cs.LG（2024-11-13）

📊 共 12 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	FinRobot: AI Agent for Equity Research and Valuation with Large Language Models	提出FinRobot以解决股权研究中的自动化分析问题	large language model chain-of-thought
2	Accelerating Quasi-Static Time Series Simulations with Foundation Models	利用电网基础模型加速准静态时间序列仿真，降低AI应用门槛。	foundation model
3	Quantifying Qualitative Insights: Leveraging LLMs to Market Predict	利用LLM量化金融研报洞见，提升市场预测准确性	large language model multimodal
4	Lynx: Enabling Efficient MoE Inference through Dynamic Batch-Aware Expert Selection	Lynx：通过动态批处理感知专家选择实现高效MoE推理	large language model
5	Sparse Upcycling: Inference Inefficient Finetuning	对比稀疏Upcycling与持续预训练，探索模型质量与推理效率的权衡。	large language model
6	Can sparse autoencoders be used to decompose and interpret steering vectors?	研究表明稀疏自编码器直接分解和解释steering vectors效果不佳，并分析了其原因。	large language model
7	Measuring similarity between embedding spaces using induced neighborhood graphs	提出基于近邻图结构的嵌入空间相似度度量方法，用于评估配对嵌入的质量。	multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Material Property Prediction with Element Attribute Knowledge Graphs and Multimodal Representation Learning	提出ESNet，融合元素属性知识图谱和多模态表示学习，提升晶体材料性能预测精度。	representation learning multimodal
9	Towards Secure Intelligent O-RAN Architecture: Vulnerabilities, Threats and Promising Technical Solutions using LLMs	利用LLM增强O-RAN安全：分析漏洞、威胁并提出技术解决方案	reinforcement learning deep reinforcement learning large language model
10	Estimating unknown parameters in differential equations with a reinforcement learning based PSO method	提出基于强化学习的粒子群优化算法DERLPSO，用于求解微分方程未知参数估计问题	reinforcement learning
11	Conditional Variable Flow Matching: Transforming Conditional Densities with Amortized Conditional Optimal Transport	提出条件变量流匹配(CVFM)，用于学习条件分布的变换，解决条件随机动力系统预测问题。	flow matching

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

#	题目	一句话要点	标签	🔗	⭐
12	SAD-TIME: a Spatiotemporal-fused network for depression detection with Automated multi-scale Depth-wise and TIME-interval-related common feature extractor	SAD-TIME：融合时空信息的抑郁症脑电检测网络	spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页