cs.LG（2023-11-27）

📊 共 15 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱一：机器人控制 (Robot Control) (2)

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

#题目一句话要点标签🔗⭐
1 Utilizing Explainability Techniques for Reinforcement Learning Model Assurance 提出ARLIN工具包以增强深度强化学习模型的可解释性 reinforcement learning deep reinforcement learning DRL ✅
2 Reward Shaping for Improved Learning in Real-time Strategy Game Play 提出奖励塑形方法以提升实时战略游戏中的学习效果 reinforcement learning reward shaping
3 Multi-Agent Reinforcement Learning for Power Control in Wireless Networks via Adaptive Graphs 提出基于自适应图的多智能体强化学习以解决无线网络功率控制问题 reinforcement learning deep reinforcement learning
4 A Graph Neural Network-Based QUBO-Formulated Hamiltonian-Inspired Loss Function for Combinatorial Optimization using Reinforcement Learning 提出基于图神经网络的QUBO形式哈密顿启发损失函数以解决组合优化问题 reinforcement learning
5 Reinforcement Learning for Wildfire Mitigation in Simulated Disaster Environments 提出SimFire与SimHarness以应对野火灾害管理问题 reinforcement learning
6 QuickDrop: Efficient Federated Unlearning by Integrated Dataset Distillation 提出QuickDrop以高效解决联邦学习中的数据删除问题 distillation
7 Program Machine Policy: Addressing Long-Horizon Tasks by Integrating Program Synthesis and State Machines 提出程序机器策略以解决长时间任务的挑战 reinforcement learning deep reinforcement learning

🔬 支柱九：具身大模型 (Embodied Foundation Models) (6 篇)

#题目一句话要点标签🔗⭐
8 Visual cognition in multimodal large language models 评估多模态大语言模型在视觉认知中的表现 large language model multimodal
9 Continual Instruction Tuning for Large Multimodal Models 提出持续指令调优方法以解决多模态模型遗忘问题 multimodal
10 SPIN: Sparsifying and Integrating Internal Neurons in Large Language Models for Text Classification 提出SPIN框架以提升大语言模型文本分类性能 large language model
11 vTrain: A Simulation Framework for Evaluating Cost-effective and Compute-optimal Large Language Model Training 提出vTrain框架以优化大语言模型训练成本与效率 large language model
12 Can Out-of-Domain data help to Learn Domain-Specific Prompts for Multimodal Misinformation Detection? 提出DPOD框架以利用外域数据提升多模态虚假信息检测 multimodal ✅
13 Function-constrained Program Synthesis 提出函数约束程序合成方法以提升代码生成能力 large language model

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
14 Replay across Experiments: A Natural Extension of Off-Policy RL 提出跨实验重放框架以提升离线强化学习性能 locomotion manipulation reinforcement learning
15 A precise symbolic emulator of the linear matter power spectrum 提出基于符号回归的线性物质功率谱精确模拟方法 MPC

⬅️ 返回 cs.LG 首页 · 🏠 返回主页