cs.LG（2024-03-06）

📊 共 11 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (6) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗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	Population-aware Online Mirror Descent for Mean-Field Games by Deep Reinforcement Learning	提出基于深度强化学习的种群感知在线镜面下降算法以解决均值场博弈问题	reinforcement learning deep reinforcement learning DRL
2	A Teacher-Free Graph Knowledge Distillation Framework with Dual Self-Distillation	提出无教师图知识蒸馏框架以提升MLP性能	teacher-student distillation
3	Unsupervised Contrastive Learning for Robust RF Device Fingerprinting Under Time-Domain Shift	提出无监督对比学习以解决RF设备指纹识别中的域偏移问题	contrastive learning
4	Sampling-based Safe Reinforcement Learning for Nonlinear Dynamical Systems	提出基于采样的安全强化学习以解决非线性动态系统控制问题	reinforcement learning
5	Can Distillation Mitigate Backdoor Attacks in Pre-trained Encoders?	提出蒸馏方法以缓解自监督学习中的后门攻击问题	distillation
6	A Survey on Applications of Reinforcement Learning in Spatial Resource Allocation	综述强化学习在空间资源分配中的应用	reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
7	Temporal Cross-Attention for Dynamic Embedding and Tokenization of Multimodal Electronic Health Records	提出动态嵌入与标记化框架以解决电子健康记录的时间性问题	multimodal
8	RouteExplainer: An Explanation Framework for Vehicle Routing Problem	提出RouteExplainer以解决车辆路径问题的可解释性	large language model	✅
9	DPOT: Auto-Regressive Denoising Operator Transformer for Large-Scale PDE Pre-Training	提出DPOT以解决大规模PDE预训练的效率与稳定性问题	foundation model	✅
10	GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection	提出GaLore以解决大规模语言模型训练中的内存效率问题	large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Stop Regressing: Training Value Functions via Classification for Scalable Deep RL	通过分类训练价值函数以提升深度强化学习的可扩展性	manipulation reinforcement learning deep reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页