PPL
Kai Liu
Papers (4)
GRASP: Plan-Guided Graph Retrieval with Adaptive Fusion and Reranking on Semi-Structured Knowledge BasesDRScaffold: Boosting Dense-Scene Reasoning in Lightweight Vision Language ModelsBiomedAP: A Vision-Informed Dual-Anchor Framework with Gated Cross-Modal Fusion for Robust Medical Vision-Language AdaptationToward Better Geometric Representations for Molecule Generative Models