3 papers
cs.CV2025
RedVTP: Training-Free Acceleration of Diffusion Vision-Language Models Inference via Masked Token-Guided Visual Token Pruning
Jingqi Xu, Jingxi Lu, Chenghao Li +3
Vision-Language Models (VLMs) have achieved remarkable progress in multimodal reasoning and generation, yet their high computational demands remain a major challenge. Diffusion Vis…
cs.CV2025
HIVTP: A Training-Free Method to Improve VLMs Efficiency via Hierarchical Visual Token Pruning Using Middle-Layer-Based Importance Score
Jingqi Xu, Jingxi Lu, Chenghao Li +2
Vision-Language Models (VLMs) have shown strong capabilities on diverse multimodal tasks. However, the large number of visual tokens output by the vision encoder severely hinders i…
cs.LG2025
Graph Neural Networks with Diversity-aware Neighbor Selection and Dynamic Multi-scale Fusion for Multivariate Time Series Forecasting
Jingqi Xu, Guibin Chen, Jingxi Lu +1
Recently, numerous deep models have been proposed to enhance the performance of multivariate time series (MTS) forecasting. Among them, Graph Neural Networks (GNNs)-based methods h…