Institution profile

University of Modena and Reggio Emilia

Academic institutioneurope · it
Official website
Research library170linked papers
Opportunities0open roles
Selected work

Representative Papers

Forecasting Energy Availability in Local Energy Communities via LSTM Federated Learning

Jan 31, 2026

This study addresses the challenge of achieving accurate energy availability forecasting in local energy communities, where privacy concerns often restrict access to individual electricity consumption data, thereby hindering the deployment of high-precision predictive models. To overcome this limitation, the work proposes a novel decentralized forecasting framework that integrates Long Short-Term Memory (LSTM) networks with federated learning, enabling collaborative model training without sharing raw user data. Experimental results demonstrate that the proposed approach effectively preserves user privacy while still delivering prediction accuracy sufficient for practical applications. This method offers a viable and innovative technical pathway for intelligent energy management in privacy-sensitive environments.

3 citationsRead paper

CounterVid: Counterfactual Video Generation for Mitigating Action and Temporal Hallucinations in Video-Language Models

Jan 08, 2026arXiv.org

This work addresses the tendency of video-language models to generate hallucinations in action recognition and temporal reasoning due to overreliance on linguistic priors. To mitigate this, the authors propose CounterVid, the first large-scale counterfactual video synthesis framework specifically designed for action- and temporality-related hallucinations. The framework leverages multimodal large language models to guide action editing and combines image and video diffusion models to generate semantically hard negative samples that preserve scene consistency while altering actions or temporal order. This process yields the CounterVid dataset, comprising 26,000 preference pairs. Furthermore, the authors introduce MixDPO, a unified preference optimization strategy that jointly utilizes textual and visual signals to fine-tune Qwen2.5-VL, achieving significant performance gains on temporal ordering tasks and demonstrating strong generalization on standard video hallucination benchmarks.

1 citationsRead paper
Recent publications

Latest Papers