cs.LG（2023-10-30）

📊 共 22 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) (7) 支柱一：机器人控制 (Robot Control) (6) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗1) 支柱八：物理动画 (Physics-based Animation) (2) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

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

#题目一句话要点标签🔗⭐
1 Convolutional State Space Models for Long-Range Spatiotemporal Modeling 提出卷积状态空间模型以解决长距离时空建模问题 SSM state space model spatiotemporal
2 Adversarial Batch Inverse Reinforcement Learning: Learn to Reward from Imperfect Demonstration for Interactive Recommendation 提出对抗性批量逆强化学习以解决不完美演示的奖励学习问题 reinforcement learning inverse reinforcement learning
3 Efficient Exploration in Continuous-time Model-based Reinforcement Learning 提出基于非线性常微分方程的连续时间强化学习算法 reinforcement learning
4 Asymmetric Diffusion Based Channel-Adaptive Secure Wireless Semantic Communications 提出DiffuSeC以解决语义通信中的安全问题 reinforcement learning deep reinforcement learning DRL
5 Differentially Private Reward Estimation with Preference Feedback 提出差分隐私奖励估计方法以保护用户反馈隐私 reinforcement learning RLHF
6 Free from Bellman Completeness: Trajectory Stitching via Model-based Return-conditioned Supervised Learning 提出基于回报条件监督学习的轨迹拼接方法以解决贝尔曼完备性问题 policy learning offline RL
7 Diversify & Conquer: Outcome-directed Curriculum RL via Out-of-Distribution Disagreement 提出D2C方法以解决无知识强化学习中的探索问题 reinforcement learning curriculum learning

🔬 支柱一：机器人控制 (Robot Control) (6 篇)

#题目一句话要点标签🔗⭐
8 GOPlan: Goal-conditioned Offline Reinforcement Learning by Planning with Learned Models 提出GOPlan以解决离线目标条件强化学习中的数据不足问题 manipulation reinforcement learning offline reinforcement learning
9 On the Theory of Risk-Aware Agents: Bridging Actor-Critic and Economics 提出双重演员-评论家算法以解决风险感知强化学习问题 humanoid locomotion manipulation
10 DrM: Mastering Visual Reinforcement Learning through Dormant Ratio Minimization 提出DrM以解决视觉强化学习中的无效探索问题 manipulation dexterous hand reinforcement learning
11 Variational Curriculum Reinforcement Learning for Unsupervised Discovery of Skills 提出变分课程强化学习以解决无监督技能发现问题 manipulation reinforcement learning curriculum learning
12 Sim2Real for Environmental Neural Processes 提出Sim2Real方法以提升环境神经过程的预测精度 sim2real spatiotemporal
13 Scalable and Privacy-Preserving Synthetic Data Generation on Decentralised Web 提出Libertas改进方案以解决可扩展性问题 MPC

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
14 Early detection of inflammatory arthritis to improve referrals using multimodal machine learning from blood testing, semi-structured and unstructured patient records 提出多模态机器学习方法以改善炎症性关节炎的早期检测 multimodal
15 The Expressibility of Polynomial based Attention Scheme 提出多项式注意力机制以解决长文本处理的复杂性问题 large language model
16 ExPT: Synthetic Pretraining for Few-Shot Experimental Design 提出ExPT以解决少样本实验设计问题 foundation model ✅
17 Model Uncertainty based Active Learning on Tabular Data using Boosted Trees 基于模型不确定性的主动学习方法解决表格数据标注问题 multimodal
18 Musical Form Generation 提出一种生成结构化音乐片段的方法以解决音乐创作的无序问题 large language model

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

#题目一句话要点标签🔗⭐
19 Deep Learning for Spatiotemporal Big Data: A Vision on Opportunities and Challenges 提出深度学习方法以应对时空大数据的挑战 spatiotemporal foundation model
20 TempME: Towards the Explainability of Temporal Graph Neural Networks via Motif Discovery 提出TempME以解决TGNN可解释性问题 spatiotemporal

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
21 Fast and Expressive Gesture Recognition using a Combination-Homomorphic Electromyogram Encoder 提出组合同态肌电图编码器以实现快速且富有表现力的手势识别 OMOMO

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
22 Generative Neural Fields by Mixtures of Neural Implicit Functions 提出生成神经场的新方法以提升数据生成能力 NeRF

⬅️ 返回 cs.LG 首页 · 🏠 返回主页