RL-PLUS: Countering Capability Boundary Collapse of LLMs in Reinforcement Learning with Hybrid-policy Optimization Paper • 2508.00222 • Published Jul 31 • 6
Running 5 Memorization Or Generation Of Big Code Model Leaderboard 🌖 5 Compare code models on benchmarks
DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories Paper • 2405.19856 • Published May 30, 2024 • 10