cs.LG（2024-08-28）

📊 共 17 篇论文 | 🔗 4 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (8 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗2) 支柱一：机器人控制 (Robot Control) (1) 支柱七：动作重定向 (Motion Retargeting) (1 🔗1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (8 篇)

#题目一句话要点标签🔗⭐
1 Meta-Learn Unimodal Signals with Weak Supervision for Multimodal Sentiment Analysis 提出元学习框架以解决多模态情感分析中的单模态标签学习问题 multimodal
2 SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding SciLitLLM：提出结合持续预训练和监督微调的LLM，用于科学文献理解 large language model instruction following
3 LeMON: Learning to Learn Multi-Operator Networks LeMON：学习学习多算子网络，解决PDE求解中的泛化难题 foundation model
4 EPO: Hierarchical LLM Agents with Environment Preference Optimization 提出EPO：一种基于环境偏好优化的分层LLM Agent，用于长程决策任务 multimodal
5 3-in-1: 2D Rotary Adaptation for Efficient Finetuning, Efficient Batching and Composability 提出RoAd：一种基于2D旋转的参数高效微调方法，提升效率、批量处理能力和可组合性 large language model
6 Exploring Selective Layer Fine-Tuning in Federated Learning 提出一种联邦学习中选择性层微调策略，提升异构环境下的模型收敛性。 foundation model
7 How Reliable are Causal Probing Interventions? 评估因果探测干预的可靠性，揭示完备性与选择性之间的权衡。 foundation model ✅
8 ANVIL: Anomaly-based Vulnerability Identification without Labelled Training Data ANVIL：利用LLM的异常检测能力，无需标注数据进行漏洞识别 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🔗⭐
9 An Extremely Data-efficient and Generative LLM-based Reinforcement Learning Agent for Recommenders 提出基于生成式LLM的强化学习推荐Agent，实现数据高效训练 reinforcement learning PPO DPO
10 Mamba or Transformer for Time Series Forecasting? Mixture of Universals (MoU) Is All You Need 提出混合通用模型(MoU)，融合Mamba与Transformer，提升时间序列预测精度。 Mamba ✅
11 wav2pos: Sound Source Localization using Masked Autoencoders 提出wav2pos，使用掩码自编码器解决分布式麦克风阵列的3D声源定位问题 masked autoencoder
12 Learning Harmonized Representations for Speculative Sampling 提出HArmonized Speculative Sampling (HASS)以解决LLM推断加速中的上下文不一致问题 distillation large language model ✅
13 Multi-Graph Inductive Representation Learning for Large-Scale Urban Rail Demand Prediction under Disruptions 提出mGraphSAGE模型，用于应对扰动下大规模城市轨道交通需求预测。 representation learning
14 Statistical QoS Provision in Business-Centric Networks 提出面向业务的BCN网络，利用DRL实现可扩展的统计QoS保障 reinforcement learning deep reinforcement learning DRL
15 MODULI: Unlocking Preference Generalization via Diffusion Models for Offline Multi-Objective Reinforcement Learning MODULI：利用扩散模型解锁离线多目标强化学习中的偏好泛化 reinforcement learning

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
16 Skills Regularized Task Decomposition for Multi-task Offline Reinforcement Learning 提出技能正则化任务分解方法，解决异构离线数据集上的多任务强化学习问题 manipulation reinforcement learning offline RL

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#题目一句话要点标签🔗⭐
17 AutoGeo: Automating Geometric Image Dataset Creation for Enhanced Geometry Understanding AutoGeo：自动化生成几何图像数据集，提升几何理解能力 spatial relationship large language model multimodal ✅

⬅️ 返回 cs.LG 首页 · 🏠 返回主页