cs.LG（2024-01-26）

📊 共 9 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) (5 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱五：交互与反应 (Interaction & Reaction) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Large Language Model Guided Knowledge Distillation for Time Series Anomaly Detection	提出AnomalyLLM以解决时间序列异常检测中的样本稀缺问题	distillation large language model
2	Better Representations via Adversarial Training in Pre-Training: A Theoretical Perspective	通过对抗训练改进预训练表示以增强下游任务的鲁棒性	contrastive learning large language model
3	Expert with Clustering: Hierarchical Online Preference Learning Framework	提出专家聚类框架以加速用户偏好学习	preference learning
4	Fully Independent Communication in Multi-Agent Reinforcement Learning	提出独立学习者间通信方法以解决MARL中的复杂性问题	reinforcement learning
5	Off-Policy Primal-Dual Safe Reinforcement Learning	提出保守策略优化以解决离线策略安全强化学习中的成本估计问题	reinforcement learning	✅

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

#	题目	一句话要点	标签	🔗	⭐
6	On the generalization capacity of neural networks during generic multimodal reasoning	提出多模态问答基准以评估神经网络的泛化能力	large language model multimodal
7	SliceGPT: Compress Large Language Models by Deleting Rows and Columns	提出SliceGPT以压缩大型语言模型的计算和内存需求	large language model	✅
8	EAGLE: Speculative Sampling Requires Rethinking Feature Uncertainty	提出EAGLE以提高大语言模型的推理效率	large language model instruction following

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
9	GuardML: Efficient Privacy-Preserving Machine Learning Services Through Hybrid Homomorphic Encryption	提出混合同态加密以解决隐私保护机器学习问题	OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页