cs.LG（2024-11-19）

📊 共 13 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) (6) 支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱八：物理动画 (Physics-based Animation) (2 🔗1) 支柱一：机器人控制 (Robot Control) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	SkillTree: Explainable Skill-Based Deep Reinforcement Learning for Long-Horizon Control Tasks	SkillTree：面向长时程控制任务的可解释技能型深度强化学习	reinforcement learning deep reinforcement learning DRL
2	Just KIDDIN: Knowledge Infusion and Distillation for Detection of INdecent Memes	提出基于知识注入与蒸馏的框架，用于检测网络有害Meme	distillation multimodal
3	LEDRO: LLM-Enhanced Design Space Reduction and Optimization for Analog Circuits	LEDRO：利用LLM增强模拟电路设计空间缩减与优化	reinforcement learning AMP large language model
4	Reward Modeling with Ordinal Feedback: Wisdom of the Crowd	提出基于序数反馈的奖励模型学习框架，提升LLM对齐效果	DPO distillation large language model
5	Emergence of Implicit World Models from Mortal Agents	基于可死亡智能体的内隐世界模型涌现研究	reinforcement learning world model
6	Contrast Similarity-Aware Dual-Pathway Mamba for Multivariate Time Series Node Classification	提出CS-DPMamba，结合对比学习相似度和双向Mamba，用于多变量时间序列节点分类。	Mamba

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

#	题目	一句话要点	标签	🔗	⭐
7	Generalized Prompt Tuning: Adapting Frozen Univariate Time Series Foundation Models for Multivariate Healthcare Time Series	提出广义Prompt Tuning，将单变量时间序列基础模型适配于多变量医疗时间序列预测。	foundation model
8	Forecasting Application Counts in Talent Acquisition Platforms: Harnessing Multimodal Signals using LMs	提出基于多模态语言模型的招聘申请数量预测方法，优化人才招聘。	multimodal
9	Enhancing Reasoning Capabilities of LLMs via Principled Synthetic Logic Corpus	提出Additional Logic Training (ALT)方法，提升LLM的逻辑推理能力。	large language model

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

#	题目	一句话要点	标签	🔗	⭐
10	Diffusion Transformers as Open-World Spatiotemporal Foundation Models	UrbanDiT：基于扩散Transformer的开放世界时空基础模型，用于城市环境建模。	spatiotemporal foundation model	✅
11	Advancing Marine Heatwave Forecasts: An Integrated Deep Learning Approach	提出结合图表示、不平衡回归和时间扩散的深度学习方法，用于全球海洋热浪预测。	spatiotemporal

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
12	Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning	提出CQN-AS算法，通过序列动作预测提升数据效率强化学习在机器人控制任务中的性能。	humanoid humanoid control manipulation

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

#	题目	一句话要点	标签	🔗	⭐
13	Integrating Secondary Structures Information into Triangular Spatial Relationships (TSR) for Advanced Protein Classification	提出SSE-TSR方法，通过整合二级结构信息提升蛋白质分类精度	spatial relationship

⬅️ 返回 cs.LG 首页 · 🏠 返回主页