揭秘大脑连续工作记忆的数学机制，看归一化如何塑造低秩慢流形。
arXiv:2608.01947v1 Announce Type: cross Abstract: The ability to robustly maintain and update continuous variables is a hallmark of working memory. Wh…
用张量列低秩分解攻克扩散模型高维采样难题，带来理论与计算效率双重飞跃。
arXiv:2607.06841v1 Announce Type: cross Abstract: Diffusion models offer a powerful framework for sampling from complex probability densities by learn…
揭示RLVR训练中参数轨迹的秩一结构，仅需极小规模训练即可外推LLM推理能力，颠覆传统认知。
arXiv:2605.21468v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving rea…