Sihan Yang, Runsen Xu, Chenhang Cui, Tai Wang, Dahua Lin, Jiangmiao Pang

IEEE/CVF International Conference on Computer Vision (ICCV) · 2025

VFlowOpt is proposed, a token pruning framework that introduces an importance map derivation process and a progressive pruning module with a recycling mechanism that minimizes the discrepancy between token representations in LMMs with and without pruning, thereby enabling superior pruning strategies tailored to different LMMs.

Haoqin Tu, Chenhang Cui, Zijun Wang, Yiyang Zhou, Bingchen Zhao, Junlin Han, Wangchunshu Zhou, Huaxiu Yao, +1 more

Lecture notes in computer science · 2024

Zichen Wen, Tianyi Wu, Yazhou Ren, Yawen Ling, Chenhang Cui, Xiaorong Pu, Lifang He

ACM International Conference on Multimedia (ACM MM) · 2024

A novel multi-view graph clustering method based on dual-optimized adaptive graph reconstruction, named DOAGC, which mainly aims to reconstruct the graph structure adapted to traditional GNNs to deal with heterophilous graph issues while maintaining the advantages of traditional GNNs.

Chenhang Cui, Xie, Jinyu, Yechenhao Yang

arXiv · 2023

A new method bright channel prior attention for enhancing pedestrian detection in low-light conditions by integrating image enhancement and detection within a unified framework, which includes a self-attention enhancement module and a detection module, which work together to improve object detection.

Sihan Yang, Chenhang Cui, Zihao Zhao, Yiyang Zhou, Weilong Yan, Ying Wei, Huaxiu Yao

Findings of the Association for Computational Linguistics: EMNLP 2025 · 2025