Silvio Martinico headshot

Silvio Martinico

PhD Researcher @ UniPi & ISTI-CNR | Founding Member @ tusKANNy
Email Scholar ORCID GitHub LinkedIn X

I'm a Computer Science PhD Researcher at the University of Pisa and ISTI-CNR, and a founding member of the tusKANNy research group. My work bridges theory and systems. I specialize in Information Retrieval and Approximate Nearest Neighbors (ANN), translating deep academic research into high-performance AI infrastructure. Specifically, I architect and maintain scalable, open-source Rust libraries for vector retrieval.

Open Source Projects

  1. TACHIOM
    TACHIOM is a fast and scalable data structure for late-interaction multi-vector retrieval, written in Rust with Python bindings. It allows to cluster hundreds of millions of vectors in few minutes on CPU and to retrieve from large multivector collections in under 10 ms on a single core.
    GitHub
  2. kANNolo
    A flexible Rust library combining state-of-the-art indexing techniques for both dense, sparse, and multivector embeddings. Designed to make prototyping new ANN algorithms fast and ergonomic.
    GitHub
  3. Vectorium
    A Rust library for storing, accessing, and compressing dense, sparse, and multi-vector embedding datasets. Provides a unified dataset/encoder interface shared across TusKANNy's indexing and search crates. Includes an exhaustive search API and a CLI tool for ground-truth computation.
    GitHub
  4. Awesome Multivector Retrieval
    A curated list of papers, code, models, and datasets for late-interaction multivector retrieval - covering ColBERT-style models, indexing techniques, software libraries, and benchmarks.
    GitHub

Publications

  1. Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing
    Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, and Rossano Venturini
    ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2026
    PDF Code
  2. Multivector Reranking in the Era of Strong First-Stage Retrievers
    Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, and Rossano Venturini
    European Conference on Information Retrieval (ECIR), 2026
    PDF DOI Code
  3. Efficient Approximate Nearest Neighbor Search on a Raspberry Pi
    Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, and Rossano Venturini
    ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2025
    DOI Code
  4. kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search
    Leonardo Delfino, Domenico Erriquez, Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, and Rossano Venturini
    European Conference on Information Retrieval (ECIR), 2025
    PDF DOI Code

Experience

Education

  • PhD in Computer Science @ University of Pisa
    Pisa, Italy · 2023 - ongoing
    Conducting research at the intersection of theory and systems, specializing in Information Retrieval and Approximate Nearest Neighbor (ANN) Search with a focus on high-performance, large-scale vector retrieval.
  • MSc in Computer Science @ University of Pisa
    Pisa, Italy · October 6, 2023
    Graduated with honors. Thesis on Approximate Nearest Neighbors Search.
  • BSc in Mathematics @ University of Pisa
    Pisa, Italy · May 14, 2021
    Thesis on the nature and computability of exponential algebraic structures.
    Thesis

Work

  • Founding Member & Core Maintainer @ tusKANNy
    Pisa, Italy · March 2024 – Present
    Conducting applied research to architect and maintain high-performance, open-source Rust infrastructure for vector search. Serving as a lead developer for retrieval libraries within the group, managing the end-to-end lifecycle from designing algorithms and data structures to translating them into production-ready code, optimizing repository infrastructure and technical documentation.
  • Research Associate @ ISTI-CNR
    Pisa, Italy · 2023 - ongoing
    Conduct research on Information Retrieval and Approximate Nearest Neighbor search at the HPC Lab, designing and engineering high-performance systems for large-scale vector retrieval.
  • Visiting Researcher @ University of Tokyo
    Tokyo, Japan · 02/2025 - 03/2025
  • Teaching Assistant @ University of Pisa
    Pisa, Italy · 03/2024 - 06/2024
    Held weekly Q&A sessions for students of the Algorithms and Data Structures course within the M.Sc. program in Data Science.
  • Research Grant @ ISTI-CNR
    Pisa, Italy · 02/2023 - 08/2023
    Implemented efficient data structures for vectors retrieval.

Out of Office

Beyond research and systems engineering, you can find me lifting at the gym, casually playing beach volleyball or basketball, traveling, or grabbing a Spritz or a beer with friends. I'm a massive One Piece fan, I survive mostly on pasta, and I write my fastest Rust code while listening to heavy metal and Italian hardcore rap.

Contact