代码大模型靠记忆还是真理解？这项研究揭示传统记忆化探针在大规模模型上严重失效，诊断方法必须随规模调整。
arXiv:2608.12771v1 Announce Type: cross Abstract: The extent to which large language models for code rely on memorization over genuine understanding r…
教你用记忆化指导数据重用的策略，在不大幅延长训练时间的前提下提升LLM训练效率，顶级会议论文的实用思路。
arXiv:2607.04969v1 Announce Type: new Abstract: The training paradigm of large language models has shifted from traditional one-pass training to multi…
大模型训练数据泄露风险新视角：引入倾向性评估，揭示记忆化并非模型本意
arXiv:2606.06286v1 Announce Type: cross Abstract: Large language models can reproduce training data, but existing memorization evaluations mostly meas…
React Compiler 1.0 稳定版发布，自动记忆化优化组件，无需重写，已与主流工具链集成，生产就绪。
We are releasing the compiler's first stable release today.
React官宣Compiler Beta，自动记忆化优化性能，支持React 17+，并开放工作组供社区参与
At React Conf 2024, we announced the experimental release of React Compiler, a build-time tool that optimizes your React app through automatic memoiza…