| 1 |
NetMamba: Efficient Network Traffic Classification via Pre-training Unidirectional Mamba |
NetMamba：通过预训练单向Mamba实现高效网络流量分类 |
Mamba state space model |
|
|
| 2 |
On Robust Reinforcement Learning with Lipschitz-Bounded Policy Networks |
提出基于Lipschitz约束策略网络的鲁棒强化学习方法，提升抗扰动能力 |
reinforcement learning deep reinforcement learning |
|
|
| 3 |
Do No Harm: A Counterfactual Approach to Safe Reinforcement Learning |
提出基于反事实推理的安全强化学习方法，解决约束优化中惩罚力度难以确定的问题。 |
reinforcement learning |
|
|
| 4 |
Switched Flow Matching: Eliminating Singularities via Switching ODEs |
提出Switched Flow Matching，通过切换ODE消除Flow Matching中的奇异性问题 |
flow matching |
|
|
| 5 |
From Fourier to Neural ODEs: Flow Matching for Modeling Complex Systems |
提出基于傅里叶分析的神经ODE（FNODEs），用于高效建模复杂系统。 |
flow matching |
|
|
| 6 |
Comparisons Are All You Need for Optimizing Smooth Functions |
提出比较方法以优化平滑函数，解决梯度计算难题 |
reinforcement learning large language model |
|
|