cs.LG（2024-04-02）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7) 支柱九：具身大模型 (Embodied Foundation Models) (4) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	MESEN: Exploit Multimodal Data to Design Unimodal Human Activity Recognition with Few Labels	提出MESEN以解决人类活动识别中的标签稀缺问题	contrastive learning multimodal
2	Propensity Score Alignment of Unpaired Multimodal Data	提出倾向评分对齐方法以解决非配对多模态数据对齐问题	representation learning multimodal
3	Is Exploration All You Need? Effective Exploration Characteristics for Transfer in Reinforcement Learning	提出有效探索特征以提升强化学习中的迁移学习效果	reinforcement learning deep reinforcement learning
4	Position: Lifetime tuning is incompatible with continual reinforcement learning	提出针对持续强化学习的评估方法改进方案	reinforcement learning SAC
5	Emergence of Chemotactic Strategies with Multi-Agent Reinforcement Learning	利用多智能体强化学习研究化学趋向策略	reinforcement learning
6	Federated Distillation: A Survey	提出联邦蒸馏以解决联邦学习中的通信成本问题	distillation
7	Unifying Qualitative and Quantitative Safety Verification of DNN-Controlled Systems	提出统一定性与定量安全验证框架以解决DNN控制系统安全问题	reinforcement learning deep reinforcement learning

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

#	题目	一句话要点	标签	🔗	⭐
8	Attribution Regularization for Multimodal Paradigms	提出归因正则化以解决多模态模型决策中的单模态主导问题	embodied AI multimodal
9	Enhancing Inference Efficiency of Large Language Models: Investigating Optimization Strategies and Architectural Innovations	提出跳过Transformer后续注意力层以提高大语言模型推理效率	large language model
10	Designing Network Algorithms via Large Language Models	提出NADA框架以自动设计网络算法	large language model
11	Predicting the Performance of Foundation Models via Agreement-on-the-Line	通过线性一致性预测基础模型的性能	foundation model

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Improved Text Emotion Prediction Using Combined Valence and Arousal Ordinal Classification	提出基于序数分类的情感预测方法以提升文本情感识别准确性	motion prediction

⬅️ 返回 cs.LG 首页 · 🏠 返回主页