一作ICML 2026Poster· Deep Learning / Large Language Models
Do Sparse Autoencoders Identify Reasoning Features in Language Models?
George Ma · Zhongyuan Liang · Irene Y. Chen · Somayeh Sojoudi
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。
George Ma · Zhongyuan Liang · Irene Y. Chen · Somayeh Sojoudi
George Ma · Anurag Koul · Qi Chen · Yawen Wu · Sachit Kuhar · Yu Yu · Aritra Sengupta · Varun Kumar · Murali Krishna Ramanathan
Large Language Models (LLMs) excel at code-related tasks but often struggle in realistic software repositories, where project-specific APIs and cross-file dependencies are crucial. Retrieval-augmented methods mitigate this by injecting repository context at inference time. Low inference time late...