Guancheng Wan

8 papers University of California, Los Angeles

• DKDR: Dynamic Knowledge Distillation for Reliability in Federated Learning
• Don’t Forget the Enjoin: FocalLoRA for Instruction Hierarchical Alignment in Large Language Models
• Flow Field Reconstruction with Sensor Placement Policy Learning
• G-Memory: Tracing Hierarchical Memory for Multi-Agent Systems
• HYPERION: Fine-Grained Hypersphere Alignment for Robust Federated Graph Learning
• MOTION: Multi-Sculpt Evolutionary Coarsening for Federated Continual Graph Learning
• Multi-order Orchestrated Curriculum Distillation for Model-Heterogeneous Federated Graph Learning
• OASIS: One-Shot Federated Graph Learning via Wasserstein Assisted Knowledge Integration