cs.LG（2024-03-19）
📊 共 21 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) (10 🔗3)
支柱九：具身大模型 (Embodied Foundation Models) (7 🔗2)
支柱八：物理动画 (Physics-based Animation) (2)
支柱一：机器人控制 (Robot Control) (2)
🔬 支柱二：RL算法与架构 (RL & Architecture) (10 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Simple Ingredients for Offline Reinforcement Learning | 提出简单方法以解决离线强化学习中的数据多样性问题 | reinforcement learning offline reinforcement learning IQL | ||
| 2 | Understanding and Improving Training-free Loss-based Diffusion Guidance | 提出训练无关的损失引导方法以提升扩散模型性能 | reinforcement learning motion generation | ||
| 3 | STG-Mamba: Spatial-Temporal Graph Learning via Selective State Space Model | 提出STG-Mamba以解决时空图学习中的动态特征建模问题 | Mamba state space model | ✅ | |
| 4 | Policy Bifurcation in Safe Reinforcement Learning | 提出多模态策略优化以解决安全强化学习中的策略分叉问题 | reinforcement learning multimodal | ||
| 5 | Automated Contrastive Learning Strategy Search for Time Series | 提出自动化对比学习策略搜索以优化时间序列分析 | reinforcement learning representation learning contrastive learning | ||
| 6 | Do Generated Data Always Help Contrastive Learning? | 提出自适应数据膨胀方法以优化对比学习效果 | representation learning contrastive learning | ✅ | |
| 7 | Equivariant Ensembles and Regularization for Reinforcement Learning in Map-based Path Planning | 提出等变集成与正则化以提升路径规划中的强化学习效率 | reinforcement learning | ||
| 8 | Non-negative Contrastive Learning | 提出非负对比学习以提升特征可解释性与分类性能 | contrastive learning | ✅ | |
| 9 | Optimal Flow Matching: Learning Straight Trajectories in Just One Step | 提出最优流匹配方法以实现单步学习直线路径 | flow matching | ||
| 10 | Stochastic Halpern iteration in normed spaces and applications to reinforcement learning | 提出随机Halpern迭代以优化强化学习中的固定点求解 | reinforcement learning |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 11 | VL-ICL Bench: The Devil in the Details of Multimodal In-Context Learning | 提出VL-ICL Bench以探索多模态上下文学习的潜力与局限性 | large language model multimodal | ✅ | |
| 12 | Advancing Time Series Classification with Multimodal Language Modeling | 提出InstructTime以解决时间序列分类中的标签表示与迁移学习问题 | foundation model multimodal | ||
| 13 | AffineQuant: Affine Transformation Quantization for Large Language Models | 提出AffineQuant以解决大规模语言模型量化问题 | large language model | ||
| 14 | AlignRec: Aligning and Training in Multimodal Recommendations | 提出AlignRec以解决多模态推荐中的对齐问题 | multimodal | ✅ | |
| 15 | Multi-fidelity surrogate with heterogeneous input spaces for modeling melt pools in laser-directed energy deposition | 提出异构输入空间的多保真代理模型以预测激光沉积熔池几何 | multimodal | ||
| 16 | MELTing point: Mobile Evaluation of Language Transformers | 提出MELT框架以解决移动设备上大语言模型执行效率问题 | large language model | ||
| 17 | Towards Better Statistical Understanding of Watermarking LLMs | 提出水印大语言模型的新方法以提高检测能力 | large language model |
🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 18 | Modal Analysis of Spatiotemporal Data via Multivariate Gaussian Process Regression | 提出多变量高斯过程回归以解决稀疏时序数据的模态分析问题 | spatiotemporal | ||
| 19 | FairSTG: Countering performance heterogeneity via collaborative sample-level optimization | 提出FairSTG以解决样本性能异质性问题 | spatiotemporal |
🔬 支柱一：机器人控制 (Robot Control) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 20 | Sim2Real in Reconstructive Spectroscopy: Deep Learning with Augmented Device-Informed Data Simulation | 提出Sim2Real框架以解决重构光谱信号重建问题 | sim2real | ||
| 21 | Sample Complexity of Offline Distributionally Robust Linear Markov Decision Processes | 提出离线分布鲁棒线性马尔可夫决策过程的样本复杂度分析 | sim-to-real reinforcement learning offline reinforcement learning |