Denis Sutter

Theses & Labs

	Title	Type	Contact/Supervisor	Assigned
Available Theses & Labs
	Optimal Transport for Federated Learning: Bridging Semantics and Alignment through Mechanistic Interpretability	M	Denis Sutter, Antonio Di Maio	available
	Sparse Autoencoders for Sensitive Feature Removal in Federated Learning	M	Denis Sutter, Antonio Di Maio	available
Current Theses & Labs
	Title	Type	Contact/Supervisor	Assigned	Student(s)
	Privacy-Preserving Federated RAG via Bottleneck Hidden Representations for Multi-Institutional Medical Knowledge Sharing	B	Denis Sutter, Antonio Di Maio	HS 26
	Sparse Autoencoders for Sensitive Feature Removal in Federated Learning	M	Denis Sutter, Antonio Di Maio	HS 26
Past Theses & Labs
	Title	Type	Contact/Supervisor	Assigned	Student(s)
	Latent Activation Reconstruction Anchoring for Federated Learning under Feature Skew [confidential]	B	Denis Sutter, Antonio Di Maio	FS 26
	Blockwise Lloyd–Max Quantization for Federated Learning: An Empirical Study of Granularity and Dynamic Bit Allocation [confidential]	S	Denis Sutter, Antonio Di Maio	FS 26
	Bridging Feature and Weight Spaces: USAE-Guided Model Merging [confidential]	B	Denis Sutter, Antonio Di Maio	FS 26