FinePruner: Unbiased Attention-Head-Level Fine-Grained Token Reduction for Efficient Inference of Large Vision-Language Models
IEEE Transactions on Image Processing · 2026 · 35 · 4907-4920
DOI: 10.1109/tip.2026.3687073 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Image Processing, 2026. Verfasst von Zishuo Wang und 2 weiteren Autor:innen. Die Arbeit nennt 54 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Beijing Natural Science Foundation.
Abstract (Originalsprache)
Kein Abstract verfügbar.
Förderung
- National Natural Science Foundation of China
- Beijing Natural Science Foundation
Zitieren
APA
Wang, Z., Zheng, X., & Peng, Y. (2026). FinePruner: Unbiased Attention-Head-Level Fine-Grained Token Reduction for Efficient Inference of Large Vision-Language Models. IEEE Transactions on Image Processing, 35, 4907-4920. https://doi.org/10.1109/tip.2026.3687073
Vancouver
Wang Z, Zheng X, Peng Y. FinePruner: Unbiased Attention-Head-Level Fine-Grained Token Reduction for Efficient Inference of Large Vision-Language Models. IEEE Transactions on Image Processing. 2026;35:4907-4920. doi:10.1109/tip.2026.3687073
BibTeX
@article{Wang2026,
author = {Wang, Zishuo and Zheng, Xiangtian and Peng, Yuxin},
title = {FinePruner: Unbiased Attention-Head-Level Fine-Grained Token Reduction for Efficient Inference of Large Vision-Language Models},
journal = {IEEE Transactions on Image Processing},
year = {2026},
volume = {35},
pages = {4907--4920},
doi = {10.1109/tip.2026.3687073}
}
EUVIMED