cs.LG（2025-01-07）

📊 共 17 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) (11 🔗2) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱八：物理动画 (Physics-based Animation) (2)

🔬 支柱二：RL算法与架构 (RL & Architecture) (11 篇)

#题目一句话要点标签🔗⭐
1 SALE-Based Offline Reinforcement Learning with Ensemble Q-Networks 提出基于SALE的离线强化学习算法，融合集成Q网络与梯度多样性惩罚，提升稳定性和性能。 reinforcement learning offline reinforcement learning behavior cloning
2 Discriminative Representation learning via Attention-Enhanced Contrastive Learning for Short Text Clustering 提出AECL模型，通过注意力增强对比学习解决短文本聚类中的伪负例分离问题。 representation learning contrastive learning
3 Rethinking Adversarial Attacks in Reinforcement Learning from Policy Distribution Perspective 提出分布感知投影梯度下降攻击以解决DRL中的对抗攻击问题 reinforcement learning deep reinforcement learning DRL
4 Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment Align-Pro：一种基于原则的LLM对齐提示优化方法 reinforcement learning RLHF large language model
5 Stochastic Process Learning via Operator Flow Matching 提出算子流匹配(OFM)用于学习任意域上的随机过程，提升函数空间先验学习效果。 flow matching
6 Explainable Reinforcement Learning via Temporal Policy Decomposition 提出时间策略分解以解决强化学习可解释性问题 reinforcement learning
7 More is not always better? Enhancing Many-Shot In-Context Learning with Differentiated and Reweighting Objectives 提出DrICL方法，通过差异化和重加权目标增强大语言模型的多样本上下文学习能力。 reinforcement learning large language model ✅
8 Explainable Reinforcement Learning for Formula One Race Strategy 提出RSRL，一种基于强化学习的F1赛车策略优化方法，优于传统策略。 reinforcement learning
9 FedKD-hybrid: Federated Hybrid Knowledge Distillation for Lithography Hotspot Detection 提出FedKD-hybrid，一种用于光刻热点检测的联邦混合知识蒸馏方法 distillation ✅
10 Deep Learning within Tabular Data: Foundations, Challenges, Advances and Future Directions 综述表格数据深度学习：探讨基础、挑战、进展与未来方向 representation learning foundation model
11 Few-Shot Radar Signal Recognition through Self-Supervised Learning and Radio Frequency Domain Adaptation 提出基于自监督学习和射频域自适应的少样本雷达信号识别方法 masked autoencoder MAE

🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)

#题目一句话要点标签🔗⭐
12 RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance 提出RAG-Check框架，用于评估多模态检索增强生成系统的性能，关注检索相关性和生成正确性。 large language model multimodal
13 Exploring the Potential of Large Language Models in Public Transportation: San Antonio Case Study 探索大语言模型在公共交通中的潜力：圣安东尼奥案例研究 large language model
14 A Multimodal Lightweight Approach to Fault Diagnosis of Induction Motors in High-Dimensional Dataset 提出基于迁移学习的轻量级多模态方法，用于高维数据集下感应电机故障诊断。 multimodal
15 Context-Alignment: Activating and Enhancing LLM Capabilities in Time Series 提出Context-Alignment框架，激活并增强LLM在时间序列任务中的能力 large language model multimodal ✅

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

#题目一句话要点标签🔗⭐
16 AADNet: Exploring EEG Spatiotemporal Information for Fast and Accurate Orientation and Timbre Detection of Auditory Attention Based on A Cue-Masked Paradigm 提出AADNet，利用脑电时空信息快速准确解码听觉注意的方向和音色 spatiotemporal
17 MHGNet: Multi-Heterogeneous Graph Neural Network for Traffic Prediction 提出MHGNet，用于建模时空多重异构图，提升交通流量预测精度。 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页