cs.LG（2024-09-13）

📊 共 13 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) (7) 支柱九：具身大模型 (Embodied Foundation Models) (3 🔗1) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 Eureka: Evaluating and Understanding Large Foundation Models Eureka框架：标准化评估大型模型，揭示模型能力差异与不足 Eureka foundation model multimodal
2 Applying Action Masking and Curriculum Learning Techniques to Improve Data Efficiency and Overall Performance in Operational Technology Cyber Security using Reinforcement Learning 应用动作掩码与课程学习提升强化学习在工控网络安全中的数据效率与性能 reinforcement learning PPO curriculum learning
3 Can Kans (re)discover predictive models for Direct-Drive Laser Fusion? 利用KANs在直接驱动激光聚变中发现可预测模型，解决数据匮乏难题。 predictive model
4 Multi-intent Aware Contrastive Learning for Sequential Recommendation 提出多意图感知对比学习序列推荐模型，解决单意图表示的局限性。 contrastive learning
5 Acoustic identification of individual animals with hierarchical contrastive learning 提出基于层级对比学习的动物声音个体识别方法，提升识别精度。 contrastive learning
6 Integration of Mamba and Transformer -- MAT for Long-Short Range Time Series Forecasting with Application to Weather Dynamics 提出MAT模型，融合Mamba与Transformer，用于长短期天气动力学时间序列预测。 Mamba
7 Curricula for Learning Robust Policies with Factored State Representations in Changing Environments 提出基于分解状态表示的课程学习方法，提升强化学习策略在动态环境中的鲁棒性 reinforcement learning policy learning

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

#题目一句话要点标签🔗⭐
8 Exploring Graph Structure Comprehension Ability of Multimodal Large Language Models: Case Studies 探索多模态大语言模型图结构理解能力：案例研究 large language model multimodal
9 PHemoNet: A Multimodal Network for Physiological Signals PHemoNet：一种用于生理信号多模态情感识别的超复数网络 multimodal ✅
10 ProcessTBench: An LLM Plan Generation Dataset for Process Mining ProcessTBench：用于流程挖掘的LLM计划生成数据集，扩展TaskBench以评估LLM在流程视角下的能力。 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
11 Hierarchical Hypercomplex Network for Multimodal Emotion Recognition 提出一种层级超复数网络，用于多模态情感识别，提升了脑电和生理信号的情感分类性能。 manipulation PHC multimodal ✅
12 Towards safe and tractable Gaussian process-based MPC: Efficient sampling within a sequential quadratic programming framework 提出基于高斯过程的MPC方法，通过高效采样和序列二次规划框架，实现安全且易于处理的控制。 MPC model predictive control

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

#题目一句话要点标签🔗⭐
13 SAUC: Sparsity-Aware Uncertainty Calibration for Spatiotemporal Prediction with Graph Neural Networks 提出SAUC框架，解决时空图神经网络在稀疏数据上的不确定性校准问题 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页