cs.LG（2025-05-04）

📊 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) (6 🔗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) (6 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Learning Local Causal World Models with State Space Models and Attention	提出基于状态空间模型的因果世界建模方法以提升预测能力	world model SSM state space model
2	Efficient Multivariate Time Series Forecasting via Calibrated Language Models with Privileged Knowledge Distillation	提出TimeKD框架以提高多变量时间序列预测效率	distillation privileged information large language model
3	Deep Representation Learning for Electronic Design Automation	提出深度表示学习以提升电子设计自动化效率	representation learning multimodal
4	D3HRL: A Distributed Hierarchical Reinforcement Learning Approach Based on Causal Discovery and Spurious Correlation Detection	提出D3HRL以解决层次强化学习中的延迟效应与虚假相关性问题	reinforcement learning
5	Universal Approximation Theorem of Deep Q-Networks	建立连续时间框架分析深度Q网络的逼近能力	reinforcement learning deep reinforcement learning
6	Meta-Black-Box-Optimization through Offline Q-function Learning	提出Q-Mamba框架以解决MetaBBO的效率问题	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	🔗	⭐
7	Restoring Calibration for Aligned Large Language Models: A Calibration-Aware Fine-Tuning Approach	提出校准感知微调方法以解决大语言模型校准问题	large language model
8	From Biometrics to Environmental Control: AI-Enhanced Digital Twins for Personalized Health Interventions in Healing Landscapes	提出AI增强数字双胞胎框架以实现个性化健康干预	multimodal
9	An Empirical Study of Qwen3 Quantization	系统评估Qwen3量化技术以提升资源受限环境下的应用效率	large language model	✅
10	GRAIL: Graph Edit Distance and Node Alignment Using LLM-Generated Code	提出GRAIL以解决图编辑距离计算中的数据需求与可解释性问题	large language model
11	Lightweight Defense Against Adversarial Attacks in Time Series Classification	提出基于数据增强的轻量级对抗攻击防御方法以提升时间序列分类的鲁棒性	foundation model
12	Wide & Deep Learning for Node Classification	提出GCNIII以解决节点分类中的异质性与表达能力问题	large language model	✅

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
13	Coupled Distributional Random Expert Distillation for World Model Online Imitation Learning	提出基于随机网络蒸馏的奖励模型以解决模仿学习不稳定性问题	locomotion manipulation imitation learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页