cs.LG（2023-12-09）

📊 共 13 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) (8 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (4 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (8 篇)

#题目一句话要点标签🔗⭐
1 Improving Adversarial Robust Fairness via Anti-Bias Soft Label Distillation 提出反偏置软标签蒸馏(ABSLD)方法，提升对抗鲁棒公平性。 distillation
2 Unsupervised Multi-modal Feature Alignment for Time Series Representation Learning 提出无监督多模态特征对齐方法以提升时间序列表示学习 representation learning
3 PerfRL: A Small Language Model Framework for Efficient Code Optimization PerfRL：利用小语言模型高效优化代码的强化学习框架 reinforcement learning large language model
4 Boosting the Cross-Architecture Generalization of Dataset Distillation through an Empirical Study 提出ELF方法，提升数据集蒸馏在跨架构上的泛化能力 distillation ✅
5 Isomorphic-Consistent Variational Graph Auto-Encoders for Multi-Level Graph Representation Learning 提出IsoC-VGAE，解决VGAE在高阶图表示学习中同构一致性不足的问题 representation learning
6 On Task-Relevant Loss Functions in Meta-Reinforcement Learning and Online LQR 提出一种基于任务相关损失的元强化学习算法，提升样本效率。 reinforcement learning
7 Distributional Bellman Operators over Mean Embeddings 提出基于均值嵌入的分布贝尔曼算子，用于提升强化学习性能 reinforcement learning deep reinforcement learning
8 Reinforcement Neighborhood Selection for Unsupervised Graph Anomaly Detection 提出RAND：基于强化学习的邻域选择方法，用于无监督图异常检测。 reinforcement learning representation learning

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

#题目一句话要点标签🔗⭐
9 Batched Low-Rank Adaptation of Foundation Models 提出FLoRA框架，通过批量低秩适配实现高效的个性化模型服务。 foundation model
10 Stateful Large Language Model Serving with Pensieve Pensieve：一种用于多轮对话LLM服务的高效状态保持系统 large language model
11 Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge Agile-Quant：面向边缘设备LLM加速，提出激活引导量化框架。 large language model ✅
12 ESPN: Memory-Efficient Multi-Vector Information Retrieval ESPN：通过存储卸载降低多向量信息检索的内存需求 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
13 Evolving Reservoirs for Meta Reinforcement Learning 提出进化Reservoir元强化学习方法，提升智能体在复杂环境中的适应性和泛化能力 locomotion reinforcement learning

⬅️ 返回 cs.LG 首页 · 🏠 返回主页