cs.LG（2024-04-16）

📊 共 17 篇论文 | 🔗 5 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2) 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) (9 篇)

#题目一句话要点标签🔗⭐
1 Continual Offline Reinforcement Learning via Diffusion-based Dual Generative Replay 提出双生成回放框架以解决持续离线强化学习中的遗忘问题 reinforcement learning offline reinforcement learning behavior cloning ✅
2 Continuous Control Reinforcement Learning: Distributed Distributional DrQ Algorithms 提出分布式分布式DrQ算法以提升连续控制任务性能 reinforcement learning
3 EMC$^2$: Efficient MCMC Negative Sampling for Contrastive Learning with Global Convergence 提出EMC$^2$以解决对比学习中的负样本生成问题 contrastive learning
4 Tripod: Three Complementary Inductive Biases for Disentangled Representation Learning 提出Tripod模型以解决解耦表示学习中的偏置问题 representation learning
5 What Hides behind Unfairness? Exploring Dynamics Fairness in Reinforcement Learning 提出动态公平性概念以解决强化学习中的不公平问题 reinforcement learning ✅
6 Randomized Exploration in Cooperative Multi-Agent Reinforcement Learning 提出随机化探索算法以解决合作多智能体强化学习中的效率问题 reinforcement learning
7 Automatic re-calibration of quantum devices by reinforcement learning 提出基于强化学习的量子设备自动再校准方法 reinforcement learning
8 AGHINT: Attribute-Guided Representation Learning on Heterogeneous Information Networks with Transformer 提出AGHINT以解决异构信息网络中节点属性差异问题 representation learning
9 Social Choice Should Guide AI Alignment in Dealing with Diverse Human Feedback 提出社会选择理论以解决AI对多样人类反馈的对齐问题 reinforcement learning foundation model

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

#题目一句话要点标签🔗⭐
10 Shears: Unstructured Sparsity with Neural Low-rank Adapter Search 提出Shears以提升大语言模型的参数高效微调 large language model
11 Nearly Optimal Algorithms for Contextual Dueling Bandits from Adversarial Feedback 提出稳健的上下文对抗赌博算法以应对对抗反馈问题 large language model
12 Automating REST API Postman Test Cases Using LLM 提出基于大语言模型的REST API自动化测试用例生成方法 large language model
13 VDTuner: Automated Performance Tuning for Vector Data Management Systems 提出VDTuner以解决向量数据管理系统的自动性能调优问题 large language model ✅
14 Hierarchical Context Merging: Better Long Context Understanding for Pre-trained LLMs 提出HOMER以解决长上下文理解问题 large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
15 Offline Trajectory Optimization for Offline Reinforcement Learning 提出OTTO以解决离线强化学习中的数据增强问题 trajectory optimization reinforcement learning policy learning ✅
16 Learning Wireless Data Knowledge Graph for Green Intelligent Communications: Methodology and Experiments 提出PML架构以解决6G网络智能通信中的数据处理问题 manipulation

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

#题目一句话要点标签🔗⭐
17 Four-hour thunderstorm nowcasting using a deep diffusion model of satellite data 提出深度扩散模型以实现四小时雷暴短期预报 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页