cs.LG（2024-11-21）

📊 共 17 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (9) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱一：机器人控制 (Robot Control) (2) 支柱六：视频提取与匹配 (Video Extraction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (9 篇)

#题目一句话要点标签🔗⭐
1 Movable Antenna-Equipped UAV for Data Collection in Backscatter Sensor Networks: A Deep Reinforcement Learning-based Approach 提出基于深度强化学习的移动天线无人机数据收集方案，优化反向散射传感器网络性能。 reinforcement learning deep reinforcement learning DRL
2 Natural Language Reinforcement Learning 提出自然语言强化学习(NLRL)，通过语言价值函数提升智能体理解与主动学习能力。 reinforcement learning large language model
3 Enhancing Prediction Models with Reinforcement Learning Aureus：利用强化学习增强预测模型，提升新闻推荐系统性能 reinforcement learning large language model
4 Multi-agent reinforcement learning strategy to maximize the lifetime of Wireless Rechargeable 提出基于多智能体强化学习的无线可充电传感器网络寿命最大化策略 reinforcement learning PPO
5 Parameter Efficient Mamba Tuning via Projector-targeted Diagonal-centric Linear Transformation 提出ProDiaL，一种针对Mamba投影层的参数高效微调方法 Mamba SSM
6 CodeSAM: Source Code Representation Learning by Infusing Self-Attention with Multi-Code-View Graphs CodeSAM：通过多代码视图图增强自注意力机制，提升源代码表示学习能力。 representation learning
7 Umbrella Reinforcement Learning -- computationally efficient tool for hard non-linear problems 提出Umbrella强化学习，高效解决具有稀疏奖励的非线性强化学习难题 reinforcement learning
8 Trajectory Representation Learning on Road Networks and Grids with Spatio-Temporal Dynamics TIGR：融合路网与网格时空动态的轨迹表示学习模型 representation learning
9 Learning to Cooperate with Humans using Generative Agents 提出GAMMA，利用生成模型学习人类合作策略，提升人机协作性能 reinforcement learning behavior cloning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
10 From RNNs to Foundation Models: An Empirical Study on Commercial Building Energy Consumption 研究数据集异构性对商业建筑能耗预测模型性能的影响，并探索了基础模型微调的潜力。 foundation model
11 Towards Knowledge Checking in Retrieval-augmented Generation: A Representation Perspective 提出基于表征的知识检查方法，提升检索增强生成系统的可靠性 large language model
12 Variable Extraction for Model Recovery in Scientific Literature 提出基于LLM的变量提取方法，助力科学文献中数学模型的自动恢复。 large language model
13 Schemato -- An LLM for Netlist-to-Schematic Conversion 提出Schemato，一种用于网表到原理图转换的大语言模型。 large language model
14 AutoMixQ: Self-Adjusting Quantization for High Performance Memory-Efficient Fine-Tuning AutoMixQ：一种自适应量化框架，用于高性能、内存高效的大模型微调 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
15 Rethinking the Intermediate Features in Adversarial Attacks: Misleading Robotic Models via Adversarial Distillation 提出基于对抗蒸馏的对抗提示攻击，用于欺骗语言条件机器人模型 manipulation distillation language conditioned
16 Exploration by Running Away from the Past 提出RAMP算法，通过远离过去行为实现强化学习高效探索。 locomotion manipulation reinforcement learning

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

#题目一句话要点标签🔗⭐
17 FLRNet: A Deep Learning Method for Regressive Reconstruction of Flow Field From Limited Sensor Measurements FLRNet：一种基于深度学习的流场回归重建方法，从有限传感器数据中重建流场 sparse sensors

⬅️ 返回 cs.LG 首页 · 🏠 返回主页