作者位次 #2/5ICML 2026Poster· Deep Learning / Large Language Models
Critique-Guided Distillation for Robust Reasoning via Refinement
Berkcan Kapusuzoglu · Supriyo Chakraborty · Zain Sarwar · Michael Lee · Sambit Sahu
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。
Berkcan Kapusuzoglu · Supriyo Chakraborty · Zain Sarwar · Michael Lee · Sambit Sahu
Tianyi Niu · Justin Chen · Genta Indra Winata · Shi-Xiong Zhang · Supriyo Chakraborty · Sambit Sahu · Yue Zhang · Elias Stengel-Eskin · Mohit Bansal
Large Language Model (LLM) routers dynamically select optimal models for given inputs. Existing approaches typically assume access to ground-truth labeled data, which is often unavailable in practice, especially when user request distributions are heterogeneous and unknown. We introduce Routing w...