cs.LG（2023-11-15）

📊 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) (5 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱五：交互与反应 (Interaction & Reaction) (1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
1 Frequency Domain-based Dataset Distillation 提出FreD方法以解决数据集蒸馏中的预算限制问题 distillation ✅
2 Challenges for Predictive Modeling with Neural Network Techniques using Error-Prone Dietary Intake Data 探讨神经网络在饮食摄入数据预测建模中的挑战与解决方案 predictive model
3 Assessing the Robustness of Intelligence-Driven Reinforcement Learning 提出基于奖励机器的智能驱动强化学习以增强鲁棒性 reinforcement learning
4 On the Foundation of Distributionally Robust Reinforcement Learning 提出基于鲁棒马尔可夫决策过程的分布鲁棒强化学习框架 reinforcement learning
5 Adversarial Attacks to Reward Machine-based Reinforcement Learning 提出对基于奖励机器的强化学习的对抗攻击分析 reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
6 HEALNet: Multimodal Fusion for Heterogeneous Biomedical Data 提出HEALNet以解决异构生物医学数据的多模态融合问题 multimodal
7 A Multimodal Dataset of 21,412 Recorded Nights for Sleep and Respiratory Research 提出多模态数据集以推动睡眠与呼吸研究 multimodal
8 Auto-ICL: In-Context Learning without Human Supervision 提出自动化上下文学习框架以解决人工标注的局限性 large language model
9 Wrapper Boxes: Faithful Attribution of Model Predictions to Training Data 提出Wrapper Boxes以解决模型决策可解释性问题 large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
10 Supported Trust Region Optimization for Offline Reinforcement Learning 提出支持信任区域优化以解决离线强化学习中的分布外问题 locomotion reinforcement learning offline reinforcement learning
11 Self-Supervised Curriculum Generation for Autonomous Reinforcement Learning without Task-Specific Knowledge 提出自监督课程生成方法以解决自主强化学习中的环境重置问题 manipulation reinforcement learning

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

#题目一句话要点标签🔗⭐
12 Converting Transformers to Polynomial Form for Secure Inference Over Homomorphic Encryption 提出多项式变换器以解决同态加密下的安全推理问题 OMOMO

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

#题目一句话要点标签🔗⭐
13 Semidefinite programs simulate approximate message passing robustly 提出半正定规划以稳健模拟近似消息传递算法 AMP

⬅️ 返回 cs.LG 首页 · 🏠 返回主页