一作ICLR 2026Poster· Deep Learning / Algorithms
LeSTD: LLM Compression via Learning-based Sparse Tensor Decomposition
Yi Li · Zhichun Guo · Miao Yin · Bingzhe Li
效率与系统OpenReview
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。
Yi Li · Zhichun Guo · Miao Yin · Bingzhe Li
Dongming Jiang · Yi Li · Guanpeng Li · Bingzhe Li
Memory-Augmented Generation (MAG) extends large language models with external memory to support long-context reasoning, but existing approaches largely rely on semantic similarity over monolithic memory stores, entangling temporal, causal, and entity information. This design limits interpretabili...