Zihan Chen

ProMoS: Prototype-Guided Distillation for Generalist Graph Anomaly Detection

Training-Free Speedup for Retrieval-Augmented Generation with Staged Parallel Speculation

Navigating Sparsities in High-Dimensional Linear Contextual Bandits

Lean Clients, Full Accuracy: Hybrid Zeroth- and First-Order Split Federated Learning

GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks

MAPLE: Many-Shot Adaptive Pseudo-Labeling for In-Context Learning

Understanding Prejudice and Fidelity of Diverge-to-Converge Multi-Agent Systems

Separate the Wheat from the Chaff: Winnowing Down Divergent Views in Retrieval Augmented Generation

Channel-Wise Mixed-Precision Quantization for Large Language Models