Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL 文章

ArXiv CS.CL2026-05-28NEWSen作者: Kunhao Zheng, Pierre Chambon, Juliette Decugis, Jonas Gehring, Taco Cohen, Benjamin Negrevergne, Gabriel Synnaeve

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL · 相关技术

暂无数据