cs.LG（2023-10-04）

📊 共 27 篇论文

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (15) 支柱九：具身大模型 (Embodied Foundation Models) (6) 支柱一：机器人控制 (Robot Control) (3) 支柱八：物理动画 (Physics-based Animation) (2) 支柱五：交互与反应 (Interaction & Reaction) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (15 篇)

#题目一句话要点标签🔗⭐
1 Deep reinforcement learning for machine scheduling: Methodology, the state-of-the-art, and future directions 综述深度强化学习在机器调度中的应用与挑战 reinforcement learning deep reinforcement learning DRL
2 Deep Reinforcement Learning Algorithms for Hybrid V2X Communication: A Benchmarking Study 提出深度强化学习算法以解决V2X通信中的垂直切换问题 reinforcement learning deep reinforcement learning DRL
3 Reward Model Ensembles Help Mitigate Overoptimization 提出集成奖励模型以解决过度优化问题 reinforcement learning PPO RLHF
4 Neural architecture impact on identifying temporally extended Reinforcement Learning tasks 提出基于注意力机制的架构以解决强化学习任务的可解释性问题 reinforcement learning deep reinforcement learning
5 Co-modeling the Sequential and Graphical Routes for Peptide Representation Learning 提出RepCon以融合肽的序列与图形表示学习 representation learning contrastive learning
6 Discovering General Reinforcement Learning Algorithms with Adversarial Environment Design 提出GROOVE以解决深度强化学习算法的泛化问题 reinforcement learning deep reinforcement learning
7 Leveraging Model-based Trees as Interpretable Surrogate Models for Model Distillation 提出基于模型树的可解释替代模型以优化模型蒸馏 distillation
8 Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making 提出Decision ConvFormer以解决决策Transformer局部依赖捕捉不足问题 reinforcement learning offline reinforcement learning decision transformer
9 Multi-Domain Causal Representation Learning via Weak Distributional Invariances 提出多域因果表示学习方法以解决数据简化假设问题 representation learning
10 Multi-Agent Reinforcement Learning for Power Grid Topology Optimization 提出层次化多智能体强化学习框架以优化电网拓扑 reinforcement learning
11 Online Estimation and Inference for Robust Policy Evaluation in Reinforcement Learning 提出在线鲁棒策略评估方法以解决强化学习中的统计推断问题 reinforcement learning
12 Improving Knowledge Distillation with Teacher's Explanation 提出知识解释蒸馏框架以提升模型性能 distillation
13 Heterogeneous Federated Learning Using Knowledge Codistillation 提出异构联邦学习方法以解决模型架构不一致问题 distillation
14 Never Train from Scratch: Fair Comparison of Long-Sequence Models Requires Data-Driven Priors 提出数据驱动的预训练方法以公平比较长序列模型 SSM state space model
15 Learning to Reach Goals via Diffusion 提出基于扩散模型的目标导向强化学习方法Merlin reinforcement learning offline RL

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

#题目一句话要点标签🔗⭐
16 scHyena: Foundation Model for Full-Length Single-Cell RNA-Seq Analysis in Brain 提出scHyena以解决脑组织单细胞RNA测序分析中的挑战 foundation model
17 Federated Fine-Tuning of LLMs on the Very Edge: The Good, the Bad, the Ugly 提出边缘计算下的联邦微调方法以提升LLM性能 large language model foundation model
18 Differentially Private Optimization for Non-Decomposable Objective Functions 提出一种新型DP-SGD变体以解决相似性损失函数的隐私问题 large language model
19 Understanding In-Context Learning in Transformers and LLMs by Learning to Learn Discrete Functions 探讨变换器和大语言模型中的上下文学习机制 large language model
20 Comparative Study and Framework for Automated Summariser Evaluation: LangChain and Hybrid Algorithms 提出基于LangChain的自动化摘要评估框架以提升学习理解能力 large language model
21 Beyond Stationarity: Convergence Analysis of Stochastic Softmax Policy Gradient Methods 提出动态策略梯度方法以解决有限时间马尔可夫决策过程中的非平稳性问题 large language model

🔬 支柱一：机器人控制 (Robot Control) (3 篇)

#题目一句话要点标签🔗⭐
22 Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization 提出扩散生成流采样器以优化高维密度函数采样 trajectory optimization
23 Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectors 提出查询高效的对抗性HTML攻击以提升钓鱼网页检测的鲁棒性 manipulation
24 Parameterized Convex Minorant for Objective Function Approximation in Amortized Optimization 提出参数化凸小于函数以优化目标函数近似问题 model predictive control

🔬 支柱八：物理动画 (Physics-based Animation) (2 篇)

#题目一句话要点标签🔗⭐
25 Multiple Physics Pretraining for Physical Surrogate Models 提出多物理预训练方法以提升物理代理模型的性能 spatiotemporal foundation model
26 MP-FVM: Enhancing Finite Volume Method for Water Infiltration Modeling in Unsaturated Soils via Message-passing Encoder-decoder Network 提出MP-FVM以解决非饱和土壤水分渗透建模问题 spatiotemporal

🔬 支柱五：交互与反应 (Interaction & Reaction) (1 篇)

#题目一句话要点标签🔗⭐
27 Practical, Private Assurance of the Value of Collaboration via Fully Homomorphic Encryption 提出基于全同态加密的协作价值保障方案 OMOMO

⬅️ 返回 cs.LG 首页 · 🏠 返回主页