cs.LG（2025-01-21）

📊 共 22 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) (11) 支柱二：RL算法与架构 (RL & Architecture) (8) 支柱一：机器人控制 (Robot Control) (2 🔗1) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Large Language Models Meet Graph Neural Networks for Text-Numeric Graph Reasoning 提出结合大语言模型与图神经网络的文本-数值图推理方法，用于科学发现。 large language model
2 CroMe: Multimodal Fake News Detection using Cross-Modal Tri-Transformer and Metric Learning 提出CroMe模型，利用跨模态Tri-Transformer和度量学习进行多模态假新闻检测。 large language model multimodal
3 CDW-CoT: Clustered Distance-Weighted Chain-of-Thoughts Reasoning 提出CDW-CoT，通过聚类和距离加权优化提示，提升LLM在复杂推理任务中的性能。 large language model chain-of-thought
4 How Does the Spatial Distribution of Pre-training Data Affect Geospatial Foundation Models? 研究预训练数据空间分布对地理空间基础模型性能的影响 foundation model
5 Adaptive PII Mitigation Framework for Large Language Models 提出一种自适应PII缓解框架，用于应对大语言模型中的隐私合规挑战。 large language model
6 BiMarker: Enhancing Text Watermark Detection for Large Language Models with Bipolar Watermarks 提出双极水印以增强大语言模型文本水印检测能力 large language model
7 Linear Feedback Control Systems for Iterative Prompt Optimization in Large Language Models 提出基于线性反馈控制的LLM迭代提示优化方法，提升输出质量 large language model
8 The Journey Matters: Average Parameter Count over Pre-training Unifies Sparse and Dense Scaling Laws 提出基于平均参数计数的缩放法则，统一稀疏和稠密预训练LLM的性能预测。 large language model
9 Divide-Then-Aggregate: An Efficient Tool Learning Method via Parallel Tool Invocation 提出DTA-Llama，通过并行工具调用提升LLM在复杂任务中的性能与效率。 large language model
10 FOCUS: First Order Concentrated Updating Scheme 提出FOCUS优化器，提升LLM在梯度噪声下的训练稳定性和速度 large language model
11 ALoFTRAG: Automatic Local Fine Tuning for Retrieval Augmented Generation ALoFTRAG：面向RAG的自动局部微调框架，提升特定领域准确率 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
12 Compositional Instruction Following with Language Models and Reinforcement Learning 提出CERLLA，利用组合策略表示和强化学习语义解析器，提升语言模型在组合指令跟随任务中的泛化能力。 reinforcement learning instruction following language conditioned
13 GLAM: Global-Local Variation Awareness in Mamba-based World Model GLAM：基于Mamba的世界模型，通过全局-局部变异感知提升样本效率 reinforcement learning world model Mamba
14 Explainable AI for Mental Health Emergency Returns: Integrating LLMs with Predictive Modeling 融合LLM与预测模型，提升精神健康急诊返诊预测的准确性和可解释性 predictive model large language model
15 Tackling Uncertainties in Multi-Agent Reinforcement Learning through Integration of Agent Termination Dynamics 提出基于终止动态集成的多智能体强化学习方法，解决不确定性问题。 reinforcement learning policy learning
16 Reinforcement Learning Constrained Beam Search for Parameter Optimization of Paper Drying Under Flexible Constraints 提出RLCBS算法，解决强化学习中柔性约束下的参数优化问题，应用于纸张干燥过程。 reinforcement learning
17 Community-Aware Temporal Walks: Parameter-Free Representation Learning on Continuous-Time Dynamic Graphs 提出CTWalks，解决连续时间动态图表示学习中时序和结构动态建模难题 representation learning
18 Group-Agent Reinforcement Learning with Heterogeneous Agents 提出异构智能体组学习强化学习框架，加速个体智能体学习并提升性能 reinforcement learning
19 Toward Effective Digraph Representation Learning: A Magnetic Adaptive Propagation based Approach 提出磁适应传播方法，有效提升有向图表示学习性能 representation learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
20 Audio Texture Manipulation by Exemplar-Based Analogy 提出基于范例类比的音频纹理操控方法，通过配对语音样本实现声音转换。 manipulation ✅
21 SafePowerGraph-HIL: Real-Time HIL Validation of Heterogeneous GNNs for Bridging Sim-to-Real Gap in Power Grids SafePowerGraph-HIL：利用异构图神经网络和硬件在环仿真弥合电力系统Sim-to-Real差距 sim-to-real

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
22 Learning Dynamic Representations via An Optimally-Weighted Maximum Mean Discrepancy Optimization Framework for Continual Learning 提出OWMMD框架，通过优化最大均值差异动态学习表征，缓解持续学习中的灾难性遗忘。 feature matching

⬅️ 返回 cs.LG 首页 · 🏠 返回主页