| 1 |
CX-Mind: A Pioneering Multimodal Large Language Model for Interleaved Reasoning in Chest X-ray via Curriculum-Guided Reinforcement Learning |
CX-Mind：基于课程引导强化学习的胸部X光片多模态大语言模型，实现交错推理 |
reinforcement learning spatiotemporal large language model |
|
|
| 2 |
DepMicroDiff: Diffusion-Based Dependency-Aware Multimodal Imputation for Microbiome Data |
DepMicroDiff：结合依赖感知的扩散模型用于微生物组数据多模态补全 |
MAE large language model multimodal |
|
|
| 3 |
INSPIRE-GNN: Intelligent Sensor Placement to Improve Sparse Bicycling Network Prediction via Reinforcement Learning Boosted Graph Neural Networks |
提出INSPIRE-GNN，通过强化学习优化的图神经网络解决稀疏自行车网络预测问题。 |
reinforcement learning MAE |
|
|
| 4 |
One-Step Flow Policy Mirror Descent |
提出FPMD算法，实现Flow Policy单步采样，加速在线强化学习推理。 |
reinforcement learning diffusion policy flow matching |
|
|
| 5 |
Merging Memory and Space: A State Space Neural Operator |
提出状态空间神经算子（SS-NO）用于高效学习时变偏微分方程的解算子。 |
SSM state space model spatiotemporal |
|
|
| 6 |
RecoMind: A Reinforcement Learning Framework for Optimizing In-Session User Satisfaction in Recommendation Systems |
RecoMind：一种基于强化学习的框架，用于优化推荐系统中会话内的用户满意度 |
reinforcement learning |
|
|
| 7 |
RL as Regressor: A Reinforcement Learning Approach for Function Approximation |
提出基于强化学习的回归方法，解决传统回归损失函数的局限性 |
reinforcement learning |
|
|
| 8 |
Benchmarking Partial Observability in Reinforcement Learning with a Suite of Memory-Improvable Domains |
提出POBAX：用于强化学习中部分可观测性基准测试的JAX开源库 |
reinforcement learning |
|
|
| 9 |
Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning |
提出层次化消息传递策略以解决多智能体强化学习中的协调问题 |
reinforcement learning |
|
|
| 10 |
GraphRAG-R1: Graph Retrieval-Augmented Generation with Process-Constrained Reinforcement Learning |
GraphRAG-R1：提出基于过程约束强化学习的图检索增强生成框架，提升LLM多跳推理能力。 |
reinforcement learning |
|
|
| 11 |
Predicting Large-scale Urban Network Dynamics with Energy-informed Graph Neural Diffusion |
提出能量感知的图神经网络扩散模型，用于预测大规模城市网络动态。 |
predictive model spatiotemporal |
|
|