72 citations · 320 across the 36 of their papers we have counts for
39 papers
PUMA: Post-Hoc Sparsification of Universal Multimodal Embeddings for Efficient Retrieval
Matteo Attimonelli, Alessandro De Bellis, Franco Maria Nardini +4
Universal multimodal embedders enable retrieval across text, image, and combined queries, but their dense representations incur high memory and inference costs. Post-hoc sparsifica…
Efficient Multivector Retrieval with Token-Aware Clustering and Hierarchical Indexing
Silvio Martinico, Franco Maria Nardini, Cosimo Rulli +1
Multivector retrieval models achieve state-of-the-art effectiveness through fine-grained token-level representations, but their deployment incurs substantial computational and memo…
Sparton: Fast and Memory-Efficient Triton Kernel for Learned Sparse Retrieval
Thong Nguyen, Cosimo Rulli, Franco Maria Nardini +2
State-of-the-art Learned Sparse Retrieval (LSR) models, such as Splade, typically employ a Language Modeling (LM) head to project latent hidden states into a lexically-anchored log…
Forward Index Compression for Learned Sparse Retrieval
Sebastian Bruch, Martino Fontana, Franco Maria Nardini +2
Text retrieval using learned sparse representations of queries and documents has, over the years, evolved into a highly effective approach to search. It is thanks to recent advance…
Multivector Reranking in the Era of Strong First-Stage Retrievers
Silvio Martinico, Franco Maria Nardini, Cosimo Rulli +1
Learned multivector representations power modern search systems with strong retrieval effectiveness, but their real-world use is limited by the high cost of exhaustive token-level…
Exact Nearest-Neighbor Search on Energy-Efficient FPGA Devices
Patrizio Dazzi, William Guglielmo, Franco Maria Nardini +2
This paper investigates the usage of FPGA devices for energy-efficient exact kNN search in high-dimension latent spaces. This work intercepts a relevant trend that tries to support…
Blending Learning to Rank and Dense Representations for Efficient and Effective Cascades
Franco Maria Nardini, Raffaele Perego, Nicola Tonellotto +1
We investigate the exploitation of both lexical and neural relevance signals for ad-hoc passage retrieval. Our exploration involves a large-scale training dataset in which dense ne…
Efficient Sketching and Nearest Neighbor Search Algorithms for Sparse Vector Sets
Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli +1
Sparse embeddings of data form an attractive class due to their inherent interpretability: Every dimension is tied to a term in some vocabulary, making it easy to visually decipher…
Early-Exit Graph Neural Networks
Andrea Giuseppe Di Francesco, Maria Sofia Bucarelli, Franco Maria Nardini +3
Early-exit mechanisms allow deep neural networks to stop inference once prediction confidence is high, reducing latency and energy on easy inputs while retaining full-depth accurac…
Effective Inference-Free Retrieval for Learned Sparse Representations
Franco Maria Nardini, Thong Nguyen, Cosimo Rulli +2
Learned Sparse Retrieval (LSR) is an effective IR approach that exploits pre-trained language models for encoding text into a learned bag of words. Several efforts in the literatur…
Efficient Conversational Search via Topical Locality in Dense Retrieval
Cristina Ioana Muntean, Franco Maria Nardini, Raffaele Perego +2
Pre-trained language models have been widely exploited to learn dense representations of documents and queries for information retrieval. While previous efforts have primarily focu…
Investigating the Scalability of Approximate Sparse Retrieval Algorithms to Massive Datasets
Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli +2
Learned sparse text embeddings have gained popularity due to their effectiveness in top-k retrieval and inherent interpretability. Their distributional idiosyncrasies, however, hav…
kANNolo: Sweet and Smooth Approximate k-Nearest Neighbors Search
Leonardo Delfino, Domenico Erriquez, Silvio Martinico +3
Approximate Nearest Neighbors (ANN) search is a crucial task in several applications like recommender systems and information retrieval. Current state-of-the-art ANN libraries, alt…
Power- and Fragmentation-aware Online Scheduling for GPU Datacenters
Francesco Lettich, Emanuele Carlini, Franco Maria Nardini +2
The rise of Artificial Intelligence and Large Language Models is driving increased GPU usage in data centers for complex training and inference tasks, impacting operational costs,…
Rewriting Conversational Utterances with Instructed Large Language Models
Elnara Galimzhanova, Cristina Ioana Muntean, Franco Maria Nardini +2
Many recent studies have shown the ability of large language models (LLMs) to achieve state-of-the-art performance on many NLP tasks, such as question answering, text summarization…
Early Exit Strategies for Approximate k-NN Search in Dense Retrieval
Francesco Busolin, Claudio Lucchese, Franco Maria Nardini +3
Learned dense representations are a popular family of techniques for encoding queries and documents using high-dimensional embeddings, which enable retrieval by performing approxim…
Pairing Clustered Inverted Indexes with kNN Graphs for Fast Approximate Retrieval over Learned Sparse Representations
Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli +1
Learned sparse representations form an effective and interpretable class of embeddings for text retrieval. While exact top-k retrieval over such embeddings faces efficiency challen…
Optimistic Query Routing in Clustering-based Approximate Maximum Inner Product Search
Sebastian Bruch, Aditya Krishnan, Franco Maria Nardini
Clustering-based nearest neighbor search is an effective method in which points are partitioned into geometric shards to form an index, with only a few shards searched during query…
Efficient Inverted Indexes for Approximate Retrieval over Learned Sparse Representations
Sebastian Bruch, Franco Maria Nardini, Cosimo Rulli +1
Learned sparse representations form an attractive class of contextual embeddings for text retrieval. That is so because they are effective models of relevance and are interpretable…
A Learning-to-Rank Formulation of Clustering-Based Approximate Nearest Neighbor Search
Thomas Vecchiato, Claudio Lucchese, Franco Maria Nardini +1
A critical piece of the modern information retrieval puzzle is approximate nearest neighbor search. Its objective is to return a set of data points that are closest to a query…
Efficient Multi-Vector Dense Retrieval Using Bit Vectors
Franco Maria Nardini, Cosimo Rulli, Rossano Venturini
Dense retrieval techniques employ pre-trained large language models to build a high-dimensional representation of queries and passages. These representations compute the relevance…
Bridging Dense and Sparse Maximum Inner Product Search
Sebastian Bruch, Franco Maria Nardini, Amir Ingber +1
Maximum inner product search (MIPS) over dense and sparse vectors have progressed independently in a bifurcated literature for decades; the latter is better known as top- retrie…
Post-hoc Selection of Pareto-Optimal Solutions in Search and Recommendation
Vincenzo Paparella, Vito Walter Anelli, Franco Maria Nardini +2
Information Retrieval (IR) and Recommender Systems (RS) tasks are moving from computing a ranking of final results based on a single metric to multi-objective problems. Solving the…
Neural Network Compression using Binarization and Few Full-Precision Weights
Franco Maria Nardini, Cosimo Rulli, Salvatore Trani +1
Quantization and pruning are two effective Deep Neural Networks model compression methods. In this paper, we propose Automatic Prune Binarization (APB), a novel compression techniq…