Fisher-Based Layer-Wise Adaptive Sparsification for Efficient Pruning of Large Language Models
IEEE Transactions on Mobile Computing · 2026-09 · 25 (9) · 14930-14942
DOI: 10.1109/tmc.2026.3689307 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Mobile Computing, 2026-09. Verfasst von Chuan Sun und 2 weiteren Autor:innen. Die Arbeit nennt 48 Literaturangaben. Gefördert von: Chongqing Municipal Social Science Planning Project, Ministry of Education - Singapore, Academic Research Fund Tier 1.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Chongqing Municipal Social Science Planning Project
- Ministry of Education - Singapore
- Academic Research Fund Tier 1
- Alignment Fund Industry Collaboration Projects
- A*STAR
- Chongqing Normal University Foundation Projection for Doctoral Start-up Foundation
- Alibaba Group and NTU Singapore through Alibaba-NTU Global e-Sustainability CorpLab
Zitieren
APA
Sun, C., Yu, H., & Li, X. (2026). Fisher-Based Layer-Wise Adaptive Sparsification for Efficient Pruning of Large Language Models. IEEE Transactions on Mobile Computing, 25(9), 14930-14942. https://doi.org/10.1109/tmc.2026.3689307
Vancouver
Sun C, Yu H, Li X. Fisher-Based Layer-Wise Adaptive Sparsification for Efficient Pruning of Large Language Models. IEEE Transactions on Mobile Computing. 2026;25(9):14930-14942. doi:10.1109/tmc.2026.3689307
BibTeX
@article{Sun2026,
author = {Sun, Chuan and Yu, Han and Li, Xiaoxiao},
title = {Fisher-Based Layer-Wise Adaptive Sparsification for Efficient Pruning of Large Language Models},
journal = {IEEE Transactions on Mobile Computing},
year = {2026},
volume = {25},
number = {9},
pages = {14930--14942},
doi = {10.1109/tmc.2026.3689307}
}
EUVIMED