Profile of Prof NERI, Ferrante - The Education University of Hong Kong


Chair Professor	Department of Mathematics and Information Technology
Dean	Faculty of Liberal Arts and Social Sciences

Contact

ORCiD

0000-0002-6100-6532

Phone

(852) 2948 8815

fneri@eduhk.hk

Address

10 Lo Ping Road, Tai Po, New Territories, Hong Kong

Website

https://pappl.eduhk.hk/rich/web/person.xhtml?pid=338856&name=NERI, Ferrante

Scopus ID

8729046500

Research Outputs


All Other Outputs Neri, F. (2026). Associate Editor of IEEE Transactions on Emerging Topics in Computational Intelligence. IEEE. https://cis.ieee.org/publications/t-emerging-topics-in-ci/tetci-editors-and-associate-editors Neri, F. (2026). Associate Editor of IEEE Transactions on Knowledge and Data Engineering. IEEE. https://www.computer.org/csdl/journal/tk/about/107358?title=Editorial%20Board&periodical=IEEE%20Transactions%20on%20Knowledge%20and%20Data%20Engineering

All Other Outputs
Neri, F. (2026). Associate Editor of IEEE Transactions on Emerging Topics in Computational Intelligence. IEEE. https://cis.ieee.org/publications/t-emerging-topics-in-ci/tetci-editors-and-associate-editors
Neri, F. (2026). Associate Editor of IEEE Transactions on Knowledge and Data Engineering. IEEE. https://www.computer.org/csdl/journal/tk/about/107358?title=Editorial%20Board&periodical=IEEE%20Transactions%20on%20Knowledge%20and%20Data%20Engineering

Projects


MERGEN: Weight-Space Learning for Model Merging and Neural Architecture Generation This project develops a unified weight-space learning framework for representing, aligning and transforming trained neural networks, with a focus on model merging and Neural Architecture Generation for efficient model reuse and generation under task and resource constraints. Outputs include algorithms, benchmarks, open-source software and publications. Project Start Year: 2026, Principal Investigator(s): NERI, Ferrante SDGs Information: 9 - Industry, Innovation and Infrastructure, 12 - Responsible Consumption and Production, 17 - Partnerships for the Goals

MERGEN: Weight-Space Learning for Model Merging and Neural Architecture Generation
This project develops a unified weight-space learning framework for representing, aligning and transforming trained neural networks, with a focus on model merging and Neural Architecture Generation for efficient model reuse and generation under task and resource constraints. Outputs include algorithms, benchmarks, open-source software and publications.
Project Start Year: 2026, Principal Investigator(s): NERI, Ferrante
SDGs Information: 9 - Industry, Innovation and Infrastructure, 12 - Responsible Consumption and Production, 17 - Partnerships for the Goals