cs.AI（2024-05-28）

📊 共 21 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (13 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (13 篇)

#题目一句话要点标签🔗⭐
1 LLM experiments with simulation: Large Language Model Multi-Agent System for Simulation Model Parametrization in Digital Twins 提出基于LLM多智能体系统的数字孪生仿真模型参数自动配置方法 large language model ✅
2 The Evolution of Multimodal Model Architectures 对多模态模型架构进行系统性分类，促进多模态领域发展监控。 multimodal
3 A Human-Like Reasoning Framework for Multi-Phases Planning Task with Large Language Models 提出类人推理框架，提升大语言模型在多阶段旅行规划任务中的性能 large language model
4 Large Language Models as Partners in Student Essay Evaluation 利用大语言模型作为伙伴，提升学生论文评估效率与质量 large language model
5 LLaMA-NAS: Efficient Neural Architecture Search for Large Language Models LLaMA-NAS：面向大语言模型的高效神经架构搜索 large language model
6 Metaheuristics and Large Language Models Join Forces: Toward an Integrated Optimization Approach 利用大型语言模型进行模式识别，提升元启发式算法在社交网络优化中的性能 large language model ✅
7 Attention-based sequential recommendation system using multimodal data 提出一种基于注意力机制的多模态序列推荐系统，提升电商产品推荐性能。 multimodal
8 Automated Real-World Sustainability Data Generation from Images of Buildings 提出一种基于图像的建筑可持续性数据自动生成方法，优于人工标注。 large language model
9 Instruct-MusicGen: Unlocking Text-to-Music Editing for Music Language Models via Instruction Tuning Instruct-MusicGen：通过指令微调解锁音乐语言模型的文本到音乐编辑能力 large language model
10 Towards Dialogues for Joint Human-AI Reasoning and Value Alignment 提出基于逻辑的对话框架，促进人机联合推理与价值观对齐 large language model
11 Self-Guiding Exploration for Combinatorial Problems 提出自引导探索(SGE)方法，利用LLM解决组合优化问题 large language model
12 LoRA-Switch: Boosting the Efficiency of Dynamic LLM Adapters via System-Algorithm Co-design LoRA-Switch：通过系统-算法协同设计提升动态LLM适配器的效率 large language model
13 Facilitating Holistic Evaluations with LLMs: Insights from Scenario-Based Experiments 利用LLM促进整体评估：基于情景实验的洞察 large language model

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

#题目一句话要点标签🔗⭐
14 Unleashing the Potential of Text-attributed Graphs: Automatic Relation Decomposition via Large Language Models 提出RoSE框架，利用大语言模型自动分解文本属性图中的混合语义关系，提升图神经网络性能。 representation learning large language model
15 Defending Large Language Models Against Jailbreak Attacks via Layer-specific Editing 提出层特定编辑（LED）方法，增强大语言模型抵御越狱攻击的能力。 reinforcement learning large language model ✅
16 Coupled Mamba: Enhanced Multi-modal Fusion with Coupled State Space Model 提出耦合Mamba模型，增强多模态融合，提升跨模态交互动态建模能力。 Mamba SSM state space model
17 Unified Preference Optimization: Language Model Alignment Beyond the Preference Frontier 提出统一偏好优化（UPO），在DPO框架下优化用户和设计者偏好，无需额外数据。 reinforcement learning RLHF DPO
18 Getting More Juice Out of the SFT Data: Reward Learning from Human Demonstration Improves SFT for LLM Alignment 提出基于逆强化学习的SFT方法，提升LLM对齐效果并增强对低质量数据的鲁棒性 reinforcement learning inverse reinforcement learning preference learning
19 Safe Reinforcement Learning in Black-Box Environments via Adaptive Shielding 提出ADVICE，通过自适应屏蔽提升黑盒环境下的强化学习安全性 reinforcement learning
20 PyTAG: Tabletop Games for Multi-Agent Reinforcement Learning PyTAG：用于多智能体强化学习的桌面游戏框架 reinforcement learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
21 RealitySummary: Exploring On-Demand Mixed Reality Text Summarization and Question Answering using Large Language Models RealitySummary：探索基于大语言模型的混合现实文本摘要与问答 affordance large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页