Sheng Wang

MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models

Group Ligands Docking to Protein Pockets

Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension

MMedPO: Aligning Medical Vision-Language Models with Clinical-Aware Multimodal Preference Optimization

FM-TS: Flow Matching for Time Series Generation

MMICL: Empowering Vision-language Model with Multi-Modal In-Context Learning