3 papers
cs.AI2026
Diagnose Before You Compress: Prediction-Independent Bottleneck Witness Refinement for LLM Serving Traces
Liming Liu, Chao Hu, Mingfei Lu +7
Production LLM serving generates millions of diverse requests, making full-trace replay across serving configurations increasingly expensive. Existing trace reduction methods mainl…
cs.AI2026
PREF-Gate: Provenance-Constrained Relational Evidence Fusion with Validation-Gated Selection for Graph Fraud Detection
Liming Liu, Chao Hu, Mingfei Lu +3
Relational fraud detection can exploit both label-free graph context and label-derived neighborhood evidence, but these two information sources obey different validity conditions.…
cs.LG2026
Beyond Sparse Supervision: Diffusion-Guided Learning for Few-Shot Graph Fraud Detection
Liming Liu, Chao Hu, Mingfei Lu +3
Graph-based fraud detection is essential for safeguarding large-scale transaction systems, where undetected anomalies may lead to substantial financial losses and security risks. R…