cs.LG（2023-12-10）

📊 共 9 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (5) 支柱八：物理动画 (Physics-based Animation) (2) 支柱九：具身大模型 (Embodied Foundation Models) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1 🔗1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	The Generalization Gap in Offline Reinforcement Learning	揭示离线强化学习泛化能力不足，并提出首个离线泛化能力评测基准。	reinforcement learning offline RL offline reinforcement learning
2	CLeaRForecast: Contrastive Learning of High-Purity Representations for Time Series Forecasting	CLeaRForecast：提出一种对比学习框架，通过高纯度表征提升时间序列预测精度。	representation learning contrastive learning
3	Ensemble Kalman Filtering Meets Gaussian Process SSM for Non-Mean-Field and Online Inference	提出EnKF辅助的GPSSM非平均场在线推断方法，解决传统变分推断的难题。	SSM
4	Efficient Sparse-Reward Goal-Conditioned Reinforcement Learning with a High Replay Ratio and Regularization	针对稀疏奖励目标条件强化学习，提出高回放率和正则化的高效REDQ改进方法	reinforcement learning
5	DCIR: Dynamic Consistency Intrinsic Reward for Multi-Agent Reinforcement Learning	提出动态一致性内在奖励（DCIR）以提升多智能体强化学习中的协作能力	reinforcement learning

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
6	TransGlow: Attention-augmented Transduction model based on Graph Neural Networks for Water Flow Forecasting	TransGlow：基于图神经网络和注意力机制的水流预测模型	spatiotemporal
7	Detecting Toxic Flow	提出PULSE在线贝叶斯方法，预测外汇交易中的毒性交易	PULSE

🔬 支柱九：具身大模型 (Embodied Foundation Models) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Beyond Gradient and Priors in Privacy Attacks: Leveraging Pooler Layer Inputs of Language Models in Federated Learning	提出针对联邦学习中语言模型池化层输入的隐私攻击方法	large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	ICTSurF: Implicit Continuous-Time Survival Functions with Neural Networks	提出ICTSurF，利用隐式表达构建连续时间生存函数，提升生存分析性能。	implicit representation	✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页