LINGMING ZHANG

SEC-bench: Automated Benchmarking of LLM Agents on Real-World Software Security Tasks

SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution

PurpCode: Reasoning for Safer Code Generation

Top Leaderboard Ranking = Top Coding Proficiency, Always? EvoEval: Evolving Coding Benchmarks via LLM

Evaluating Language Models for Efficient Code Generation

SelfCodeAlign: Self-Alignment for Code Generation

Can LLMs Implicitly Learn Numeric Parameter Constraints in Data Science APIs?