cs.LG(2024-04-07)
📊 共 9 篇论文 | 🔗 1 篇有代码
🎯 兴趣领域导航
支柱九:具身大模型 (Embodied Foundation Models) (5 🔗1)
支柱二:RL算法与架构 (RL & Architecture) (2)
支柱一:机器人控制 (Robot Control) (1)
支柱八:物理动画 (Physics-based Animation) (1)
🔬 支柱九:具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | A Note on LoRA | 扩展LoRA方法以提升大语言模型适应性 | large language model | ||
| 2 | Initial Exploration of Zero-Shot Privacy Utility Tradeoffs in Tabular Data Using GPT-4 | 利用GPT-4探索表格数据中的隐私效用权衡 | large language model | ||
| 3 | Adapting LLMs for Efficient Context Processing through Soft Prompt Compression | 提出SoftPromptComp以高效处理长文本上下文问题 | large language model | ||
| 4 | TimeGPT in Load Forecasting: A Large Time Series Model Perspective | 提出TimeGPT以解决负荷预测中的数据稀缺问题 | large language model | ||
| 5 | SqueezeAttention: 2D Management of KV-Cache in LLM Inference via Layer-wise Optimal Budget | 提出SqueezeAttention以优化LLM推理中的KV缓存管理 | large language model | ✅ |
🔬 支柱二:RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 6 | Percentile Criterion Optimization in Offline Reinforcement Learning | 提出基于风险价值的动态规划算法以优化离线强化学习中的百分位准则 | reinforcement learning offline reinforcement learning | ||
| 7 | TimeCSL: Unsupervised Contrastive Learning of General Shapelets for Explorable Time Series Analysis | 提出TimeCSL以解决时间序列分析中的无监督表示学习问题 | representation learning contrastive learning |
🔬 支柱一:机器人控制 (Robot Control) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 8 | Skill Transfer and Discovery for Sim-to-Real Learning: A Representation-Based Viewpoint | 提出基于表示学习的技能转移与发现方法以解决仿真与现实间的差距问题 | sim-to-real representation learning |
🔬 支柱八:物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | Gradient-based Design of Computational Granular Crystals | 提出基于梯度优化的计算颗粒晶体设计方法以提升计算效率 | spatiotemporal |