Training-free merging of depth-heterogeneous models via activation-driven neuron matching
International Journal of Machine Learning and Cybernetics · 2026-12 · 17 (12)
DOI: 10.1007/s13042-026-03382-0 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Machine Learning and Cybernetics, online erschienen am 18.11.2026. Verfasst von Shuo An und 3 weiteren Autor:innen. Die Arbeit nennt 42 Literaturangaben. Gefördert von: Natural Science Foundation of Sichuan Province, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Natural Science Foundation of Sichuan Province
- Fundamental Research Funds for the Central Universities
Zitieren
APA
An, S., Qin, K., Zhang, D., & Wu, X. (2026). Training-free merging of depth-heterogeneous models via activation-driven neuron matching. International Journal of Machine Learning and Cybernetics, 17(12). https://doi.org/10.1007/s13042-026-03382-0
Vancouver
An S, Qin K, Zhang D, Wu X. Training-free merging of depth-heterogeneous models via activation-driven neuron matching. International Journal of Machine Learning and Cybernetics. 2026;17(12). doi:10.1007/s13042-026-03382-0
BibTeX
@article{An2026,
author = {An, Shuo and Qin, Ke and Zhang, Dongyang and Wu, Xin},
title = {Training-free merging of depth-heterogeneous models via activation-driven neuron matching},
journal = {International Journal of Machine Learning and Cybernetics},
year = {2026},
volume = {17},
number = {12},
doi = {10.1007/s13042-026-03382-0}
}
EUVIMED