Cosimo Rulli

Research output

2026

Neural Lexical Search with Learned Sparse Retrieval

Andrew Yates, Carlos Lassance, Cosimo Rulli, Eugene Yang, Sean MacAvaney, Siddharth A. K. Singh, Thong Nguyen, Yibin Lei

ECIR • 2026

DOI

Multivector Reranking in the Era of Strong First-Stage Retrievers

Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

ECIR • 2026

DOI

Forward Index Compression for Learned Sparse Retrieval

Sebastian Bruch, Martino Fontana, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

ECIR • 2026

DOI

Evaluating the Efficiency and Effectiveness of Learned Sparse Retrieval with the lsr_benchmark

Maik Fröbe, Ferdinand Schlatt, Cosimo Rulli, Tim Hagen, Jan Heinrich Merker, Gijs Hendriksen, Carlos Lassance, Franco Maria Nardini, Rossano Venturini, Martin Potthast

ECIR • 2026

DOI

Sparton: Fast and Memory-Efficient Triton Kernel for Learned Sparse Retrieval

Thong Nguyen, Cosimo Rulli, Franco Maria Nardini, Rossano Venturini, Andrew Yates

SIGIR • 2026 (Accepted (to appear))

Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing

Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

SIGIR • 2026 (Accepted (to appear))

Gender Disparities in StackOverflow's Community-Based Question Answering: A Matter of Quantity versus Quality

Maddalena Amendola, Cosimo Rulli, Carlos Castillo, Andrea Passarella, Raffaele Perego

ICWSM • 2026

DOI

2025

ChatGPT Versus Modest Large Language Models: An Extensive Study on Benefits and Drawbacks for Conversational Search

Guido Rocchietti, Cosimo Rulli, Franco Maria Nardini, Cristina Ioana Muntean, Raffaele Perego, Ophir Frieder

IEEE Access • 2025

DOI

Neural network compression using binarization and few full-precision weights

Franco Maria Nardini, Cosimo Rulli, Salvatore Trani, Rossano Venturini

Inf. Sci. • 2025

DOI

kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search

Leonardo Delfino, Domenico Erriquez, Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

ECIR • 2025

DOI

Investigating the Scalability of Approximate Sparse Retrieval Algorithms to Massive Datasets

Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini, Leonardo Venuta

ECIR • 2025

DOI

FoodSafeSum: Enabling Natural Language Processing Applications for Food Safety Document Summarization and Analysis

Juli Bakagianni, Korbinian Randl, Guido Rocchietti, Cosimo Rulli, Franco Maria Nardini, Salvatore Trani, Aron Henriksson, Anna Romanova, John Pavlopoulos

EMNLP (Findings) • 2025

PDF

Efficient Conversational Search via Topical Locality in Dense Retrieval

Cristina Ioana Muntean, Franco Maria Nardini, Raffaele Perego, Guido Rocchietti, Cosimo Rulli

SIGIR • 2025

DOI

Effective Inference-Free Retrieval for Learned Sparse Representations

Franco Maria Nardini, Thong Nguyen, Cosimo Rulli, Rossano Venturini, Andrew Yates

SIGIR • 2025

DOI

Efficient Approximate Nearest Neighbor Search on a Raspberry Pi

Silvio Martinico, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

SIGIR • 2025

DOI

Neural Lexical Search with Learned Sparse Retrieval

Andrew Yates, Carlos Lassance, Cosimo Rulli, Eugene Yang, Sean MacAvaney, Siddharth A. K. Singh, Thong Nguyen, Yibin Lei

SIGIR • 2025

DOI

Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Sets

Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

arXiv • 2025

DOI

2024

Efficient Inverted Index-based Approximate Retrieval over High-dimensional Learned Sparse Representations

Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

IEEE Data Eng. Bull. • 2024

PDF

Pairing Clustered Inverted Indexes with κ-NN Graphs for Fast Approximate Retrieval over Learned Sparse Representations

Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

CIKM • 2024

DOI

Efficient Multi-vector Dense Retrieval with Bit Vectors

Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

ECIR • 2024

DOI

Distilled Neural Networks for Efficient Learning to Rank: (Extended Abstract)

Franco Maria Nardini, Cosimo Rulli, Salvatore Trani, Rossano Venturini

ICDE • 2024

DOI

LongDoc Summarization using Instruction-tuned Large Language Models for Food Safety Regulations

Guido Rocchietti, Cosimo Rulli, Korbinian Randl, Cristina Ioana Muntean, Franco Maria Nardini, Raffaele Perego, Salvatore Trani, Manos Karvounis, Jakub Janostik

IIR • 2024

PDF

Seismic: Efficient and Effective Retrieval over Learned Sparse Representation

Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

IIR • 2024

PDF

Efficient and Effective Multi-Vector Dense Retrieval with EMVB

Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

SEBD • 2024

PDF

Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations

Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli, Rossano Venturini

SIGIR • 2024

DOI

2023

Distilled Neural Networks for Efficient Learning to Rank

Franco Maria Nardini, Cosimo Rulli, Salvatore Trani, Rossano Venturini

IEEE Trans. Knowl. Data Eng. • 2023

DOI

Neural Network Compression using Binarization and Few Full-Precision Weights

Franco Maria Nardini, Cosimo Rulli, Salvatore Trani, Rossano Venturini

arXiv • 2023

DOI

CosimoRulli

2026

Neural Lexical Search with Learned Sparse Retrieval

Multivector Reranking in the Era of Strong First-Stage Retrievers

Forward Index Compression for Learned Sparse Retrieval

Evaluating the Efficiency and Effectiveness of Learned Sparse Retrieval with the lsr_benchmark

Sparton: Fast and Memory-Efficient Triton Kernel for Learned Sparse Retrieval

Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing

Gender Disparities in StackOverflow's Community-Based Question Answering: A Matter of Quantity versus Quality

2025

ChatGPT Versus Modest Large Language Models: An Extensive Study on Benefits and Drawbacks for Conversational Search

Neural network compression using binarization and few full-precision weights

kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search

Investigating the Scalability of Approximate Sparse Retrieval Algorithms to Massive Datasets

FoodSafeSum: Enabling Natural Language Processing Applications for Food Safety Document Summarization and Analysis

Efficient Conversational Search via Topical Locality in Dense Retrieval

Effective Inference-Free Retrieval for Learned Sparse Representations

Efficient Approximate Nearest Neighbor Search on a Raspberry Pi

Neural Lexical Search with Learned Sparse Retrieval

Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Sets

2024

Efficient Inverted Index-based Approximate Retrieval over High-dimensional Learned Sparse Representations

Pairing Clustered Inverted Indexes with κ-NN Graphs for Fast Approximate Retrieval over Learned Sparse Representations

Efficient Multi-vector Dense Retrieval with Bit Vectors

Distilled Neural Networks for Efficient Learning to Rank: (Extended Abstract)

LongDoc Summarization using Instruction-tuned Large Language Models for Food Safety Regulations

Seismic: Efficient and Effective Retrieval over Learned Sparse Representation

Efficient and Effective Multi-Vector Dense Retrieval with EMVB

Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations

2023

Distilled Neural Networks for Efficient Learning to Rank

Neural Network Compression using Binarization and Few Full-Precision Weights

Cosimo
Rulli