| 1 |
SSAMBA: Self-Supervised Audio Representation Learning with Mamba State Space Model |
提出SSAMBA：基于Mamba的自监督音频表征学习模型 |
Mamba SSM state space model |
|
|
| 2 |
Robust Deep Reinforcement Learning with Adaptive Adversarial Perturbations in Action Space |
提出自适应对抗扰动（A2P）方法，提升DRL在动作空间中的鲁棒性 |
reinforcement learning deep reinforcement learning DRL |
✅ |
|
| 3 |
TinyM$^2$Net-V3: Memory-Aware Compressed Multimodal Deep Neural Networks for Sustainable Edge Deployment |
TinyM$^2$Net-V3：面向可持续边缘部署的内存感知压缩多模态深度神经网络 |
distillation multimodal |
|
|
| 4 |
Continual Deep Reinforcement Learning for Decentralized Satellite Routing |
提出基于持续深度强化学习的去中心化卫星路由方案 |
reinforcement learning deep reinforcement learning DRL |
|
|
| 5 |
Feasibility Consistent Representation Learning for Safe Reinforcement Learning |
提出可行性一致性强化学习(FCSRL)框架，解决安全强化学习中安全约束难以估计的问题。 |
reinforcement learning policy learning representation learning |
|
|
| 6 |
Investigating the Impact of Choice on Deep Reinforcement Learning for Space Controls |
研究离散动作空间选择对空间控制深度强化学习性能的影响 |
reinforcement learning deep reinforcement learning |
|
|
| 7 |
Learning Future Representation with Synthetic Observations for Sample-efficient Reinforcement Learning |
提出LFS方法，通过合成未来观测数据提升强化学习样本效率 |
reinforcement learning policy learning representation learning |
|
|
| 8 |
Scrutinize What We Ignore: Reining In Task Representation Shift Of Context-Based Offline Meta Reinforcement Learning |
针对上下文离线元强化学习中的任务表征偏移问题，提出一种新的优化框架。 |
reinforcement learning offline reinforcement learning model-based RL |
|
|
| 9 |
Diffusion for World Modeling: Visual Details Matter in Atari |
DIAMOND：基于扩散模型的Atari世界模型，提升强化学习智能体性能 |
reinforcement learning world model |
|
|
| 10 |
Federated Learning for Time-Series Healthcare Sensing with Incomplete Modalities |
提出FLISM，解决联邦学习中不完整模态时间序列医疗健康感知问题。 |
representation learning distillation multimodal |
✅ |
|
| 11 |
Reward-Punishment Reinforcement Learning with Maximum Entropy |
提出softDMP算法，通过最大熵奖励-惩罚强化学习提升样本效率和鲁棒性。 |
reinforcement learning |
|
|
| 12 |
A Unified Linear Programming Framework for Offline Reward Learning from Human Demonstrations and Feedback |
提出基于线性规划的统一框架，用于离线奖励学习与人类反馈对齐 |
reinforcement learning inverse reinforcement learning RLHF |
|
|
| 13 |
Efficient Multi-agent Reinforcement Learning by Planning |
MAZero：结合规划的强化学习提升多智能体系统样本效率 |
reinforcement learning |
✅ |
|
| 14 |
Asymptotic theory of in-context learning by linear attention |
通过线性注意力机制，论文精确解析了Transformer上下文学习的渐近理论。 |
linear attention |
|
|
| 15 |
Highway Graph to Accelerate Reinforcement Learning |
提出Highway Graph加速强化学习，提升确定性离散环境下的训练效率。 |
reinforcement learning |
✅ |
|