3 papers
cs.LG2026
Graph Navier Stokes Networks
Zexing Zhao, Guangsi Shi, Yu Gong +4
Graph Neural Networks (GNNs) have emerged as a cornerstone of deep learning, with most existing methods rooted in graph signal processing and diffusion equations to model message p…
cs.CV2025
HOP: Heterogeneous Topology-based Multimodal Entanglement for Co-Speech Gesture Generation
Hongye Cheng, Tianyu Wang, Guangsi Shi +2
Co-speech gestures are crucial non-verbal cues that enhance speech clarity and expressiveness in human communication, which have attracted increasing attention in multimodal resear…
cs.LG2024
Contrastive Dual-Interaction Graph Neural Network for Molecular Property Prediction
Zexing Zhao, Guangsi Shi, Xiaopeng Wu +3
Molecular property prediction is a key component of AI-driven drug discovery and molecular characterization learning. Despite recent advances, existing methods still face challenge…