| 13 |
Multimodal Prescriptive Deep Learning |
提出多模态处方深度学习框架PNN，用于优化医疗决策。 |
distillation multimodal |
|
|
| 14 |
TFG-Flow: Training-free Guidance in Multimodal Generative Flow |
TFG-Flow：用于多模态生成Flow的免训练引导方法，应用于分子设计。 |
flow matching foundation model multimodal |
|
|
| 15 |
Coordinating Ride-Pooling with Public Transit using Reward-Guided Conservative Q-Learning: An Offline Training and Online Fine-Tuning Reinforcement Learning Framework |
提出基于奖励引导的保守Q学习算法，协调拼车与公共交通，提升多模式交通系统效率。 |
reinforcement learning CQL conservative q-learning |
|
|
| 16 |
Age and Power Minimization via Meta-Deep Reinforcement Learning in UAV Networks |
提出基于元深度强化学习的无人机网络AoI与功耗最小化方案 |
reinforcement learning deep reinforcement learning |
|
|
| 17 |
Reducing Action Space for Deep Reinforcement Learning via Causal Effect Estimation |
提出基于因果效应估计的动作空间缩减方法，提升深度强化学习探索效率。 |
reinforcement learning deep reinforcement learning |
✅ |
|
| 18 |
ACT-JEPA: Novel Joint-Embedding Predictive Architecture for Efficient Policy Representation Learning |
ACT-JEPA：一种高效策略表示学习的联合嵌入预测架构 |
imitation learning world model representation learning |
|
|
| 19 |
Fat-to-Thin Policy Optimization: Offline RL with Sparse Policies |
提出Fat-to-Thin策略优化算法，解决离线强化学习中稀疏策略学习问题 |
reinforcement learning offline RL offline reinforcement learning |
✅ |
|
| 20 |
A Deep State Space Model for Rainfall-Runoff Simulations |
提出基于S4D-FT的深度状态空间模型，用于提升降雨径流模拟精度。 |
SSM state space model |
|
|
| 21 |
E-Gen: Leveraging E-Graphs to Improve Continuous Representations of Symbolic Expressions |
E-Gen：利用E-图改进符号表达式的连续表示 |
contrastive learning large language model |
✅ |
|
| 22 |
Reinforcement Learning for Efficient Returns Management |
提出基于强化学习的在线多背包问题解决方案，优化零售退货管理效率。 |
reinforcement learning |
|
|
| 23 |
Bi-directional Curriculum Learning for Graph Anomaly Detection: Dual Focus on Homogeneity and Heterogeneity |
提出双向课程学习（BCL）策略，提升图异常检测模型性能。 |
curriculum learning |
|
|