cs.LG（2025-05-04）

📊 共 14 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) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗2) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
1 SkillMimic-V2: Learning Robust and Generalizable Interaction Skills from Sparse and Noisy Demonstrations SkillMimic-V2：从稀疏噪声交互演示中学习鲁棒且泛化的技能 reinforcement learning
2 Learning Local Causal World Models with State Space Models and Attention 利用状态空间模型和注意力机制学习局部因果世界模型 world model SSM state space model
3 Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation TimeKD：利用校准语言模型和特权知识蒸馏的高效多元时间序列预测框架 distillation privileged information large language model
4 Deep Representation Learning for Electronic Design Automation 利用深度表征学习提升电子设计自动化（EDA）的效率与准确性 representation learning multimodal
5 D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation Detection 提出D3HRL，通过因果发现与伪相关检测解决分层强化学习中的延迟效应和伪相关问题 reinforcement learning
6 Universal Approximation Theorem of Deep Q-Networks 通过随机控制和FBSDE，证明DQN在连续时间MDP中的通用逼近定理 reinforcement learning deep reinforcement learning
7 Meta-Black-Box-Optimization through Offline Q-function Learning 提出基于离线Q函数学习的元黑盒优化框架Q-Mamba，提升算法配置效率。 conservative q-learning Mamba ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
8 Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach 提出校准感知微调方法，恢复对齐后大语言模型的校准性。 large language model
9 From Biometrics to Environmental Control: AI-Enhanced Digital Twins for Personalized Health Interventions in Healing Landscapes 提出AI增强的数字孪生框架，用于个性化健康干预和疗愈环境控制。 multimodal
10 An Empirical Study of Qwen3 Quantization 针对Qwen3大语言模型，系统性研究了不同量化方案对其性能的影响。 large language model ✅
11 GRAIL: Graph Edit Distance and Node Alignment Using LLM-Generated Code GRAIL：利用LLM生成代码进行图编辑距离计算和节点对齐 large language model
12 Lightweight Defense Against Adversarial Attacks in Time Series Classification 提出基于数据增强的时间序列分类对抗攻击轻量级防御方法 foundation model
13 Wide & Deep Learning for Node Classification GCNIII：结合Wide & Deep架构提升节点分类性能，关注节点特征利用 large language model ✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning 提出耦合分布随机专家蒸馏，用于世界模型在线模仿学习 locomotion manipulation imitation learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页