cs.LG（2023-10-19）

📊 共 15 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (8 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

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

#题目一句话要点标签🔗⭐
1 Neurosymbolic Grounding for Compositional World Models 提出Cosmos框架以解决组合泛化问题 world model world models foundation model ✅
2 Towards Robust Offline Reinforcement Learning under Diverse Data Corruption 提出鲁棒的离线强化学习方法以应对数据腐蚀问题 reinforcement learning policy learning offline RL
3 MTS-LOF: Medical Time-Series Representation Learning via Occlusion-Invariant Features 提出MTS-LOF以解决医疗时间序列表示学习中的标注挑战 representation learning masked autoencoder MAE
4 Eureka-Moments in Transformers: Multi-Step Tasks Reveal Softmax Induced Optimization Problems 提出Eureka时刻机制以解决Transformer多步任务优化问题 Eureka
5 Semi-Supervised Learning of Dynamical Systems with Neural Ordinary Differential Equations: A Teacher-Student Model Approach 提出TS-NODE以解决动态系统建模中的数据不足问题 teacher-student
6 Unsupervised Representation Learning to Aid Semi-Supervised Meta Learning 提出无监督表示学习以辅助半监督元学习 representation learning
7 Learn from the Past: A Proxy Guided Adversarial Defense Framework with Self Distillation Regularization 提出LAST框架以解决对抗训练中的不稳定性问题 distillation ✅
8 SDGym: Low-Code Reinforcement Learning Environments using System Dynamics Models 提出SDGym以解决强化学习环境设计难题 reinforcement learning

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

#题目一句话要点标签🔗⭐
9 The Foundation Model Transparency Index 提出基础模型透明度指数以提升透明性和问责性 foundation model
10 Model Merging by Uncertainty-Based Gradient Matching 提出基于不确定性的梯度匹配方法以优化模型合并 large language model
11 TabuLa: Harnessing Language Models for Tabular Data Synthesis 提出TabuLa以解决表格数据合成中的隐私与效率问题 large language model ✅
12 Knowledge from Uncertainty in Evidential Deep Learning 提出基于不确定性的证据深度学习以提升分类性能 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
13 Vision-Language Models are Zero-Shot Reward Models for Reinforcement Learning 提出VLM-RMs以解决强化学习中的奖励函数指定问题 humanoid reinforcement learning
14 Probabilistic Modeling of Human Teams to Infer False Beliefs 提出概率图模型以推断人类团队的错误信念 manipulation

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
15 CAT: Closed-loop Adversarial Training for Safe End-to-End Driving 提出闭环对抗训练框架以提升自动驾驶安全性 motion prediction ✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页