Get started
Author

Davide Traini

Observed names: D. Traini, Traini, Davide
ORCID: 0009-0007-3098-9349
Observed ORCID: 0009-0007-3098-9349
OpenAlex ID: A5116937652
Efficient token pruning in Vision Transformers using an attention-based Multilayer Network
2025 · Michele Marchetti, Davide Traini, et al. · Expert Systems with Applications · 19
Adaptive patch selection to improve Vision Transformers through Reinforcement Learning
2025 · Francesco Cauteruccio, Michele Marchetti, et al. · Applied Intelligence · 11
Multiplex network-based representation of vision transformers for visual explainability
2025 · Michele Marchetti, Davide Traini, et al. · Neural Computing and Applications · 6
PDF
Behavioral Engagement in VR-Based Sign Language Learning: Visual Attention as a Predictor of Performance and Temporal Dynamics
2026 · Davide Traini, José Manuel Alcalde-Llergo, et al. · Multimodal Technologies and Interaction · 3
PDF
Exploiting knowledge graph communities to fine-tune large language models
2025 · Alessia Amelio, Christopher Buratti, et al. · Expert Systems with Applications · 3
A Matryoshka Hierarchical RAG for Efficient Multi-Hop Question Answering
2026 · Bonifazi, Gianluca, Buratti, Christopher, et al. · arXiv (Cornell University)
PDF
Attention-Based Contrastive Learning for AI Text Detection
2026 · Christopher Buratti, Michele Marchetti, et al. · Lecture notes in computer science
Token Reduction in Vision Transformers via Discrete Wavelet Decomposition
2026 · Christopher Buratti, Michele Marchetti, et al. · Lecture notes in computer science
Generating masks from similarity-based graphs for vision transformer explainability
2026 · Michele Marchetti, Davide Traini, et al. · Neural Computing and Applications
PDF
Latent Trajectory Discrimination for AI-Generated Text Detection
2026 · Bonifazi, Gianluca, Buratti, Christopher, et al. · arXiv (Cornell University)
PDF
Gradient-Skipping Relevance Propagation for Efficient Explainability of Vision Transformers
2026 · Buratti, Christopher, Marchetti, Michele, et al. · arXiv (Cornell University)
PDF
Efficient Retrieval-Augmented Generation via Token Co-occurrence Graphs
2026 · Bonifazi, Gianluca, Buratti, Christopher, et al. · arXiv (Cornell University)
PDF
An ego network-based approach to fine-tune large language models using knowledge graphs
2026 · Alessia Amelio, Christopher Buratti, et al. · Information Sciences
Graph-Enhanced Retrieval Augmented Generation Through Cross-Attention and Contrastive Learning
2026 · Gianluca Bonifazi, Christopher Buratti, et al. · International Joint Conference on Neural Networks (IJCNN)
Leveraging Adversarial Attacks to Generate Multiple-Choice Quizzes Robust Against Large Language Models
2026 · Gianluca Bonifazi, Christopher Buratti, et al. · ACM Transactions on Intelligent Systems and Technology
GradQuiz
2026 · Bonifazi, Gianluca, Buratti, Christopher, et al. · Zenodo (CERN European Organization for Nuclear Research)
Explaining Vision Transformers Through Similarity-based Graphs
2025 · Michele Marchetti, Davide Traini, et al. · International Joint Conference on Neural Networks (IJCNN)
Integrating Gradient and Mask-based Approaches for Vision Transformer Explainability
2025 · Michele Marchetti, Davide Traini, et al. · International Joint Conference on Neural Networks (IJCNN)
A Hybrid FinBERT-GAT-Based Framework for Predicting the ESG Score of a Company
· S. Baiocco, G. Bonifazi, et al. · Università Politecnica delle Marche (Università Politecnica delle Marche)
Efficient Path-Coherent Retrieval via Branch Pruning in KG-RAG
· C. Buratti, M. Marchetti, et al. · Università Politecnica delle Marche (Università Politecnica delle Marche)
Language-Aware Multilingual Retrieval-Augmented Generation via Local-to-Global Retrieval
· G. Bonifazi, C. Buratti, et al. · Università Politecnica delle Marche (Università Politecnica delle Marche)
Using complex network analysis to detect connectome motifs in the larval Drosophila
· Christopher Buratti, Enrico Corradini, et al. · Università Politecnica delle Marche (Università Politecnica delle Marche)
Works count: 25
Citation count: 43
H-index: 3
I10-index: 2
Year
Topic
Type