Institution profile

University of Milano-Bicocca

Academic institutioneurope · it
Official website
Research library259linked papers
Opportunities0open roles
Selected work

Representative Papers

Local Level Dynamic Random Partition Models for Changepoint Detection

Jul 29, 2024

Addressing the challenges of modeling dynamic structures and detecting change points in multivariate time series (e.g., biomechanical and motion sensor data), this paper proposes a state-space-based stochastic partitioning model. Our method innovatively embeds a dynamic stochastic partitioning mechanism into the state equation, using Markovian latent variables to capture piecewise temporal dependencies. We design a non-marginalized false discovery rate (FDR) control strategy that explicitly accounts for statistical dependencies among change-point decisions, and support joint clustering of multi-view sequences. Integrating dynamic linear models, stochastic partition priors, and Gibbs sampling, the framework balances interpretability and computational efficiency. Evaluated on synthetic benchmarks and real human gesture phase data, our approach achieves significant improvements in change-point detection accuracy and robustness—reducing FDR by 20–35% over state-of-the-art methods—while demonstrating strong scalability.

3 citationsRead paper

Bayesian Transfer Learning for Artificially Intelligent Geospatial Systems: A Predictive Stacking Approach

Oct 12, 2024

To address the reliance on manual intervention and high-performance hardware for automated analysis, model evaluation, and uncertainty quantification in large-scale geospatial data, this paper introduces the first Bayesian predictive stacking framework tailored for geospatial transfer learning. The method integrates Bayesian modeling, predictive stacking, streaming minibatch training, and spatial statistical inference to enable continual learning propagation and full-scale inference. It achieves low-overhead, scalable, and interpretable joint uncertainty quantification for multivariate geospatial predictions on commodity GPUs. Experiments on climate science datasets—sea surface temperature and vegetation index—demonstrate over 60% faster inference and significantly improved accuracy, while eliminating dependence on high-end hardware and manual hyperparameter tuning. This framework advances practical, resource-efficient uncertainty-aware geospatial modeling.

2 citations1 influentialRead paper

LeWiDi-2025 at NLPerspectives: The Third Edition of the Learning with Disagreements Shared Task

Oct 09, 2025

This work addresses the challenge of modeling and evaluating AI systems’ capacity to capture human judgment variability—such as disagreement and subjectivity. Methodologically, we (1) extend the LeWiDi benchmark to four tasks (paraphrase identification, irony/sarcasm detection, natural language inference) with ordinal annotations and individual-perspective prediction; (2) introduce the first integration of soft-label learning and annotator modeling, moving beyond hard-classification paradigms; and (3) propose a multi-task training framework jointly optimizing distributional prediction, individual annotator modeling, and population-level judgment distribution learning. Contributions include two novel evaluation metrics that surpass conventional measures like cross-entropy, and comprehensive empirical analysis revealing strengths and limitations of existing approaches in modeling judgment variability. These advances significantly enhance LeWiDi’s utility and extensibility as a benchmark platform for controversy-aware AI.

2 citationsRead paper

PerspAct: Enhancing LLM Situated Collaboration Skills through Perspective Taking and Active Vision

Nov 11, 2025

Current large language models (LLMs) and multimodal models exhibit limited perspective-taking capabilities in multi-agent collaboration, hindering accurate modeling of subjective agent perceptions and multi-observer environments. To address this, we propose PerspAct—a novel method that integrates active visual exploration with the ReAct reasoning framework for the first time. PerspAct explicitly samples and models diverse agent-centric perspectives, enabling dynamic comprehension of hierarchical perspective complexity in an extended Director task. Built upon multimodal LLMs, it leverages prompt engineering and explicit state representation. We systematically evaluate PerspAct across seven progressively complex scenarios. Experiments demonstrate significant improvements in both coreference resolution and collaborative task accuracy, validating the efficacy of jointly modeling active perception and perspective understanding. Our work establishes a new paradigm for situational awareness in multi-agent settings.

1 citations1 influentialRead paper

The cost of ensembling: is it always worth combining?

Jun 05, 2025

Time-series ensemble forecasting faces a critical trade-off between predictive accuracy and computational cost. This paper systematically evaluates ten base models and eight ensemble strategies on the M5 and VN1 retail datasets, measuring performance in point forecasting (RMSE) and probabilistic forecasting (CRPS), alongside computational overhead. Methodologically, we analyze ensemble size scalability, propose an “efficiency-driven ensemble” paradigm, and assess downsampling-based retraining frequency reduction. Key contributions: (1) Ensembles of only two to three models achieve near-optimal accuracy; (2) The efficiency-driven paradigm reduces average computational cost by over 40% while retaining ≥95% of baseline accuracy; (3) Reducing retraining frequency cuts training overhead by up to 70%, with negligible impact on point forecasts and robust performance in probabilistic forecasting. Results confirm that ensembling consistently improves prediction—especially probabilistic calibration—but high accuracy typically incurs high cost. Our framework delivers a scalable, cost-effective ensemble strategy for resource-constrained deployment.

1 citations1 influentialRead paper
Recent publications

Latest Papers

Overview of ROMCIR 2026: The 6th Workshop on Reducing Online Misinformation through Credible Information Retrieval

Sep 04, 2026

In the digital online ecosystem, we are surrounded by distinct forms of information pollution, posing significant threats to both individuals and society. Fake news, for instance, wields power to sway public opinion on matters of politics and finance. Deceptive reviews can either bolster or tarnish the reputation of businesses, while unverified medical advice may steer people toward harmful health practices. In light of this challenging landscape, it has become imperative to ensure that users have access to both topically relevant and factually accurate information that does not warp their perception of reality, and there has been a surge of interest in various strategies to combat misinformation through different contexts and multiple tasks. The purpose of the ROMCIR Workshop, for some years now, is precisely that of engaging the Information Retrieval community to explore potential solutions that extend beyond conventional misinformation detection approaches. Key objectives include identifying subjective and objective factors associated with information credibility and truthfulness, respectively, and integrating such factors as fundamental dimensions of relevance within IR Systems (IRSs), achieving early detection of misinformation, and ensuring that the search results retrieved are not only truthful but also explainable to the users of IRSs. Moreover, it is essential to evaluate the role of generative models such as Large Language Models (LLMs) in inadvertently amplifying misinformation problems, and how they can be used to support IRSs, together with the contribution that the human-in-the-loop paradigm can have in this context.

0 citationsRead paper