SAC Flow: Sample-Efficient Reinforcement Learning of Flow-Based Policies via Velocity-Reparameterized Sequential Modeling
Yixian Zhang · Shu-ang Yu · Tonghe Zhang · Mo Guang · Haojia Hui · Kaiwen Long · Yu Wang · Chao Yu · Wenbo Ding
首次获取该候选人的完整档案及 StartLux 评估共 20 积分;每位用户单独解锁,之后查看免费。主动刷新 20 积分。
实时查找电子邮箱,费用不超过20积分;未找到邮箱不扣费。
Yixian Zhang · Shu-ang Yu · Tonghe Zhang · Mo Guang · Haojia Hui · Kaiwen Long · Yu Wang · Chao Yu · Wenbo Ding
Huining Yuan · Zelai Xu · Zheyue Tan · Xiangmin Yi · Mo Guang · Kaiwen Long · Haojia Hui · Boxun Li · Xinlei Chen · Bo Zhao · Xiao-Ping Zhang · Chao Yu · Yu Wang
Yanxiao Zhao · Yaqian Li · Zihao Bo · Rinyoichi Takezoe · Haojia Hui · Mo Guang · Lei Ren · Xiaolin Qin · Kaiwen Long
Large language models (LLMs) exhibit strong general reasoning, yet the community lacks controllable, scalable, and verifiable tools to analyze and improve these abilities. We present SATQuest, a verifier that generates diverse SAT-based reasoning tasks directly from Conjunctive Normal Form (CNF)...