Confira a produção científica do ICTi desenvolvida a partir de pesquisas de colaboradores, pesquisadores-bolsistas.
Inteligência Artificial:
Aroeira: A Curated Corpus for the Portuguese Language with a Large Number of Tokens
LIRA, Thiago et al. Aroeira: A Curated Corpus for the Portuguese Language with a Large Number of Tokens. In: Brazilian Conference on Intelligent Systems. Cham: Springer Nature Switzerland, 2024. p. 185-199.
LOPES, Rogério Gomes; BORGES, Díbio L. Business Activity Classification Extraction from Commercial Footage: A Multimodal LLM Approach Based on CNAE (Comparable to NACE and NAICS). In: International Conference on Image Analysis and Processing. Cham: Springer Nature Switzerland, 2025. p. 548-560.
Template-Driven Specification of Requirements for LLM-Based Chatbots
DA SILVA, Caio V. Melo et al. Template-Driven Specification of Requirements for LLM-Based Chatbots. In: Workshop sobre Bots na Engenharia de Software (WBOTS). SBC, 2025. p. 11-20.
Evaluating LLM-Based Chatbots through Touchpoint-Driven Process Models
DA SILVA, Carlos H. Camillo et al. Evaluating LLM-Based Chatbots through Touchpoint-Driven Process Models. In: Workshop sobre Bots na Engenharia de Software (WBOTS). SBC, 2025. p. 1-10.
Quantitative Analysis of Visual XAI for Multiclass DeepFake Detection based on CNN
DE ARAÚJO, Leandro Santiago et al. Quantitative Analysis of Visual XAI for Multiclass DeepFake Detection Based on CNN. In: 2025 38th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI). IEEE, 2025. p. 1-6.
Assessing Demographic Bias and Fairness in Facial Recognition Systems: A Framework
RABANNI, Darian SR et al. Assessing Demographic Bias and Fairness in Facial Recognition Systems: A Framework. In: Brazilian Conference on Intelligent Systems. Cham: Springer Nature Switzerland, 2025. p. 78-93.
Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation
ZEN, Hilary et al. Ensemble-Based Biometric Verification: Defending Against Multi-Strategy Deepfake Image Generation. Computers, v. 14, n. 6, p. 225, 2025.
Probabilities of Causation and Root Cause Analysis with Quasi-Markovian Models
LAURENTINO, Eduardo Rocha et al. Probabilities of Causation and Root Cause Analysis with Quasi-Markovian Models. In: Brazilian Conference on Intelligent Systems. Cham: Springer Nature Switzerland, 2025. p. 362-376.
PERES, Sarajane Marques et al. Methodological and Educational Foundations for Information Systems in the Age of Generative Artificial Intelligence. Créditos de elaboração, p. 118, 2025.
Efficient LLMs with AMP: Attention Heads and MLP Pruning
MUGNAINI, Leandro Giusti et al. Efficient LLMs with AMP: Attention Heads and MLP Pruning. arXiv preprint arXiv:2504.21174, 2025.
RASHID, Sharaf et al. Evaluating Prompt Injection Attacks with LSTM-Based Generative Adversarial Networks: A Lightweight Alternative to Large Language Models. Machine Learning and Knowledge Extraction, v. 7, n. 3, p. 77, 2025.
ARROYO, João P. et al. Multilinear and Linear Programs for Partially Identifiable Queries in Quasi-Markovian Structural Causal Models. arXiv preprint arXiv:2509.03548, 2025.
On the Potential of Tool-Enhanced Small Language Models to Match Large Models in Finance
ASSIS, Gabriel et al. On the Potential of Tool-Enhanced Small Language Models to Match Large Models in Finance. In: Proceedings of the 6th ACM International Conference on AI in Finance. 2025. p. 847-855.
Computação Quântica:
Multiclass Portfolio Optimization via Variational Quantum Eigensolver with Dicke State Ansatz
SCURSULIM, José Victor S. et al. Multiclass Portfolio Optimization via Variational Quantum Eigensolver with Dicke State Ansatz. arXiv preprint arXiv:2508.13954, 2025.
Managing a Quantum Computing Team—Insights and Challenges at Itaú Unibanco
SOTELO, Rafael et al. Managing a quantum computing team—insights and challenges at itaú unibanco. IEEE Engineering Management Review, v. 50, n. 1, p. 24-27, 2022
Encoding of Probability Distributions for Quantum Monte Carlo Using Tensor Networks
PEREIRA, Antonio et al. Encoding of Probability Distributions for Quantum Monte Carlo Using Tensor Networks. arXiv preprint arXiv:2411.11660, 2024.
Improved financial forecasting via quantum machine learning
THAKKAR, Sohum et al. Improved financial forecasting via quantum machine learning. Quantum Machine Intelligence, v. 6, n. 1, p. 27, 2024.
