cs.LG（2025-01-19）

📊 共 10 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (6 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Blockchain-assisted Demonstration Cloning for Multi-Agent Deep Reinforcement Learning	提出区块链辅助的多专家示教克隆框架，提升多智能体深度强化学习效率与鲁棒性	reinforcement learning deep reinforcement learning imitation learning
2	Adaptive Target Localization under Uncertainty using Multi-Agent Deep Reinforcement Learning with Knowledge Transfer	提出基于知识迁移的多智能体深度强化学习方法，解决不确定环境下目标定位问题。	reinforcement learning deep reinforcement learning
3	Federated Deep Reinforcement Learning for Energy Efficient Multi-Functional RIS-Assisted Low-Earth Orbit Networks	提出基于联邦深度强化学习的低轨卫星多功能RIS辅助节能网络	reinforcement learning deep reinforcement learning
4	A Novel Switch-Type Policy Network for Resource Allocation Problems: Technical Report	提出Switch-Type网络，提升DRL在排队网络资源分配中的泛化性和效率	reinforcement learning deep reinforcement learning DRL
5	Reinforcement Learning Based Goodput Maximization with Quantized Feedback in URLLC	提出基于强化学习的量化反馈好吞吐量最大化方案，用于URLLC	reinforcement learning
6	Model Predictive Task Sampling for Efficient and Robust Adaptation	提出模型预测任务采样(MPTS)框架，提升模型在分布偏移下的适应鲁棒性和学习效率。	predictive model foundation model	✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
7	Multimodal Techniques for Malware Classification	提出基于多模态机器学习的恶意软件分类方法，提升Windows PE文件恶意软件检测精度。	multimodal
8	Control LLM: Controlled Evolution for Intelligence Retention in LLM	提出Control LLM，通过可控演化提升LLM在持续学习中的智能保持能力。	large language model	✅
9	Gradient-Based Multi-Objective Deep Learning: Algorithms, Theories, Applications, and Beyond	综述梯度多目标深度学习：算法、理论、应用及未来方向	large language model	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Conditional Feature Importance with Generative Modeling Using Adversarial Random Forests	提出cARFi，利用对抗随机森林生成模型进行条件特征重要性评估。	manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页