LightTrafficLLM: Accelerating large language models for network traffic analysis via vocabulary-preserving context compression and structural pruning distillation
Journal of Systems Architecture · 2026-12 · 181 · 104046
DOI: 10.1016/j.sysarc.2026.104046 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Systems Architecture, 2026-12. Verfasst von Haifeng Lv und 4 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Gefördert von: Guilin University of Electronic Technology, Guangxi Academy of Agricultural Science.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- Guilin University of Electronic Technology
- Guangxi Academy of Agricultural Science
Zitieren
APA
Lv, H., Tan, K., Wang, S., Mo, Z., & Ding, Y. (2026). LightTrafficLLM: Accelerating large language models for network traffic analysis via vocabulary-preserving context compression and structural pruning distillation. Journal of Systems Architecture, 181, 104046. https://doi.org/10.1016/j.sysarc.2026.104046
Vancouver
Lv H, Tan K, Wang S, Mo Z, Ding Y. LightTrafficLLM: Accelerating large language models for network traffic analysis via vocabulary-preserving context compression and structural pruning distillation. Journal of Systems Architecture. 2026;181:104046. doi:10.1016/j.sysarc.2026.104046
BibTeX
@article{Lv2026,
author = {Lv, Haifeng and Tan, Kaizhong and Wang, Shuo and Mo, Zhiyi and Ding, Yong},
title = {LightTrafficLLM: Accelerating large language models for network traffic analysis via vocabulary-preserving context compression and structural pruning distillation},
journal = {Journal of Systems Architecture},
year = {2026},
volume = {181},
pages = {104046},
doi = {10.1016/j.sysarc.2026.104046}
}
EUVIMED