作者位次 #6/7ICML 2026Poster· Theory / Deep Learning
Understanding Deep Representation Learning via Layerwise Feature Compression and Discrimination
Peng Wang · Xiao Li · Can Yaras · Zhihui Zhu · Laura Balzano · Wei Hu · Qing Qu
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。
Peng Wang · Xiao Li · Can Yaras · Zhihui Zhu · Laura Balzano · Wei Hu · Qing Qu
Lechen Zhang · Yunxiang Zhang · Wei Hu · Lu Wang
Large reasoning models such as DeepSeek-R1 and their distilled variants achieve strong performance on complex reasoning tasks. Yet, distilling these models often demands large-scale data for supervised fine-tuning (SFT), motivating the pursuit of data-efficient training methods. To address this,...