cs.AI（2024-05-27）

📊 共 19 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9) 支柱二：RL算法与架构 (RL & Architecture) (7 🔗1) 支柱一：机器人控制 (Robot Control) (2) 支柱四：生成式动作 (Generative Motion) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#题目一句话要点标签🔗⭐
1 The Economic Implications of Large Language Model Selection on Earnings and Return on Investment: A Decision Theoretic Model 提出基于决策理论的LLM选型框架，优化投资回报率 large language model
2 Exploring and steering the moral compass of Large Language Models 探索并引导大型语言模型的道德准则 large language model
3 WirelessLLM: Empowering Large Language Models Towards Wireless Intelligence 提出WirelessLLM框架，赋能大语言模型解决无线通信网络挑战。 large language model
4 Laurel: Unblocking Automated Verification with Large Language Models Laurel：利用大语言模型自动生成断言，解决程序验证中的阻塞问题 large language model
5 TrojFM: Resource-efficient Backdoor Attacks against Very Large Foundation Models 提出TrojFM以解决大规模基础模型的后门攻击问题 foundation model
6 Video Enriched Retrieval Augmented Generation Using Aligned Video Captions 提出利用对齐视频字幕增强检索增强生成，提升视频信息在聊天助手中的应用。 large language model multimodal
7 Position: Foundation Agents as the Paradigm Shift for Decision Making 提出Foundation Agents，变革决策制定范式，提升泛化能力与样本效率。 large language model foundation model
8 Revision Matters: Generative Design Guided by Revision Edits 提出基于人类修订指导的生成式设计方法，提升多模态布局生成质量。 multimodal
9 Recent advances in text embedding: A Comprehensive Review of Top-Performing Methods on the MTEB Benchmark 综述MTEB基准上最优文本嵌入方法，提升通用文本表示能力。 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🔗⭐
10 GTA: Generative Trajectory Augmentation with Guidance for Offline Reinforcement Learning 提出GTA：一种基于生成轨迹增强的离线强化学习方法，提升数据质量。 reinforcement learning offline RL offline reinforcement learning ✅
11 A Large Language Model-based multi-agent manufacturing system for intelligent shopfloor 提出基于大语言模型的多智能体制造系统，用于智能车间管理，无需预训练。 reinforcement learning large language model
12 Biological Neurons Compete with Deep Reinforcement Learning in Sample Efficiency in a Simulated Gameworld 体外生物神经元在Pong游戏中样本效率优于深度强化学习算法 reinforcement learning deep reinforcement learning PPO
13 Vision-and-Language Navigation Generative Pretrained Transformer 提出VLN-GPT，利用生成式预训练Transformer解决视觉语言导航中的指令遵循难题。 reinforcement learning imitation learning VLN
14 Reinforcement Learning Based Escape Route Generation in Low Visibility Environments 提出基于强化学习的低能见度环境逃生路径生成方法，用于火灾救援。 reinforcement learning
15 CLIBD: Bridging Vision and Genomics for Biodiversity Monitoring at Scale 提出CLIBD，融合视觉与基因组信息，实现大规模生物多样性监测 contrastive learning multimodal
16 Multiple Heads are Better than One: Mixture of Modality Knowledge Experts for Entity Representation Learning 提出MoMoK框架，利用模态知识专家混合建模实体表示，提升多模态知识图谱补全效果。 representation learning

🔬 支柱一：机器人控制 (Robot Control) (2 篇)

#题目一句话要点标签🔗⭐
17 Can We Trust Embodied Agents? Exploring Backdoor Attacks against Embodied LLM-based Decision-Making Systems 提出BALD框架，揭示具身LLM决策系统在自动驾驶和家庭机器人中的后门攻击漏洞 manipulation embodied AI large language model
18 AbstractBeam: Enhancing Bottom-Up Program Synthesis using Library Learning AbstractBeam通过库学习增强自底向上程序合成，提升DSL效率 manipulation

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
19 BehaviorGPT: Smart Agent Simulation for Autonomous Driving with Next-Patch Prediction BehaviorGPT：基于下一块预测的智能体行为模拟，用于自动驾驶 motion generation

⬅️ 返回 cs.AI 首页 · 🏠 返回主页