cs.LG（2024-03-25）

📊 共 8 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) (3) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱一：机器人控制 (Robot Control) (1) 支柱八：物理动画 (Physics-based Animation) (1 🔗1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Offline Reinforcement Learning: Role of State Aggregation and Trajectory Data	提出离线强化学习新方法以解决样本复杂性问题	reinforcement learning offline reinforcement learning
2	Convergence of a model-free entropy-regularized inverse reinforcement learning algorithm	提出无模型熵正则化逆强化学习算法以解决奖励恢复问题	reinforcement learning inverse reinforcement learning
3	Exploring the potential of prototype-based soft-labels data distillation for imbalanced data classification	提出基于原型的软标签数据蒸馏以解决数据不平衡问题	distillation

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

#	题目	一句话要点	标签	🔗	⭐
4	Multimodal Physical Fitness Monitoring (PFM) Framework Based on TimeMAE-PFM in Wearable Scenarios	提出多模态PFM框架以解决传统健康监测不足问题	multimodal
5	To Err is Machine: Vulnerability Detection Challenges LLM Reasoning	提出针对大语言模型的漏洞检测挑战与解决方案	large language model
6	Do LLM Agents Have Regret? A Case Study in Online Learning and Games	提出无监督的遗憾损失以提升LLM代理的决策性能	large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
7	Bridging Privacy and Robustness for Trustworthy Machine Learning	提出隐私与鲁棒性结合的方法以提升可信机器学习	manipulation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
8	LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting	提出LSTTN以解决交通流预测中的长短期特征提取问题	spatiotemporal	✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页