论文提出平滑MMD对齐方法，显著提升大语言模型数值预测准确性，为LLM数理能力优化提供新思路。
arXiv:2606.27731v1 Announce Type: cross Abstract: Despite their strong general capabilities, large language models (LLMs) often remain unreliable when…
强化学习价值函数的新方法，通过平滑化提升训练稳定性与性能。
arXiv:2602.23280v2 Announce Type: replace Abstract: Offline goal-conditioned reinforcement learning (GCRL) learns goal-reaching behaviors from static …
纵向数据下多策略因果效应平滑估计，提升精度与可解释性，适合因果推断研究者。
arXiv:2605.14284v2 Announce Type: replace Abstract: Comparative evaluation of multiple dynamic treatment policies is essential for healthcare and poli…
提出先验校正正交信任区域引导，优化动作分块流策略，平滑性与性能兼得。
arXiv:2605.24433v1 Announce Type: cross Abstract: Flow-matching robot policies commonly use action-chunking inference for efficient closed-loop contro…
利用新视图合成实现语义平滑，显著提升SAR图像分类的鲁棒性，创新性融合3D视角与遥感识别。
arXiv:2605.16440v1 Announce Type: new Abstract: Deep neural networks are vulnerable to adversarial perturbations, limiting deployment in safety-critic…
通过平滑策略提升随机森林性能，创新方法值得关注
arXiv:2505.06852v2 Announce Type: replace Abstract: Random forest regression is a powerful non-parametric method that adapts to local data characteris…
基于扩散模型的文本生成新方法，通过在token嵌入上平滑去噪，实现高质量离散文本生成
arXiv:2505.18853v2 Announce Type: replace Abstract: Diffusion models have achieved state-of-the-art performance in generating images, audio, and video…
LLM极端量化中平滑性比数值拟合更重要，揭示性能下降新成因。
arXiv:2605.08894v2 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve strong performance but incur high deployment costs, mot…