作者位次 #2/15ICML 2026Poster· Deep Learning / Large Language Models
IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
Zhoujun Cheng · Yutao Xie · Yuxiao Qu · Amrith Setlur · Shibo Hao · Varad Pimpalkhute · Tongtong Liang · Feng Yao · Zhengzhong Liu · Eric Xing · Virginia Smith · Russ Salakhutdinov · Zhiting Hu · Taylor W. Killian · Aviral Kumar
强化学习与后训练OpenReview