cs.LG（2023-11-10）

📊 共 7 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (3) 支柱二：RL算法与架构 (RL & Architecture) (2) 支柱四：生成式动作 (Generative Motion) (1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Parameter-Efficient Orthogonal Finetuning via Butterfly Factorization	提出蝶形因子化的正交微调方法以提高参数效率	large language model foundation model
2	MultiIoT: Benchmarking Machine Learning for the Internet of Things	提出MultiIoT基准以解决IoT领域机器学习的评估问题	foundation model multimodal
3	Learning material synthesis-process-structure-property relationship by data fusion: Bayesian Coregionalization N-Dimensional Piecewise Function Learning	提出SAGE算法以解决材料合成-过程-结构-性质关系学习问题	multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
4	ID Embedding as Subtle Features of Content and Structure for Multimodal Recommendation	提出ID嵌入作为多模态推荐中的细微特征以提升推荐效果	contrastive learning multimodal
5	Clipped-Objective Policy Gradients for Pessimistic Policy Optimization	提出剪切目标策略梯度以优化悲观策略	reinforcement learning deep reinforcement learning PPO

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
6	Differentiable VQ-VAE's for Robust White Matter Streamline Encodings	提出可微分向量量化变分自编码器以解决白质纤维编码问题	VQ-VAE

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

#	题目	一句话要点	标签	🔗	⭐
7	FourierGNN: Rethinking Multivariate Time Series Forecasting from a Pure Graph Perspective	提出FourierGNN以解决多变量时间序列预测中的模型兼容性问题	spatiotemporal TAMP

⬅️ 返回 cs.LG 首页 · 🏠 返回主页