| 1 |
Learning Multimodal One-step Flow Policy via Value-weighted Optimal Transport |
提出OptiFlow框架以解决离线强化学习中的多模态行为学习问题 |
reinforcement learning policy learning offline RL |
✅ |
|
| 2 |
Not All Prompts Are Equal: Exploration-Guided Prompt Scaffolding for Multimodal Reinforcement Post-Training |
提出探索引导的提示支架以优化多模态强化学习后训练 |
reinforcement learning large language model multimodal |
|
|
| 3 |
Assembling the CREW: A Collaborative Multi-agent Reinforcement Learning Framework for Automated Related Work Generation |
提出CREW框架以解决自动相关工作生成中的协作问题 |
reinforcement learning large language model |
✅ |
|
| 4 |
What Does an LLM Learn from Reinforcement Learning? A Mechanistic Interpretability Perspective with Fixed-SAE Track |
提出Fixed-SAE Track以深入理解强化学习对大语言模型的影响 |
reinforcement learning large language model |
|
|
| 5 |
Transfer Learning for Socioeconomic Estimation in Forced-Displacement Settings |
提出多模态时空视觉变换器以解决强迫迁移背景下的社会经济估计问题 |
MAE spatiotemporal multimodal |
|
|
| 6 |
Refinement-based Flow Policy Optimization |
提出RFPO以解决流政策优化中的样本获取问题 |
reinforcement learning flow matching multimodal |
|
|
| 7 |
HiGFRL: Hierarchical Graph Fusion-Driven Reinforcement Learning for Dependency-Aware Task Scheduling in Heterogeneous Cloud |
提出HiGFRL以解决异构云中依赖感知任务调度问题 |
reinforcement learning DRL |
✅ |
|
| 8 |
Cloud Workflow Scheduling Based on Graph Attention-Driven Hierarchical Reinforcement Learning |
提出基于图注意力的层次强化学习调度云工作流 |
reinforcement learning PPO |
✅ |
|
| 9 |
Bellman Policy Optimization |
提出Bellman策略优化以提升大语言模型推理能力 |
reinforcement learning large language model |
|
|
| 10 |
Safe Meta-Reinforcement Learning via Information Space Reachability |
提出安全元强化学习框架以解决安全性问题 |
reinforcement learning |
|
|
| 11 |
LLM-Based Schema-Aware Split Learning for Privacy-Preserving Mental Distress Prediction Across Heterogeneous Surveys |
提出基于LLM的架构感知分割学习以解决隐私保护的心理困扰预测问题 |
predictive model large language model |
|
|
| 12 |
Sharp Rates and a One-Line Correction for Spectral Representation Learning |
提出一种新方法以优化自监督特征在任务转移中的表现 |
representation learning |
|
|
| 13 |
Principal-timestep Restricted Init via Sparse Matrix-decomposition in Flow-matching |
提出Prism-LoRA以解决扩散模型微调中的梯度对齐问题 |
flow matching |
|
|
| 14 |
Specifying Reward Functions for RL Without Environment Sampling |
提出EARS方法以解决无环境采样的奖励函数指定问题 |
reinforcement learning RLHF reward design |
|
|
| 15 |
When Correlations Mislead: Confounder-Aware Multi-View Urban Region Representation Learning |
提出CURE框架以解决多视角城市区域表示学习中的混淆问题 |
representation learning |
|
|
| 16 |
Admissable: Training Reinforcement Learning Agents against Adversarial Missingness |
提出对抗性缺失特征训练方法以提升强化学习鲁棒性 |
reinforcement learning |
|
|
| 17 |
Temporal Self-Distillation: Faster Inference in Discrete Diffusion Language Models |
提出时间自蒸馏方法以加速离散扩散语言模型推理 |
distillation |
|
|
| 18 |
$\mathbb{SL}(n)$ Representation Learning: An Intrinsic Mixed-Curvature Space with Higher Curvature Capacities and Deeper Order-Aware Composition |
提出$ ext{SL}(n)$空间以解决混合曲率表示学习问题 |
representation learning |
|
|