default author photo

Jinglin Xu

University of Science and Technology Beijing

30 Xueyuan Road, Haidian District

beijing, 100083

China

SCHOLARLY PAPERS

1

DOWNLOADS

79

TOTAL CITATIONS

0

Scholarly Papers (1)

1.

Ctp2Fic: From Coarse‑grained Token Pruning to Fine‑grained Token Clustering for LVLM Inference Acceleration (ChinaMM 2025)

Number of pages: 18 Posted: 29 Sep 2025
Yulong Lei, Zishuo Wang, Jinglin Xu and Yuxin Peng
University of Science and Technology Beijing, Peking University, University of Science and Technology Beijing and Peking University
Downloads 79 (823,616)

Abstract:

Loading...

Large Vision-Language Models, Inference Acceleration, Token Compression, Training-free Framework