cs.LG（2023-10-17）

📊 共 14 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) (7 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱一：机器人控制 (Robot Control) (2)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (7 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Group Preference Optimization: Few-Shot Alignment of Large Language Models	提出群体偏好优化框架以解决大语言模型对群体偏好的适应问题	large language model
2	MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection	提出MST-GAT以解决多模态时间序列异常检测问题	multimodal
3	Unlocking Emergent Modularity in Large Language Models	提出解锁大型语言模型的自发模块化方法	large language model	✅
4	Context-Aware Meta-Learning	提出上下文感知元学习算法以解决视觉模型学习新概念的挑战	large language model	✅
5	Bias and Error Mitigation in Software-Generated Data: An Advanced Search and Optimization Framework Leveraging Generative Code Models	提出先进搜索与优化框架以缓解软件生成数据中的偏差与错误	large language model
6	Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning	比较分析LoRA、SPT和ICL在安全与隐私方面的表现	large language model
7	Sparse-DySta: Sparsity-Aware Dynamic and Static Scheduling for Sparse Multi-DNN Workloads	提出Sparse-DySta以解决稀疏多DNN调度问题	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
8	Value-Biased Maximum Likelihood Estimation for Model-based Reinforcement Learning in Discounted Linear MDPs	提出值偏置最大似然估计以解决线性MDP中的计算效率问题	reinforcement learning
9	Butterfly Effects of SGD Noise: Error Amplification in Behavior Cloning and Autoregression	提出EMA以缓解行为克隆中的SGD噪声引发的错误放大问题	behavior cloning
10	Keep Various Trajectories: Promoting Exploration of Ensemble Policies in Continuous Control	提出TEEN以解决强化学习中样本多样性不足问题	reinforcement learning deep reinforcement learning DRL
11	Understanding Contrastive Learning via Distributionally Robust Optimization	通过分布鲁棒优化理解对比学习的容忍性	contrastive learning	✅
12	SignGT: Signed Attention-based Graph Transformer for Graph Representation Learning	提出Signed Attention图变换器以解决图表示学习中的频率信息捕获问题	representation learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
13	Neural Packing: from Visual Sensing to Reinforcement Learning	提出神经打包框架以解决3D运输与打包问题	motion planning reinforcement learning
14	Feature Pyramid biLSTM: Using Smartphone Sensors for Transportation Mode Detection	提出Feature Pyramid biLSTM以解决交通模式检测问题	locomotion

⬅️ 返回 cs.LG 首页 · 🏠 返回主页