Semantic-Guided Slow-Fast Pruning of Visual Tokens for Vision-Language Models

Authors: Zheng-Wei Liu, Eugene Lee, Jui-Huang Tsai et al.
Publication: ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
Published: May 3, 2026
Source: Crossref
Back to Search View Original Cite This Article

Related Articles

Comparative Study of Point Cloud, Voxel and Mesh Representations for 3D Semantic Object Detection

Joseph Davis, Danda B. Rawat - Jul 2026

Read More
Enhancing infiltration event detection using Keras slim residual network (ResNet) with training schedule and pruning techniques

Olanrewaju Bucknor, Arlene Cole-Rhodes et al. - Jun 2026

Read More
Multimodal prompt adaptation for fast text-guided object detection

Xintong Li, Jiacan Li et al. - Jun 2026

Read More
Semantic similarity deficits in neural network critical learning periods

Mikolaj Jakowski, Hector J. Santos-Villalobos - Jun 2026

Read More
Vision language model-based multimodal voice activity detection

Jiacan Li, Xintong Li et al. - Jun 2026

Read More