I am Lorenzo — AI Research Engineer — I produce novel research and code leveraging Large Language Models. I focus on workflows automation with AI Agents and code generation.
An example of my my research on a new generation of data engineering tools.. More details on Github.
A podcast conversation on Graph Wiring, epiplexity, and the next generation of tools for machine learning and LLM operations.
No projects match this filter yet.
The theoretical foundations, implementation, and empirical proof for each project.
Spectral indexing for vector similarity search combining cosine similarity with graph-Laplacian roughness (λτ-indexing) to produce topology-aware similarity scores. Published in the Journal of Open Source Software.
A transformer architecture that reasons through vibrational (oscillatory) modes in embedding spaces, using spectral decomposition to uncover latent structure beyond static attention patterns.
A library for vector analysis, retrieval and curation using graph-wiring techniques. Explores how topological structure in embedding spaces improves retrieval quality beyond naive cosine similarity.
Epiplexity measures spectral feature interactions in high-dimensional embedding spaces, providing a formal framework for understanding how graph Laplacian eigenstructure influences retrieval quality and manifold geometry.
Open-source implementations, tools, and libraries.