Xu Shen

FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning

Metacognitive Self-Correction for Multi-Agent System via Prototype-Guided Next-Execution Reconstruction

Explicit Column Relationship-Based Diffusion Model for High-Quality Synthetic Tabular Data Generation

Unifying Unsupervised Graph-Level Anomaly Detection and Out-of-Distribution Detection: A Benchmark

MPHIL: Multi-Prototype Hyperspherical Invariant Learning for Graph Out-of-Distribution Generalization