作者位次 #4/6ICLR 2026Poster· Reinforcement Learning / Planning
TRIM: Hybrid Inference via Targeted Stepwise Routing in Multi-Step Reasoning Tasks
Vansh Kapoor · Aman Gupta · Hao Chen · Anurag Beniwal · Jing Huang · Aviral Kumar
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。
Vansh Kapoor · Aman Gupta · Hao Chen · Anurag Beniwal · Jing Huang · Aviral Kumar