cs.LG（2024-07-17）
📊 共 12 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) (5)
支柱九：具身大模型 (Embodied Foundation Models) (5 🔗2)
支柱一：机器人控制 (Robot Control) (1)
支柱八：物理动画 (Physics-based Animation) (1 🔗1)
🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Mamba-PTQ: Outlier Channels in Recurrent Large Language Models | Mamba-PTQ：揭示循环LLM中激活异常通道问题并初步探索量化方案 | Mamba SSM large language model | ||
| 2 | Maintenance Strategies for Sewer Pipes with Multi-State Degradation and Deep Reinforcement Learning | 利用多状态退化模型与深度强化学习优化污水管道维护策略 | reinforcement learning deep reinforcement learning DRL | ||
| 3 | Subequivariant Reinforcement Learning in 3D Multi-Entity Physical Environments | 提出Subequivariant分层神经网络，解决3D多实体物理环境中强化学习的维度灾难问题。 | reinforcement learning policy learning | ||
| 4 | Variable-Agnostic Causal Exploration for Reinforcement Learning | 提出VACERL，无需预定义变量即可在强化学习中进行因果探索 | reinforcement learning | ||
| 5 | Chip Placement with Diffusion Models | 提出基于扩散模型的芯片布局方法，实现零样本泛化和高性能。 | reinforcement learning zero-shot transfer |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models | 提出利用环境交互的LLM自动PDDL转换与规划方法，无需人工干预。 | large language model chain-of-thought | ✅ | |
| 7 | The 2024 Foundation Model Transparency Index | 基金模型透明度指数评估：揭示行业透明度提升与持续不透明领域 | foundation model | ||
| 8 | Evaluating the transferability potential of deep learning models for climate downscaling | 评估深度学习模型在气候降尺度中的迁移潜力，探索更通用的气候预测模型 | zero-shot transfer | ||
| 9 | Spectra: Surprising Effectiveness of Pretraining Ternary Language Models at Scale | Spectra：大规模三元语言模型预训练效果显著，性能超越同等规模浮点模型。 | large language model | ✅ | |
| 10 | Questionable practices in machine learning | 揭示机器学习中44种可疑实践，强调LLM评估并关注可复现性问题 | large language model |
🔬 支柱一：机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 11 | Sparsity-based Safety Conservatism for Constrained Offline Reinforcement Learning | 提出基于数据稀疏性的保守度量，提升约束离线强化学习的安全性 | manipulation reinforcement learning offline RL |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 12 | UniTE: A Survey and Unified Pipeline for Pre-training Spatiotemporal Trajectory Embeddings | UniTE：时空轨迹预训练嵌入的综述与统一流程 | spatiotemporal | ✅ |