cs.LG（2023-10-10）

📊 共 22 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱二：RL算法与架构 (RL & Architecture) (16 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (5) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (16 篇)

#题目一句话要点标签🔗⭐
1 Zero-Shot Transfer in Imitation Learning 提出一种零样本迁移模仿学习算法以解决领域适应问题 imitation learning zero-shot transfer
2 Understanding the Effects of RLHF on LLM Generalisation and Diversity 分析RLHF对LLM泛化与多样性的影响 reinforcement learning RLHF large language model
3 Deep reinforcement learning uncovers processes for separating azeotropic mixtures without prior knowledge 提出深度强化学习方法以解决无知识前提的共沸混合物分离问题 reinforcement learning deep reinforcement learning
4 Boosting Continuous Control with Consistency Policy 提出一致性策略以解决扩散模型在强化学习中的效率问题 reinforcement learning offline reinforcement learning consistency policy
5 DrugCLIP: Contrastive Protein-Molecule Representation Learning for Virtual Screening 提出DrugCLIP以解决虚拟筛选中的高计算成本问题 representation learning contrastive learning
6 Pi-DUAL: Using Privileged Information to Distinguish Clean from Noisy Labels 提出Pi-DUAL以解决标签噪声问题 privileged information
7 Positivity-free Policy Learning with Observational Data 提出无正性假设的政策学习框架以解决观察数据中的挑战 policy learning
8 Scalable Semantic Non-Markovian Simulation Proxy for Reinforcement Learning 提出语义非马尔可夫模拟代理以解决强化学习可扩展性问题 reinforcement learning
9 Inverse Factorized Q-Learning for Cooperative Multi-agent Imitation Learning 提出逆因子化Q学习以解决合作多智能体模仿学习问题 imitation learning
10 Spectral Entry-wise Matrix Estimation for Low-Rank Reinforcement Learning 提出谱入项矩阵估计以解决低秩强化学习问题 reinforcement learning
11 Self-Supervised Representation Learning for Online Handwriting Text Classification 提出部分笔画遮蔽方法以解决在线手写文本分类问题 representation learning
12 Self-Supervised Dataset Distillation for Transfer Learning 提出自监督数据集蒸馏方法以提升迁移学习效果 distillation
13 Bi-Level Offline Policy Optimization with Limited Exploration 提出双层离线策略优化算法以解决探索不足问题 reinforcement learning offline RL offline reinforcement learning
14 A Unified View on Solving Objective Mismatch in Model-Based Reinforcement Learning 提出统一视角解决模型基础强化学习中的目标不匹配问题 reinforcement learning
15 Information Content Exploration 提出信息内容探索方法以解决稀疏奖励环境中的探索问题 reinforcement learning distillation
16 Gem5Pred: Predictive Approaches For Gem5 Simulation Time 提出Gem5Pred以解决Gem5仿真时间预测问题 predictive model MAE ✅

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#题目一句话要点标签🔗⭐
17 FedMFS: Federated Multimodal Fusion Learning with Selective Modality Communication 提出FedMFS以解决多模态联邦学习中的通信挑战 multimodal
18 LLMs Killed the Script Kiddie: How Agents Supported by Large Language Models Change the Landscape of Network Threat Testing 利用大语言模型提升网络威胁测试的自动化能力 large language model
19 MuseChat: A Conversational Music Recommendation System for Videos 提出MuseChat以解决视频音乐推荐中的用户偏好问题 large language model
20 Implicit Variational Inference for High-Dimensional Posteriors 提出隐式变分推断以解决高维后验分布问题 multimodal
21 Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrations 提出In-Context攻击与防御以提升语言模型安全性 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
22 Taking the human out of decomposition-based optimization via artificial intelligence: Part II. Learning to initialize 通过人工智能优化初始化以提升分解优化效率 model predictive control

⬅️ 返回 cs.LG 首页 · 🏠 返回主页