cs.LG（2026-04-24）
📊 共 14 篇论文 | 🔗 2 篇有代码
🎯 兴趣领域导航
支柱二：RL算法与架构 (RL & Architecture) (6 🔗2)
支柱九：具身大模型 (Embodied Foundation Models) (5)
支柱一：机器人控制 (Robot Control) (3)
🔬 支柱二：RL算法与架构 (RL & Architecture) (6 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | SpikingBrain2.0: Brain-Inspired Foundation Models for Efficient Long-Context and Cross-Platform Inference | SpikingBrain2.0：面向高效长上下文和跨平台推理的类脑基础模型 | linear attention foundation model multimodal | ||
| 2 | SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning | 提出SOLAR-RL以解决长时间任务中的强化学习效率问题 | reinforcement learning offline RL large language model | ||
| 3 | Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning | DROL：通过动态路由而非对应关系，提升离线强化学习单步策略的性能 | reinforcement learning offline RL offline reinforcement learning | ✅ | |
| 4 | Beyond Patient Invariance: Learning Cardiac Dynamics via Action-Conditioned JEPAs | 提出基于动作条件JEPAs的心脏动力学学习方法，提升心电图分析性能 | world model world models JEPA | ✅ | |
| 5 | On the Properties of Feature Attribution for Supervised Contrastive Learning | 对比学习特征归因研究：监督对比学习提升特征解释质量 | contrastive learning | ||
| 6 | ReCast: Recasting Learning Signals for Reinforcement Learning in Generative Recommendation | ReCast：在生成式推荐中重塑强化学习信号，解决稀疏反馈下的学习难题。 | reinforcement learning |
🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 7 | FeatEHR-LLM: Leveraging Large Language Models for Feature Engineering in Electronic Health Records | 提出FeatEHR-LLM以解决电子健康记录特征工程问题 | large language model | ||
| 8 | A Nationwide Japanese Medical Claims Foundation Model: Balancing Model Scaling and Task-Specific Computational Efficiency | 构建日本全国医疗理赔数据Foundation Model，平衡模型规模与任务效率 | foundation model | ||
| 9 | FETS Benchmark: Foundation Models Outperform Dataset-specific Machine Learning in Energy Time Series Forecasting | FETS基准测试表明：能源时间序列预测中，预训练模型优于特定数据集的机器学习方法 | foundation model | ||
| 10 | How LLMs Detect and Correct Their Own Errors: The Role of Internal Confidence Signals | 大型语言模型通过内部置信度信号检测和纠正自身错误 | large language model | ||
| 11 | Sovereign Agentic Loops: Decoupling AI Reasoning from Execution in Real-World Systems | 提出Sovereign Agentic Loops，解耦AI推理与真实系统执行，提升安全性 | large language model |
🔬 支柱一：机器人控制 (Robot Control) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 12 | Iterative Model-Learning Scheme via Gaussian Processes for Nonlinear Model Predictive Control of (Semi-)Batch Processes | 提出基于高斯过程的迭代模型学习NMPC方案，用于半批量过程控制。 | model predictive control | ||
| 13 | Decoding High-Dimensional Finger Motion from EMG Using Riemannian Features and RNNs | 提出基于黎曼特征和RNN的框架以解码高维手指运动 | teleoperation | ||
| 14 | Data-Free Contribution Estimation in Federated Learning using Gradient von Neumann Entropy | 提出基于梯度von Neumann熵的联邦学习无数据贡献度评估方法 | manipulation |