cs.LG（2025-07-05）

📊 共 13 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) (9 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (2) 支柱八：物理动画 (Physics-based Animation) (2 🔗1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 Risk-sensitive Actor-Critic with Static Spectral Risk Measures for Online and Offline Reinforcement Learning 提出基于静态谱风险度量的风险敏感Actor-Critic算法，用于在线和离线强化学习 reinforcement learning DRL offline RL
2 Where to Intervene: Action Selection in Deep Reinforcement Learning 提出基于Knockoff抽样的深度强化学习动作选择方法，提升复杂环境下的决策效率。 reinforcement learning deep reinforcement learning
3 Accurate and Efficient World Modeling with Masked Latent Transformers 提出EMERALD，一种基于掩码潜在Transformer的高精度、高效率世界模型，并在Crafter基准上超越人类专家。 world model dreamer
4 MCST-Mamba: Multivariate Mamba-Based Model for Traffic Prediction 提出基于Mamba的MCST-Mamba模型，用于多变量交通预测，提升预测精度。 Mamba representation learning
5 Enhancing Adaptive Behavioral Interventions with LLM Inference from Participant-Described States 利用LLM推断参与者状态，增强自适应行为干预效果 reinforcement learning policy learning large language model
6 When Data-Free Knowledge Distillation Meets Non-Transferable Teacher: Escaping Out-of-Distribution Trap is All You Need 提出ATEsc方法，解决数据自由知识蒸馏中非迁移教师的OOD陷阱问题 distillation ✅
7 Consistency-Aware Padding for Incomplete Multi-Modal Alignment Clustering Based on Self-Repellent Greedy Anchor Search 提出CAPIMAC，解决不完整多模态数据对齐聚类中的数据缺失填充问题。 contrastive learning multimodal ✅
8 Predictive Modeling of Effluent Temperature in SAT Systems Using Ambient Meteorological Data: Implications for Infiltration Management 利用气象数据预测SAT系统出水温度，优化渗滤管理 predictive model
9 GenAI-Powered Inference 提出基于GenAI的推理框架GPI，用于非结构化数据的因果和预测推断。 representation learning large language model

🔬 支柱九：具身大模型 (Embodied Foundation Models) (2 篇)

#题目一句话要点标签🔗⭐
10 Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data Real-TabPFN：通过真实世界数据持续预训练提升表格数据基础模型性能 foundation model
11 KEA Explain: Explanations of Hallucinations using Graph Kernel Analysis 提出KEA Explain框架，利用图核分析解释大语言模型中的幻觉现象 large language model

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
12 Transformer with Koopman-Enhanced Graph Convolutional Network for Spatiotemporal Dynamics Forecasting 提出TK-GCN模型，用于解决不规则几何域上的时空动力学预测问题 spatiotemporal
13 Enhanced accuracy through ensembling of randomly initialized auto-regressive models for time-dependent PDEs 提出基于随机初始化自回归模型集成的深度学习框架，提升时变偏微分方程求解精度。 spatiotemporal ✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页