cs.LG（2024-03-27）

📊 共 14 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (8) 支柱一：机器人控制 (Robot Control) (3) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
1 CoRAST: Towards Foundation Model-Powered Correlated Data Analysis in Resource-Constrained CPS and IoT 提出CoRAST以解决资源受限环境中的相关数据分析问题 representation learning foundation model multimodal
2 Detecting Generative Parroting through Overfitting Masked Autoencoders 提出过拟合掩码自编码器以检测生成性模仿问题 masked autoencoder MAE
3 Exploiting Symmetry in Dynamics for Model-Based Reinforcement Learning with Asymmetric Rewards 提出基于对称性动态的强化学习方法以应对不对称奖励问题 reinforcement learning
4 Robustness and Visual Explanation for Black Box Image, Video, and ECG Signal Classification with Reinforcement Learning 提出一种通用的强化学习框架以提升图像、视频和ECG信号分类的鲁棒性与可解释性 reinforcement learning
5 Preventing Collapse in Contrastive Learning with Orthonormal Prototypes (CLOP) 提出CLOP以解决对比学习中的神经崩溃问题 contrastive learning
6 Deep Fusion: Capturing Dependencies in Contrastive Learning via Transformer Projection Heads 提出变换器投影头以提升对比学习性能 contrastive learning
7 Generalized Policy Learning for Smart Grids: FL TRPO Approach 提出FL TRPO框架以优化智能电网的能源管理 policy learning
8 From Two-Dimensional to Three-Dimensional Environment with Q-Learning: Modeling Autonomous Navigation with Reinforcement Learning and no Libraries 提出无库Q学习算法以解决二维与三维环境导航问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
9 Safe and Robust Reinforcement Learning: Principles and Practice 提出安全与稳健的强化学习框架以应对现实应用挑战 sim-to-real reinforcement learning
10 Mistake, Manipulation and Margin Guarantees in Online Strategic Classification 提出新算法以解决在线战略分类中的操控与错误问题 manipulation
11 The Artificial Neural Twin -- Process Optimization and Continual Learning in Distributed Process Chains 提出人工神经双胞胎以解决工业过程优化问题 model predictive control

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
12 Understanding the Learning Dynamics of Alignment with Human Feedback 提出人类反馈对齐学习动态的理论分析方法 large language model
13 The Topos of Transformer Networks 通过拓扑理论分析Transformer网络的表达能力 large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
14 Synthesizing EEG Signals from Event-Related Potential Paradigms with Conditional Diffusion Models 提出条件扩散模型以生成特定EEG信号 classifier-free guidance

⬅️ 返回 cs.LG 首页 · 🏠 返回主页