| 1 |
A Multiparty Homomorphic Encryption Approach to Confidential Federated Kaplan Meier Survival Analysis |
提出一种基于多方同态加密的联邦Kaplan-Meier生存分析方法，保护患者隐私。 |
MAE OMOMO |
|
|
| 2 |
The intrinsic motivation of reinforcement and imitation learning for sequential tasks |
提出基于内在动机的强化与模仿学习框架，用于序列任务的自动课程学习。 |
reinforcement learning imitation learning curriculum learning |
|
|
| 3 |
Game Theory and Multi-Agent Reinforcement Learning : From Nash Equilibria to Evolutionary Dynamics |
结合博弈论与多智能体强化学习，提升复杂动态环境下的智能体鲁棒性 |
reinforcement learning |
|
|
| 4 |
A Comprehensive Framework for Reliable Legal AI: Combining Specialized Expert Systems and Adaptive Refinement |
提出结合专家系统与自适应优化的法律AI框架，提升法律服务可靠性 |
reinforcement learning RLHF |
|
|