3 papers
cs.SD2026
HybridSB-MoE: Dual-Domain Schrödinger Bridges with Scene-Adaptive Expert Routing for Speech Enhancement
Zhengyi Lu, Aswini Sivakumar, Jie Hu +1
Generative speech enhancement faces three gaps: spectral models capture harmonic structure but often disrupt phase, waveform models preserve phase but miss harmonics, and Schröding…
cs.LG2026
Multi-level Self-supervised Pretraining on Compositional Hierarchical Graph for Molecular Property Prediction
Xiayu Liu, Zhengyi Lu, Hou-biao Li
Self-supervised pretraining on molecular graphs has emerged as a promising approach for molecular property prediction, yet most existing methods operate at a single structural gran…
cs.LG2026
Local-Global Multimodal Contrastive Learning for Molecular Property Prediction
Xiayu Liu, Zhengyi Lu, Yunhong Liao +2
Accurate molecular property prediction requires integrating complementary information from molecular structure and chemical semantics. In this work, we propose LGM-CL, a local-glob…