cs.LG（2026-07-14）

📊 共 15 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱一：机器人控制 (Robot Control) (2) 支柱八：物理动画 (Physics-based Animation) (1) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 The Computational Basis of Confidence in Large Language Models 提出统计决策信心框架以解析大语言模型的信心机制 large language model multimodal
2 Accelerating Masked Diffusion Large Language Models: A Survey of Efficient Inference Techniques 提出统一延迟分解框架以加速扩散大语言模型推理 large language model
3 Learning Mechanistic Reasoning for Chemical Reactions with Large Language Models 提出大规模推理数据集以提升化学反应机制学习 large language model
4 Exploring Zero-Shot Foundation Models for Multivariate Time Series Anomaly Detection 探索零-shot基础模型用于多变量时间序列异常检测 foundation model
5 From Many to Meaningful: Feature-Guided Zero-Shot Chronic Kidney Disease Screening Using Large Language Models 提出特征引导的零-shot框架以解决慢性肾病筛查问题 large language model
6 The Spectrum Is Not Enough: When Context Helps Time-Series Forecasting 提出上下文增强的时间序列预测方法以解决谱信息不足问题 foundation model
7 Watermark Forensics for Generative Models: An Information-Theoretic Perspective 提出水印取证方法以解决生成模型输出归属问题 TAMP
8 Ensemble Controlled-Flow Filtering for Implicit Data Assimilation 提出Ensemble Controlled-Flow Filtering以解决隐式数据同化问题 multimodal

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
9 A Shortcut to Statistically Steady-State Turbulence with Flow Matching 提出GyroFlow以解决高保真模拟的计算成本问题 flow matching
10 Constraint-Aware Aggregation for Federated Reinforcement Learning in Microgrid Energy Coordination 提出约束感知聚合方法以解决微电网能量协调问题 reinforcement learning
11 OOD-RL-Bench: A Benchmark Framework for Out-of-Distribution Detection in Reinforcement Learning 提出OOD-RL-Bench以解决强化学习中的分布外检测问题 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
12 Learning-enabled Acceleration of Scenario-based Model Predictive Control 提出学习加速的场景基础模型预测控制方法以解决实时规划问题 MPC model predictive control
13 Verifier-Based Reinforcement Fine-Tuning of Reasoning Models for Thermal Energy Storage Control 提出基于验证者的强化微调方法以优化热能存储控制 MPC model predictive control reinforcement learning

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

#题目一句话要点标签🔗⭐
14 Robustness of Deep Learning Models for PV Power Forecasting under NWP Forecast Errors: A Spatiotemporal and Physically Interpretable Analysis 提出基于物理约束的鲁棒性评估框架以应对PV功率预测中的NWP误差 spatiotemporal

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
15 Differentiable Clone-Structured Causal Graphs for End-to-End Cognitive Map Learning from Image Sequences 提出可微分克隆结构因果图以解决认知地图学习问题 VQ-VAE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页