cs.LG（2024-03-13）

📊 共 14 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) (7 🔗1) 支柱九：具身大模型 (Embodied Foundation Models) (6 🔗1) 支柱一：机器人控制 (Robot Control) (1)

🔬 支柱二：RL算法与架构 (RL & Architecture) (7 篇)

#题目一句话要点标签🔗⭐
1 Human Alignment of Large Language Models through Online Preference Optimisation 提出IPO-MD以优化语言模型的人类偏好对齐问题 reinforcement learning RLHF DPO
2 MolBind: Multimodal Alignment of Language, Molecules, and Proteins 提出MolBind框架以解决多模态对齐问题 contrastive learning multimodal
3 HRLAIF: Improvements in Helpfulness and Harmlessness in Open-domain Reinforcement Learning From AI Feedback 提出HRLAIF以提升开放域强化学习的有用性与无害性 reinforcement learning RLHF large language model
4 Digital Twin-assisted Reinforcement Learning for Resource-aware Microservice Offloading in Edge Computing 提出DTDRLMO以解决边缘计算中的微服务卸载问题 reinforcement learning deep reinforcement learning DRL
5 Multi-Objective Optimization Using Adaptive Distributed Reinforcement Learning 提出多目标自适应分布式强化学习以优化智能交通系统 reinforcement learning
6 A Sparsity Principle for Partially Observable Causal Representation Learning 提出稀疏性原则以解决部分可观测因果表示学习问题 representation learning
7 Learning to Watermark LLM-generated Text via Reinforcement Learning 提出一种基于强化学习的LLM生成文本水印方法 reinforcement learning ✅

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

#题目一句话要点标签🔗⭐
8 Second-Order Information Matters: Revisiting Machine Unlearning for Large Language Models 基于二阶信息的机器遗忘方法以解决隐私泄露问题 large language model
9 Simple and Scalable Strategies to Continually Pre-train Large Language Models 提出简单可扩展策略以持续预训练大型语言模型 large language model
10 Usable XAI: 10 Strategies Towards Exploiting Explainability in the LLM Era 提出可用的可解释人工智能策略以提升大语言模型的应用效果 large language model ✅
11 SoK: Reducing the Vulnerability of Fine-tuned Language Models to Membership Inference Attacks 提出系统性评估以减少微调语言模型的成员推断攻击脆弱性 large language model
12 CleanAgent: Automating Data Standardization with LLM-based Agents 提出CleanAgent以自动化数据标准化过程 large language model
13 CodingTeachLLM: Empowering LLM's Coding Ability via AST Prior Knowledge 提出CodingTeachLLM以提升大语言模型的编程教学能力 large language model

🔬 支柱一：机器人控制 (Robot Control) (1 篇)

#题目一句话要点标签🔗⭐
14 Data augmentation with automated machine learning: approaches and performance comparison with classical data augmentation methods 提出基于自动化机器学习的数据增强方法以提升模型泛化能力 manipulation

⬅️ 返回 cs.LG 首页 · 🏠 返回主页