多模态大模型训练新范式：阶段感知稀疏性动态消除冗余，大幅提升效率而保持性能。
arXiv:2509.18150v2 Announce Type: replace Abstract: Multimodal Large Language Models (MLLMs) have demonstrated outstanding performance across a variet…
探讨组合稀疏性作为神经网络架构设计的归纳偏置，从理论上破解高维学习中的维度灾难。
arXiv:2605.14764v1 Announce Type: cross Abstract: Identifying the structural priors that enable Deep Neural Networks (DNNs) to overcome the curse of d…
揭示FFN架构稀疏性如何重塑注意力计算，影响小型Transformer模型学习机制。
arXiv:2605.09403v2 Announce Type: replace-cross Abstract: Architectural choices inside the Transformer feedforward network (FFN) block do not merely a…