cs.LG（2024-08-26）

📊 共 12 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

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

#题目一句话要点标签🔗⭐
1 Reprogramming Foundational Large Language Models(LLMs) for Enterprise Adoption for Spatio-Temporal Forecasting Applications: Unveiling a New Era in Copilot-Guided Cross-Modal Time Series Representation Learning 利用LLM重编程进行时空预测，实现企业级跨模态时间序列表示学习 representation learning large language model
2 Exploring the Potential of Large Language Models for Heterophilic Graphs 提出LLM增强的异质图学习框架，提升节点分类性能 distillation large language model
3 Model-Based Reinforcement Learning for Control of Strongly-Disturbed Unsteady Aerodynamic Flows 提出基于模型的强化学习方法，用于控制强扰动下的非定常气动流 reinforcement learning deep reinforcement learning latent dynamics
4 Unsupervised Representation Learning of Complex Time Series for Maneuverability State Identification in Smart Mobility 提出TNC4Maneuvering和DLG4Maneuvering，用于智能交通中机动状态识别的无监督表征学习。 representation learning
5 Rethinking Knowledge Transfer in Learning Using Privileged Information 重新审视特权信息学习中的知识迁移有效性 privileged information
6 TSAK: Two-Stage Semantic-Aware Knowledge Distillation for Efficient Wearable Modality and Model Optimization in Manufacturing Lines TSAK：面向智能工厂可穿戴设备高效人体活动识别的双阶段语义感知知识蒸馏 distillation
7 ReLExS: Reinforcement Learning Explanations for Stackelberg No-Regret Learners ReLExS：Stackelberg博弈中无遗憾学习者的强化学习解释 reinforcement learning

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

#题目一句话要点标签🔗⭐
8 Hyperdimensional Computing Empowered Federated Foundation Model over Wireless Networks for Metaverse 提出基于超维计算的联邦分裂学习框架，用于元宇宙中资源受限设备的联邦学习。 foundation model
9 AgentMove: A Large Language Model based Agentic Framework for Zero-shot Next Location Prediction AgentMove：基于大语言模型的Agent框架，用于零样本的下一位置预测 large language model ✅
10 DefectTwin: When LLM Meets Digital Twin for Railway Defect Inspection DefectTwin：利用LLM赋能数字孪生，实现铁路缺陷智能检测 large language model multimodal
11 CURLoRA: Stable LLM Continual Fine-Tuning and Catastrophic Forgetting Mitigation CURLoRA：利用CUR分解和低秩适应，稳定LLM的持续微调并缓解灾难性遗忘 large language model

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
12 On-Chip Learning with Memristor-Based Neural Networks: Assessing Accuracy and Efficiency Under Device Variations, Conductance Errors, and Input Noise 提出基于忆阻器的片上学习硬件加速器，提升抗干扰能力与能效 PULSE

⬅️ 返回 cs.LG 首页 · 🏠 返回主页