1
When Does Sparsity Mitigate the Curse of Depth in LLMs
深度揭示稀疏性如何破解大模型层数诅咒，图证详实，值得一读。
arXiv:2603.15389v2 Announce Type: replace Abstract: Recent work has demonstrated the curse of depth in large language models (LLMs), where later layer…
2
Convergence of Continual Learning in Homogeneous Deep Networks
首次从理论层面证明同质深度网络在持续学习中的收敛性质，为灾难性遗忘提供数学解释
arXiv:2606.30559v1 Announce Type: new Abstract: We characterize weakly regularized continual classification in homogeneous models as sequential projec…