning Architectures on Stock Prediction [confidential]GFlorian Grötschla,
Joël Mathys
FS 24,
Structured Sparsity for Efficiency in Model InferenceSPeter BelcákFS 24
Text-to-Speech Arena [confidential]SLuca Lanzendörfer,
Florian Grötschla
FS 24
Using Physics-Informed Neural Networks to Predict Railway IrregularitiesMAndreas PlesnerFS 24
Exploring Typical and Uncertainty-Driven Active Learning on DINO Embeddings to Enhance Versatility [confidential]STill Aczel,
Benjamin Estermann
HS 23
AEye: A Visualization Tool for Image Datasets [confidential]GFlorian Grötschla,
Luca Lanzendörfer
HS 23
Airdrop Mechanisms and Their Sybil Resistance [confidential]BLioba Heimbach,
Yann Vonlanthen
HS 23
Tokenization of Ethereum Stake [confidential]SLucianna Kiffer,
Lioba Heimbach
HS 23
Object-Centric Reasoning with Language and Code [confidential]GBenjamin Estermann,
Joël Mathys
HS 23
Locating and Hiding Validators in the Ethereum Consensus Network [confidential]MLucianna Kiffer,
Yann Vonlanthen
HS 23
Attacks on DAOs [confidential]SLioba Heimbach,
Yann Vonlanthen
HS 23
Generative Musical Source Separation Based on Neural Audio Codecs [confidential]SLuca Lanzendörfer,
Florian Grötschla
HS 23
Best Pokémon TeamBAndreas PlesnerHS 23
I’m a Robot. Solving CAPTCHAs with Advanced Machine Learning Techniques [confidential]SAndreas PlesnerHS 23
Audio Data Visualization Using Text-Audio Embeddings [confidential]BLuca Lanzendörfer,
Florian Grötschla
HS 23
Building Practical Distributed AlgorithmsGYann VonlanthenHS 23,
Building Practical Longest Chain ProtocolsGYann VonlanthenHS 23
WikiGame: Graph-Exploration, Fun includedGLuca LanzendörferHS 23,
,
,
Dawn of an Era: How Layer 2 Solutions Change the Workload on Ethereum Blockchains [confidential]MLioba Heimbach,
Quentin Kniep
HS 23
Improving Non-Linear Redundancy Reduction in Self-Supervised Contrastive Learning [confidential]GBéni EgressyHS 23
Crawling the Bitcoin Client EcosystemSLucianna Kiffer,
Lioba Heimbach
HS 23
Cue and Mix-Point Estimation for Automated DJ Systems [confidential]MLuca LanzendörferHS 23
DataComp ChallengeGTill Aczel,
Benjamin Estermann
HS 23
Personalized Federated Learning with Pre-Trained GNNs [confidential]MBéni EgressyHS 23
Diverse Datasets for BCI [confidential]SArd KastratiHS 23
Pre-training a Deep Learning Model for Decoding Brain Activity [confidential]BArd KastratiHS 23
Leveraging Dense Text Representations for Efficient Language ModelingMPeter BelcákHS 23
SUPClust: Active Learning at the BoundariesSBenjamin Estermann,
Till Aczel
HS 23
Exploring Activation Ensembles for Feed-Forward Neural NetworksBFlorian Grötschla,
Joël Mathys
HS 23
Fair Transaction Ordering WebsiteBLioba HeimbachHS 23
Logarithmic Approximation for Road Pricing on Grids [confidential]MAndrei ConstantinescuHS 23
GNN PretrainingMBéni EgressyHS 23
GNNs for TPU GraphsSJoël Mathys,
Florian Grötschla
HS 23
Bridging Image and Audio Compression: A Spectrogram-based Neural ApproachMLuca LanzendörferHS 23
Machine Unlearning ChallengeSLuca Lanzendörfer,
Benjamin Estermann
HS 23
Evaluating Generative Models on Musical Mel Spectrogram Inversion [confidential]GLuca LanzendörferHS 23
Adding Music Modality to LLMs by Leveraging Contrastive Pretraining [confidential]BLuca LanzendörferHS 23
Network-level Attacks Against Ethereum PoSBLioba HeimbachHS 23
In-Depth Analysis of Bidding Strategies in MEV Auctions [confidential]GBenjamin Estermann,
Ye Wang
HS 23
Train Small - Solve Big: Reinforcement Learning on Logic Puzzles using Graph Neural Networks [confidential]MBenjamin Estermann,
Joël Mathys
HS 23
Understanding the Effects of Improved Representations on Downstream Reinforcement Learning Tasks [confidential]SBenjamin EstermannHS 23
Automated Positioning for Smart Lighting [confidential]MJudith Beestermöller,
Andreas Plesner
HS 23
Peer-to-peer Networks under ChurnSLucianna KifferHS 23
Scaling MARL with Graph Neural NetworksMBenjamin Estermann,
Florian Grötschla
HS 23
Text Compression for Efficient Language GenerationMPeter BelcákHS 23
Coarse-to-Fine Unsupervised Text-to-Music Latent Diffusion [confidential]MLuca LanzendörferHS 23
The Peer Discovery Layer of the Ethereum NetworkSLucianna KifferHS 23
The Price of Weighted Majority Support [confidential]GAndrei ConstantinescuHS 23
Distributed Reinforcement Learning for Autonomous Driving in TrackMania [confidential]GBenjamin Estermann,
Luca Lanzendörfer
HS 23
Validity Properties of Byzantine Agreement [confidential]GAndrei Constantinescu,
Diana Ghinea
HS 23
Enhancing GNNs: An Exploration of Iterative Solving and Augmentation TechniquesBJoël Mathys,
Florian Grötschla
FS 23

Interested in a previous thesis? Show all past theses!

Templates & Guidelines