cs.LG（2024-08-05）

📊 共 14 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (7 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#题目一句话要点标签🔗⭐
1 Cross-Modality Clustering-based Self-Labeling for Multimodal Data Classification 提出基于跨模态聚类的自标记方法CMCSL，解决多模态数据分类中的标注难题。 multimodal
2 Large Language Model Aided QoS Prediction for Service Recommendation 提出llmQoS模型，利用大语言模型提升Web服务推荐中的QoS预测精度 large language model
3 Evaluating the Performance of Large Language Models for SDG Mapping (Technical Report) 评估大型语言模型在可持续发展目标映射任务中的性能 large language model
4 Pre-trained Encoder Inference: Revealing Upstream Encoders In Downstream Machine Learning Services 提出预训练编码器推断攻击（PEI），揭示下游机器学习服务中的编码器信息。 multimodal ✅
5 A Novel Hybrid Approach for Tornado Prediction in the United States: Kalman-Convolutional BiLSTM with Multi-Head Attention 提出Kalman-Convolutional BiLSTM与多头注意力混合模型，提升美国龙卷风预测精度。 large language model
6 Black-Box Adversarial Attacks on LLM-Based Code Completion INSEC：针对LLM代码补全的隐蔽黑盒对抗攻击，显著提升不安全代码生成率 large language model
7 A Lean Transformer Model for Dynamic Malware Analysis and Detection 提出精简Transformer模型，用于动态恶意软件分析与检测。 large language model

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

#题目一句话要点标签🔗⭐
8 MDM: Advancing Multi-Domain Distribution Matching for Automatic Modulation Recognition Dataset Synthesis 提出MDM：一种用于自动调制识别数据集合成的多域分布匹配方法 distillation MDM
9 Toward Cost-efficient Adaptive Clinical Trials in Knee Osteoarthritis with Reinforcement Learning 提出基于强化学习的主动感知方法，用于膝骨关节炎自适应临床试验，降低成本。 reinforcement learning multimodal
10 Spatial-temporal Graph Convolutional Networks with Diversified Transformation for Dynamic Graph Representation Learning 提出STGCNDT模型，通过多样化变换的时空图卷积网络学习动态图表示，提升链路权重估计精度。 representation learning spatiotemporal
11 DisCoM-KD: Cross-Modal Knowledge Distillation via Disentanglement Representation and Adversarial Learning 提出DisCoM-KD，通过解耦表示和对抗学习实现跨模态知识蒸馏 representation learning distillation
12 Generalized Gaussian Temporal Difference Error for Uncertainty-aware Reinforcement Learning 提出基于广义高斯TD误差的强化学习框架，提升不确定性感知能力 reinforcement learning deep reinforcement learning
13 One-Shot Collaborative Data Distillation 提出CollabDM，一种单轮通信的协同数据蒸馏方法，解决分布式环境下数据异构问题。 distillation
14 Contrastive Learning and Abstract Concepts: The Case of Natural Numbers 对比学习用于抽象概念：自然数计数任务的探索 contrastive learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页