Research

Publications

Peer-reviewed papers from the TusKANNy team, covering approximate nearest neighbor search across dense, sparse, and multi-vector representations.

2026

SIGIR 2026Multivector RetrievalLate-InteractionClustering

Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing

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

Proposes TACHIOM, a multivector retrieval system that uses Token-Aware Clustering (TAC) for accurate and scalable token clustering. By combining hierarchical indexing with a MaxSim-optimized Product Quantization layout, TACHIOM achieves up to 247x faster clustering than standard k-means and delivers up to 9.8x faster retrieval compared to state-of-the-art systems.

Read PDF
SIGIR 2026Sparse RetrievalScalability

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

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

Sparton is a Triton kernel for the Language Model head in Learned Sparse Retrieval models that fuses tiled matrix multiplication, ReLU, log1p, and max-reduction into a single GPU kernel, achieving up to 4.8x speedup and an order-of-magnitude reduction in peak memory usage compared to PyTorch baselines.

Read PDF
ECIR 2026Sparse RetrievalCompression

Forward Index Compression for Learned Sparse Retrieval

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

Introduces DotVByte, a compression technique optimized for inner product computation that achieves significant space savings while maintaining sparse retrieval efficiency.

Read PDF
ECIR 2026Multi-vectorReranking

Multivector Reranking in the Era of Strong First-Stage Retrievers

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

Demonstrates that replacing token-level gatherer phases with learned sparse retrieval achieves over 24x speedup over state-of-the-art multivector retrieval systems.

Read PDF

2025

Under review at the Journal of the ACMSparse RetrievalSketchingInverted Index

Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Sets

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

Introduces theoretically-grounded sketching algorithm to reduce effective dimensionality while preserving inner product-induced ranks, and shows its link with the Seismic data structure.

Read PDF
ECIR 2025DenseSparseLibrary

kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search

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

A Rust-based ANN research library combining state-of-the-art indexing for dense and sparse vectors with vector quantization, designed for easy prototyping.

Read PDF
ECIR 2025Sparse RetrievalScalability

Investigating the Scalability of Approximate Sparse Retrieval Algorithms to Massive Datasets

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

Compares graph-based and inverted index-based sparse retrieval methods on the 138M-passage MS MARCO v2 dataset, uncovering scalability challenges and efficiency trade-offs.

Read PDF
SIGIR 2025Sparse RetrievalInference-Free

Effective Inference-Free Retrieval for Learned Sparse Representations

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

Proposes Li-LSR, which replaces the query encoder with a fast lookup table by learning a static relevance score per token at training time, achieving state-of-the-art inference-free sparse retrieval and surpassing SPLADE-v3-Doc by 1 mRR@10 point on MsMarco and 1.8 nDCG@10 points on BEIR.

Read PDF

2024

CIKM 2024Sparse Retrievalk-NN Graph

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

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

Enhances Seismic with k-NN graph integration and a clustering hypothesis, achieving nearly 2.2x speedup over standard Seismic while maintaining accuracy.

Read PDF
SIGIR 2024Sparse RetrievalInverted Index

Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations

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

Presents Seismic, a novel inverted index organization that enables fast retrieval over learned sparse embeddings, competitive with dense retrieval on BigANN benchmarks.

Read PDF