| 1 |
AdaKD: Dynamic Knowledge Distillation of ASR models using Adaptive Loss Weighting |
AdaKD：提出自适应损失权重动态知识蒸馏方法，提升语音识别模型性能 |
curriculum learning distillation |
|
|
| 2 |
Fairness in Reinforcement Learning: A Survey |
综述性研究：全面回顾强化学习中的公平性问题与前沿进展 |
reinforcement learning RLHF |
|
|
| 3 |
Predictive Modeling in the Reservoir Kernel Motif Space |
提出基于核Reservoir时间序列Motif的预测模型，性能优于Transformer。 |
predictive model |
|
|
| 4 |
DTMamba : Dual Twin Mamba for Time Series Forecasting |
DTMamba：用于时间序列预测的双孪Mamba模型 |
Mamba |
|
|
| 5 |
Translating Expert Intuition into Quantifiable Features: Encode Investigator Domain Knowledge via LLM for Enhanced Predictive Analytics |
利用LLM将专家直觉转化为可量化特征，提升预测分析效果 |
predictive model large language model |
|
|
| 6 |
Fair Graph Representation Learning via Sensitive Attribute Disentanglement |
提出FairSAD框架，通过敏感属性解耦提升图神经网络的公平性和效用性。 |
representation learning |
✅ |
|
| 7 |
Semi-supervised Anomaly Detection via Adaptive Reinforcement Learning-Enabled Method with Causal Inference for Sensor Signals |
提出Tri-CRLAD，利用因果推理和自适应强化学习进行半监督传感器信号异常检测。 |
reinforcement learning |
✅ |
|
| 8 |
CTRL: Continuous-Time Representation Learning on Temporal Heterogeneous Information Network |
提出CTRL模型，用于时序异构信息网络上的连续时间表示学习。 |
representation learning |
|
|
| 9 |
Stealthy Imitation: Reward-guided Environment-free Policy Stealing |
提出Stealthy Imitation，实现无环境、无输入范围知识的策略窃取 |
reinforcement learning deep reinforcement learning |
|
|