Hongyu Zhang
3 papers · Latest:
Software Engineering
ClassEval-Pro: A Cross-Domain Benchmark for Class-Level Code Generation
ClassEval-Pro is a new cross-domain benchmark for evaluating LLMs on class-level code generation, revealing significant challenges in compositional code creation.
2604.26923
Software EngineeringTORAI: Unsupervised Fine-grained RCA using Multi-Source Telemetry Data
TORAI is an unsupervised method for fine-grained root cause analysis in microservice systems, effectively handling "blind spots" without relying on service call graphs.
2604.13522
Software EngineeringDeepGuard: Secure Code Generation via Multi-Layer Semantic Aggregation
DeepGuard enhances secure code generation by aggregating multi-layer semantic cues, improving security by 11.9% while maintaining correctness.
2604.09089
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.