cs.LG（2023-10-24）

📊 共 25 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) (14 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (7 🔗1) 支柱一：机器人控制 (Robot Control) (3) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (14 篇)

#题目一句话要点标签🔗⭐
1 Finetuning Offline World Models in the Real World 提出离线世界模型微调方法以解决现实世界中的数据效率问题 reinforcement learning offline RL world model
2 Graph Attention-based Deep Reinforcement Learning for solving the Chinese Postman Problem with Load-dependent costs 提出基于图注意力的深度强化学习解决负载依赖成本的中国邮递员问题 reinforcement learning deep reinforcement learning DRL ✅
3 State Sequences Prediction via Fourier Transform for Representation Learning 提出傅里叶变换状态序列预测方法以提升样本效率 reinforcement learning deep reinforcement learning representation learning
4 STRIDE: Structure and Embedding Distillation with Attention for Graph Neural Networks 提出STRIDE以解决图神经网络压缩中的知识蒸馏问题 teacher-student distillation
5 Confounder Balancing in Adversarial Domain Adaptation for Pre-Trained Large Models Fine-Tuning 提出对抗性领域适应中的混杂因素平衡方法以优化大模型微调 representation learning foundation model
6 Good Better Best: Self-Motivated Imitation Learning for noisy Demonstrations 提出自我激励模仿学习以解决噪声示范问题 imitation learning
7 AGaLiTe: Approximate Gated Linear Transformers for Online Reinforcement Learning 提出AGaLiTe以解决在线强化学习中的变压器架构问题 reinforcement learning
8 Causal Representation Learning Made Identifiable by Grouping of Observational Variables 提出基于观测变量分组的可识别因果表示学习方法 representation learning
9 Generative and Contrastive Paradigms Are Complementary for Graph Self-Supervised Learning 提出图对比掩码自编码器以解决图自监督学习问题 masked autoencoder MAE contrastive learning
10 General Identifiability and Achievability for Causal Representation Learning 提出一种新算法以解决因果表示学习中的可识别性与可达性问题 representation learning
11 Grid Frequency Forecasting in University Campuses using Convolutional LSTM 提出卷积LSTM模型以提高大学校园电网频率预测精度 MAE spatiotemporal
12 On the Convergence and Sample Complexity Analysis of Deep Q-Networks with $ε$-Greedy Exploration 提出深度Q网络的收敛性与样本复杂性分析以解决理论不足问题 reinforcement learning deep reinforcement learning
13 COPR: Continual Learning Human Preference through Optimal Policy Regularization 提出COPR以解决人类偏好持续学习问题 reinforcement learning RLHF
14 Fractal Landscapes in Policy Optimization 提出框架以理解策略优化中的分形景观问题 reinforcement learning deep reinforcement learning

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

#题目一句话要点标签🔗⭐
15 WhiteFox: White-Box Compiler Fuzzing Empowered by Large Language Models 提出WhiteFox以解决编译器模糊测试中的深层逻辑错误问题 large language model
16 E-Sparse: Boosting the Large Language Model Inference through Entropy-based N:M Sparsity 提出E-Sparse以提升大语言模型推理效率 large language model
17 Improving generalization in large language models by learning prefix subspaces 通过学习前缀子空间提高大语言模型的泛化能力 large language model ✅
18 ZzzGPT: An Interactive GPT Approach to Enhance Sleep Quality 提出ZzzGPT以提升睡眠质量预测与反馈 large language model
19 Alquist 5.0: Dialogue Trees Meet Generative Models. A Novel Approach for Enhancing SocialBot Conversations 提出Alquist 5.0以提升社交机器人对话体验 multimodal
20 What Algorithms can Transformers Learn? A Study in Length Generalization 提出RASP框架以解决Transformer模型的长度泛化问题 large language model
21 KITAB: Evaluating LLMs on Constraint Satisfaction for Information Retrieval 提出KITAB以评估LLMs在信息检索中的约束满足能力 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 TimewarpVAE: Simultaneous Time-Warping and Representation Learning of Trajectories 提出TimewarpVAE以解决轨迹表示学习中的时间对齐问题 manipulation dexterous manipulation representation learning
23 On the Foundations of Shortcut Learning 提出生成框架以研究深度学习中的快捷学习现象 manipulation
24 Deceptive Fairness Attacks on Graphs via Meta Learning 提出FATE框架以实现图学习中的欺骗性公平攻击 manipulation

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
25 Graph Deep Learning for Time Series Forecasting 提出图深度学习方法以解决时间序列预测问题 spatiotemporal

⬅️ 返回 cs.LG 首页 · 🏠 返回主页