← authors · overview

• DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model
  2024 · 102 citations
• Improving Tree-Structured Decoder Training for Code Generation via Mutual Learning
  2021 · 4 citations
• PMSS: Pretrained Matrices Skeleton Selection for LLM Fine-tuning
  2024 · 1 citations
• Learning to Generate Secure Code via Token-Level Rewards
  2026
• Step 3.5 Flash: Open Frontier-Level Intelligence with 11B Active Parameters
  2026
• AI Code in the Wild: Measuring Security Risks and Ecosystem Shifts of AI-Generated Code in Modern Software
  2025
• Reflection-Driven Control for Trustworthy Code Agents
  2025
• RA-Gen: A Controllable Code Generation Framework Using ReAct for Multi-Agent Task Execution
  2025
• Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies
  2025
• RefleXGen:The unexamined code is not worth using
  2025
• Function-to-Style Guidance of LLMs for Code Translation
  2025
• A.S.E: A Repository-Level Benchmark for Evaluating Security in AI-Generated Code
  2025
• Structure-Unified M-Tree Coding Solver for MathWord Problem
  2022