Research Continuity
Several projects continue completed work, explore a new branch of the same research question, or prepare a shared foundation for a later project. The maps below show those explicit relationships; projects without a stated lineage are not included.
How to read the map: Arrows indicate research continuity. Branches are projects that can develop independently from the same foundation. A converging dependency means the later project follows the combined results of every preceding branch.
Project Families
Recursive vision transformers
One completed bachelor project opens three specialised master-level research directions.
Combining Recursive Weight-Sharing with Token Merging for Edge Vision Transformers
Hardware-aware design-space exploration
Input-adaptive token merging
Spatially aware token reconstruction
Transformer deployment on FPGA
The first deployment study becomes a foundation for optimisation and reusable hardware blocks.
Automated Transformer Deployment on FPGA for Particle Tracking
Latency improvement for partitioned FPGA deployment
Reusable Transformer block synthesis
Industrial CPS streaming
Postmortem, phase-based analysis continues as a runtime monitoring project, which is extended through three parallel specialisations.
Postmortem, phase-based analysis of industrial CPS time-series data
Runtime stream processing for industrial CPS behaviour monitoring
Generative models for synthetic industrial CPS data streams
Adaptive preprocessing for streaming industrial CPS data
Specialised model routing for streaming fault detection
Information position effects
The InfoPos framework continues with a transfer study on knowledge-informed segmentation.
Knowledge- and data-position framework for ML-assisted fault identification
Knowledge-informed segmentation for milling tool-wear detection
Efficient model design
Distributed model-parallelism research leads to a data-efficiency optimisation project.
Transforming Convolutional Neural Networks for Model Parallelism
Neural Architecture Search Optimisations for Data-Efficiency
REDVID simulation framework
Five parallel extensions expand the simulator before a shared performance study can begin.
REDuced VIrtual Detector simulation framework for particle propagation
Multiple enhancements
Time dimension and 4D tracking
Track generation and complexity levels
Electron simulation
Muon simulation
Performance Analysis and Benchmarking for Simulations