cs.LG(2023-10-25)

📊 共 23 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱二:RL算法与架构 (RL & Architecture) (11 🔗3) 支柱九:具身大模型 (Embodied Foundation Models) (7) 支柱一:机器人控制 (Robot Control) (4) 支柱八:物理动画 (Physics-based Animation) (1)

🔬 支柱二:RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗
1 Conditionally Combining Robot Skills using Large Language Models 提出Language-World与PCBC方法以提升机器人技能组合能力 reinforcement learning deep reinforcement learning large language model
2 Privately Aligning Language Models with Reinforcement Learning 提出隐私保护的强化学习对齐方法以提升语言模型性能 reinforcement learning RLHF large language model
3 Towards Control-Centric Representations in Reinforcement Learning from Images 提出ReBis以解决图像强化学习中的控制中心表示问题 reinforcement learning latent dynamics spatiotemporal
4 Zephyr: Direct Distillation of LM Alignment 提出Zephyr以解决语言模型对用户意图的对齐问题 RLHF direct preference optimization distillation
5 MultiPrompter: Cooperative Prompt Optimization with Multi-Agent Reinforcement Learning 提出MultiPrompter以解决提示优化中的协作问题 reinforcement learning foundation model
6 Model-enhanced Contrastive Reinforcement Learning for Sequential Recommendation 提出模型增强对比强化学习以解决推荐系统中的数据稀疏问题 reinforcement learning offline RL contrastive learning
7 Pitfall of Optimism: Distributional Reinforcement Learning by Randomizing Risk Criterion 提出随机化风险标准的分布式强化学习算法以解决偏见探索问题 reinforcement learning
8 Hyperparameter Optimization for Multi-Objective Reinforcement Learning 提出超参数优化方法以解决多目标强化学习挑战 reinforcement learning
9 Transfer of Reinforcement Learning-Based Controllers from Model- to Hardware-in-the-Loop 结合迁移学习与硬件仿真加速强化学习控制器开发 reinforcement learning
10 RedCoast: A Lightweight Tool to Automate Distributed Training of LLMs on Any GPU/TPUs 提出RedCoast以自动化大语言模型的分布式训练 reinforcement learning large language model
11 Modality-Agnostic Self-Supervised Learning with Meta-Learned Masked Auto-Encoder 提出MetaMAE以实现模态无关的自监督学习 MAE contrastive learning

🔬 支柱九:具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗
12 Transferring a molecular foundation model for polymer property predictions 提出基于小分子的转移学习模型以解决聚合物性质预测问题 large language model foundation model
13 Multiple Key-value Strategy in Recommendation Systems Incorporating Large Language Model 提出多键值策略以解决推荐系统中的信息匹配问题 large language model
14 General Point Model with Autoencoding and Autoregressive 提出通用点模型以提升点云理解与生成任务 large language model
15 Improving Few-shot Generalization of Safety Classifiers via Data Augmented Parameter-Efficient Fine-Tuning 通过数据增强的参数高效微调提升安全分类器的少样本泛化能力 large language model
16 From Molecules to Materials: Pre-training Large Generalizable Models for Atomic Property Prediction 提出联合多领域预训练方法以提升原子属性预测精度 foundation model
17 QMoE: Practical Sub-1-Bit Compression of Trillion-Parameter Models 提出QMoE以解决大规模模型内存占用问题 large language model
18 Learning Generalizable Program and Architecture Representations for Performance Modeling 提出PerfVec以解决性能建模中的高成本与低灵活性问题 foundation model

🔬 支柱一:机器人控制 (Robot Control) (4 篇)

#题目一句话要点标签🔗
19 TD-MPC2: Scalable, Robust World Models for Continuous Control 提出TD-MPC2以提升连续控制任务的模型性能 MPC trajectory optimization reinforcement learning
20 Model predictive control-based value estimation for efficient reinforcement learning 基于模型预测控制的价值估计方法提升强化学习效率 model predictive control reinforcement learning
21 Reinforcement Learning for SBM Graphon Games with Re-Sampling 提出图论游戏重采样算法以解决多种群体均衡问题 manipulation reinforcement learning
22 ClearMark: Intuitive and Robust Model Watermarking via Transposed Model Training 提出ClearMark以解决深度学习模型水印的可理解性问题 manipulation

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

#题目一句话要点标签🔗
23 Quantum Long Short-Term Memory (QLSTM) vs Classical LSTM in Time Series Forecasting: A Comparative Study in Solar Power Forecasting 比较量子长短期记忆与经典LSTM在太阳能预测中的应用 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页