Mingzhe Du PRO

Elfsong's activity

• All
• Models
• Datasets
• Spaces
• Papers
• Collections
• Community
• Posts
• Upvotes
• Likes
• Articles

authored a paper 30 days ago

Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization

Paper • 2505.23387 • Published May 29 • 7

authored a paper about 2 months ago

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

Paper • 2505.11049 • Published May 16 • 59

authored 2 papers 4 months ago

Rethinking the Influence of Source Code on Test Case Generation

Paper • 2409.09464 • Published Sep 14, 2024 • 1

CodeArena: A Collective Evaluation Platform for LLM Code Generation

Paper • 2503.01295 • Published Mar 3 • 8

authored 2 papers 7 months ago

Mercury: An Efficiency Benchmark for LLM Code Synthesis

Paper • 2402.07844 • Published Feb 12, 2024 • 2

AntiLeak-Bench: Preventing Data Contamination by Automatically Constructing Benchmarks with Updated Real-World Knowledge

Paper • 2412.13670 • Published Dec 18, 2024 • 6